Data-Driven Fault Diagnosis Techniques: Non-Linear Directional Residual vs. Machine-Learning-Based Methods

Abstract

Linear dependence of variables is a commonly used assumption in most diagnostic systems for which many robust methodologies have been developed over the years. In case the system nonlinearities are relevant, fault diagnosis methods, relying on the assumption of linearity, might potentially provide unsatisfactory results in terms of false alarms and missed detections. In recent years, many authors have proposed machine learning (ML) techniques to improve fault diagnosis performance to mitigate this problem. Although very powerful, these techniques require faulty data samples that are representative of any fault scenario. Additionally, ML techniques suffer from issues related to overfitting and unpredictable performance in regions which are not fully explored in the training phase. This paper proposes a non-linear additive model to characterize the non-linear redundancy relationships among the system signals. Using the multivariate adaptive regression splines (MARS) algorithm, these relationships are identified directly from the data. Next, the non-linear redundancy relationships are linearized to derive a local time-dependent fault signature matrix. The faulty sensor can then be isolated by measuring the angular distance between the column vectors of the fault signature matrix and the primary residual vector. A quantitative analysis of fault isolation and fault estimation performance is performed by exploiting real data from multiple flights of a semi-autonomous aircraft, thus allowing a detailed quantitative comparison with state-of-the-art machine-learning-based fault diagnosis algorithms.

Identification of heat exchanger process through Hammerstein and polynomial models

“…The Output-Error (OE) estimator has the advantage of being more readily calculable than the predictionerror estimator. Using SI techniques such as the Hammerstein Weiner, Auto Regressive with Exogenous Input (ARX), Auto Regressive Moving Average with Exogenous Input (ARMX), Box-Jenkins (BJ) and OE models, a mathematical model was designed for a laboratory-based heating system [11][12][13][14][15][16][17]. The BJ model provides the greatest Final Prediction Error (FPE), correlation analysis, percentage of fitness, and loss function according to the simulated results [18][19][20][21].…”

Hybrid regression model via multivariate adaptive regression spline and online sequential extreme learning machine and its application in vision servo system

“…Bose et al 26 proposed a hybrid model combining MARS and deep neural network (DNN) for stock price prediction, used MARS to screen important data, and passed the screened data to DNN for training. Cartocci et al 27 proposed a nonlinear model to characterize the nonlinear redundancy relationship between system signals. MARS is used to identify the relevant fault characteristic matrix in the data, which improves the performance of the diagnosis system.…”