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
Torsional vibration of roller oscillating tooth gear drive (ROTGD) is studied in this paper. On the basis of conservation law for kinetic energy and potential energy, the mathematical expressions are developed which d...Torsional vibration of roller oscillating tooth gear drive (ROTGD) is studied in this paper. On the basis of conservation law for kinetic energy and potential energy, the mathematical expressions are developed which describe transformation of moment of inertia of inertial components into input shaft. Also, the formula is derived which expresses transformation of contact stiffness of elastic components into input shaft torsional stiffness. Besides, torsional vibration model of ROTGD is presented by using the transfer matrix method, and natural frequencies and vibration mode shapes are determined. Eventually, an example is given.展开更多
To minimize quenching distortion and dispersion, carburizing and quenching process conditions must be optimized; this includes the parts racking design used for quenching. We investigated some factors affecting carbur...To minimize quenching distortion and dispersion, carburizing and quenching process conditions must be optimized; this includes the parts racking design used for quenching. We investigated some factors affecting carburized quenching distortion with an experiment using a hypoid gear having a shaft and with numerical simulation methods. The experimental results and those obtained from simulation were generally in agreement. Focusing on the surface temperature distribution in the gear, we studied quenching distortion characteristics in terms of changes in tooth profile and helix deviation. In our experiments, distortions occur during quenching in 373 K oil after austenitized temperature treatments conducted with various attitudes. We calculated the distortions by simulating the carburized oil-quenching process for the hypoid gear. Our results show large differences between the cooling rates of the tooth toe, middle section, and heel edges, and these greatly influence the change in tooth profile and helix deviation. We found that reducing the differences in temperatures on the gear surfaces during quenching is most important for minimizing the quench distortion of the hypoid gear.展开更多
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Torsional vibration of roller oscillating tooth gear drive (ROTGD) is studied in this paper. On the basis of conservation law for kinetic energy and potential energy, the mathematical expressions are developed which describe transformation of moment of inertia of inertial components into input shaft. Also, the formula is derived which expresses transformation of contact stiffness of elastic components into input shaft torsional stiffness. Besides, torsional vibration model of ROTGD is presented by using the transfer matrix method, and natural frequencies and vibration mode shapes are determined. Eventually, an example is given.
文摘To minimize quenching distortion and dispersion, carburizing and quenching process conditions must be optimized; this includes the parts racking design used for quenching. We investigated some factors affecting carburized quenching distortion with an experiment using a hypoid gear having a shaft and with numerical simulation methods. The experimental results and those obtained from simulation were generally in agreement. Focusing on the surface temperature distribution in the gear, we studied quenching distortion characteristics in terms of changes in tooth profile and helix deviation. In our experiments, distortions occur during quenching in 373 K oil after austenitized temperature treatments conducted with various attitudes. We calculated the distortions by simulating the carburized oil-quenching process for the hypoid gear. Our results show large differences between the cooling rates of the tooth toe, middle section, and heel edges, and these greatly influence the change in tooth profile and helix deviation. We found that reducing the differences in temperatures on the gear surfaces during quenching is most important for minimizing the quench distortion of the hypoid gear.