Effective fault diagnosis has a crucial impact on the safety and cost of complex manufacturing systems.However,the complex structure of the collected multisource data and scarcity of fault samples make it difficult to...Effective fault diagnosis has a crucial impact on the safety and cost of complex manufacturing systems.However,the complex structure of the collected multisource data and scarcity of fault samples make it difficult to accurately identify multiple fault conditions.To address this challenge,this paper proposes a novel deep-learning model for multisource data augmentation and small sample fault diagnosis.The raw multisource data are first converted into two-dimensional images using the Gramian Angular Field,and a generator is built to transform random noise into images through transposed convolution operations.Then,two discriminators are constructed to evaluate the authenticity of input images and the fault diagnosis ability.The Vision Transformer network is built to diagnose faults and obtain the classification error for the discriminator.Furthermore,a global optimization strategy is designed to upgrade parameters in the model.The discriminators and generator compete with each other until Nash equilibrium is achieved.A real-world multistep forging machine is adopted to compare and validate the performance of different methods.The experimental results indicate that the proposed method has multisource data augmentation and minority sample fault diagnosis capabilities.Compared with other state-of-the-art models,the proposed approach has better fault diagnosis accuracy in various scenarios.展开更多
Aiming at the sensor faults of near-space hypersonic vehicles(NSHV), a fault identification method based on the extended state observer and kernel extreme learning machine(ESO-KELM) is proposed in this paper. The meth...Aiming at the sensor faults of near-space hypersonic vehicles(NSHV), a fault identification method based on the extended state observer and kernel extreme learning machine(ESO-KELM) is proposed in this paper. The method is generated by a combination of the model-based method and the data-driven method. As the source of the fault diagnosis, the residual signals represent the difference between the ESO output and the result measured by the sensor in particular. The energy of the residual signals is distributed in both low frequency bands and high frequency bands. However, the energy of the sensor concentrates on the low-frequency bands. Combined with more different features detected by KELM, the proposed method devotes to improving the accuracy. Meanwhile, it is competent to calculate the magnitude of minor faults based on time-frequency analysis. Finally, the simulation is performed on the longitudinal channel of the Winged-Cone model published by the national aeronautics and space administration(NASA). Results show the validity and the accuracy in calculating the magnitude of the minor faults.展开更多
基金supported by“the Fundamental Research Funds for the Central Universities,”Grant/Award Number 30923011008.
文摘Effective fault diagnosis has a crucial impact on the safety and cost of complex manufacturing systems.However,the complex structure of the collected multisource data and scarcity of fault samples make it difficult to accurately identify multiple fault conditions.To address this challenge,this paper proposes a novel deep-learning model for multisource data augmentation and small sample fault diagnosis.The raw multisource data are first converted into two-dimensional images using the Gramian Angular Field,and a generator is built to transform random noise into images through transposed convolution operations.Then,two discriminators are constructed to evaluate the authenticity of input images and the fault diagnosis ability.The Vision Transformer network is built to diagnose faults and obtain the classification error for the discriminator.Furthermore,a global optimization strategy is designed to upgrade parameters in the model.The discriminators and generator compete with each other until Nash equilibrium is achieved.A real-world multistep forging machine is adopted to compare and validate the performance of different methods.The experimental results indicate that the proposed method has multisource data augmentation and minority sample fault diagnosis capabilities.Compared with other state-of-the-art models,the proposed approach has better fault diagnosis accuracy in various scenarios.
基金supported by the National Natural Science Foundation of China(62073020)。
文摘Aiming at the sensor faults of near-space hypersonic vehicles(NSHV), a fault identification method based on the extended state observer and kernel extreme learning machine(ESO-KELM) is proposed in this paper. The method is generated by a combination of the model-based method and the data-driven method. As the source of the fault diagnosis, the residual signals represent the difference between the ESO output and the result measured by the sensor in particular. The energy of the residual signals is distributed in both low frequency bands and high frequency bands. However, the energy of the sensor concentrates on the low-frequency bands. Combined with more different features detected by KELM, the proposed method devotes to improving the accuracy. Meanwhile, it is competent to calculate the magnitude of minor faults based on time-frequency analysis. Finally, the simulation is performed on the longitudinal channel of the Winged-Cone model published by the national aeronautics and space administration(NASA). Results show the validity and the accuracy in calculating the magnitude of the minor faults.