Mohammed Obaid Mustafa

Principal Component Analysis of the start-up transient and Hidden Markov Modeling for broken rotor bar fault diagnosis in asynchronous machines

This article presents a novel computational method for the diagnosis of broken rotor bars in three phase asynchronous machines. The proposed method is based on Principal Component Analysis (PCA) and is applied to the stators three phase start-up current. The fault detection is easier in the start-up transient because of the increased current in the rotor circuit, which amplifies the effects of the fault in the stators current independently of the motors load. In the proposed fault detection methodology, PCA is initially utilized to extract a characteristic component, which reflects the rotor asymmetry caused by the broken bars. This component can be subsequently processed using Hidden Markov Models (HMMs). Two schemes, a multiclass and a one-class approach are proposed. The efficiency of the novel proposed schemes is evaluated by multiple experimental test cases. The results obtained indicate that the suggested approaches based on the combination of PCA and HMMs, can be successfully utilized not only for identifying the presence of a broken bar but also for estimating the severity (number of broken bars) of the fault.

A Fault diagnosis scheme for three phase induction motors based on uncertainty bounds

The aim of this article is to present a fault diagnosis scheme for the case of squirrel-cage Three Phase Induction Motors based on uncertainty bounds violation conditions. The suggested scheme has the capability to diagnose two types of faults: a) broken rotor bar and b) short circuit in stator winding. The fault diagnosis is being performed through a two steps procedure. In the first step the parameters of the healthy induction motor are being identified by utilizing a Set Membership Identification approach, where corresponding uncertainty bounds are also being provided. In the second step, specific proposed bound violation conditions for the fault detection and fault diagnosis are being on-line evaluated during a sliding time window. Multiple simulation results are being presented that prove the efficacy of the proposed scheme towards fault detection and fault diagnosis.

Stator winding short circuit fault detection based on set membership identification for three phase induction motors

In this article a fault detection scheme for stator winding short circuit fault detection in the case of a three phase induction motor is being presented. The three phase motor is being modeled in the equivalent two phase motor (q-d) space, while the modeling of the faulty case is being also formulated. The motor is being identified by the utilization of Set Membership Identification (SMI) that has the merit of identifying both the parameters of the motor as also providing uncertainty safety bounds by calculating orthotopes which bounds the systems parameter vector. Based on the volume and the trend of these orthotopes, rules for identifying the existence of a fault are being presented. If the current values of the identified parameters do not lie inside the safety bounds in the healthy case, but lie in an area that is being defined by the model of the short circuit case, then a fault is being triggered. Detailed analysis of the proposed approach as also extended simulation results are being presented that prove the efficiency of the suggested scheme.

Experimental evaluation of a broken rotor bar fault detection scheme based on Uncertainty Bounds violation

This paper proposed a new technique for an experimental evaluation of a broken rotor bar fault detection based on Uncertainty Bounds violation. The novelty of this article stems from the establishment and the experimental evaluation of fault detection scheme being able to detect faults at the beginning of its occurrence, based on Set Membership Identification and novel proposed boundary violation rules for the identified motors parameters. By the utilization of the SMI technique, the simplified equivalent model of the induction motor is being identified during the steady state operation (non-fault case), while at the same time safety bounds for the identified variables are being provided, based on an a priori defined corrupting additive noise. On the event of a fault, specific fault detection conditions are being proposed that can capture the fault of a broken bar. Detailed analysis of the proposed approach as also extended experimental results are being presented that prove the efficiency of the proposed scheme.

Faults Classification Scheme for Three Phase Induction Motor

In every kind of industrial application, the operation of fault detection and diagnosis for induction motors is of paramount importance. Fault diagnosis and detection led to minimize the downtime and improves its reliability and availability of the systems. In this article, a fault classification algorithm based on a robust linear discrimination scheme, for the case of a squirrel-cage three phase induction motor, will be presented. The suggested scheme is based on a novel feature extraction mechanism from the measured magnitude and phase of current parks vector pattern. The proposed classification algorithm is applied to detect of two kinds of induction machine faults, which area broken rotor bar, and b short circuit in stator winding. The novel feature generation technique is able to transform the problem of fault detection and diagnosis into a simpler space, where direct robust linear discrimination can be applied for solving the classification problem. And thus a clear classification of the healthy and the faulty cases can be robustly performed, by having the optimal hyper plane. This method can separate the feature current classes in a low dimensional subspace. Robust linear discrimination has been one of the most widely used fault detection methods in real-life applications, as this methodology seeks for directions that are efficient for discrimination and at the same time applies a straight-forward implementation. The efficacy of the proposed scheme will be evaluated based on multiple simulation results in different fault types.

Bearing fault classification based on Minimum Volume Ellipsoid feature extraction

This article presents a novel fault classification and diagnosis technique for bearings based on a Minimum Volume Ellipsoid (MVE) method for feature extraction. Data from two accelerometers located at two different sites of the test bed are combined to create a two dimensional representation and the feature extraction stage condenses that information using an ellipsoid description. The proposed features feed a simple non-linear classifier which separates almost perfectly between normal and faulty conditions, with also very high diagnostic accuracy between the faulty classes. The obtained results suggest that this novel representation can be used within a condition monitoring system.

Fault classification of broken rotor bars in induction motors based on envelope current analysis

In this article a method for the detection of one, two, and three broken bars in induction motors under full load condition is presented. The proposed methodo is based on current envelope analysis. The information obtained from the envelope current is valuable in manifesting and validating the presence of a broken bar fault, since it contains important information about the existence of a fault as well as its severity. The proposed method mainly focuses on the case of steady-state operation under full load. In the established fault diagnosis scheme six features are extracted from the envelope of the current and after the application of a Principal Component Analysis stage are fed to a classifier to perform the diagnosis. Three different classifiers, a linear, a quadratic and a nearest neighbour are investigated for the final stage of the diagnosis. The presented approach manifested promising results using experimental data.

Principal component analysis anomaly detector for rotor broken bars

In this article a method for the detection of broken rotor bars in asynchronous machines operating under full load is presented. Unlike most Motor Current Signature Analysis (MCSA) approaches, which operate in the frequency domain, our method operates in the time domain. The scheme is based on the use of a Principal Component Analysis (PCA) fault/anomaly detector. PCA is applied on the three stator currents to subsequently calculate the Q statistic which is employed for detecting the presence/absence of a fault. The efficiency of the proposed scheme was experimentally evaluated using different fault severity levels, ranging from 1/4 of a broken bar to three broken bars. The obtained results indicate that the method can detect the caused asymmetry with a very restricted amount of data.

Broken rotor bar fault detection based on uncertainty ellipsoidal intersection for three phase induction motors

In this article a fault detection scheme for broken rotor bar fault detection in three phase induction motor is presented. In the proposed scheme the induction motor has been transformed in the equivalent two phase (q-d) space, while the modeling of the faulty case has been also formulated. The model has been identified by the utilization of the Set Membership Identification (SMI) algorithm that has the merit of identifying both the parameters of the motor as also providing uncertainty bounds in both the healthy and the faulty cases. Based on the adopted methodology, the uncertainty bounds and the corresponding identified parameters of the induction motor is presented as 3D-ellipsoids, while a novel fast and efficient fault detection scheme has been proposed that is able to track iteratively the ellipsoid centers, the distance among centers, the intersection between the initial and a priori known converged states of the motor and the current ones, before or after the fault occurrence. Detailed analysis of the proposed approach and the fault detection strategy, as also extended simulation results are being presented that prove the efficiency of the suggested scheme.