Gravel packing sand control(GPSC),as the optimization of mechanical sand control technology,is widely used in the deep water completion and sand control of loose sandstone heavy oil reservoirs and highly argillaceous....Gravel packing sand control(GPSC),as the optimization of mechanical sand control technology,is widely used in the deep water completion and sand control of loose sandstone heavy oil reservoirs and highly argillaceous.To explore the blocking mechanism of GPSC,the influence of its structural parameters on the blocking of GPSC is investigated.This paper establishes a particle element model based on computational fluid dynamics-discrete element method coupling using the discrete element method and establishes a fluid flow model combined with computational fluid dynamics to realize their full coupling solution.And sand control experiments were carried out using a micro visual sand control simulation device to verify the blocking model.The blocking mechanism is analyzed from the microscopic point of view,and then,the influence of sand control structure parameters on the blocking in GPSC design is evaluated.The results show the following:(1)the blocking process of GPSC can be divided into three stages:an initial stage,sand accumulation stage,and equilibrium stage.(2)There are two main types of gravel packing blockage.The first type of blocking is blocking on the surface of the gravel layer.Sand particles on the surface of gravel layer mainly exist in the form of large particle size blocking gravel pores and sand particles bridging each other.The second type of blockage is the blockage inside the gravel layer.Sand particles mainly exist in the form of internal mud cakes and adsorption on gravels inside the gravel layer.(3)To ensure the sand control performance of the gravel layer,the gravel layer thickness is designed between 23 and 28 mm.The displacement or pressure of the on-site packing pump should be increased to ensure that the gravel layer packing solidity ranges between 59%and 62%.In the design of GPSC,it should be ensured that the median particle size of gravel is 5–6 times the median particle size of sand.This study provides an effective technical reference for the design of gravel structural parameters in on-site gravel packing completion sand control.展开更多
In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed ...In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed to provide core technical support for real-time water surface litter detection by water surface litter cleanup vessels.The method reduces network parameters by introducing the deep separable convolution GhostConv in the lightweight network GhostNet to substitute the ordinary convolution in the original YOLOv5s feature extraction and fusion network;introducing the C3Ghost module to substitute the C3 module in the original backbone and neck networks to further reduce computational effort.Using a Convolutional Block Attention Mechanism(CBAM)module in the backbone network to strengthen the network’s ability to extract significant target features from images.Finally,the loss function is optimized using the Focal-EIoU loss func-tion to improve the convergence speed and model accuracy.The experimental results illustrate that the improved algorithm outperforms the original Yolov5s in all aspects of the homemade water surface litter dataset and has certain advantages over some current mainstream algorithms in terms of model size,detection accuracy,and speed,which can deal with the problems of real-time detection of water surface litter in real life.展开更多
An optimal design problem of local buffer allocation in the FMS is discussed in order to maximize a reward earned from processed jobs at all workstations. Structural properties of the optimal design problem are analyz...An optimal design problem of local buffer allocation in the FMS is discussed in order to maximize a reward earned from processed jobs at all workstations. Structural properties of the optimal design problem are analyzed for the model with two job routing policies. Based on these properties, approaches to optimal solutions are given.展开更多
A“cloud-edge-end”collaborative system architecture is adopted for real-time security management of power system on-site work,and mobile edge computing equipment utilizes lightweight intelligent recognition algorithm...A“cloud-edge-end”collaborative system architecture is adopted for real-time security management of power system on-site work,and mobile edge computing equipment utilizes lightweight intelligent recognition algorithms for on-site risk assessment and alert.Owing to its lightweight and fast speed,YOLOv4-Tiny is often deployed on edge computing equipment for real-time video stream detection;however,its accuracy is relatively low.This study proposes an improved YOLOv4-Tiny algorithm based on attention mechanism and optimized training methods,achieving higher accuracy without compromising the speed.Specifically,a convolution block attention module branch is added to the backbone network to enhance the feature extraction capability and an efficient channel attention mechanism is added in the neck network to improve feature utilization.Moreover,three optimized training methods:transfer learning,mosaic data augmentation,and label smoothing are used to improve the training effect of this improved algorithm.Finally,an edge computing equipment experimental platform equipped with an NVIDIA Jetson Xavier NX chip is established and the newly developed algorithm is tested on it.According to the results,the speed of the improved YOLOv4-Tiny algorithm in detecting on-site dress code compliance datasets is 17.25 FPS,and the mean average precision(mAP)is increased from 70.89%to 85.03%.展开更多
In the Wenchuan Earthquake area,many co-seismic landslides formed blocking-dams in debris flow channels. This blocking and bursting of landslide dams amplifies the debris flow scale and results in severe catastrophes....In the Wenchuan Earthquake area,many co-seismic landslides formed blocking-dams in debris flow channels. This blocking and bursting of landslide dams amplifies the debris flow scale and results in severe catastrophes. The catastrophic debris flow that occurred in Qipan gully(Wenchuan,Southwest China) on July 11,2013 was caused by intense rainfall and upstream cascading bursting of landslide dams. To gain an understanding of the processes of dam bursting and subsequent debris flow scale amplification effect,we attempted to estimate the bursting debris flow peak discharges along the main gully and analyzed the scale amplification process. The results showed that the antecedent and triggering rainfalls for 11 July debris flow event were 88.0 mm and 21.6 mm,respectively. The event highlights the fact that lower rainfall intensity can trigger debris flows after the earthquake. Calculations of the debris flow peak discharge showed that the peak discharges after the dams-bursting were 1.17–1.69 times greater than the upstream peak discharge. The peak discharge at the gully outlet reached 2553 m^3/s which was amplified by 4.76 times in comparison with the initial peak discharge in the upstream. To mitigate debris flow disasters,a new drainage channel with a trapezoidal V-shaped cross section was proposed. The characteristic lengths(h1 and h2) under optimal hydraulic conditions were calculated as 4.50 m and 0.90 m,respectively.展开更多
基金The National Natural Science Foundation of China(Grant No.51504040).
文摘Gravel packing sand control(GPSC),as the optimization of mechanical sand control technology,is widely used in the deep water completion and sand control of loose sandstone heavy oil reservoirs and highly argillaceous.To explore the blocking mechanism of GPSC,the influence of its structural parameters on the blocking of GPSC is investigated.This paper establishes a particle element model based on computational fluid dynamics-discrete element method coupling using the discrete element method and establishes a fluid flow model combined with computational fluid dynamics to realize their full coupling solution.And sand control experiments were carried out using a micro visual sand control simulation device to verify the blocking model.The blocking mechanism is analyzed from the microscopic point of view,and then,the influence of sand control structure parameters on the blocking in GPSC design is evaluated.The results show the following:(1)the blocking process of GPSC can be divided into three stages:an initial stage,sand accumulation stage,and equilibrium stage.(2)There are two main types of gravel packing blockage.The first type of blocking is blocking on the surface of the gravel layer.Sand particles on the surface of gravel layer mainly exist in the form of large particle size blocking gravel pores and sand particles bridging each other.The second type of blockage is the blockage inside the gravel layer.Sand particles mainly exist in the form of internal mud cakes and adsorption on gravels inside the gravel layer.(3)To ensure the sand control performance of the gravel layer,the gravel layer thickness is designed between 23 and 28 mm.The displacement or pressure of the on-site packing pump should be increased to ensure that the gravel layer packing solidity ranges between 59%and 62%.In the design of GPSC,it should be ensured that the median particle size of gravel is 5–6 times the median particle size of sand.This study provides an effective technical reference for the design of gravel structural parameters in on-site gravel packing completion sand control.
基金Support for this work was in part from the China University Industry-University Research Innovation Fund Project(No.2022BL052),author B.T,https://www.cutech.edu.cnin part by the Science and Technology InnovationR&DProject of the State GeneralAdministration of Sports of China(No.22KJCX024),author B.T,https://www.sport.gov.cn+1 种基金in part by the Major Project of Philosophy and Social Science Research in Higher Education Institutions in Hubei Province(No.21ZD054),author B.T,https://jyt.hubei.gov.cnKey Project of Hubei Provincial Key Laboratory of Intelligent Transportation Technology and Equipment Open Fund(No.2022XZ106),author B.T,https://hbpu.edu.cn.
文摘In response to the problem of the high cost and low efficiency of traditional water surface litter cleanup through manpower,a lightweight water surface litter detection algorithm based on improved YOLOv5s is proposed to provide core technical support for real-time water surface litter detection by water surface litter cleanup vessels.The method reduces network parameters by introducing the deep separable convolution GhostConv in the lightweight network GhostNet to substitute the ordinary convolution in the original YOLOv5s feature extraction and fusion network;introducing the C3Ghost module to substitute the C3 module in the original backbone and neck networks to further reduce computational effort.Using a Convolutional Block Attention Mechanism(CBAM)module in the backbone network to strengthen the network’s ability to extract significant target features from images.Finally,the loss function is optimized using the Focal-EIoU loss func-tion to improve the convergence speed and model accuracy.The experimental results illustrate that the improved algorithm outperforms the original Yolov5s in all aspects of the homemade water surface litter dataset and has certain advantages over some current mainstream algorithms in terms of model size,detection accuracy,and speed,which can deal with the problems of real-time detection of water surface litter in real life.
文摘An optimal design problem of local buffer allocation in the FMS is discussed in order to maximize a reward earned from processed jobs at all workstations. Structural properties of the optimal design problem are analyzed for the model with two job routing policies. Based on these properties, approaches to optimal solutions are given.
基金supported by the Science and technology project of State Grid Information&Telecommunication Group Co.,Ltd (SGTYHT/19-JS-218)
文摘A“cloud-edge-end”collaborative system architecture is adopted for real-time security management of power system on-site work,and mobile edge computing equipment utilizes lightweight intelligent recognition algorithms for on-site risk assessment and alert.Owing to its lightweight and fast speed,YOLOv4-Tiny is often deployed on edge computing equipment for real-time video stream detection;however,its accuracy is relatively low.This study proposes an improved YOLOv4-Tiny algorithm based on attention mechanism and optimized training methods,achieving higher accuracy without compromising the speed.Specifically,a convolution block attention module branch is added to the backbone network to enhance the feature extraction capability and an efficient channel attention mechanism is added in the neck network to improve feature utilization.Moreover,three optimized training methods:transfer learning,mosaic data augmentation,and label smoothing are used to improve the training effect of this improved algorithm.Finally,an edge computing equipment experimental platform equipped with an NVIDIA Jetson Xavier NX chip is established and the newly developed algorithm is tested on it.According to the results,the speed of the improved YOLOv4-Tiny algorithm in detecting on-site dress code compliance datasets is 17.25 FPS,and the mean average precision(mAP)is increased from 70.89%to 85.03%.
基金financially supported by the National Natural Science Foundation of China (Grant No.41572302)the Funds for Creative Research Groups of China (Grant No.41521002)
文摘In the Wenchuan Earthquake area,many co-seismic landslides formed blocking-dams in debris flow channels. This blocking and bursting of landslide dams amplifies the debris flow scale and results in severe catastrophes. The catastrophic debris flow that occurred in Qipan gully(Wenchuan,Southwest China) on July 11,2013 was caused by intense rainfall and upstream cascading bursting of landslide dams. To gain an understanding of the processes of dam bursting and subsequent debris flow scale amplification effect,we attempted to estimate the bursting debris flow peak discharges along the main gully and analyzed the scale amplification process. The results showed that the antecedent and triggering rainfalls for 11 July debris flow event were 88.0 mm and 21.6 mm,respectively. The event highlights the fact that lower rainfall intensity can trigger debris flows after the earthquake. Calculations of the debris flow peak discharge showed that the peak discharges after the dams-bursting were 1.17–1.69 times greater than the upstream peak discharge. The peak discharge at the gully outlet reached 2553 m^3/s which was amplified by 4.76 times in comparison with the initial peak discharge in the upstream. To mitigate debris flow disasters,a new drainage channel with a trapezoidal V-shaped cross section was proposed. The characteristic lengths(h1 and h2) under optimal hydraulic conditions were calculated as 4.50 m and 0.90 m,respectively.
