Ionic polymer-metal composites(IPMCs)constitute a new type of artificial muscle material that is commonly used in bionic soft robots and medical devices because of its small driving voltage and considerable deformatio...Ionic polymer-metal composites(IPMCs)constitute a new type of artificial muscle material that is commonly used in bionic soft robots and medical devices because of its small driving voltage and considerable deformation.However,IPMCs are limited by performance issues such as low output force and small operating time away from water.Silicon dioxide sulfonated graphene(SiO_(2)-SGO)particles are often used to improve the performance of polymer membranes because of their hydrophilicity and high chemical stability.Reported here is the addition of SiO_(2)-SGO particles prepared by in situ hydrolysis to perfluorosulfonic acid in order to improve the IPMC properties.Also,a predictive model was constructed based on a backpropagation neural network,with the SiO_(2)-SGO doping amount and the IPMC excitation voltage in the input layer and the driving displacement in the output layer.The results show that the IPMC prepared with 1.0 wt.%doping content performed the best,with a maximum output displacement of 47.7 mm.The correlation coefficient(R2)was 0.9842 and the mean square error was 0.00037073,which show that the predictive model has high predictive accuracy and is suitable for predicting the performance of the SiO_(2)-SGO-modified IPMC.展开更多
Objective:To analyze the factors related to vessel vasovagal reaction(VVR)in apheresis donors,establish a mathematical model for predicting the correlation factors and occurrence risk,and use the prediction model to i...Objective:To analyze the factors related to vessel vasovagal reaction(VVR)in apheresis donors,establish a mathematical model for predicting the correlation factors and occurrence risk,and use the prediction model to intervene in high-risk VVR blood donors,improve the blood donation experience,and retain blood donors.Methods:A total of 316 blood donors from the Xi'an Central Blood Bank from June to September 2022 were selected to statistically analyze VVR-related factors.A BP neural network prediction model is established with relevant factors as input and DRVR risk as output.Results:First-time blood donors had a high risk of VVR,female risk was high,and sex difference was significant(P value<0.05).The blood pressure before donation and intergroup differences were also significant(P value<0.05).After training,the established BP neural network model has a minimum RMS error of o.116,a correlation coefficient R=0.75,and a test model accuracy of 66.7%.Conclusion:First-time blood donors,women,and relatively low blood pressure are all high-risk groups for VVR.The BP neural network prediction model established in this paper has certain prediction accuracy and can be used as a means to evaluate the risk degree of clinical blood donors.展开更多
The rapid prediction of aerodynamic performance is critical in the conceptual and preliminary design of hypersonic vehicles. This study focused on axisymmetric body configurations commonly used in such vehicles and pr...The rapid prediction of aerodynamic performance is critical in the conceptual and preliminary design of hypersonic vehicles. This study focused on axisymmetric body configurations commonly used in such vehicles and proposed a multi-fidelity neural network (MFNN) framework to fuse aerodynamic data of varying quality. A data-driven prediction model was constructed using a pointwise modeling method based on generating lines to input geometric features into the network. The MFNN framework combined low-fidelity and high-fidelity networks, trained on aerodynamic performance data from engineering rapid computation methods and CFD, respectively, using spherically blunted cones as examples. The results showed that the MFNN effectively integrated multi-fidelity data, achieving prediction accuracy close to CFD results in most regions, with errors under 5% in key stagnation areas. The model demonstrated strong generalization capabilities for varying cone dimensions and flight conditions. Furthermore, it significantly reduced dependence on high-fidelity data, enabling efficient aerodynamic performance predictions with limited datasets. This study provides a novel methodology for rapid aerodynamic performance prediction, offering both accuracy and efficiency, and contributes to the design of hypersonic vehicles.展开更多
This paper presents a back-propagation neural network model for sound quality prediction (BPNN-SQP) of multiple working conditions’ vehicle interior noise. According to the standards and regulations, four kinds of ve...This paper presents a back-propagation neural network model for sound quality prediction (BPNN-SQP) of multiple working conditions’ vehicle interior noise. According to the standards and regulations, four kinds of vehicle interior noises under operating conditions, including idle, constant speed, accelerating and braking, are acquired. The objective psychoacoustic parameters and subjective annoyance results are respectively used as the input and output of the BPNN-SQP model. With correlation analysis and significance test, some psychoacoustic parameters, such as loudness, A-weighted sound pressure level, roughness, articulation index and sharpness, are selected for modeling. The annoyance values of unknown noise samples estimated by the BPNN-SQP model are highly correlated with the subjective annoyances. Conclusion can be drawn that the proposed BPNN-SQP model has good generalization ability and can be applied in sound quality prediction of vehicle interior noise under multiple working conditions.展开更多
In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predi...In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predicting the fatigue life of structures becomes notably arduous.This paper proposed an approach to predict the fatigue life of structure based on the optimized load spectra,which is accurately estimated by an efficient hinging hyperplane neural network(EHH-NN)model.The construction of the EHH-NN model includes initial network generation and parameter optimization.Through the combination of working conditions design,multi-body dynamics analysis and structural static mechanics analysis,the simulated load spectra of the structure are obtained.The simulated load spectra are taken as the input variables for the optimized EHH-NN model,while the measurement load spectra are used as the output variables.The prediction results of case structure indicate that the optimized EHH-NN model can achieve the high-accuracy load spectra,in comparison with support vector machine(SVM),random forest(RF)model and back propagation(BP)neural network.The error rate between the prediction values and the measurement values of the optimized EHH-NN model is 4.61%.In the Cauchy-Lorentz distribution,the absolute error data of 92%with EHH-NN model appear in the intermediate range of±1.65%.Also,the fatigue life analysis is performed for the case structure,based on the accurately predicted load spectra.The fatigue life of the case structure is calculated based on the comparison between the measured and predicted load spectra,with an accuracy of 93.56%.This research proposes the optimized EHH-NN model can more accurately reflect the measurement load spectra,enabling precise calculation of fatigue life.Additionally,the optimized EHH-NN model provides reliability assessment for industrial engineering equipment.展开更多
Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of t...Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000？8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth（SD） 〉 electrical conductivity （EC）. Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus（TP） and total nitrogen（TN） were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data（chlorophyll-α prediction） and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.展开更多
In terms of 34-year monthly mean temperature series in 1946-1979,the multi-level maPPing model of neural netWork BP type was applied to calculate the system's fractual dimension Do=2'8,leading tO a three-level...In terms of 34-year monthly mean temperature series in 1946-1979,the multi-level maPPing model of neural netWork BP type was applied to calculate the system's fractual dimension Do=2'8,leading tO a three-level model of this type with ixj=3x2,k=l,and the 1980 monthly mean temperture predichon on a long-t6rm basis were prepared by steadily modifying the weighting coefficient,making for the correlation coefficient of 97% with the measurements.Furthermore,the weighhng parameter was modified for each month of 1980 by means of observations,therefore constrcuhng monthly mean temperature forecasts from January to December of the year,reaching the correlation of 99.9% with the measurements.Likewise,the resulting 1981 monthly predictions on a long-range basis with 1946-1980 corresponding records yielded the correlahon of 98% and the month-tO month forecasts of 99.4%.展开更多
In order to calculate the propagation loss of electromagnetic waves produced by a transmitter, a variety of models based on empirical and deterministic formulas are used. In this study, one of the artificial neural ne...In order to calculate the propagation loss of electromagnetic waves produced by a transmitter, a variety of models based on empirical and deterministic formulas are used. In this study, one of the artificial neural networks models, Levenberg-Marquardt algorithm, which is quite effective for predicting the propagation is used and the results obtained by this algorithm are compared with the simulation results based on ITU-R 1546 and Epstein-Peterson models. In this paper, the propagation loss of FM radio station using artificial neural networks models is studied depending on the Levenberg-Marquardt algorithm. For training the artificial neural network, as the input data;range (r), effective antenna height (h) and terrain irregularity (△H) parameters are involved and measured values are treated as the output data. The good results obtained in the city area reveal that the artificial neural network is a very efficient method to compute models which integrate theoretical and experimental data. Meanwhile, the results show that an ANN model performs very well compared with theoretical and empiric propagation models with regard to prediction accuracy, complexity, and prediction time. By comparing the results, the RMSE for Neural Network Model using Levenberg-Marquardt is 9.57, and it is lower than that of classical propagation model using Epstein-Peterson for which RMSE is 10.26.展开更多
The aim of this study is to evaluate the performance of BP neural network techniques in predicting earthquakes occurring in the region of Himalayan belt (with the use of different types of input data). These parameter...The aim of this study is to evaluate the performance of BP neural network techniques in predicting earthquakes occurring in the region of Himalayan belt (with the use of different types of input data). These parameters are extracted from Himalayan Earthquake catalogue comprised of all minor, major events and their aftershock sequences in the Himalayan basin for the past 128 years from 1887 to 2015. This data warehouse contains event data, event time with seconds, latitude, longitude, depth, standard deviation and magnitude. These field data are converted into eight mathematically computed parameters known as seismicity indicators. These seismicity indicators have been used to train the BP Neural Network for better decision making and predicting the magnitude of the pre-defined future time period. These mathematically computed indicators considered are the clustered based on every events above 2.5 magnitude, total number of events from past years to 2014, frequency-magnitude distribution b-values, Gutenberg-Richter inverse power law curve for the n events, the rate of square root of seismic energy released during the n events, energy released from the event, the mean square deviation about the regression line based on the Gutenberg-Richer inverse power law for the n events, coefficient of variation of mean time and average value of the magnitude for last n events. We propose a three-layer feed forward BP neural network model to identify factors, with the actual occurrence of the earthquake magnitude M and other seven mathematically computed parameters seismicity indicators as input and target vectors in Himalayan basin area. We infer through comparing curve as observed from seismometer in Himalayan Earthquake catalogue comprised of all events above magnitude 2.5 mg, their aftershock sequences in the Himalayan basin of year 2015 and BP neural network predicting earthquakes in 2015. The model yields good prediction result for the earthquakes of magnitude between 4.0 and 6.0.展开更多
Phase pure ZrB2-SiC composite powders were prepared after 1 450℃/3 h via carbothermal reduction route,by using ZrSiO4,B2O3 and carbon as the raw materials.The influences of firing temperature as well as the type and ...Phase pure ZrB2-SiC composite powders were prepared after 1 450℃/3 h via carbothermal reduction route,by using ZrSiO4,B2O3 and carbon as the raw materials.The influences of firing temperature as well as the type and amount of additive on the phase composition of final products were detailedly investigated.The results indicated that the onset formation temperature of ZrB2-SiC was reduced to 1 400℃by the present conditions,and oxide additive（including CoSO4·7H2O,Y2O3 and TiO2）was effective in enhancing the decomposition of raw ZrSiO4,therefore accelerating the synthesis of ZrB2-SiC.Moreover,microstructural observation showed that the as-prepared ZrB2 and SiC respectively had well-defined hexagonal columnar and fibrous morphology.Furthermore,the methodology of back-propagation artificial neural networks（BP-ANNs）was adopted to establish a model for predicting the reaction extent（e g,the content of ZrB2-SiC in final product）in terms of various processing conditions.The results predicted by the as-established BP-ANNs model matched well with that of testing experiment（with a mean square error in 10^（-3） degree）,verifying good effectiveness of the proposed strategy.展开更多
Ever since the appearance of"Implementation Measures for Suspending and Terminating the Listing of Loss-making Companies"in 2001,the delisting system has emerged.However,the proportion of delisted companies ...Ever since the appearance of"Implementation Measures for Suspending and Terminating the Listing of Loss-making Companies"in 2001,the delisting system has emerged.However,the proportion of delisted companies in China has never exceeded 1% each year.The number of delisted companies in the security market is far less than the number of companies with financial distress.The capital market lacks a good delisting system and investors lack risk identification capabilities.Financial risk is directly related to delisting risk.Therefore,an early warning model of financial distress prediction for China.s stock market can provide guidance to stakeholders such as listed companies and capital markets.This paper first explains the immature delisting system of China.s capital market and the overall high risk of listed companies.financial distress.Then,the paper further elaborates previous research on financial distress prediction model of listed companies and analyzes the advantages and disadvantages of different models.This paper chooses the Analytic Hierarchy Process(AHP)to screen out the main factors that affect the risk of financial distress.The main factors are included in Logistic regression model and BP neural network model for predicting financial distress of listed companies.The overall effect of two models are assessed and compared.Finally,this paper proposes policy implications according to empirical results.展开更多
AIM:To predict cutting formula of small incision lenticule extraction(SMILE)surgery and assist clinicians in identifying candidates by deep learning of back propagation(BP)neural network.METHODS:A prediction program w...AIM:To predict cutting formula of small incision lenticule extraction(SMILE)surgery and assist clinicians in identifying candidates by deep learning of back propagation(BP)neural network.METHODS:A prediction program was developed by a BP neural network.There were 13188 pieces of data selected as training validation.Another 840 eye samples from 425 patients were recruited for reverse verification of training results.Precision of prediction by BP neural network and lenticule thickness error between machine learning and the actual lenticule thickness in the patient data were measured.RESULTS:After training 2313 epochs,the predictive SMILE cutting formula BP neural network models performed best.The values of mean squared error and gradient are 0.248 and 4.23,respectively.The scatterplot with linear regression analysis showed that the regression coefficient in all samples is 0.99994.The final error accuracy of the BP neural network is-0.003791±0.4221102μm.CONCLUSION:With the help of the BP neural network,the program can calculate the lenticule thickness and residual stromal thickness of SMILE surgery accurately.Combined with corneal parameters and refraction of patients,the program can intelligently and conveniently integrate medical information to identify candidates for SMILE surgery.展开更多
Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. First...Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. Firstly, the error between the fitting and actual injection-production ratio is calculated with such methods as the injection-production ratio and water-oil ratio method, the material balance method, the multiple regression method, the gray theory GM (1,1) model and the back-propogation (BP) neural network method by computer applications in this paper. The relative average errors calculated are respectively 1.67%, 1.08%, 19.2%, 1.38% and 0.88%. Secondly, the reasons for the errors from different prediction methods are analyzed theoretically, indicating that the prediction precision of the BP neural network method is high, and that it has a better self-adaptability, so that it can reflect the internal relationship between the injection-production ratio and the influencing factors. Therefore, the BP neural network method is suitable to the prediction of injection-production ratio.展开更多
Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial pro...Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.展开更多
Polylactic acid(PLA)is a potential polymer material used as a substitute for traditional plastics,and the accurate molecular weight distribution range of PLA is strictly required in practical applications.Therefore,ex...Polylactic acid(PLA)is a potential polymer material used as a substitute for traditional plastics,and the accurate molecular weight distribution range of PLA is strictly required in practical applications.Therefore,exploring the relationship between synthetic conditions and PLA molecular weight is crucially important.In this work,direct polycondensation combined with overlay sampling uniform design(OSUD)was applied to synthesize the low molecular weight PLA.Then a multiple regression model and two artificial neural network models on PLA molecular weight versus reaction temperature,reaction time,and catalyst dosage were developed for PLA molecular weight prediction.The characterization results indicated that the low molecular weight PLA was efficiently synthesized under this method.Meanwhile,the experimental dataset acquired from OSUD successfully established three predictive models for PLA molecular weight.Among them,both artificial neural network models had significantly better predictive performance than the regression model.Notably,the radial basis function neural network model had the best predictive accuracy with only 11.9%of mean relative error on the validation dataset,which improved by 67.7%compared with the traditional multiple regression model.This work successfully predicted PLA molecular weight in a direct polycondensation process using artificial neural network models combined with OSUD,which provided guidance for the future implementation of molecular weight-controlled polymer's synthesis.展开更多
A distributionally robust model predictive control(DRMPC)scheme is proposed based on neural network(NN)modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraint...A distributionally robust model predictive control(DRMPC)scheme is proposed based on neural network(NN)modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraints.First,an NN is used to fit the motion data of robot manipulators for data-driven dynamic modeling,converting it into a linear prediction model through gradients.Then,by statistically analyzing the stochastic characteristics of the NN modeling errors,a distributionally robust model predictive controller is designed based on the chance constraints,and the optimization problem is transformed into a tractable quadratic programming(QP)problem under the distributionally robust optimization(DRO)framework.The recursive feasibility and convergence of the proposed algorithm are proven.Finally,the effectiveness of the proposed algorithm is verified through numerical simulation.展开更多
This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknow...This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predictive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max optimization problem(referred to as min-max OP)is formulated to design the controller.The feasibility of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank system is conducted.The results of the simulation serve as verification of the effectualness of the proposed scheme.展开更多
Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety man...Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety management.Aiming at the shortcomings of the BP Neural Network(BPNN)model,such as low learning efficiency,sensitivity to initial weights,and easy falling into a local optimal state,an Improved Sparrow Search Algorithm(ISSA)is adopted to optimize the initial weights and thresholds of BPNN,and an ISSA-BPNN failure pressure prediction model for corroded pipelines is established.Taking 61 sets of pipelines blasting test data as an example,the prediction model was built and predicted by MATLAB software,and compared with the BPNN model,GA-BPNN model,and SSA-BPNN model.The results show that the MAPE of the ISSA-BPNN model is 3.4177%,and the R2 is 0.9880,both of which are superior to its comparison model.Using the ISSA-BPNN model has high prediction accuracy and stability,and can provide support for pipeline inspection and maintenance.展开更多
The goals of this study are to assess the viability of waste tire-derived char(WTDC)as a sustainable,low-cost fine aggregate surrogate material for asphalt mixtures and to develop the statistically coupled neural netw...The goals of this study are to assess the viability of waste tire-derived char(WTDC)as a sustainable,low-cost fine aggregate surrogate material for asphalt mixtures and to develop the statistically coupled neural network(SCNN)model for predicting volumetric and Marshall properties of asphalt mixtures modified with WTDC.The study is based on experimental data acquired from laboratory volumetric and Marshall properties testing on WTDCmodified asphalt mixtures(WTDC-MAM).The input variables comprised waste tire char content and asphalt binder content.The output variables comprised mixture unit weight,total voids,voids filled with asphalt,Marshall stability,and flow.Statistical coupled neural networks were utilized to predict the volumetric and Marshall properties of asphalt mixtures.For predictive modeling,the SCNN model is employed,incorporating a three-layer neural network and preprocessing techniques to enhance accuracy and reliability.The optimal network architecture,using the collected dataset,was a 2:6:5 structure,and the neural network was trained with 60%of the data,whereas the other 20%was used for cross-validation and testing respectively.The network employed a hyperbolic tangent(tanh)activation function and a feed-forward backpropagation.According to the results,the network model could accurately predict the volumetric and Marshall properties.The predicted accuracy of SCNN was found to be as high value>98%and low prediction errors for both volumetric and Marshall properties.This study demonstrates WTDC's potential as a low-cost,sustainable aggregate replacement.The SCNN-based predictive model proves its efficiency and versatility and promotes sustainable practices.展开更多
基金funded by the Digital workshop dynamic Reconstruction modeling Technology(Grant No.2020YFB1710701)the National Natural Science Foundation of China(Grant No.52172099)the Provincial Joint Fund of Shaanxi(Grant No.2021JLM-28).
文摘Ionic polymer-metal composites(IPMCs)constitute a new type of artificial muscle material that is commonly used in bionic soft robots and medical devices because of its small driving voltage and considerable deformation.However,IPMCs are limited by performance issues such as low output force and small operating time away from water.Silicon dioxide sulfonated graphene(SiO_(2)-SGO)particles are often used to improve the performance of polymer membranes because of their hydrophilicity and high chemical stability.Reported here is the addition of SiO_(2)-SGO particles prepared by in situ hydrolysis to perfluorosulfonic acid in order to improve the IPMC properties.Also,a predictive model was constructed based on a backpropagation neural network,with the SiO_(2)-SGO doping amount and the IPMC excitation voltage in the input layer and the driving displacement in the output layer.The results show that the IPMC prepared with 1.0 wt.%doping content performed the best,with a maximum output displacement of 47.7 mm.The correlation coefficient(R2)was 0.9842 and the mean square error was 0.00037073,which show that the predictive model has high predictive accuracy and is suitable for predicting the performance of the SiO_(2)-SGO-modified IPMC.
基金Xi'an Municipal Bureau of Science and Technology,Science and Technology Program,Medical Research Project。
文摘Objective:To analyze the factors related to vessel vasovagal reaction(VVR)in apheresis donors,establish a mathematical model for predicting the correlation factors and occurrence risk,and use the prediction model to intervene in high-risk VVR blood donors,improve the blood donation experience,and retain blood donors.Methods:A total of 316 blood donors from the Xi'an Central Blood Bank from June to September 2022 were selected to statistically analyze VVR-related factors.A BP neural network prediction model is established with relevant factors as input and DRVR risk as output.Results:First-time blood donors had a high risk of VVR,female risk was high,and sex difference was significant(P value<0.05).The blood pressure before donation and intergroup differences were also significant(P value<0.05).After training,the established BP neural network model has a minimum RMS error of o.116,a correlation coefficient R=0.75,and a test model accuracy of 66.7%.Conclusion:First-time blood donors,women,and relatively low blood pressure are all high-risk groups for VVR.The BP neural network prediction model established in this paper has certain prediction accuracy and can be used as a means to evaluate the risk degree of clinical blood donors.
文摘The rapid prediction of aerodynamic performance is critical in the conceptual and preliminary design of hypersonic vehicles. This study focused on axisymmetric body configurations commonly used in such vehicles and proposed a multi-fidelity neural network (MFNN) framework to fuse aerodynamic data of varying quality. A data-driven prediction model was constructed using a pointwise modeling method based on generating lines to input geometric features into the network. The MFNN framework combined low-fidelity and high-fidelity networks, trained on aerodynamic performance data from engineering rapid computation methods and CFD, respectively, using spherically blunted cones as examples. The results showed that the MFNN effectively integrated multi-fidelity data, achieving prediction accuracy close to CFD results in most regions, with errors under 5% in key stagnation areas. The model demonstrated strong generalization capabilities for varying cone dimensions and flight conditions. Furthermore, it significantly reduced dependence on high-fidelity data, enabling efficient aerodynamic performance predictions with limited datasets. This study provides a novel methodology for rapid aerodynamic performance prediction, offering both accuracy and efficiency, and contributes to the design of hypersonic vehicles.
文摘This paper presents a back-propagation neural network model for sound quality prediction (BPNN-SQP) of multiple working conditions’ vehicle interior noise. According to the standards and regulations, four kinds of vehicle interior noises under operating conditions, including idle, constant speed, accelerating and braking, are acquired. The objective psychoacoustic parameters and subjective annoyance results are respectively used as the input and output of the BPNN-SQP model. With correlation analysis and significance test, some psychoacoustic parameters, such as loudness, A-weighted sound pressure level, roughness, articulation index and sharpness, are selected for modeling. The annoyance values of unknown noise samples estimated by the BPNN-SQP model are highly correlated with the subjective annoyances. Conclusion can be drawn that the proposed BPNN-SQP model has good generalization ability and can be applied in sound quality prediction of vehicle interior noise under multiple working conditions.
基金Supported by National Natural Science Foundation of China(Grant No.51805447)Natural Science Foundation of Jiangsu Higher Education of China(Grant No.22KJB460010)+2 种基金Jiangsu Provincial Innovation and Promotion Project of Forestry Science and Technology of China(Grant No.LYKJ[2023]06)Yangzhou Science and Technology Plan(City School Cooperation Project)of China(Grant No.YZ2022193)Cyan Blue Project of Yangzhou University of China。
文摘In the realm of engineering practice,various factors such as limited availability of measurement data and complex working conditions pose significant challenges to obtaining accurate load spectra.Thus,accurately predicting the fatigue life of structures becomes notably arduous.This paper proposed an approach to predict the fatigue life of structure based on the optimized load spectra,which is accurately estimated by an efficient hinging hyperplane neural network(EHH-NN)model.The construction of the EHH-NN model includes initial network generation and parameter optimization.Through the combination of working conditions design,multi-body dynamics analysis and structural static mechanics analysis,the simulated load spectra of the structure are obtained.The simulated load spectra are taken as the input variables for the optimized EHH-NN model,while the measurement load spectra are used as the output variables.The prediction results of case structure indicate that the optimized EHH-NN model can achieve the high-accuracy load spectra,in comparison with support vector machine(SVM),random forest(RF)model and back propagation(BP)neural network.The error rate between the prediction values and the measurement values of the optimized EHH-NN model is 4.61%.In the Cauchy-Lorentz distribution,the absolute error data of 92%with EHH-NN model appear in the intermediate range of±1.65%.Also,the fatigue life analysis is performed for the case structure,based on the accurately predicted load spectra.The fatigue life of the case structure is calculated based on the comparison between the measured and predicted load spectra,with an accuracy of 93.56%.This research proposes the optimized EHH-NN model can more accurately reflect the measurement load spectra,enabling precise calculation of fatigue life.Additionally,the optimized EHH-NN model provides reliability assessment for industrial engineering equipment.
文摘Bayesian regularized BP neural network（BRBPNN） technique was applied in the chlorophyll-α prediction of Nanzui water area in Dongting Lake. Through BP network interpolation method, the input and output samples of the network were obtained. After the selection of input variables using stepwise/multiple linear regression method in SPSS i1.0 software, the BRBPNN model was established between chlorophyll-α and environmental parameters, biological parameters. The achieved optimal network structure was 3-11-1 with the correlation coefficients and the mean square errors for the training set and the test set as 0.999 and 0.000？8426, 0.981 and 0.0216 respectively. The sum of square weights between each input neuron and the hidden layer of optimal BRBPNN models of different structures indicated that the effect of individual input parameter on chlorophyll- α declined in the order of alga amount 〉 secchi disc depth（SD） 〉 electrical conductivity （EC）. Additionally, it also demonstrated that the contributions of these three factors were the maximal for the change of chlorophyll-α concentration, total phosphorus（TP） and total nitrogen（TN） were the minimal. All the results showed that BRBPNN model was capable of automated regularization parameter selection and thus it may ensure the excellent generation ability and robustness. Thus, this study laid the foundation for the application of BRBPNN model in the analysis of aquatic ecological data（chlorophyll-α prediction） and the explanation about the effective eutrophication treatment measures for Nanzui water area in Dongting Lake.
文摘In terms of 34-year monthly mean temperature series in 1946-1979,the multi-level maPPing model of neural netWork BP type was applied to calculate the system's fractual dimension Do=2'8,leading tO a three-level model of this type with ixj=3x2,k=l,and the 1980 monthly mean temperture predichon on a long-t6rm basis were prepared by steadily modifying the weighting coefficient,making for the correlation coefficient of 97% with the measurements.Furthermore,the weighhng parameter was modified for each month of 1980 by means of observations,therefore constrcuhng monthly mean temperature forecasts from January to December of the year,reaching the correlation of 99.9% with the measurements.Likewise,the resulting 1981 monthly predictions on a long-range basis with 1946-1980 corresponding records yielded the correlahon of 98% and the month-tO month forecasts of 99.4%.
文摘In order to calculate the propagation loss of electromagnetic waves produced by a transmitter, a variety of models based on empirical and deterministic formulas are used. In this study, one of the artificial neural networks models, Levenberg-Marquardt algorithm, which is quite effective for predicting the propagation is used and the results obtained by this algorithm are compared with the simulation results based on ITU-R 1546 and Epstein-Peterson models. In this paper, the propagation loss of FM radio station using artificial neural networks models is studied depending on the Levenberg-Marquardt algorithm. For training the artificial neural network, as the input data;range (r), effective antenna height (h) and terrain irregularity (△H) parameters are involved and measured values are treated as the output data. The good results obtained in the city area reveal that the artificial neural network is a very efficient method to compute models which integrate theoretical and experimental data. Meanwhile, the results show that an ANN model performs very well compared with theoretical and empiric propagation models with regard to prediction accuracy, complexity, and prediction time. By comparing the results, the RMSE for Neural Network Model using Levenberg-Marquardt is 9.57, and it is lower than that of classical propagation model using Epstein-Peterson for which RMSE is 10.26.
文摘The aim of this study is to evaluate the performance of BP neural network techniques in predicting earthquakes occurring in the region of Himalayan belt (with the use of different types of input data). These parameters are extracted from Himalayan Earthquake catalogue comprised of all minor, major events and their aftershock sequences in the Himalayan basin for the past 128 years from 1887 to 2015. This data warehouse contains event data, event time with seconds, latitude, longitude, depth, standard deviation and magnitude. These field data are converted into eight mathematically computed parameters known as seismicity indicators. These seismicity indicators have been used to train the BP Neural Network for better decision making and predicting the magnitude of the pre-defined future time period. These mathematically computed indicators considered are the clustered based on every events above 2.5 magnitude, total number of events from past years to 2014, frequency-magnitude distribution b-values, Gutenberg-Richter inverse power law curve for the n events, the rate of square root of seismic energy released during the n events, energy released from the event, the mean square deviation about the regression line based on the Gutenberg-Richer inverse power law for the n events, coefficient of variation of mean time and average value of the magnitude for last n events. We propose a three-layer feed forward BP neural network model to identify factors, with the actual occurrence of the earthquake magnitude M and other seven mathematically computed parameters seismicity indicators as input and target vectors in Himalayan basin area. We infer through comparing curve as observed from seismometer in Himalayan Earthquake catalogue comprised of all events above magnitude 2.5 mg, their aftershock sequences in the Himalayan basin of year 2015 and BP neural network predicting earthquakes in 2015. The model yields good prediction result for the earthquakes of magnitude between 4.0 and 6.0.
基金Funded by National Natural Science Foundation of China(Nos.51502212,51672194 and 51472184)Hubei Province Natural Science Foundation of China(No.2018CFB760)+1 种基金Program for Innovative Teams of Outstanding Young and Middle-aged Researchers in the Higher Education Institutions of Hubei Province(No.T201602)Key Program of Natural Science Foundation of Hubei Province(No.2017CFA004)
文摘Phase pure ZrB2-SiC composite powders were prepared after 1 450℃/3 h via carbothermal reduction route,by using ZrSiO4,B2O3 and carbon as the raw materials.The influences of firing temperature as well as the type and amount of additive on the phase composition of final products were detailedly investigated.The results indicated that the onset formation temperature of ZrB2-SiC was reduced to 1 400℃by the present conditions,and oxide additive（including CoSO4·7H2O,Y2O3 and TiO2）was effective in enhancing the decomposition of raw ZrSiO4,therefore accelerating the synthesis of ZrB2-SiC.Moreover,microstructural observation showed that the as-prepared ZrB2 and SiC respectively had well-defined hexagonal columnar and fibrous morphology.Furthermore,the methodology of back-propagation artificial neural networks（BP-ANNs）was adopted to establish a model for predicting the reaction extent（e g,the content of ZrB2-SiC in final product）in terms of various processing conditions.The results predicted by the as-established BP-ANNs model matched well with that of testing experiment（with a mean square error in 10^（-3） degree）,verifying good effectiveness of the proposed strategy.
文摘Ever since the appearance of"Implementation Measures for Suspending and Terminating the Listing of Loss-making Companies"in 2001,the delisting system has emerged.However,the proportion of delisted companies in China has never exceeded 1% each year.The number of delisted companies in the security market is far less than the number of companies with financial distress.The capital market lacks a good delisting system and investors lack risk identification capabilities.Financial risk is directly related to delisting risk.Therefore,an early warning model of financial distress prediction for China.s stock market can provide guidance to stakeholders such as listed companies and capital markets.This paper first explains the immature delisting system of China.s capital market and the overall high risk of listed companies.financial distress.Then,the paper further elaborates previous research on financial distress prediction model of listed companies and analyzes the advantages and disadvantages of different models.This paper chooses the Analytic Hierarchy Process(AHP)to screen out the main factors that affect the risk of financial distress.The main factors are included in Logistic regression model and BP neural network model for predicting financial distress of listed companies.The overall effect of two models are assessed and compared.Finally,this paper proposes policy implications according to empirical results.
基金Supported by the National Natural Science Foundation of China(No.82271100)Jiangsu Province Science and Technology Support Plan Project(No.BE2022805).
文摘AIM:To predict cutting formula of small incision lenticule extraction(SMILE)surgery and assist clinicians in identifying candidates by deep learning of back propagation(BP)neural network.METHODS:A prediction program was developed by a BP neural network.There were 13188 pieces of data selected as training validation.Another 840 eye samples from 425 patients were recruited for reverse verification of training results.Precision of prediction by BP neural network and lenticule thickness error between machine learning and the actual lenticule thickness in the patient data were measured.RESULTS:After training 2313 epochs,the predictive SMILE cutting formula BP neural network models performed best.The values of mean squared error and gradient are 0.248 and 4.23,respectively.The scatterplot with linear regression analysis showed that the regression coefficient in all samples is 0.99994.The final error accuracy of the BP neural network is-0.003791±0.4221102μm.CONCLUSION:With the help of the BP neural network,the program can calculate the lenticule thickness and residual stromal thickness of SMILE surgery accurately.Combined with corneal parameters and refraction of patients,the program can intelligently and conveniently integrate medical information to identify candidates for SMILE surgery.
文摘Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. Firstly, the error between the fitting and actual injection-production ratio is calculated with such methods as the injection-production ratio and water-oil ratio method, the material balance method, the multiple regression method, the gray theory GM (1,1) model and the back-propogation (BP) neural network method by computer applications in this paper. The relative average errors calculated are respectively 1.67%, 1.08%, 19.2%, 1.38% and 0.88%. Secondly, the reasons for the errors from different prediction methods are analyzed theoretically, indicating that the prediction precision of the BP neural network method is high, and that it has a better self-adaptability, so that it can reflect the internal relationship between the injection-production ratio and the influencing factors. Therefore, the BP neural network method is suitable to the prediction of injection-production ratio.
文摘Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.
基金funded by the Zhejiang Provincial Natural Science Foundation of China(LD21B060001)the National Natural Science Foundation of China(22078296,21576240).
文摘Polylactic acid(PLA)is a potential polymer material used as a substitute for traditional plastics,and the accurate molecular weight distribution range of PLA is strictly required in practical applications.Therefore,exploring the relationship between synthetic conditions and PLA molecular weight is crucially important.In this work,direct polycondensation combined with overlay sampling uniform design(OSUD)was applied to synthesize the low molecular weight PLA.Then a multiple regression model and two artificial neural network models on PLA molecular weight versus reaction temperature,reaction time,and catalyst dosage were developed for PLA molecular weight prediction.The characterization results indicated that the low molecular weight PLA was efficiently synthesized under this method.Meanwhile,the experimental dataset acquired from OSUD successfully established three predictive models for PLA molecular weight.Among them,both artificial neural network models had significantly better predictive performance than the regression model.Notably,the radial basis function neural network model had the best predictive accuracy with only 11.9%of mean relative error on the validation dataset,which improved by 67.7%compared with the traditional multiple regression model.This work successfully predicted PLA molecular weight in a direct polycondensation process using artificial neural network models combined with OSUD,which provided guidance for the future implementation of molecular weight-controlled polymer's synthesis.
基金Project supported by the National Natural Science Foundation of China(Nos.62273245 and 62173033)the Sichuan Science and Technology Program of China(No.2024NSFSC1486)the Opening Project of Robotic Satellite Key Laboratory of Sichuan Province of China。
文摘A distributionally robust model predictive control(DRMPC)scheme is proposed based on neural network(NN)modeling to achieve the trajectory tracking control of robot manipulators with state and control torque constraints.First,an NN is used to fit the motion data of robot manipulators for data-driven dynamic modeling,converting it into a linear prediction model through gradients.Then,by statistically analyzing the stochastic characteristics of the NN modeling errors,a distributionally robust model predictive controller is designed based on the chance constraints,and the optimization problem is transformed into a tractable quadratic programming(QP)problem under the distributionally robust optimization(DRO)framework.The recursive feasibility and convergence of the proposed algorithm are proven.Finally,the effectiveness of the proposed algorithm is verified through numerical simulation.
文摘This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predictive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max optimization problem(referred to as min-max OP)is formulated to design the controller.The feasibility of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank system is conducted.The results of the simulation serve as verification of the effectualness of the proposed scheme.
文摘Oil and gas pipelines are affected by many factors,such as pipe wall thinning and pipeline rupture.Accurate prediction of failure pressure of oil and gas pipelines can provide technical support for pipeline safety management.Aiming at the shortcomings of the BP Neural Network(BPNN)model,such as low learning efficiency,sensitivity to initial weights,and easy falling into a local optimal state,an Improved Sparrow Search Algorithm(ISSA)is adopted to optimize the initial weights and thresholds of BPNN,and an ISSA-BPNN failure pressure prediction model for corroded pipelines is established.Taking 61 sets of pipelines blasting test data as an example,the prediction model was built and predicted by MATLAB software,and compared with the BPNN model,GA-BPNN model,and SSA-BPNN model.The results show that the MAPE of the ISSA-BPNN model is 3.4177%,and the R2 is 0.9880,both of which are superior to its comparison model.Using the ISSA-BPNN model has high prediction accuracy and stability,and can provide support for pipeline inspection and maintenance.
基金the University of Teknologi PETRONAS(UTP),Malaysia,and Ahmadu Bello University,Nigeria,for their vital help and availability of laboratory facilities that allowed this work to be conducted successfully.
文摘The goals of this study are to assess the viability of waste tire-derived char(WTDC)as a sustainable,low-cost fine aggregate surrogate material for asphalt mixtures and to develop the statistically coupled neural network(SCNN)model for predicting volumetric and Marshall properties of asphalt mixtures modified with WTDC.The study is based on experimental data acquired from laboratory volumetric and Marshall properties testing on WTDCmodified asphalt mixtures(WTDC-MAM).The input variables comprised waste tire char content and asphalt binder content.The output variables comprised mixture unit weight,total voids,voids filled with asphalt,Marshall stability,and flow.Statistical coupled neural networks were utilized to predict the volumetric and Marshall properties of asphalt mixtures.For predictive modeling,the SCNN model is employed,incorporating a three-layer neural network and preprocessing techniques to enhance accuracy and reliability.The optimal network architecture,using the collected dataset,was a 2:6:5 structure,and the neural network was trained with 60%of the data,whereas the other 20%was used for cross-validation and testing respectively.The network employed a hyperbolic tangent(tanh)activation function and a feed-forward backpropagation.According to the results,the network model could accurately predict the volumetric and Marshall properties.The predicted accuracy of SCNN was found to be as high value>98%and low prediction errors for both volumetric and Marshall properties.This study demonstrates WTDC's potential as a low-cost,sustainable aggregate replacement.The SCNN-based predictive model proves its efficiency and versatility and promotes sustainable practices.
