Remaining useful life prediction for train bearing based on an ILSTM network with adaptive hyperparameter optimization

Remaining useful life(RUL)prediction for bearing is a significant part of the maintenance of urban rail transit trains.Bearing RUL is closely linked to the reliability and safety of train running,but the current prediction accuracy makes it difficult to meet the re-quirements of high reliability operation.Aiming at the problem,a prediction model based on an improved long short-term memory(ILSTM)network is proposed.Firstly,the variational mode decomposition is used to process the signal,the intrinsic mode function with stronger representation ability is determined according to energy entropy and the degradation feature data is constructed com-bined with the time domain characteristics.Then,to improve learning ability,a rectified linear unit(ReLU)is applied to activate a fully connected layer lying after the long short-term memory(LSTM)network,and the hidden state outputs of the layer are weighted by attention mechanism.The Harris Hawks optimization algorithm is introduced to adaptively set the hyperparameters to improve the performance of the LSTM.Finally,the ILSTM is applied to predict bearing RUL.Through experimental cases,the better perfor-mance in bearing RUL prediction and the effectiveness of each improving measures of the model are validated,and its superiority of hyperparameters setting is demonstrated.

Hybrid fiber Bragg grating sensor for vibration and temperature monitoring of a train bearing

We report a fiber Bragg grating（FBG）-based sensor for the simultaneous measurement of a train bearing’s vibration and temperature. A pre-stretched optical fiber with an FBG and a mass is designed for axial vibration sensing. Another multiplexed FBG is embedded in a selected copper-based alloy with a high thermal expansion to detect temperature. Experiments show that the sensor possesses a high resonant frequency of 970 Hz, an acceleration sensitivity of 27.28 pm/g, and a high temperature sensitivity of 35.165 pm/℃. A resonant excitation test is also carried out that demonstrates the robustness and reliability of the sensor.

Dynamic load sharing behavior of transverse-torsional coupled planetary gear train with multiple clearances

A new nonlinear transverse-torsional coupled model with backlash and bearing clearance was proposed for planetary gear set. Meanwhile, sun gear and planet's eccentricity errors, static transmission error, and time-varying meshing stiffness were taken into consideration. The differential governing equations of motion were solved by employing variable step-size Rung-Kutta numerical integration method. The behavior of dynamic load sharing characteristics affected by the system parameters including input rate, sun gear's supporting stiffness and eccentricity error, planet's eccentricity error, sun gear's bearing clearance, backlashes of sun-planet and planet-ring meshes were investigated qualitatively and systematically. Some theoretical results are summarized at last which extend the current understanding of the dynamic load sharing behavior of planet gear train, enrich the related literature and provide references for the design of planetary gear train.

Research on the mechanics of high speed rails

In the preceding theme issue on＂Current research progress on mechanics of high speed rails＂（Acta Mechanica Sinica,30：846–909（2014））,we invited several authors in the fiel to present their research on high speed rails（HSR）,including work on dynamic derailment analysis（Ling et al.[1]）,