Random Load Pattern Recognition of Test Road Based on a Laser Direct Writing Carbon-Based Strain Sensor and a Deep Neural Network

The practical application of hydrogen-based fuel cell vehicles (HFCVs) requires the design of advanced stress monitoring system on the hydrogen storage devices, relying on accurate feedback and recognition from the vehicles load conditions. Herein, we proposed an intelligent monitoring method for continuous monitoring of dynamic load parameters and load recognition by combining carbon-based strain sensor, data acquisition and wireless transmission embedded unit, and machine learning (ML). The carbon-based strain sensor, prepared by laser direct writing (LDW) on polyimide (PI) film, exhibited a sensitivity of 6.08 and a frequency response of 1 Hz for effectively measuring the strain status under varying road conditions. A miniaturized and highly integrated data acquisition and wireless transmission unit was adopted to implement edge computing and wireless communication. Wavelet packet decomposition (WPD) and Hilbert–Huang transform (HHT) were fused to extract intrinsic features in random load spectrum, and the distance-based feature evaluation method was used to evaluate sensitive features to optimize the structure of the deep neural network (DNN). The DNN model could effectively recognize six types of test road conditions, with a test accuracy over 90%. This research effectively advances the design of the loading condition monitoring system of the HFCVs hydrogen storage device.

I. Introduction

From the perspective of environmental sustainability and the global energy shortages, hydrogen-based fuel cell vehicles (HFCVs) have shown its promising potential to be an important part of future vehicles [1]. Although hydrogen has the characteristics of clean consumption, high-efficiency, and sufficient reserves, safe storage and transportation of hydrogen is still a huge obstacle to the development of HFCV industry. High-pressure hydrogen storage vessels (HSVs) may suffer unforeseen failure during long-term use, resulting in severe accidents, such as fatigue failure, gas leakage, filament wound breakage, hydrogen embrittlement, and so on [2], [3]. Particularly, fatigue failure caused by random loads under different road conditions is one of the most important causes of various failures. To prevent such accidents, an accurate, real-time, and long-term wireless monitoring of the load status of vehicle-mounted HSV is indispensable.