Fault Detection and Diagnosis Using Support Vector Machines - A SVC and SVR Comparison

Abstract

This paper presents the use of Support Vector Machines (SVM) methodology for fault detection and diagnosis. Two approaches are addressed: the SVM for classification (Support Vector Classification-SVC) and SVM for regression (Support Vector Regression-SVR). A comparison was made between the two techniques through the study of a reactor of cyclopentenol production. In the case studied, different fault scenarios were introduced and it was evaluated which technique was able to detect and diagnose them. Finally, a comparison was made between the fault detection methodologies based on SVM and Dynamic Principal Component Analysis (DPCA) based detection techniques for a jacketed CSTR.

Anomaly Detection in Railway Sensor Data Environments: State-of-the-Art Methods and Empirical Performance Evaluation

“…SVMs are a set of related supervised learning methods [ 46 ], typically used for classification [ 47 ] and regression [ 48 ]. In addition, by offering a unique solution backed by a strong regularization function, SVMSs are particularly suited to classification problems that may be poorly conditioned [ 49 ]. A key strength lies in their ability to use a hyperplane with maximum margin to differentiate classes of data, ensuring commendable overall performance.…”

“…Support Vector Classification (SVC) is an SVM algorithm for two-group classification problems [ 51 ]; it has the ability to effectively perform non-linear classification by exploiting the kernel trick of implicitly mapping inputs into high-dimensional feature spaces [ 49 ]. In addition, SVC is particularly praised for its ability to diagnose faults, adding another layer of utility to its application.…”

Data‐driven fault diagnosis approaches for industrial equipment: A review

“…The SVM based fault diagnosis is used to avoid the major failure of the industrial machinery using one-class or ʋ-SVM technique to discriminate the normal and fault conditions, as well as to detect and identify the location of the fault (Fernandez-Francos et al, 2013;Jung, 2019). The SVM based fault diagnosis is used to solve classification as well as regression problems in industrial machinery ( de Souza D et al, 2014).…”

“…Hybrid system/ industries 25 Electric overhead travelling crane (Dhalmahapatra et al, 2019), electrical traction system (Chen et al, 2020), anode production equipment (Kolokas et al, 2018), carbon black production (Jones et al, 2010), actuator system (Waghen & Ouali, 2019), pneumatic systems (Demetgul et al, 2009;Nasiri et al, 2017), electronics system (Cai et al, 2016b), and fixture fault (Jin et al, 2012), moving window (Melani et al, 2021), water tank (Lampis & Andrews, 2009;Lindner & Auret, 2014), heavy-duty horizontal lathe (Mi et al, 2018), waste water treatment equipment (Hernandez-Chover et al, 2021;Kutyłowska, 2015;Lee, Yoo, & Lee, 2004), Tennessee Eastman process (Cai et al, 2015;Ge & Song, 2007;Oliveira et al, 2017), reactor for cyclopentenol ( de Souza D et al, 2014), distillation column (Chetouani, 2014), continuously-stirred tank heater (Rodriguez Ramos et al, 2017;Rodriguez Ramos et al, 2019;Smith & Powell, 2019), and automotive exhaust systems (Soleimani et al, 2021).…”

Global relaxation-based LP–Newton method formultiple hyperparameter selection in support vector classification with feature selection

“…Classification tasks arise in a wide range of areas, including in economics, finance, and engineering, just to name a few. In engineering more specifically, applications of SVC have been discovered in chemical engineering [1][2][3][4][5], civil engineering [6][7][8][9][10], mechanics [11][12][13][14][15], and so on. In civil engineering, for example, SVC can be applied for the prediction of traffic flow and congestion in a road network [6], seismic hazard assessment [7], soil quality classification [8], pavement condition evaluation [9], as well as land use classification [10].…”