Monitoring Of Electrical Machines Research Articles

Application of Salp Swarm Algorithm and Extended Repository Feature Selection Method in Bearing Fault Diagnosis

Motor fault diagnosis is an important task in the operational monitoring of electrical machines in manufacturing. This study proposes an effective bearing fault diagnosis model for electrical machinery based on machine learning techniques. The proposed model is a combination of three processes: feature extraction of signals collected from the motor based on multi-resolution analysis, fast Fourier transform, and envelope analysis. Next, redundant or irrelevant features are removed using the feature selection technique. A binary salps swarm algorithm combined with an extended repository is the proposed method to remove unnecessary features. As a result, an optimal feature subset is obtained to improve the performance of the classification model. Finally, two classifiers, k-nearest neighbor and support vector machine, are used to classify the fault of the electric motor. There are four input datasets used to evaluate the model performance, and UCI is the benchmark dataset to verify the effectiveness of the proposed feature selection technique. The remaining three datasets include the bearing dataset collected from experiments, with an average classification accuracy of 99.9%, as well as Case Western Reserve University (CWRU) and Machinery Failure Prevention Technology (MFPT), which are public datasets with average classification accuracies of 99.6% and 98.98%, respectively. The experimental results show that this method is more effective in diagnosing bearing faults than other traditional methods and prove its robustness.

Condition-Based Health Monitoring of Electrical Machines Using DWT and LDA Classifier

In the industry, continuous health monitoring of electric motors is considered as an essential requirement. The continuous operation of the electric motor may cause malfunctions and addressing them timely is a critical challenge. The development of an efficient health monitoring system based on the identification of electrical motor faults is on great demand. This paper addresses the fault detection technique using discrete wavelet transform (DWT) algorithm for continuous health monitoring of electric motor-based systems. The faults have been detected through Motor Current Signature Analysis (MCSA) series procedures using the proposed method. Concurrently, the wavelet transform algorithm produces frequency-based spectrum related to the stator current parameters to accomplish the fault classification. This study provides an analysis of three motor faults of Phase imbalance, Rotor misalignment, and High contact resistance (HCR). DWT has the ability to categorize the input signals into approximate coefficient state for low frequency signals and detailed coefficient state for high frequency signals. In this research, this technique is used to detect faults because it is able of processing signals of very low frequency, and effectively deal with intermittent sharp signals that appear frequently during processing. DWT technique based on conditional monitoring of an induction motor with precise detailed coefficients and more skilled at light loads given on a motor-shaft with relatively fast execution time compared to FFT. Furthermore, the comparison of healthy and faulty induction motors has been compiled by Linear Discriminant Analysis (LDA) technique, a sub-application of MATLAB, and used for faults management purposes. LDA in comparison with PCA gives more perfect results. In this research, different faults have been detected with 100% accuracy using LDA classifier. The implementation of the proposed scheme will be beneficial in avoiding faults by ensuring that preemptive measures are taken timely against these faults, and the production of industries is protected from revenue losses.

Monitoring of Single-Phase Induction Motor through IoT Using ESP32 Module

The condition monitoring of rotating machines for critical applications plays an important role in reducing downtime. With Industry 4.0, the role of IoT in online condition monitoring of electrical machines has gained considerable significance. The main aim of the paper is the use of IoT for online monitoring of motor parameters like current, temperature, vibration, and humidity and observing its online trending using a web server. Data can be accessed in form of graphs and widgets by visiting the web page. The advantage of this project is the real-time monitoring of the motor from any remote area and in case of any abnormality operating personnel can take necessary steps for preventing complete breakdown. The proposed work can help industry people in online monitoring of motors and in the future work can be extended for fault prediction and classification.

Recent Trends in Magnetic Sensors and Flux-Based Condition Monitoring of Electromagnetic Devices

As one of the most promising techniques, magnetic flux-based condition monitoring of electrical machines, has gained significant traction in the past decade. One of the key enabling factor is the advancements in sensor technologies to measure both the airgap magnetic flux and stray magnetic flux around the motors with high accuracy. This study presents a comprehensive review of advances in flux sensors and the recent trends in magnetic flux-based diagnostic techniques for various faults and electrical machines. In this context, various magnetic sensor technologies suitable for measuring both the airgap flux and the stray magnetic flux are introduced. Each of the sensor technologies are discussed exhaustively, including their working principles and applications in electrical machine fault diagnostics. In the following sections, various flux-based diagnostic techniques are discussed for different types of common faults in various ac machines. Finally, the future trends are discussed briefly under the light of several applications and their impact.

Trends and Challenges in Intelligent Condition Monitoring of Electrical Machines Using Machine Learning

A review of the fault diagnostic techniques based on machine is presented in this paper. As the world is moving towards industry 4.0 standards, the problems of limited computational power and available memory are decreasing day by day. A significant amount of data with a variety of faulty conditions of electrical machines working under different environments can be handled remotely using cloud computation. Moreover, the mathematical models of electrical machines can be utilized for the training of AI algorithms. This is true because the collection of big data is a challenging task for the industry and laboratory because of related limited resources. In this paper, some promising machine learning-based diagnostic techniques are presented in the perspective of their attributes.

An Approach to Remote Condition monitoring of Electrical Machines based on IOT

With the progress and development of national economy, the power system reliability and safety issues of power system is also to be considered important. Predictive maintenance is preferred in many of the systems as it reduces the downtime, increase efficiency and reliability. Condition monitoring is important to identify the fault early in distribution transformer and generator. If any fault occurs in the generator or transformer it may affect the entire process of the generating and distributing system. And it results in unexpected shut down of power supply and expenses. Therefore real-time monitoring of transformer/generator is mandatory for supplying the constant supply to the consumers. IOT based monitoring of transformer and generator system is proposed in this paper, which could monitor the most important parameters such as temperature, current and voltage in transformer & fuel level, oil level, temperature in generator with help of sensors and the information is also updated to server via Wi-Fi module. If Any abnormal conditions is detected it will automatically result in tripping off of the system and the information is send to the server via Wi-Fi. Therefore remote condition monitoring protection becomes possible with the proposed technology.

Real-Time Digital Twin of a Wound Rotor Induction Machine Based on Finite Element Method

Monitoring and early fault prediction of large electrical machines is important to maintain a sustainable and safe power system. With the ever-increasing computational power of modern processors, real-time simulation based monitoring of electrical machines is becoming a topic of interest. This work describes the development of a real-time digital twin (RTDT) of a wound rotor induction machine (WRIM) using a precomputed finite element model fed with online measurements. It computes accurate outputs in real-time of electromagnetic quantities otherwise difficult to measure such as local magnetic flux, current in bars and torque. In addition, it considers space harmonics, magnetic imbalance and fault conditions. The development process of the RTDT is described thoroughly and outputs are compared in real-time to measurements taken from the actual machine in rotation. Results show that they are accurate with harmonic content respected.

Wideband Fiber Bragg Grating Accelerometer Suitable for Health Monitoring of Electrical Machines

A fiber Bragg grating (FBG) accelerometer suitable for health monitoring of electrical machines has been proposed. A polymer composite material is used to design the cantilever of the accelerometer. Thus it is ensured that there are no conducting parts in the accelerometer. Detailed finite element analysis of the cantilever is done to optimize the sensitivity and the resonant frequency. The sensitivity is significantly improved compared to the conventional FBG accelerometer having similar bandwidth of operation. Two different configurations, one having sensitivity 14.4 pm/g with resonant frequency 444 Hz, and the other having sensitivity 7.5 pm/g with resonant frequency 940 Hz have been designed and fabricated. The wide band optical accelerometers will enable monitoring of vibration modes of critical components of electrical machines and more importantly using commercially available standard FBG interrogators, instead of using any complex interrogation techniques. A good match between the simulation and experimental results was observed.

Stray Flux Sensor Core Impact on the Condition Monitoring of Electrical Machines.

The analysis of the stray flux for electrical machine condition monitoring is a very modern and active research topic. Thanks to this technique, it is possible to detect several types of failures, including stator and rotor inter-turn faults, broken rotor bars and mechanical faults, among others. The main advantages are that it involves a non-invasive technique and low-cost monitoring equipment. The standard practice is to use coreless flux sensors, with which the stray flux of the machine is not perturbed and there are no problems due to saturation or nonlinear behavior of the iron. However, the induced voltage in the coreless coil sensor may be very low and even, in some cases, have a similar amplitude to the noise floor. This paper studies the use of iron core stray flux sensors for condition monitoring of electrical machines. The main advantage of iron core flux sensors is that the measured electromotive force is stronger. In the case of large machines in noisy environments, this can be crucial. Two different types of iron core stray flux sensors and a coreless flux sensor are tested. A comparison of the three sensors is presented. Extensive experimental testing with all sensors shows the superiority and greater sensitivity of sensors with core versus the coreless ones.

Aging monitoring of electrical machines using winding high frequency equivalent circuits

Abstract This study defines a monitoring method based on impedance analysis in the upper part of the spectrum. It focuses on the analysis of the high frequency behavior of electrical machines windings considering the turn-to-turn capacitance variations (delta-C) due to insulation aging. An equivalent circuit is automatically generated from the turn arrangements in coils; parameters are computed considering the coil shape and the characteristics of insulation materials. PSpice analysis of the equivalent circuit yields the resonance frequencies to be monitored. With this software and a database giving the relationship between the turn-to-turn capacitance variation delta-C and the reduction of insulation performances due to aging, it is possible to build a monitoring system able to produce an alert when the probability of failure becomes higher than a predetermined level.

Fault Detection and Isolation in Electrical Machines using Deep Neural Networks

Condition and health monitoring of electrical machines during dynamic loading is a common, yet challenging problem in main battle tanks. Existing methods address this issue by extracting various features which are subsequently used in a classifier to isolate faults. However, this approach relies on the feature set being extracted and therefore most of the time does not provide expected accuracy in identification of faults. In this work, we have used convolution neural network that utilises the original time domain measurements for fault detection and isolation (FDI). Results from experimental studies indicate that the proposed approach can perform FDI with more than 95\% accuracy using commonly available current measurements.

IoT-Based Vibration Analytics of Electrical Machines

The aim of this paper is to propose an IoT-based model for real-time condition monitoring of electrical machines, which addresses the challenges of data storage and scalability. The proposed model is evolved with an experimental setup having two sets of dc motor coupled to ac generator and an IoT device to elucidate integrated monitoring and decision making. This IoT-based vibration analytic model uses an IoT2040 Gateway with custom Linux OS image built for acquisition and streaming of vibration signals. The Python target application acquires dc motors shaft vibration using vibration sensors and communicates the data as events to cloud through serial device driver interface. The IoT service running in cloud receives the data from multiple machines through lightweight RESTful HTTP and records the same which are retrievable for analysis and algorithm development in any platform. The retrieved data have been analyzed using the proposed statistical classification-based signal decomposition algorithm as well as time-frequency analysis to estimate the vibration thresholds of every machine connected to IoT cloud. Such estimated thresholds corresponding to different operating and environmental conditions maintained in cloud are used to build a repository of context specific solutions for machine conditions leading to improved maintenance decisions. The uniformity of threshold values obtained from IoT-based model in comparison with that of analysis carried out on the machines locally using myRIO for data acquisition ensures the integrity of the proposed statistical classification algorithm and reliability of the IoT model for condition monitoring with assured scalability.

Robust Condition Assessment of Electrical Equipment with One Class Support Vector Machines Based on the Measurement of Partial Discharges

This paper presents a system for the detection of partial discharges (PD) in industrial applications based on One Class Support Vector Machines (OCSVM). The study stresses the detection of Partial Discharges (PD) as they represent a major source of information related to degradation in the equipment. PD measurement is a widely extended technique for condition monitoring of electrical machines and power cables to avoid catastrophic failures and the consequent blackouts. One of the most important keystones in the interpretation of partial discharges is their separation from other signals considered as not-PD especially in low SNR measurements. In this sense, the OCSVM is an interesting alternative to binary SVMs since it does not need a training set with examples of all the output classes correctly labelled. On the contrary, the OCSVM learns a model of the signals acquired when the equipment is in PD-free mode, defined as a state where no degradation mechanism is active, so one only needs to make sure that the training signals were recorded under this setting. These default mode signals are easier to characterize and acquire in industrial environments than PD and lead to more robust detectors that practically do not need domain adaptation to perform in scenarios prone to different types of PD. In fact, the experimental results show that the performance of the OCSVM is comparable to that achieved by a binary SVM trained using both noise and PD pulses. Finally, the method is successfully applied to a more realistic scenario involving the detection of PD in a damaged distribution power cable.

A Novel Approach for Multi Class Fault Diagnosis in Induction Machine Based on Statistical Time Features and Random Forest Classifier

Fault diagnosis and detection is the important area in health monitoring of electrical machines. This paper proposes the recently developed machine learning classifier for multi class fault diagnosis in induction machine. The classification is based on random forest (RF) algorithm. Initially, stator currents are acquired from the induction machine under various conditions. After preprocessing the currents, fourteen statistical time features are estimated for each phase of the current. These parameters are considered as inputs to the classifier. The main scope of the paper is to evaluate effectiveness of RF classifier for individual and mixed fault diagnosis in induction machine. The stator, rotor and mixed faults (stator and rotor faults) are classified using the proposed classifier. The obtained performance measures are compared with the multilayer perceptron neural network (MLPNN) classifier. The results show the much better performance measures and more accurate than MLPNN classifier. For demonstration of planned fault diagnosis algorithm, experimentally obtained results are considered to build the classifier more practical.

Guest Editorial Special Issue on Fault Diagnosis of Electric Machines, Power Electronics, and Drives

The papers in this special section focus on fault diagnosis of electric machines, power electronics, and drives. This section aims to offer an insight into the state-of-the-art of diagnostics and condition monitoring of electrical machines, power electronics, adjustable speed drives, and related areas.

Fault Diagnosis of Three-Phase Induction Motor: A Review

Now a days the use of Condition Monitoring of electrical machines are increasing due to its potential to reduce operating costs, enhance the reliability of operation and improve service to customers. Different alternatives to detect and diagnose faults in induction machines have been proposed and implemented in the last years. These new alternatives are characterized by an on-line and non-invasive feature, that is to say, the capacity to detect faults while the machine is working and the capacity to work sensor less. These characteristics, obtained by the new techniques, distinguish them from the traditional ones, which, in most cases, need that the machine which is being analyzed is not working to do the diagnosis. The main purpose of this article is to revise the main alternatives in the detection of faults in induction machines and compare their contributions according to the information they require for the diagnosis, the number and relevance of the faults that can be detected, the speed to anticipate a fault and the accuracy in the diagnosis. and to identify various such diagnosis techniques that can be applied for automatic condition monitoring of induction motors and can be extended easily to other electrical machines also.

Detection and Diagnosis of Faults in Induction Motor Using an Improved Artificial Ant Clustering Technique

The presence of electrical and mechanical faults in the induction motors (IMs) can be detected by analysis of the stator current spectrum. However, when an IM is fed by a frequency converter, the spectral analysis of stator current signal becomes difficult. For this reason, the monitoring must depend on multiple signatures in order to reduce the effect of harmonic disturbance on the motor-phase current. The aim of this paper is the description of a new approach for fault detection and diagnosis of IMs using signal-based method. It is based on signal processing and an unsupervised classification technique called the artificial ant clustering. The proposed approach is tested on a squirrel-cage IM of 5.5 kW in order to detect broken rotor bars and bearing failure at different load levels. The experimental results prove the efficiency of our approach compared with supervised classification methods in condition monitoring of electrical machines.

Noninvasive Fault Monitoring of Electrical Machines by Solving the Steady-State Magnetic Inverse Problem

This paper proposes an original approach for detection, localization, and quantification of faults appearing in electrical machines. The used method in this work deals with the analysis of the external magnetic field of a machine. This approach is already known, but until now, classical methods only detect if a fault is present or not. Thus, we propose a new approach based on the theory of inverse problems. From magnetic measurements realized on sensors located around the machine, a numerical model of the machine is inverted to get the distribution of the flux in the air gap. Therefore, the analysis of this distribution can allow us not only to identify a faulty mode, but also to quantify its importance.

FDI based on pattern recognition using Kalman prediction: Application to an induction machine

A pattern recognition technique associated with a new state estimator is developed in order to supervise electrical process. For this purpose, diagnostic features are extracted from current and voltage measurements for monitoring different operating modes. Then, a feature selection method is applied in order to select the most relevant features which define the feature space. In this frame, the classification is realized by a non-parametric method (“ k-nearest neighbors” rule) with reject options. However, this method does not take into account the evolution of the operating modes. Thus, it is necessary to enhance the initial knowledge database. For that, a polynomial approach allows characterizing the intermediate states of each operating modes and an original use of Kalman algorithm allows predicting the evolution of the partially known modes. A simple behavioral model is used to describe the evolution of the pattern vector. An estimation step provides the parameter of such model and a prediction step determines the future evolution of the pattern vector. This approach is illustrated on an asynchronous motor of 5.5 kW, in order to detect broken bars under any load level. The experimental results prove the efficiency of pattern recognition methods in condition monitoring of electrical machines.

A method for condition monitoring and fault diagnosis in electromechanical system

Condition monitoring of electrical machines has received considerable attention in recent years. Many monitoring techniques have been proposed for electrical machine fault detection and localization. In this paper, the feasibility of using a nonlinear feature extraction method noted as Kernel independent component analysis (KICA) is studied and it is applied in self-organizing map to classify the faults of induction motor. In nonlinear feature extraction, we employed independent component analysis (ICA) procedure and adopted the kernel trick to nonlinearly map the Gaussian chirplet distributions into a feature space. First, the adaptive Gaussian chirplet distributions are mapped into an implicit feature space by the kernel trick, and then ICA is performed to extract nonlinear independent components of the Gaussian chirplet distributions. A thorough laboratory study shows that the diagnostic methods provide accurate diagnosis, high sensitivity with respect to faults, and good diagnostic resolution.