The incremental improved Back-Propagation （BP） neural network prediction model using the Levenberg-Marquardt algorithm based on optimizing theory is put forward, which can solve the problems existing in the process ...The incremental improved Back-Propagation （BP） neural network prediction model using the Levenberg-Marquardt algorithm based on optimizing theory is put forward, which can solve the problems existing in the process of calcinations for ammonium diuranate （ADU） by microwave heating, such as long testing cycle, high testing quan- tity, difficulty of optimization for process parameters. Many training data probably were offered by the way of increment batch and the limitation of the system mem- ory could make the training data infeasible when the sample scale was large. The prediction model of the nonlinear system is built, which can effectively predict the experiment of microwave calcining of ADU, and the incremental improved BP neural network is very useful in overeoining the local minimum problem, finding the global optimal solution and accelerating the convergence speed.展开更多
This study proposes a classification model of equipment fault diagnosis based on integrated incremental learning mechanism on the basis of characteristics of industrial equipment status data.The model first proposes a...This study proposes a classification model of equipment fault diagnosis based on integrated incremental learning mechanism on the basis of characteristics of industrial equipment status data.The model first proposes a dynamic weight combination classification model based on long short-term memory(LSTM)and support vector machine(SVM).It solved the problem of fault feature extraction and classification in high noise equipment state data.Then,in this model,integrated incremental learning mechanism and unbalanced data processing technology were introduced to solve problems of massive unbalanced new data feature extraction and classification and sample category imbalance under equipment status data.Finally,an equipment fault diagnosis classification model based on integrated incremental dynamic weight combination is formed.Experiments prove that the model can effectively overcome the problems of excessive data volume,unbalanced,high noise,and inability to correlate data samples in the process of equipment fault diagnosis.展开更多
基金supported by the National Natural Science Foundation of China (No.50734007)Technology Project of Yunnan Province (No.2007GA002)
文摘The incremental improved Back-Propagation （BP） neural network prediction model using the Levenberg-Marquardt algorithm based on optimizing theory is put forward, which can solve the problems existing in the process of calcinations for ammonium diuranate （ADU） by microwave heating, such as long testing cycle, high testing quan- tity, difficulty of optimization for process parameters. Many training data probably were offered by the way of increment batch and the limitation of the system mem- ory could make the training data infeasible when the sample scale was large. The prediction model of the nonlinear system is built, which can effectively predict the experiment of microwave calcining of ADU, and the incremental improved BP neural network is very useful in overeoining the local minimum problem, finding the global optimal solution and accelerating the convergence speed.
基金Tianjin Science and Technology Project under Grant No.18YFCZZC00060 and No.18ZXZNGX00100Hebei Provincial Natural Science Foundation Project under Grant No.F2019202062.
文摘This study proposes a classification model of equipment fault diagnosis based on integrated incremental learning mechanism on the basis of characteristics of industrial equipment status data.The model first proposes a dynamic weight combination classification model based on long short-term memory(LSTM)and support vector machine(SVM).It solved the problem of fault feature extraction and classification in high noise equipment state data.Then,in this model,integrated incremental learning mechanism and unbalanced data processing technology were introduced to solve problems of massive unbalanced new data feature extraction and classification and sample category imbalance under equipment status data.Finally,an equipment fault diagnosis classification model based on integrated incremental dynamic weight combination is formed.Experiments prove that the model can effectively overcome the problems of excessive data volume,unbalanced,high noise,and inability to correlate data samples in the process of equipment fault diagnosis.
