Fault Detection System Research Articles

A customised artificial neural network for power distribution system fault detection

AbstractMachine learned fault detection approaches are being increasingly used for fault detection in distribution grid. However, the performance of the models can be improved by customizing the models. In this regard, a customised artificial neural network (CANN) for fault detection in a distribution grid is proposed in this paper. The proposed work develops a CANN that combines the “up‐pyramid” and “down‐pyramid” model of ANN into a “custom‐pyramid” model. As a result, the same model can be used both for determining the types of fault as well as its location. The data needed to train the model has been taken from a reconfigured IEEE‐33 bus distribution system developed in Typhoon HIL real‐time simulator. Spectral‐kurtosis is utilized for extraction of features of the faulted transient signals which are used as input data to develop the CANN. The result showcases that the reduction of input features reduces computational complexity without compromising its accuracy. The proposed model classifies fault location with an accuracy of 95.43%. The proposed method also identifies fault type with an accuracy of 96.08%. Several test cases have been developed to test the method. The method proved to be able to perform in most of the cases.

Using Deep Learning for PCB Fault Detection

Electronic components are mainly connected to one another using printed circuit boards, or PCBs. This phase holds significant importance in the production of electronic goods. The finished product may become unusable due to a minor PCB flaw. As a result, throughout the PCB manufacturing process, rigorous and thorough flaw identification procedures are essential. To guarantee the dependability and performance of electronic products, quality control and assurance procedures are essential in the electronics manufacturing process, especially when producing printed circuit boards (PCBs). Conventional inspection techniques are not always effective in locating different kinds of PCB flaws. Defect identification is essential to guaranteeing the dependability and functionality of electronic products since printed circuit boards, or PCBs, are essential parts of electronic gadgets. Conventional approaches to PCB defect detection, like manual inspection or traditional image processing methods, are frequently laborious, imprecise, and prone to human error. This research suggests utilizing the YOLOv5 model, a cutting-edge deep learning-based object detection technique, to create an automated PCB flaw detection system in order to overcome these difficulties

Fault detection in linear systems via interval parity relations

The problem of fault detection via interval parity relations designed for systems described by linear models under the external disturbances and measurement noise is considered. To solve the problem, the reduced-order model of minimal dimension insensitive or having minimal sensitivity to the external disturbances is used. Based on this model, the interval parity relations are designed. The relations that allow to construct two residuals are obtained and theorem showing that zero is between these residuals for healthy system is proved. Theoretical results are illustrated by example.

Fabric4show: real-time vision system for fabric defect detection and post-processing

The exploration of computer vision applications for fabric defect detection has immense potential value. However, current relevant research in this area has primarily focused on detection models that aim for high detection accuracy and algorithmic efficiency, while neglecting the practical industrial production requirements. Therefore, we propose a fabric defect detection and post-processing system that integrates an optimized region with convolutional neural network (CNN) features (i.e., Faster R-CNN) for defect detection, defect localization and detection model evaluation. In addition, the proposed intelligent system incorporates novel approaches, such as a rearranged fabric dataset, anomaly detection, recommended clipping region division, and a replenishment device. This study illustrates an example of artificial intelligence (AI)-driven automated technology in fabric manufacturing. The accuracy and detection speed of different detection models under identical hardware conditions are evaluated and compared with related work. Experimental results demonstrate that the proposed approach achieves comparable performance to other models, while significantly reducing computational resource requirements. The potential efficiency of using two-stage networks on hardware systems for fabric defect detection tasks is highlighted, which is likely to have relevant implications for the textile industry.

Applying OPTICS with and without PCA for fault detection of fan coil units using building automation system data

In building operations, Heating, Ventilation, and Air Conditioning (HVAC) system faults lead to substantial energy waste. Due to the rapid growth in the availability of sensing data and advancements in computational technology, AI-based methods have emerged as a powerful tool for Fault Detection and Diagnosis (FDD) of HVAC systems, significantly enhancing the efficiency of building operations. Several studies support supervised learning methods for FDD; however, these are limited in practice due to their reliance on labeled datasets, which are generally unavailable. In this context, unsupervised methods, notably those using cluster analysis, show great promise, particularly for analysing Building Automation System (BAS) data. This paper presents a methodology using OPTICS – an ordered clustering algorithm – for fault detection and explores the impact of PCA on its accuracy for fault detection, using both published and full-scale historical building data. While beneficial for reducing computational costs and enhancing noise reduction — thereby generally improving the clarity of cluster differentiation — PCA’s dimensionality reduction may result in the loss of critical information, leading to some clusters being less discernible or entirely undetected. These overlooked clusters could be indicative of underlying faults, and their obscurity represents a significant limitation of PCA when identifying potential faults in complex data.

Information manifold and fault detection of multi-agent systems

With the increase of the number of agents in multi-agent systems and the rapid increase of the complexity of the overall structure of the system, the fault detection and diagnosis work has brought great challenges. Researchers have carried out considerable research work on fault detection and diagnosis of multi-agent systems, but there is no research on fault state estimation and diagnosis based on the information and state of the whole multi-agent system. Based on the global perspective of information geometry theory, this paper presents two new physical quantities of the information manifold of multi-agent systems, as Lagrangian and energy–momentum tensor, to express the state of the overall information of multi-agent systems, and to characterize the energy state and development trend of faults. In this paper, two new physical parameters are introduced into the research of multi-agent fault detection and diagnosis, and the fault state and trend of multi-agent system are evaluated from the global perspective, which provides more comprehensive theoretical support for designing more scientific and reasonable fault diagnosis and fault recovery strategies. Simulation of the application example confirms the competitive performance of the proposed method.

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.

Towards unsupervised fault detection for offshore wind turbine cable protection systems using contrastive learning

As offshore wind power expands globally, it is essential to ensure the reliable operation of components of such critical infrastructures. A less explored instance of such components, which are though essential in terms of operation, is found in subsea turbine cables and their protection systems, whose failure can incur prolonged shutdown periods and costly repairs. We propose a novel unsupervised machine learning approach exploiting use of Distributed Acoustic Sensing (DAS) data and contrastive learning for monitoring offshore wind turbine Cable Protection Systems (CPSs). A Transformer neural network adapted for time-series ingests the high-frequency, noisy DAS CPS time-series measurements, and is trained to learn a coherent representation of the data using a contrastive learning scheme that enforces temporal and positional consistency in the latent space. This latent representation can then be used to perform anomaly detection in an unsupervised manner, alleviating the need for costly labeled offshore anomaly data. We demonstrate that a coherent representation of the data is learnt by the model, which we then use to detect synthetic anomalies and an actual CPS stabilization event.

40‐3: Waveform Analysis System for GAN‐Based Anomaly Detection of Coater Pressure in Photolithography

With the advancement of manufacturing equipment and the development of sensing technology, the measurement cycle of data is becoming very short, and the characteristics of data observed at the same time are also diversifying. A Fault Detection and Classification (FDC) system is in operation to collect and analyze measurement data in real time in the display manufacturing factory. However, the anomaly detection function provided by the FDC system is based on a threshold comparison method for data in seconds, so there is a limit to accuracy in processing measurement data in milliseconds. In particular, if the process for one panel is divided into several steps and each of them shows various characteristics, it is difficult to manage because it takes a lot of airlift to set search conditions and thresholds for anomaly detection. To overcome this, a waveform analysis system is implemented to assist the FDC system. This system extracts waveforms from milliseconds of measurement data during the processing time of one panel in the equipment, and diagnoses whether the equipment processing is normal through GAN‐based waveform pattern analysis. Generative models are used in the anomaly detection process in consideration of the manufacturing environment in which the normal data is overwhelmingly larger than the abnormal data. The DCGAN‐based model that is excellent in image processing and the TadGAN‐based model that combines Auto encoder and GAN were implemented and used. In this paper, the anomaly detection performance of models is compared and evaluated for the display photo process Coater Pressure sensor using the waveform analysis system implemented in this way.

Automated Defect-Detection System for Water Pipelines Based on CCTV Inspection Videos of Autonomous Robotic Platforms

Automated Defect-Detection System for Water Pipelines Based on CCTV Inspection Videos of Autonomous Robotic Platforms

A Deep Learning-based Fault Detection and Classification in Smart Electrical Power Transmission System

Progressively, the energy demands and responsibilities to control the demands have expanded dramatically. Subsequently, various solutions have been introduced, including producing high-capacity electrical generating power plants, and applying the grid concept to synchronize the electrical power plants in geographically scattered grids. Electrical Power Transmission Networks (EPTN) are made of many complex, dynamic, and interrelated components. The transmission lines are essential components of the EPTN, and their fundamental duty is to transport electricity from the source area to the distribution network. These components, among others, are continually prone to electrical disturbance or failure. Hence, the EPTN required fault detection and activation of protective mechanisms in the shortest time possible to preserve stability. This research focuses on using a deep learning approach for early fault detection to improve the stability of the EPTN. Early fault detection swiftly identifies and isolates faults, preventing cascading failures and enabling rapid corrective actions. This ensures the resilience and reliability of the grid, optimizing its operation even in the face of disruptions. The design of the deep learning approach comprises a long-term and short-term memory (LSTM) model. The LSTM model is trained on an electrical fault detection dataset that contains three-phase currents and voltages at one end serving as inputs and fault detection as outputs. The proposed LSTM model has attained an accuracy of 99.65 percent with an error rate of just 1.17 percent and outperforms neural network (NN) and convolutional neural network (CNN) models.

Deep learning-based automated tile defect detection system for Portuguese cultural heritage buildings

A prominent feature in Portuguese historic architecture is Portugal’s azulejos or tiles that cover cultural heritage buildings with colorful patterns. However, tiles are prone to deterioration due to the quality of masonry materials, exposure over time, and natural and human factors. A careful approach is necessary to detect and assess tile damage in time to conserve cultural heritage. Deep learning (DL) methods are applied to detect deterioration and damage by automating vision-based monitoring. This study uses the You Only Look Once (YOLO), method to detect deterioration in tiles automatically. To obtain the initial dataset, over 5000 images of damage were collected, including cracks, craters, glaze detachment, and tile lacunae, as well as images with no defects. Additionally, a MobileNet model was used for binary classification of damaged and intact tiles to compare classification and detection approaches. Through the fine-tuning of hyperparameters and updating the dataset, an overall accuracy of over 72% for YOLO (multiple classification) and 97% accuracy for binary classification was achieved, demonstrating the adequacy of the tool for real-world applications.

Deep learning based fault detection of automobile dry clutch system using spectrogram plots

Dry friction clutches are extremely important in the context of power transmission systems. Continuous exposure to extreme heat and loading makes clutch extremely susceptible to various faults. The timely detection and diagnosis of such faults are of utmost importance to prevent any damage to internal components and also helps in avoiding transmission system failures. In this research study, a novel approach that leverages the power of transfer learning (a famous deep learning technique) is proposed to diagnose multiple types of clutch faults including, worn release fingers, fractured pressure plates, deteriorated pressure plates, loss of friction material and distorted tangential strips using spectrogram plots. To train and validate the diagnostic system, vibration readings were taken from a specially designed test rig with the help of piezoelectric accelerometer while the clutch system was operated under different load conditions of 0 (no load), 5 and 10 kg This procedure of data collection was then repeated to acquire the vibration data for all of the fault conditions by replacing the good with fault components individually. These vibration signals were further processed and transformed into spectrogram plots that serves as the input data for the deep learning models considered. Fine-tuning techniques were applied on pretrained networks to maximise the prediction accuracy of the models to effectively determine and diagnose faults in the clutch system. For this study 12 pre-trained networks were chosen namely, Xception, InceptionResNet, DenseNet, AlexNet, VGG16, GoogLeNet, VGG19, ResNet101, ResNet50, InceptionV3, MobileNetV2 and ShuffleNet. To optimize the performance of deep learning models, a systematic adjustment of hyperparameters such as the train-test split ratio, learning rate, optimizer and batch size for each network model was carried out. Through careful experimentation and analysis, significant improvements in fault classification accuracy were achieved thereby enhancing the reliability and effectiveness of the diagnostic system. From the results it was noted that 100% classification accuracy was displayed by AlexNet (for the no load condition and the 10 kg load condition) and GoogLeNet (for 5 kg load condition) with extremely low computation times.

Dynamic Weighted Slow Feature Analysis-based Fault Detection for Running Gear Systems of High-speed Trains

Dynamic Weighted Slow Feature Analysis-based Fault Detection for Running Gear Systems of High-speed Trains

Radiometric Infrared Thermography of Solar Photovoltaic Systems: An Explainable Predictive Maintenance Approach for Remote Aerial Diagnostic Monitoring

Solar photovoltaic (SPV) arrays are crucial components of clean and sustainable energy infrastructure. However, SPV panels are susceptible to thermal degradation defects that can impact their performance, thereby necessitating timely and accurate fault detection to maintain optimal energy generation. The considered case study focuses on an intelligent fault detection and diagnosis (IFDD) system for the analysis of radiometric infrared thermography (IRT) of SPV arrays in a predictive maintenance setting, enabling remote inspection and diagnostic monitoring of the SPV power plant sites. The proposed IFDD system employs a custom-developed deep learning approach which relies on convolutional neural networks for effective multiclass classification of defect types. The diagnosis of SPV panels is a challenging task for issues such as IRT data scarcity, defect-patterns’ complexity, and low thermal image acquisition quality due to noise and calibration issues. Hence, this research carefully prepares a customized high-quality but severely imbalanced six-class thermographic radiometric dataset of SPV panels. With respect to previous approaches, numerical temperature values in floating-point are used to train and validate the predictive models. The trained models display high accuracy for efficient thermal anomaly diagnosis. Finally, to create a trust in the IFDD system, the process underlying the classification model is investigated with perceptive explainability, for portraying the most discriminant image features, and mathematical-structure-based interpretability, to achieve multiclass feature clustering.

Internal thread defect detection system based on multi-vision.

In the realm of industrial inspection, the precise assessment of internal thread quality is crucial for ensuring mechanical integrity and safety. However, challenges such as limited internal space, inadequate lighting, and complex geometry significantly hinder high-precision inspection. In this study, we propose an innovative automated internal thread detection scheme based on machine vision, aimed at addressing the time-consuming and inefficient issues of traditional manual inspection methods. Compared with other existing technologies, this research significantly improves the speed of internal thread image acquisition through the optimization of lighting and image capturing devices. To effectively tackle the challenge of image stitching for complex thread textures, an internal thread image stitching technique based on a cylindrical model is proposed, generating a full-view thread image. The use of the YOLOv8 model for precise defect localization in threads enhances the accuracy and efficiency of detection. This system provides an efficient and intuitive artificial intelligence solution for detecting surface defects on geometric bodies in confined spaces.

Long-short term memory networks aided fault detection of power facilities

In recent years, long-short term memory (LSTM) networks have emerged as a promising tool for time-series analysis, offering the ability to capture temporal dependencies effectively, especially for the fault detection in power facilities which is crucial for maintaining operational integrity and ensuring continuous power supply. This paper presents a study on the utilization of LSTM networks for fault detection in power facilities, focusing on evaluating the detection accuracy as a performance metric. We propose a novel LSTM-based fault detection framework that utilizes historical operational data to identify abnormal patterns indicative of faults or anomalies. The framework is trained on labeled data to learn the normal operational behavior of the power facility, enabling it to detect deviations from expected patterns in practical data streams. To assess the effectiveness of the proposed approach, extensive experiments are conducted using real-world operational data from diverse power facilities. We systematically evaluate the detection accuracy of the LSTM-based fault detection system under various operating conditions, including different types of faults and levels of noise in the data. Comparative analyses are performed against traditional fault detection methods to demonstrate the superiority of the LSTM-based approach in terms of accuracy. Moreover, sensitivity analyses are conducted to investigate the impact of key parameters, such as network architecture and training data size, on the detection performance. The results illustrate the robustness and effectiveness of the proposed LSTM-based fault detection framework, highlighting its potential for enhancing the reliability and efficiency of power facility operations.

Edge Machine Learning-Enabled Predictive Fault Detection System for Conveyor Belt Maintenance Optimization in Industrial Settings

Digital transformation is essential for industrial and manufacturing sectors, especially in conveyor belt systems. On the other hand, Innovative electronic components and software applications offer opportunities for advanced fault prediction, minimizing operational disruptions, reducing inefficiencies, and enhancing overall industrial efficiency. Efficient conveyor belt systems are crucial for industrial operations, requiring early fault detection to prevent costly downtime and ensure safety. The utilization of embedded machine learning via the Edge Impulse platform enhances data collection and spectral feature extraction using wavelet approximation. This article presents a novel methodology for predictive fault detection in conveyor belt systems employing edge machine learning. Leveraging the ESP32 microcontroller and accelerometer sensor for real-time vibration data capture, a four-layer Artificial Neural Network (ANN) model, trained on 336 feature samples, is deployed via Edge Impulse and TensorFlow scripts. TensorFlow Lite compresses the model for microcontroller integration. The ESP32 microcontroller, acting as an edge device, achieves real-time predictions with 97.5% accuracy and 0.20 minimal loss. This work promises significant strides in predictive maintenance, offering cost savings, operational reliability, and efficiency gains in industrial settings, revolutionizing maintenance strategies.

Robust fault detection and isolation for uncertain neutral time-delay systems using a geometric approach

This paper proposes a new geometric fault detection and isolation (FDI) strategy for uncertain neutral time-delay systems (UNTDS). Firstly, the concept of unobservability subspace is extended to the considered system. Subsequently, utilizing the geometric properties of factor space and canonical projection, the fault is divided into different unobservability subspaces. Therefore, an algorithm for constructing the subspace is developed for fault isolation. Finally, a set of observers is designed for the subsystems, and generates a set of structured residuals which is sensitive only to a specific fault. Additionally, the H∞ technique is utilized to suppress the disturbances and error signals due to time-varying delays on the residual. The simulation examples verify the effectiveness of the proposed approach.

Fault detection and isolation in system of multiple sources of energy using hierarchical Bayesian belief networks

Fault detection and isolation in system of multiple sources of energy using hierarchical Bayesian belief networks