There are some disadvantages, such as complicated wiring, high cost, poor monitoring flexibility, low accuracy and high energy consumption in traditional greenhouse environment monitoring system which based on previou...There are some disadvantages, such as complicated wiring, high cost, poor monitoring flexibility, low accuracy and high energy consumption in traditional greenhouse environment monitoring system which based on previous wireless sensor networks （WSN）. Aiming at these problems, a greenhouse environmental parameter monitoring system had been designed based on internet of things technology in this paper. A set of control system with good robustness, strong adaptive ability and small overshoot was set up by combining the fuzzy proportion-integral-derivative （PID） control. The system was composed of a number of independent greenhouse monitoring systems. The server could provide remote monitoring access management services after the collected data were transmitted. The data transmission part of greenhouse was based on ZigBee networking protocol. And the data were sent to intelligent system via gateway connected to the internet. Compared to the classical PID control and fuzzy control, the fuzzy PID control could quickly and accurately adjust the corresponding parameters to the set target. The overshoot was also relatively small. The simulation results showed that the amount of overshoot was reduced 20% compared with classical PID control.展开更多
To solve the problem of mistake recognition among rice diseases, automatic recognition methods based on BP(back propagation) neural network were studied in this paper for blast, sheath blight and bacterial blight. Cho...To solve the problem of mistake recognition among rice diseases, automatic recognition methods based on BP(back propagation) neural network were studied in this paper for blast, sheath blight and bacterial blight. Chose mobile terminal equipment as image collecting tool and built database of rice leaf images with diseases under threshold segmentation method. Characteristic parameters were extracted from color, shape and texture. Furthermore, parameters were optimized using the single-factor variance analysis and the effects of BP neural network model. The optimization would simplify BP neural network model without reducing the recognition accuracy. The finally model could successfully recognize 98%, 96% and 98% of rice blast, sheath blight and white leaf blight, respectively.展开更多
In winter, the confined pig house of northern China is severe. The environment variables are nonlinear, time-varying and coupled, which seriously affect the health of pigs and the qualities of the meat. In order to so...In winter, the confined pig house of northern China is severe. The environment variables are nonlinear, time-varying and coupled, which seriously affect the health of pigs and the qualities of the meat. In order to solve the problem multi-variables coupling, a multi-variables decoupled fuzzy logic control method was proposed. Two fuzzy logic controllers were designed based on fuzzy logic theory. The fans, heaters and humidifiers were used to control temperature, humidity and ammonia. The reductions of temperature and humidity caused by ventilating were compensated by heaters and humidifiers respectively which realized the multivariables decoupling. The proposed methods were validated through theoretical, experimental and simulation analysis. The results suggested that the methods were able to regulate the confined pig house environment effectively. In addition, comparing to the manual regulation, the proposed methods could reduce 19% power consumption as well.展开更多
Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional n...Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional neural network had the disadvantages in prolonged training at the additions of new cows samples.Therefore,a cow individual identification framework was proposed based on deep feature extraction and matching,and the individual identification of dairy cows based on this framework could avoid repeated training.Firstly,the trained convolutional neural network model was used as the feature extractor;secondly,the feature extraction was used to extract features and stored the features into the template feature library to complete the enrollment;finally,the identifies of dairy cows were identified.Based on this framework,when new cows joined the herd,enrollment could be completed quickly.In order to evaluate the application performance of this method in closed-set and open-set individual identification of dairy cows,back images of 524 cows were collected,among which the back images of 150 cows were selected as the training data to train feature extractor.The data of the remaining 374 cows were used to generate the template data set and the data to be identified.The experiment results showed that in the closed-set individual identification of dairy cows,the highest identification accuracy of top-1 was 99.73%,the highest identification accuracy from top-2 to top-5 was 100%,and the identification time of a single cow was 0.601 s,this method was verified to be effective.In the open-set individual identification of dairy cows,the recall was 90.38%,and the accuracy was 89.46%.When false accept rate(FAR)=0.05,true accept rate(TAR)=84.07%,this method was verified that the application had certain research value in open-set individual identification of dairy cows,which provided a certain idea for the application of individual identification in the field of intelligent animal husbandry.展开更多
基金Supported by the 13th Five-year National Key R&D Program:Development and Verification of Information Perception and Environment Intelligent Control System for Dairy Cattle and Beef Cattle(2016YFD0700204-02)Quality and Brand Construction of "Internet+County Characteristic Agricultural Products"(ZY17C06)
文摘There are some disadvantages, such as complicated wiring, high cost, poor monitoring flexibility, low accuracy and high energy consumption in traditional greenhouse environment monitoring system which based on previous wireless sensor networks （WSN）. Aiming at these problems, a greenhouse environmental parameter monitoring system had been designed based on internet of things technology in this paper. A set of control system with good robustness, strong adaptive ability and small overshoot was set up by combining the fuzzy proportion-integral-derivative （PID） control. The system was composed of a number of independent greenhouse monitoring systems. The server could provide remote monitoring access management services after the collected data were transmitted. The data transmission part of greenhouse was based on ZigBee networking protocol. And the data were sent to intelligent system via gateway connected to the internet. Compared to the classical PID control and fuzzy control, the fuzzy PID control could quickly and accurately adjust the corresponding parameters to the set target. The overshoot was also relatively small. The simulation results showed that the amount of overshoot was reduced 20% compared with classical PID control.
基金Supported by Quality and Brand Construction of"Internet+County Characteristic Agricultural Products"(ZY17C06)
文摘To solve the problem of mistake recognition among rice diseases, automatic recognition methods based on BP(back propagation) neural network were studied in this paper for blast, sheath blight and bacterial blight. Chose mobile terminal equipment as image collecting tool and built database of rice leaf images with diseases under threshold segmentation method. Characteristic parameters were extracted from color, shape and texture. Furthermore, parameters were optimized using the single-factor variance analysis and the effects of BP neural network model. The optimization would simplify BP neural network model without reducing the recognition accuracy. The finally model could successfully recognize 98%, 96% and 98% of rice blast, sheath blight and white leaf blight, respectively.
基金Supported by the 13th Five-year National Key R&D Program(2016YFD0700204-02)the"Young Talents"Project of Northeast Agricultural University(17QC20,17QC19)the Earmarked Fund for China Agriculture Research System(CARS-35)
文摘In winter, the confined pig house of northern China is severe. The environment variables are nonlinear, time-varying and coupled, which seriously affect the health of pigs and the qualities of the meat. In order to solve the problem multi-variables coupling, a multi-variables decoupled fuzzy logic control method was proposed. Two fuzzy logic controllers were designed based on fuzzy logic theory. The fans, heaters and humidifiers were used to control temperature, humidity and ammonia. The reductions of temperature and humidity caused by ventilating were compensated by heaters and humidifiers respectively which realized the multivariables decoupling. The proposed methods were validated through theoretical, experimental and simulation analysis. The results suggested that the methods were able to regulate the confined pig house environment effectively. In addition, comparing to the manual regulation, the proposed methods could reduce 19% power consumption as well.
基金Supported by the National Key Research and Development Program of China(2019YFE0125600)China Agriculture Research System(CARS-36)。
文摘Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional neural network had the disadvantages in prolonged training at the additions of new cows samples.Therefore,a cow individual identification framework was proposed based on deep feature extraction and matching,and the individual identification of dairy cows based on this framework could avoid repeated training.Firstly,the trained convolutional neural network model was used as the feature extractor;secondly,the feature extraction was used to extract features and stored the features into the template feature library to complete the enrollment;finally,the identifies of dairy cows were identified.Based on this framework,when new cows joined the herd,enrollment could be completed quickly.In order to evaluate the application performance of this method in closed-set and open-set individual identification of dairy cows,back images of 524 cows were collected,among which the back images of 150 cows were selected as the training data to train feature extractor.The data of the remaining 374 cows were used to generate the template data set and the data to be identified.The experiment results showed that in the closed-set individual identification of dairy cows,the highest identification accuracy of top-1 was 99.73%,the highest identification accuracy from top-2 to top-5 was 100%,and the identification time of a single cow was 0.601 s,this method was verified to be effective.In the open-set individual identification of dairy cows,the recall was 90.38%,and the accuracy was 89.46%.When false accept rate(FAR)=0.05,true accept rate(TAR)=84.07%,this method was verified that the application had certain research value in open-set individual identification of dairy cows,which provided a certain idea for the application of individual identification in the field of intelligent animal husbandry.
