An explainable deep learning approach for detection and isolation of sensor and machine faults in predictive maintenance paradigm

Abstract

The predictive health maintenance techniques identify the machine faults by analyzing the data collected by low-cost sensors assuming that sensors are free from any faults. However, aging and environmental condition cause sensors also be faulty, leading to incorrect interpretations of the collected data and subsequently resulting in erroneous machine health predictions. To mitigate this problem, this paper proposes a hybrid model that can differentiate between sensor and system faults. The data used for training the model is collected from a power system hardware setup by experimental procedures. A Convolutional Neural Network (CNN) model is used to extract optimized features from the raw data automatically, which are then fed to the XGBoost model for sensor and machine fault isolation with an overall accuracy of 98.15%. The data having sensor fault was then fed to a Deep Autoencoder (DAE), which eliminated the sensor fault components and reconstructed the data with an average RMSE of 0.0576. Thereafter, the corrected signal was used to detect the system fault using the hybrid CNN-XGBoost model with 99.77% accuracy. Therefore, by isolating the sensor faults, the proposed technique establishes better confidence in predictive maintenance. Further, Explainable AI has been utilized to interpret the model prediction in human-understandable terms in order to increase trustworthiness. 

Application of Poisson’s ratio structures and decoupling algorithm for 3D force sensing

“…Both the formula method and the matrix calibration method are essentially combinations of multiple linear functions, which may lead to fitting errors. Due to the lack of stability and accuracy, the traditional decoupling method is gradually being replaced by intelligent algorithm decoupling [30].…”