An experimental platform with bracket structures,cables,parallel computer and imaging system is designed for defects detecting on steel rails. Meanwhile,an improved gradient descent algorithm based on a self-adaptive ...An experimental platform with bracket structures,cables,parallel computer and imaging system is designed for defects detecting on steel rails. Meanwhile,an improved gradient descent algorithm based on a self-adaptive learning rate and a fixed momentum factor is developed to train back-propagation neural network for accurate and efficient defects classifications. Detection results of rolling scar defects show that such detection system can achieve accurate positioning to defects edges for its improved noise suppression. More precise characteristic parameters of defects can also be extracted.Furthermore,defects classification is adopted to remedy the limitations of low convergence rate and local minimum. It can also attain the optimal training precision of 0. 00926 with the least 96 iterations. Finally,an enhanced identification rate of 95% has been confirmed for defects by using the detection system. It will also be positive in producing high-quality steel rails and guaranteeing the national transport safety.展开更多
The studies on dynamics of a fault bearing system are prevalent in recent years, however, we are studying a completely different frequency range than the one where the bearing faults are best seen. Considering a local...The studies on dynamics of a fault bearing system are prevalent in recent years, however, we are studying a completely different frequency range than the one where the bearing faults are best seen. Considering a local defect on outer raceway,a two-degree-of-freedom analytical model of a rigid-rotor ball bearing system is established. Three pulse force models are introduced to simulate the local defect. The frequency domain method—harmonic balance method with alternating frequency/time domain technique (HB-AFT) is used to calculate the response in a large frequency range. By comparing the performance at different frequencies, the fault systems with different defect models and parameters reveal the super-harmonic resonances,and the reasons for this phenomenon are uncovered as well. Finally, the theoretical calculation is verified qualitatively by the experimental results, through comparing the frequency spectrums of the defective bearing rotor system to the fault-free one.Therefore, the super-harmonic resonances can be regarded as a dynamic feature. Besides, the obvious super-harmonic resonances indicate the magnification of the harmonics of the "characteristic defect frequency" for outer race in the corresponding speed regions, which may be helpful for the diagnosis of a rotor ball bearing system with a local defect.展开更多
基金Supported by the National Natural Science Foundation of China(No.51174151)the Key Scientific Research Project of Education Department of Hubei Province(No.D20151102)the Key Scientific and Technological Project of Wuhan Technology Bureau(No.2014010202010088)
文摘An experimental platform with bracket structures,cables,parallel computer and imaging system is designed for defects detecting on steel rails. Meanwhile,an improved gradient descent algorithm based on a self-adaptive learning rate and a fixed momentum factor is developed to train back-propagation neural network for accurate and efficient defects classifications. Detection results of rolling scar defects show that such detection system can achieve accurate positioning to defects edges for its improved noise suppression. More precise characteristic parameters of defects can also be extracted.Furthermore,defects classification is adopted to remedy the limitations of low convergence rate and local minimum. It can also attain the optimal training precision of 0. 00926 with the least 96 iterations. Finally,an enhanced identification rate of 95% has been confirmed for defects by using the detection system. It will also be positive in producing high-quality steel rails and guaranteeing the national transport safety.
基金supported by the National Key Basic Research Program of China (Grant No. 2015CB057400)the National Natural Science Foundation of China (Grant No. 11602070)China Postdoctoral Science Foundation(Grant No. 2016M590277).
文摘The studies on dynamics of a fault bearing system are prevalent in recent years, however, we are studying a completely different frequency range than the one where the bearing faults are best seen. Considering a local defect on outer raceway,a two-degree-of-freedom analytical model of a rigid-rotor ball bearing system is established. Three pulse force models are introduced to simulate the local defect. The frequency domain method—harmonic balance method with alternating frequency/time domain technique (HB-AFT) is used to calculate the response in a large frequency range. By comparing the performance at different frequencies, the fault systems with different defect models and parameters reveal the super-harmonic resonances,and the reasons for this phenomenon are uncovered as well. Finally, the theoretical calculation is verified qualitatively by the experimental results, through comparing the frequency spectrums of the defective bearing rotor system to the fault-free one.Therefore, the super-harmonic resonances can be regarded as a dynamic feature. Besides, the obvious super-harmonic resonances indicate the magnification of the harmonics of the "characteristic defect frequency" for outer race in the corresponding speed regions, which may be helpful for the diagnosis of a rotor ball bearing system with a local defect.
