Deep Learning-Based Segment Trend Removal Approach for Prognostics and Health Management Signals of Rail Vehicles

To ensure the safety and reliability of rail vehicles, prognostics and health management (PHM) is crucial. However, PHM signals can often be disrupted by trend components, which fundamentally undermine the accuracy of damage identification and prediction. Removing trend components efficiently is a challenge due to the intermittent and nonlinear character of railway vehicle PHM signals. This study proposes a segmented trend removal approach (STRA) for PHM signals based on deep learning. To evaluate the effectiveness of trend removal, a drift ratio and amplitude ratio assessment metric is defined. An identification model based on convolutional neural networks is also proposed to detect start-stop features and determine overall trend points for signal segmentation. A segmented spline baseline method is presented to eliminate running segment trends, while a least squares approach (LSA) is employed to address stationary segment trends. To increase processing and training efficiency with various sampling frequencies, a frequency conversion technique is implemented. The STRA outperforms conventional methods such as LSA, spline baseline approach, and empirical mode decomposition in nonlinear trend reduction. Additionally, this method can be extended to eliminate the zero drift of intermittent acceleration signals in PHM and is similarly suitable for use in other PHM applications, including automobiles, vessels, and bridges.