Conditional Time Series Diffusion Model for High-Speed Train Multi-Sensor Signals Imputation

Sensors are widely deployed on high-speed trains for real-time operational status monitoring. The integrity of multi-sensor signals over time is critical for the train’s Prognostics and Health Management (PHM) system. However, data missing during multi-sensor signal acquisition and transmission can severely limit the performance of PHM systems. Therefore, this paper proposes a novel Conditional Time Series Diffusion (CTSDiff) model designed for efficient and accurate imputation of missing values in high-speed trains’ multi-sensor time series signals. Firstly, CTSDiff utilizes the non-missing sensor signals collected as conditional information to guide missing data generation, thereby achieving data imputation. Secondly, CTSDiff employs one-dimensional convolutional residual blocks with dilation parameters to capture complex temporal dependencies and adopts a skip-step non-Markovian sampling process to accelerate the imputation procedure. Finally, experimental results demonstrate that CTSDiff can generate high-quality and diverse imputations across various missing data scenarios. The imputation data provided by CTSDiff ensures consistency with actual data distribution and obtains confidence information of the imputed data, significantly enhancing the integrity of multi-sensor signals in high-speed trains and the accuracy of intelligent analysis within PHM systems. Notably, this study opens new avenues for addressing missing data issues in high-speed train multi-sensor datasets and showcases the great potential of diffusion models in generating sensor signals.