Successful Fault Detection Research Articles

Resolving anomalies of current signatures owing to stator winding faults and voltage unbalances in induction motor through machine learning

Purpose The early detection of frequently occurring motor faults owing to various operational stresses in the industrial environment is of utmost importance to safeguard the motors against disastrous failures. The purpose of this study is to put emphasis on the detection of varying severity of incipient stator winding inter-turn-short-circuit faults in a three-phase induction motor and to differentiate such faults from the anomalies introduced in the line currents due to unbalanced supply voltage. Design/methodology/approach First, feature extraction was performed by estimating 11 conventional statistical parameters from the normalized three-phase stator currents. Then, all the statistical features were fed to a linear discriminant analysis classifier to classify the different fault types, namely, inter-turn-short-circuit fault, voltage unbalance and voltage unbalance equivalent to turn-turn fault. Findings A minimum of 0.28% of shorted turn could be detected with 98.7% classification accuracy. Successful detection of faults on different rating of motors at different loads establishes the proposed fault diagnosis method independent of machine rating and load level. Originality/value Several fault diagnosis techniques have been presented in the referenced articles. Mostly, all the proposed techniques were carried out on balanced supply voltages. But, this study reports a novel condition monitoring method for detection of stator winding inter-turn-short-circuit faults in a three-phase induction motor, considering the unbalanced supply voltage scenarios.

A Generalized Convolutional Neural Network Model Trained on Simulated Data for Fault Diagnosis in a Wide Range of Bearing Designs.

Rolling element bearings (REBs) are critical components in rotating machinery and a leading cause of machine failures. Traditional fault detection methods rely on signal processing, but advances in machine learning (ML) and deep learning (DL) have dramatically improved diagnostic accuracy. However, existing DL models struggle with data availability, generalization, and domain adaptation, making industrial applications challenging. This study proposes a convolutional neural network (CNN) model trained on numerically simulated vibration data generated for a wide range of bearing designs. A novel hybrid signal processing method is employed to enhance feature extraction and reduce domain shifts between simulated and real-world data. The optimized CNN model, trained on simulated data, is tested using experimental and real-world vibration signals from laboratory bearings and jet engine components. The results show high classification accuracy using data from the Case Western Reserve University experimental dataset and successful fault detection in real-world Safran jet engine ground tests. The findings demonstrate the effectiveness of the developed CNN-based model for bearing fault classification, tackling training data scarcity and generalizability challenges while contributing to the development of intelligent fault diagnosis models for several industrial applications.

Travelling wave‐based fault detection and location in a real low‐voltage DC microgrid

AbstractThis paper discusses a device‐level implementation of a travelling wave (TW) protection device (PD) designed for a real low‐voltage DC microgrid. The TWPD fault detection and location algorithm is executed on a commercial digital signal processor (DSP) board, involving signal sampling at 1 MHz via the DSP board's analog‐to‐digital converter (ADC). The analogue input card measures positive pole, negative pole and pole‐to‐pole voltages at the TWPD location. Upon a successful fault detection using a second‐order high‐pass filter, the voltage data is normalised and multi‐resolution analysis (MRA) is performed on a 128‐sample buffer around the TW arrival time. MRA employs the discrete wavelet transform (DWT) to capture high‐frequency voltage patterns, and then the Parseval's energy theorem quantifies these TW characteristics by computing the energy of reconstructed wavelet coefficients. These energy values per decomposed frequency band are the basis for training a random forest classifier that predicts fault location and type. The TWPD is fully implemented and connected to a real DC microgrid in Albuquerque, NM, USA, for validation, and results are shown for field tests verifying the performance under faults.

Robust residual generator design for sensor fault detection in twin rotor aerodynamic system

The twin rotor aerodynamic system (TRAS) reflects the dynamics of vertical take-off rotor systems. TRAS considers the coupling effect and gyroscopic disturbance torque as unwanted signals. For safe and reliable TRAS operation, proper control input is vital, along with fast fault indication. This paper addresses the output sensor fault detection problem in the linear model of TRAS subjected to l2-norm bounded disturbance. A robust design of an observer is formulated as H-/H∞ optimization problem to maximize the sensitivity/robustness criterion. The approach minimizes the disturbance effect on the residual signal, which leads to successful fault detection. Furthermore, a linear quadratic regulator-based state feedback controller is proposed to meet the system's desired transient response requirement. The incorporation of an observer-based residual generator for fault detection along with the state-feedback controller differs the current work from the existing work. Successful fault detection in the output sensor of TRAS depicts the good performance of the proposed observer.

Convolutional Deep Belief Network Based Expert System for Automated Fault Diagnosis in Hydro Electrical Power Systems

The paper developed an approach for fault diagnosis in Hydro-Electrical Power Systems (HEPS). Using a Renewable Energy System (RES), HEPS has performed a significant part in contributing to addressing the evolving energy demands of the present. Several electro-mechanical elements that collectively comprise the Hydro-Electric (HE) system are susceptible to corrosion from routine usage and unplanned occurrences. Administration and servicing systems that are successful in implementing and achieving these goals are those that regularly track and predict failures. Detect models applied in the past included those that were primarily reactive or reliant on human involvement to identify and analyse abnormalities. The significant multiple variables intricacies that impact successful fault detection are disregarded by these frameworks. The research presented here proposes a Convolutional Deep Belief Network (CDBN) driven Deep Learning (DL) model for successful fault and failure detection in such power systems that address these problems. Applying sample data collected from two Chinese power plants, the proposed framework has been assessed compared to other practical DL algorithms. Different metrics have been employed to determine the effectiveness of the simulations, namely Accuracy, Precision, Recall, and F1-score. These outcomes indicated that the CDBN is capable of predicting unexpected failures. Graphic representations demonstrating control used to measure turbine blade load, vibration level, and generator heat for assessing the replicas.

Real-Time Simulation and Experimental Implementation of Luenberger Observer-Based Speed Sensor Fault Detection of BLDC Motors

Abstract Modern control systems’ dependability, safety and efficiency have all been improved by studying fault-tolerant control systems (FTCS). FTCS techniques can typically be active or passive controls. The fault detection and diagnosis (FDD) method is used in this study’s active control branch to identify probable faults that could develop in the speed Hall sensors of brushless DC motors (BLDC). FDD methodologies can be categorised into two types, depending on the available data and the process involved: model-based methods and data-based methods. The proposed approach in this study explores the implementation of the Luenberger observer methodology as part of the model-based approach. The chosen methodology was practically implemented and subjected to experimental evaluation. The proposed observer relies on the residual signal, which displays the difference between the plant’s observed and estimated speed signals and serves as a failure alert for the entire system. Given the increasing demand for BLDC motors in various industrial control applications, including medical fields, automation and robotics, this particular motor was selected as a benchmark to thoroughly evaluate and validate the proposed method. The primary contribution of this paper lies in the real-time application of model-based sensor fault detection methods to BLDC motors. The efficiency of the suggested method is showcased through extensive MATLAB simulations, where the obtained results confirm the successful detection of faults with a high level of responsiveness. As a result, the project was successfully implemented in real-time, and the experimental results exhibited a close correlation with the simulated outcomes. This consistency between simulation and practical implementation validates the accuracy and reliability of the proposed methodology for detecting faults in the BLDC motor speed sensor. The results underscore the heightened reliability and safety attained by promptly and accurately detecting sensor faults during the operation of the motor.

Autoencoder-Enhanced Regularized Prototypical Network for New Energy Vehicle battery fault detection

Autoencoder-Enhanced Regularized Prototypical Network for New Energy Vehicle battery fault detection

Fault detection of pressurized heavy water nuclear reactors with steady state and dynamic characteristics using data-driven techniques

Fault detection of pressurized heavy water nuclear reactors with steady state and dynamic characteristics using data-driven techniques

EMD/HT‐based local fault detection in DC microgrid clusters

AbstractDC faults can create serious damages if not detected and isolated in a short time. This paper proposes a fault detection technique for DC faults to enhance the protection of DC microgrid clusters. To detect such faults accurately and quickly, a DC fault detection scheme using empirical mode decomposition and Hilbert transform is proposed. Due to the strict time limits for fault interruption caused by fast high‐rising fault currents in DC systems, DC microgrid clusters' protection remains a challenging task. Furthermore, high impedance faults (HIFs) in DC systems cause a small change in the current, which can damage the power electronic converters if not detected in time. Therefore, this paper proposes a local scheme for the fast detection of faults including HIFs in DC microgrid clusters. Both simulation and experimental results using a scaled DC microgrid cluster prototype and considering several scenarios (such as low impedance faults, HIFs, noise, overload, and bad calibration of sensors) demonstrate the successful and fast detection (less than 2 ms) of DC faults by the proposed method. Compared with other techniques, the proposed scheme presents its merits from the viewpoints of accuracy and speed.

Multiplicative Fault Detection and Isolation in Dynamic Systems Using Data-Driven K-Gap Metric based kNN Algorithm

Multiplicative Fault Detection and Isolation in Dynamic Systems Using Data-Driven K-Gap Metric based kNN Algorithm

Smart Diagnosis And Maintenance Systems For Railway Tracks

In recent years, advanced technologies such as artificial intelligence (AI), the internet of things (IoT), and big data came into prominence. These technologies found an extensive area of utilization in various sectors. Railway systems as an important part of the transportation of people and goods should be improved by the integration of novel technologies. Successful detection of track faults and operating maintenance tasks accordingly are essential for the safety of railway operations. Currently, image processing and pattern recognition via machine learning applications are in common use for automated track inspections. However, it is not possible to claim that railway tracks are integrated with current technology perfectly. In this work, differences between the traditional way and the smart way of track inspection and maintenance are presented. Shortcomings of the application of advanced technologies into railway tracks are detected and required actions for further improvements are discussed. Lastly, the effects of the use of smart systems on the life cycle of the structures are evaluated.

Unstructured borderline self-organizing map: Learning highly imbalanced, high-dimensional datasets for fault detection

Unstructured borderline self-organizing map: Learning highly imbalanced, high-dimensional datasets for fault detection

Voltage Differential Protection for Series Arc Fault Detection in Low-Voltage DC Systems

Series arc faults are challenging to detect in low-voltage dc (LVDC) distribution systems because, unlike other fault types, series arc faults result in only small changes in the current and voltage waveforms. Though there have been several approaches proposed to detect series arc faults, each approach has its requirements and limitations. A step change in the current and voltage waveforms at the arc inception is one of the characteristic signatures of these faults that can be extracted without requiring one to sample the waveforms at a very high frequency. This characteristic feature is utilized to present a novel approach based on voltage differential protection to detect series arc faults in LVDC systems. The proposed method is demonstrated using an embedded controller and experimental data that emulate a hardware-in-the-loop (HIL) test environment. The successful detection of series arc faults on two sets of series arc fault experimental data validated the approach. The results presented also illustrate the computational feasibility in implementing the approach in a real-time environment using an embedded controller. In addition, the paper discusses the robustness of the approach to load changes and loss of time synchronization between measurements at the two terminals of the line.

Efficient detection of transistor stuck-on faults in CMOS circuits using low-overhead single-ended ring oscillators

Very large-scale integration technology is accelerating the growth and prevalence of nanoscale devices worldwide, but at the same time facing technical challenges in terms of fault detection due to the compact size of chips. Thus, the detection of faults in chips caused by limitations of the manufacturing process or operational aspects of the architecture is obligatory to assess the effective performance of devices. In this paper, two single-ended ring oscillator (SERO)-based transistor stuck-on (TSON) fault detection methods are proposed for complementary metal–oxide–semiconductor (CMOS) circuits. The SERO is used as a current-controlled and voltage-controlled oscillator in method 1 and 2, respectively, reducing the circuit overhead of the detection block. Simulations are carried out using Cadence Virtuoso in 90-nm technology. The results show that both methods can successfully detect TSON faults in CMOS circuits based on the oscillatory behavior of the SERO. Moreover, these methods avoid the need to sense the output voltage level or quiescent current, which increases the possibility of successful fault detection, especially for submicron-level structures by avoiding improper logic and unreliable current values. Test vectors and fault locations can also be easily identified using the proposed methods, reducing the implementation complexity of CMOS fault detection techniques.

Bilinear model-based diagnosis of lock-in-place failures of variable-air-volume HVAC systems of multizone buildings

Bilinear model-based diagnosis of lock-in-place failures of variable-air-volume HVAC systems of multizone buildings

Data-driven and deep learning-based detection and diagnosis of incipient faults with application to electrical traction systems

Data-driven and deep learning-based detection and diagnosis of incipient faults with application to electrical traction systems

Investigation of the diagnostic properties of sensors and features in a multiphase flow facility case study

Abstract Feature design and selection is one of the first steps towards successful fault detection and diagnosis. Data from different sources can contain complimentary information about a monitored system. Hence methods which fuse features from multiple sources can often detect and diagnose a greater number of fault modes with higher confidence. However, solutions that require data from multiple sensors as inputs can be susceptible to failure if one or more of those sensors cease to function. Optimally a solution will fuse data from a sufficient number of sensors so that the advantages of sensor fusion are realized, while the robustness of the system is retained. In this paper the authors investigate how the best subset of features might differ for fault detection and fault severity diagnosis in a multiphase flow facility case study. ReliefF, which is a K-nearest neighbors-based feature selection filter, is used to rank the features for different problems. The dataset used for the analysis contains data from various operating conditions and induced faults with various severities. It was found that the optimal subset of features varied for different monitoring problems. It was also shown that including features that are ranked as being uninformative into a fault classifier can also impact the robustness of the classifier to sensor failures.

Multifault Diagnosis of Induction Motor at Intermediate Operating Conditions Using Wavelet Packet Transform and Support Vector Machine

This paper proposes advancement in the fault diagnosis of induction motors (IMs) based on the wavelet packet transform (WPT) and the support vector machine (SVM). The aim of this work is to develop and perform the fault diagnosis of IMs at intermediate operating conditions (i.e., the speed and the load) to take care of situations where the data are limited or difficult to obtain at required speeds and loads. In order to check the capability of proposed fault diagnosis, ten different IM fault (mechanical and electrical) conditions are considered simultaneously. In order to obtain the useful information from raw time series data that can characterize each of the fault classes at various operating conditions, the wavelet packet is applied to decompose the data of vibration and current signals from the experimental test rig. Fault features are then obtained using the decomposed data and further used for the diagnosis. In this work, five different wavelet functions (i.e., the Haar, Daubechies, Symlet, Coiflet, and Discrete Meyer) are considered in order to analyze the impact of different wavelets on the IM fault diagnosis. The proposed fault diagnosis has been initially attempted for the same speed and load cases and then extended innovatively to the intermediate speed and load cases. In order to check the robustness of the proposed methodology, the diagnosis is performed for a wide range of motor operating conditions. The results show the feasibility of the proposed fault diagnosis for the successful detection and isolation of various faults of IM, even with limited data or information at some motor operating conditions.

Wireless Fault Detection System for an Industrial Robot Based on Statistical Control Chart

Industrial robots are now commonly used in production systems to improve productivity, quality and safety in manufacturing processes. Recent developments involve using robots cooperatively with production line operatives. Regardless of application, there are significant implications for operator safety in the event of a robot malfunction or failure, and the consequent downtime has a significant impact on productivity in manufacturing. Machine healthy monitoring is a type of maintenance inspection technique by which an operational asset is monitored and the data obtained is analysed to detect signs of degradation and thus reducing the maintenance costs. Developments in electronics and computing have opened new horizons in the area of condition monitoring. The aim of using wireless electronic systems is to allow data analysis to be carried out locally at field level and transmitting the results wirelessly to the base station, which as a result will help to overcome the need for wiring and provides an easy and cost-effective sensing technique to detect faults in machines. So, the main focuses of this research is to develop an online and wireless fault detection system for an industrial robot based on statistical control chart approach. An experimental investigation was accomplished using the PUMA 560 robot and vibration signal capturing was adopted, as it responds immediately to manifest itself if any change is appeared in the monitored machine, to extract features related to the robot health conditions. The results indicate the successful detection of faults at the early stages using the key extracted parameters.

Comparative investigations on reference models for fault detection and diagnosis in centrifugal chiller systems

Comparative investigations on reference models for fault detection and diagnosis in centrifugal chiller systems