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
Vehicle fuel economy will continue to increase in importance as world vehicle production grows and fuel supplies become more limited year by year.As OEMs strive to produce cars and trucks with greater fuel efficiency ...Vehicle fuel economy will continue to increase in importance as world vehicle production grows and fuel supplies become more limited year by year.As OEMs strive to produce cars and trucks with greater fuel efficiency and extended durability,additive technology developers are increasingly being asked to contribute to these goals from the lubricant side.Axle inefficiency can account for as much as 10% of the overall losses in an automotive driveline so improvements in axle efficiency can contribute greatly to improving vehicle fuel economy.For good durability,low axle oil operating temperatures are also needed to minimize oxidative and thermal degradation of the oil,reduce deposits and sludge formation,and extend oil drain intervals.To develop gear oils that can increase axle efficiency significantly while maintaining stable operating temperatures requires rig tests that are fast,precise and reproducible.This paper documents the development of a new axle test rig and test procedures and presents test results on several gear oils.The test results show the contributions of base oil viscosity,base oil chemistry,and additive chemistry on the fuel economy and temperature of the various oils.Having a dependable tool is enabling the development of new fuel-efficient and durable gear oil technology.展开更多
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.
文摘Vehicle fuel economy will continue to increase in importance as world vehicle production grows and fuel supplies become more limited year by year.As OEMs strive to produce cars and trucks with greater fuel efficiency and extended durability,additive technology developers are increasingly being asked to contribute to these goals from the lubricant side.Axle inefficiency can account for as much as 10% of the overall losses in an automotive driveline so improvements in axle efficiency can contribute greatly to improving vehicle fuel economy.For good durability,low axle oil operating temperatures are also needed to minimize oxidative and thermal degradation of the oil,reduce deposits and sludge formation,and extend oil drain intervals.To develop gear oils that can increase axle efficiency significantly while maintaining stable operating temperatures requires rig tests that are fast,precise and reproducible.This paper documents the development of a new axle test rig and test procedures and presents test results on several gear oils.The test results show the contributions of base oil viscosity,base oil chemistry,and additive chemistry on the fuel economy and temperature of the various oils.Having a dependable tool is enabling the development of new fuel-efficient and durable gear oil technology.
