An End-to-End Explainable Fault Prediction Pipeline for Embedded Test Systems

This work presents an explainable AI framework for fault predictions of Embedded Test Systems, combining classification and trend prediction. Random Forest (RF) and Gradient Boosting (GB) are used as baselines for classification, and the pipeline is extended with sliding-window sequence modelling using LSTM. With the data set, RF achieved 99.84% accuracy and 1.00 ROC-AUC, while Gradient Boosting achieved 98.59% accuracy and 0.96 ROC-AUC. The LSTM forecasts next timestep measurement and supports control-chart monitoring, yielding low errors for passed instances (MAE ≈ 0.007; RMSE ≈ 0.008) and higher errors for failed ones (MAE ≈ 1.158; RMSE ≈ 1.454), effectively flagging unstable behaviour. To enhance interpretability, SHAP and LIME explanations are computed and deployed in a Django-based web application for uploading data, prediction, and visualisation. Additionally, a lightweight Large Language Model (LLM) generates natural language rationales, helping engineers understand which features and time segments drive each decision. Results confirm that tree-based models provide robust baselines, while sequence-aware modelling and explainable AI add practical value for monitoring signals in production.