Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of productio...Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of production process often lead to the changes of data distribution and the emergence of new fault classes, and the number of the new fault classes is unpredictable. The reconstruction of the fault diagnosis model and the identification of new fault classes have become core issues under the circumstances. This paper presents a fault diagnosis method based on model transfer learning and the main contributions of the paper are as follows: 1) An incremental model transfer fault diagnosis method is proposed to reconstruct the new process diagnosis model. 2) Breaking the limit of existing method that the new process can only have one more class of faults than the old process, this method can identify M faults more in the new process with the thought of incremental learning. 3) The method offers a solution to a series of problems caused by the increase of fault classes. Experiments based on Tennessee-Eastman process and ore grinding classification process demonstrate the effectiveness and the feasibility of the method.展开更多
Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network an...Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network and transfer learning was proposed. Firstly, one-dimensional signal is transformed into two-dimensional time-frequency image by continuous wavelet transform. Then, a deep learning model based on ResNet50 is constructed. Attention mechanism is introduced into the model to make the model pay more attention to the useful features for the current task. The network parameters trained by ResNet50 network on ImageNet dataset were used to initialize the model and applied to the fault diagnosis field. Finally, to solve the problem of gear fault diagnosis under different working conditions, a small sample training set is proposed for fault diagnosis. The method is applied to gearbox fault diagnosis, and the results show that: The proposed deep model achieves 99.7% accuracy of gear fault diagnosis, which is better than the four models such as VGG19 and MobileNetV2. In the cross-working condition fault diagnosis, only 20% target dataset is used as the training set, and the proposed method achieves 93.5% accuracy.展开更多
Trend forecasting is an important aspect in fault diagnosis and work state supervision. The principle, where Grey theory is applied in fault forecasting, is that the forecast system is considered as a Grey system; the...Trend forecasting is an important aspect in fault diagnosis and work state supervision. The principle, where Grey theory is applied in fault forecasting, is that the forecast system is considered as a Grey system; the existing known information is used to infer the unknown information's character, state and development trend in a fault pattern, and to make possible forecasting and decisions for future development. It involves the whitenization of a Grey process. But the traditional equal time interval Grey GM (1,1) model requires equal interval data and needs to bring about accumulating addition generation and reversion calculations. Its calculation is very complex. However, the non equal interval Grey GM (1,1) model decreases the condition of the primitive data when establishing a model, but its requirement is still higher and the data were pre processed. The abrasion primitive data of plant could not always satisfy these modeling requirements. Therefore, it establishes a division method suited for general data modeling and estimating parameters of GM (1,1), the standard error coefficient that was applied to judge accuracy height of the model was put forward; further, the function transform to forecast plant abrasion trend and assess GM (1,1) parameter was established. These two models need not pre process the primitive data. It is not only suited for equal interval data modeling, but also for non equal interval data modeling. Its calculation is simple and convenient to use. The oil spectrum analysis acted as an example. The two GM (1,1) models put forward in this paper and the new information model and its comprehensive usage were investigated. The example shows that the two models are simple and practical, and worth expanding and applying in plant fault diagnosis.展开更多
文摘Fault diagnosis is an important measure to ensure the safety of production, and all kinds of fault diagnosis methods are of importance in actual production process. However, the complexity and uncertainty of production process often lead to the changes of data distribution and the emergence of new fault classes, and the number of the new fault classes is unpredictable. The reconstruction of the fault diagnosis model and the identification of new fault classes have become core issues under the circumstances. This paper presents a fault diagnosis method based on model transfer learning and the main contributions of the paper are as follows: 1) An incremental model transfer fault diagnosis method is proposed to reconstruct the new process diagnosis model. 2) Breaking the limit of existing method that the new process can only have one more class of faults than the old process, this method can identify M faults more in the new process with the thought of incremental learning. 3) The method offers a solution to a series of problems caused by the increase of fault classes. Experiments based on Tennessee-Eastman process and ore grinding classification process demonstrate the effectiveness and the feasibility of the method.
基金Supported by National Natural Science Foundation of P. R. China （60574083）, Key Laboratory of Process Industry Automation, State Education Ministry of China （PAL200514）
文摘Aiming at the problems of lack of fault diagnosis samples and low model generalization ability of cross-working gear based on deep transfer learning, a fault diagnosis method based on improved deep residual network and transfer learning was proposed. Firstly, one-dimensional signal is transformed into two-dimensional time-frequency image by continuous wavelet transform. Then, a deep learning model based on ResNet50 is constructed. Attention mechanism is introduced into the model to make the model pay more attention to the useful features for the current task. The network parameters trained by ResNet50 network on ImageNet dataset were used to initialize the model and applied to the fault diagnosis field. Finally, to solve the problem of gear fault diagnosis under different working conditions, a small sample training set is proposed for fault diagnosis. The method is applied to gearbox fault diagnosis, and the results show that: The proposed deep model achieves 99.7% accuracy of gear fault diagnosis, which is better than the four models such as VGG19 and MobileNetV2. In the cross-working condition fault diagnosis, only 20% target dataset is used as the training set, and the proposed method achieves 93.5% accuracy.
文摘Trend forecasting is an important aspect in fault diagnosis and work state supervision. The principle, where Grey theory is applied in fault forecasting, is that the forecast system is considered as a Grey system; the existing known information is used to infer the unknown information's character, state and development trend in a fault pattern, and to make possible forecasting and decisions for future development. It involves the whitenization of a Grey process. But the traditional equal time interval Grey GM (1,1) model requires equal interval data and needs to bring about accumulating addition generation and reversion calculations. Its calculation is very complex. However, the non equal interval Grey GM (1,1) model decreases the condition of the primitive data when establishing a model, but its requirement is still higher and the data were pre processed. The abrasion primitive data of plant could not always satisfy these modeling requirements. Therefore, it establishes a division method suited for general data modeling and estimating parameters of GM (1,1), the standard error coefficient that was applied to judge accuracy height of the model was put forward; further, the function transform to forecast plant abrasion trend and assess GM (1,1) parameter was established. These two models need not pre process the primitive data. It is not only suited for equal interval data modeling, but also for non equal interval data modeling. Its calculation is simple and convenient to use. The oil spectrum analysis acted as an example. The two GM (1,1) models put forward in this paper and the new information model and its comprehensive usage were investigated. The example shows that the two models are simple and practical, and worth expanding and applying in plant fault diagnosis.
