Grinding is known as the most complicated material removal process and the method for monitoring the grinding wheel wear has its own characteristics comparing with the approaches for detecting the wear on regular cutt...Grinding is known as the most complicated material removal process and the method for monitoring the grinding wheel wear has its own characteristics comparing with the approaches for detecting the wear on regular cutting tools.Research efforts were made to develop the wheel wear monitoring system due to its significance in grinding process.This paper presents a novel method for identification of grinding wheel wear signature by combination of wavelet packet decomposition(WPD) based energies.The distinctive feature of the method is that it takes advantage of the combinational information of the decomposed frequency components based on the WPD so the extracted features can be customized according to the specific monitored object to get better diagnosis effects.Experiments are researched on monitoring of grinding wheel wear states under different machining conditions.The results show that the energy ratio extracted from the measured vibration signals is consistent with the grinding wheel wear condition evaluated by experiment and the further extracted feature ratio can be used in prediction of wheel wear condition.展开更多
This paper proposes a hybrid deep reinforcement learning framework for locomotive axle temperature by combining the wavelet packet decomposition(WPD),long short-term memory(LSTM),gated recurrent unit(GRU)reinforcement...This paper proposes a hybrid deep reinforcement learning framework for locomotive axle temperature by combining the wavelet packet decomposition(WPD),long short-term memory(LSTM),gated recurrent unit(GRU)reinforcement learning and generalized autoregressive conditional heteroskedasticity(GARCH)algorithms.The WPD is utilized to decompose the raw nonlinear series into subseries.Then the deep learning predictors LSTM and GRU are established to predict the future axle temperatures in each subseries.The Q-learning could generate optimal ensembleweights to integrate the predictors to finish the deterministic forecasting and GARCH is used to conduct the deterministic forecasting based on the deterministic forecasting residual.These parts of the hybrid ensemble structure contributed to optimal modelling accuracy and provided effective support in the real-time monitoring and fault diagnosis of transportation.展开更多
基金the National Key Laboratory of Mechanical Transmission Foundation of China(No. SKLMT-KFKT-200812)
文摘Grinding is known as the most complicated material removal process and the method for monitoring the grinding wheel wear has its own characteristics comparing with the approaches for detecting the wear on regular cutting tools.Research efforts were made to develop the wheel wear monitoring system due to its significance in grinding process.This paper presents a novel method for identification of grinding wheel wear signature by combination of wavelet packet decomposition(WPD) based energies.The distinctive feature of the method is that it takes advantage of the combinational information of the decomposed frequency components based on the WPD so the extracted features can be customized according to the specific monitored object to get better diagnosis effects.Experiments are researched on monitoring of grinding wheel wear states under different machining conditions.The results show that the energy ratio extracted from the measured vibration signals is consistent with the grinding wheel wear condition evaluated by experiment and the further extracted feature ratio can be used in prediction of wheel wear condition.
基金This study is fully supported by the National Natural Science Foundation of China(Grant No.61873283)the Changsha Sci-ence&Technology Project(Grant No.KQ1707017)the Hunan Province Science and Technology Talent Support Project(Grant No.2020TJ-Q06).
文摘This paper proposes a hybrid deep reinforcement learning framework for locomotive axle temperature by combining the wavelet packet decomposition(WPD),long short-term memory(LSTM),gated recurrent unit(GRU)reinforcement learning and generalized autoregressive conditional heteroskedasticity(GARCH)algorithms.The WPD is utilized to decompose the raw nonlinear series into subseries.Then the deep learning predictors LSTM and GRU are established to predict the future axle temperatures in each subseries.The Q-learning could generate optimal ensembleweights to integrate the predictors to finish the deterministic forecasting and GARCH is used to conduct the deterministic forecasting based on the deterministic forecasting residual.These parts of the hybrid ensemble structure contributed to optimal modelling accuracy and provided effective support in the real-time monitoring and fault diagnosis of transportation.
