An Intelligent IoT Sensing System for Rail Vehicle Running States Based on TinyML

Real-time identification of the running state is one of the key technologies for a smart rail vehicle. However, it is a challenge to accurately real-time sense the complex running states of the rail vehicle on an Internet-of-Things (IoT) edge device. Traditional systems usually upload a large amount of real-time data from the vehicle to the cloud for identification, which is laborious and inefficient. In this paper, an intelligent identification method for rail vehicle running state is proposed based on Tiny Machine Learning (TinyML) technology, and an IoT system is developed with small size and low energy consumption. The system uses a Micro-Electro-Mechanical System (MEMS) sensor to collect acceleration data for machine learning training. A neural network model for recognizing the running state of rail vehicles is built and trained by defining a machine learning running state classification model. The trained recognition model is deployed to the IoT edge device at the vehicle side, and an offset time window method is utilized for real-time state sensing. In addition, the sensing results are uploaded to the IoT server for visualization. The experiments on the subway vehicle showed that the system could identify six complex running states in real-time with over 99% accuracy using only one IoT microcontroller. The model with three axes converges faster than the model with one. The model recognition accuracy remained above 98% and 95%, under different installation positions on the rail vehicle and the zero-drift phenomenon of the MEMS acceleration sensor, respectively. The presented method and system can also be extended to edge-aware applications of equipment such as automobiles and ships.

View this article on IEEE Xplore


Investigation and Analysis of Novel Skewing in a 140 kW Traction Motor of Railway Cars That Accommodate Limited Inverter Switching Frequency and Totally Enclosed Cooling System

This study facilitated the improvement of no-load back electromotive force (back-EMF) wave form, total harmonic distortion (THD) of back-EMF, and torque ripple using a novel skew angle formula, considering the specific order of a no-load THD. In real usage environments, it is taken into consideration for the fully enclosed cooling system and limited inverter switching frequency of urban railway car traction motors. Since the most railway car traction motors use high-withstand voltage rectangular wires in slot-open structure, a no-load back EMF waveform includes large space slot harmonics, which should be smaller as possible. For 6-step control, the no-load back EMF waveform is important because switching for motor control is performed once after the rotor position is determined. To improve the no-load back EMF waveform and THD, two-dimensional and three-dimensional finite element analysis (FEA) were performed using a novel skew angle formula considering specific harmonic order reduction, while the fundamental amplitude was minimally reduced. A prototype with the novel skew was fabricated and verified. In addition, it was designed by calculating a low current density for a fully enclosed cooling system. A temperature saturation experiment was also performed, and successfully verified. Therefore, we suggest that the no-load back EMF characteristics and torque ripple are improved by applying the novel skew angle instead of a traditional skew angle.

*Published in the IEEE Magnetics Society Section within IEEE Access.

View this article on IEEE Xplore