A Two-Stage Fault Detection and Classification Scheme for Electrical Pitch Drives in Offshore Wind Farms Using Support Vector Machine
Pitch systems are one of the components with the most frequent failure in wind turbines. This paper presents a two-stage fault detection and classification scheme for electric motor drives in wind turbine pitch systems. The presented approach is suitable for application in offshore wind farms with electric pitch systems driven by induction motors as well as permanent magnet synchronous motors. The adopted strategy utilizes three-phase motor current sensing at the pitch drives for fault detection and only when a fault condition is detected at this stage, features extracted from the current signals are transmitted to a support vector machine classifier located centrally to the wind farm. The …
Multiple Classifiers and Data Fusion for Robust Diagnosis of Gearbox Mixed Faults
Detection and isolation of single and mixed faults in a gearbox are very important to enhance the system reliability, lifetime, and service availability. This paper proposes a hybrid learning algorithm, consisting of multilayer perceptron (MLP)- and convolutional neural network (CNN)-based classifiers, for diagnosis of gearbox mixed faults. Domain knowledge features are required to train the MLP classifier, while the CNN classifier can learn features itself, allowing to reduce the required knowledge features for the counterpart. Vibration data from an experimental setup with gearbox mixed faults is used to validate the effectiveness of the algorithms and compare them with conventional metho…
Mixed Fault Classification of Sensorless PMSM Drive in Dynamic Operations Based on External Stray Flux Sensors
This paper aims to classify local demagnetisation and inter-turn short-circuit (ITSC) on position sensorless permanent magnet synchronous motors (PMSM) in transient states based on external stray flux and learning classifier. Within the framework, four supervised machine learning tools were tested: ensemble decision tree (EDT), k-nearest neighbours (KNN), support vector machine (SVM), and feedforward neural network (FNN). All algorithms are trained on datasets from one operational profile but tested on other different operation profiles. Their input features or spectrograms are computed from resampled time-series data based on the estimated position of the rotor from one stray flux sensor t…
Toward Self-Supervised Feature Learning for Online Diagnosis of Multiple Faults in Electric Powertrains
This article proposes a novel online fault diagnosis scheme for industrial powertrains without using historical faulty or labeled training data. The proposed method combines a one-class support vector machine (SVM) based anomaly detection and supervised convolutional neural network (CNN) algorithms to online detect multiple faults and fault severities under variable speeds and loads. The one-class SVM algorithm is to derive a score for defining faults or health classes in the first stage, and the resulting health classes are used as the training data for the CNN-based classifier in the second stage. Within this framework, the self-supervised learning of the proposed CNN algorithm allows the…