The monitoring and fault diagnosis of axle-box bearings in high-speed trains is crucial for ensuring safe train operations. The vibration signals of these bearings exhibit non-stationary and non-linear characteristics. To further enhance the accuracy of identifying rolling bearing faults, a fault diagnosis method is proposed. This method is based on the improved Dung Beetle Optimization (DBO) algorithm for optimizing Variational Mode Decomposition (VMD) combined with Stacked Sparse Autoencoder (SSAE). Firstly, the DBO algorithm is enhanced to improve its optimization precision and global optimization capability. It is then utilized for the adaptive selection of two parameters: the number of decomposition modes and the penalty factor in VMD. These improvements address issues such as mode mixing, signal loss, and excessive decomposition, which arise from poor parameter selection in the traditional VMD method. Subsequently, components of intrinsic mode functions (IMFs) that are highly correlated with the original signal are selected. The time-domain and frequency-domain features of these IMF components are used to construct the dataset. The feature set is then inputted into the deep machine learning model SSAE for training and testing. Through diagnostic experiments on various types and levels of rolling bearing faults, the model demonstrates a higher rate of fault diagnosis recognition.

In support of our planar pulsed inductive plasma thruster research, a fast electromagnetic inductive valve for a gas propellant injection system has been built and tested. A new and important design feature is the use of a conical diaphragm as the action part, which greatly contributes to the virtue of simplicity for adopting the resultant force of the diaphragm deformation as the closing force. An optical transmission technique is adopted to measure the opening and closing characters of the valve while the gas throughput is determined by measuring the pressure change per pulse in a test chamber with a capacitance manometer. The experimental results revealed that the delay time before the valve reaction is less than 40 μs, and the valve pulse width is no longer than 160 μs full width at half maximum. The valve delivers 0-2.5 mg of argon gas per pulse varied by adjusting the drive voltage and gas pressure.

A novel type of electromagnetic inductive valve has been developed for the gas injector of the planar pulsed inductive plasma thruster. However, due to the complex operation process of the valve, the design work and the performance prediction can only be accomplished by experimentation. This paper explains a two dimensional model applied to predict the valve performance. The electromagnetic and mechanical aspects which dominate the valve operation process are treated as two weakly coupled problems. The equivalent circuit method is applied to analyze the electromagnetic problem where the valve is represented by a series of sub-conductors. The Lorentz force is calculated and introduced into the mechanical problem as an analytical load. Simulation and experimental validations are implemented in a prototype valve. Compared results from experiments convince that the present model can be used to predict the valve dynamic performances with satisfying accuracy. Moreover, the detailed insight with respect to the development of magnetic flux density, induced current, Lorentz force and velocity of the diaphragm is presented to better understand the valve operation process. The results indicate that the effective acceleration of the diaphragm occurs in the initial phase of valve opening. Only the diaphragm obtains enough kinetic energy during the first half cycle of the coil current, can the valve be fully opened.