Fault Detection System Research Articles

Transformer encoder based self-supervised learning for HVAC fault detection with unlabeled data

Data driven methods are the most studied fault detection and diagnostics (FDD) type in buildings HVAC systems. However, most studies rely on labeled data for specific faults which are hard to find and collect for real systems. While the fault-free data is easier to collect, it is still time consuming to label for large systems operation. Moreover, most of the studies rely on the usage of supervised learning algorithms which do not generalize well beyond the training data making unseen faults hard to detect. In this paper, we define a methodology to use a self-supervised learning method for HVAC systems' FDD using a Transformer encoder, moreover, we tested it on a real case study. By strategically masking portions of the multivariate time-series data using Markov chain approach with two states. The model is trained by predicting these concealed segments. This approach, independent of labeled data, offers a scalable solution for practical HVAC applications. Anomalies are labeled using the Peak Over Threshold (POT) method, which dynamically determines thresholds by fitting reconstruction errors to a generalized Pareto distribution. Subsequent fault diagnostics emphasize features with pronounced reconstruction errors, pinpointing potential HVAC malfunctions. This methodology reduces dependence on labeled datasets and augments the model's generalization, facilitating detection of unobserved faults. This approach was applied to data from a real building. As a results multiple faults were detected mainly due to the malfunctioning of the monitoring system. The model demonstrates the ability to detect both sequential and individual faults. The period from October 19th to December 23rd was detected as a fault period due to the change in the trend of the data because of the monitoring system.

Enhancing robotic manipulator fault detection with advanced machine learning techniques

The optimization of rotating machinery processes is crucial for enhanced industrial productivity. Automatic machine health monitoring systems play a vital role in ensuring smooth operations. This study introduces a novel approach for fault diagnosis in robotic manipulators through motor sound analysis to enhance industrial efficiency and prevent machinery downtime. A unique dataset is generated using a custom robotic manipulator to examine the effectiveness of both deep learning and traditional machine learning in identifying motor anomalies. The investigation includes a two-stage analysis, initially leveraging 2D spectrogram features with neural network architectures, followed by an evaluation of 1D MFCC features using various conventional machine learning algorithms. The results reveal that the proposed custom CNN and 1D-CNN models significantly surpass traditional methods, achieving an F1-score exceeding 92%, highlighting the potential of sound analysis for automated fault detection in robotic systems. Additional experiments were carried out to investigate 1D MFCC features with various machine learning algorithms, including KNN, DT, LR, RF, SVM, MLP, and 1D-CNN. Augmented with additional data collected from the locally designed manipulator, our experimental setup significantly enhances model performance. Particularly, the 1D-CNN stands out as the top-performing model on the augmented dataset.

Centralized Monitoring System for Street Light and Fault Detection

The Centralized Monitoring System for Street Light and Fault Detection addresses the challenges by implementing advanced sensors, real-time monitoring, and data analytics to optimize energy consumption, enable timely fault detection, Provide well-maintained and reliable street lighting to create a safer urban environment for residents and commuters. The user interface offers an intuitive platform for administrators to monitor and manage the entire street lighting network. It provides clear visual feedback and control options.

Centrifugal Pump Fault Detection with Convolutional Neural Network Transfer Learning.

The centrifugal pump is the workhorse of many industrial and domestic applications, such as water supply, wastewater treatment and heating. While modern pumps are reliable, their unexpected failures may jeopardise safety or lead to significant financial losses. Consequently, there is a strong demand for early fault diagnosis, detection and predictive monitoring systems. Most prior work on machine learning-based centrifugal pump fault detection is based on either synthetic data, simulations or data from test rigs in controlled laboratory conditions. In this research, we attempted to detect centrifugal pump faults using data collected from real operational pumps deployed in various places in collaboration with a specialist pump engineering company. The detection was done by the binary classification of visual features of DQ/Concordia patterns with residual networks. Besides using a real dataset, this study employed transfer learning from the image detection domain to systematically solve a real-life problem in the engineering domain. By feeding DQ image data into a popular and high-performance residual network (e.g., ResNet-34), the proposed approach achieved up to 85.51% classification accuracy.

Improved YOLOv8 for B-scan image flaw detection of the heavy-haul railway

With the high speed and heavy duty of railway transportation, internal flaw detection of railway rails has become a hot issue. Existing rail flaw detection systems have problems of low detection accuracy and occasional missed flaw detection. In this paper, a high-precision flaw detection based on data augmentation and YOLOv8 improvement is proposed. Firstly, three data augmentation algorithms based on the characteristics of B-scan images are designed to enrich the dataset of rail flaws. Then, the small target detection layer and the cross-layer connectivity module are added to capture more information for small targets. Finally, the introduction of dynamic weights to coordinate attention can adjust the attentional weights and capture long-range information. The experimental results show that the mAP50 of the model after data enhancement and algorithm improvement is 97.9%, which is improved by 4.4% from the baseline model, and the frame per second is 64.52. The proposed method effectively detects many typical flaws, including the railhead flaw, rail jaw flaw, screw hole crack, and bottom flaw, which can provide technology supports for on-site maintenance staff.

Expert System for Online Defect Detection in Medical Devices Produced by Electron Beam Melting Using Layer-by-Layer Optical Images

Expert System for Online Defect Detection in Medical Devices Produced by Electron Beam Melting Using Layer-by-Layer Optical Images

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.

Fault Detection and Diagnosis in Electric Vehicle Systems using IoT and Machine Learning: A Support Vector Machine Approach

This research examines blame discovery and determination in electric vehicle (EV) frameworks utilizing Internet of Things (IoT) information and machine learning calculations, centring on a Support Vector Machine (SVM) approach. The study points to improving the unwavering quality and security of EV operations by precisely recognizing and diagnosing flaws in real time. The test comes about illustrates the adequacy of the SVM-based approach, with an exactness of 95%, accuracy of 94%, review of 96%, and F1-score of 95%. Comparative investigation with elective calculations such as k-Nearest Neighbors, Decision Tree, and Random Forest underscores the predominant execution of SVM in blame discovery and determination. The SVM calculation shows negligible misclassifications over distinctive blame classes, highlighting its strength and viability. This inquiry contributes to the headway of blame location strategies in EV frameworks and gives profitable bits of knowledge into the commonsense usage of machine learning strategies for improving framework unwavering quality. Moving forward, the discoveries clear the way for assist investigations in optimizing blame location systems and expanding their appropriateness to other spaces such as mechanical mechanization and renewable vitality frameworks.

Neural network predictive control for fault detection and identification in DFIG with SMES for low voltage ride-through requirements

The increasing reliance on renewable energy sources brings to light the operational challenges of doubly fed induction generators (DFIGs), particularly under grid disturbances. This study introduces an innovative approach employing Neural Network Predictive Control (NNPC) for fault detection and identification (FDI) in DFIG systems, integrated with Superconducting Magnetic Energy Storage (SMES) to meet Low Voltage Ride-Through (LVRT) requirements. Our method uniquely combines NNPC for dynamic wind speed prediction and precise control of rotor-side and grid-side converters with the stability enhancement offered by SMES. Simulation results demonstrate a notable improvement in DFIG performance under variable wind conditions and grid failures. The system-maintained voltage stability at the Point of Common Coupling (PCC) with less than 5% deviation during transients and ensured consistent power output, marking a significant advancement in LVRT compliance. However, the model assumes steady-state grid conditions and does not account for extreme weather scenarios, indicating areas for future research. This study's findings contribute valuable insights into the robust operation of DFIGs within modern renewable energy grids.

Physics-informed State-space Neural Networks for transport phenomena

This work introduces Physics-informed State-space neural network Models (PSMs), a novel solution to achieving real-time optimization, flexibility, and fault tolerance in autonomous systems, particularly in transport-dominated systems such as chemical, biomedical, and power plants. Traditional data-driven methods fall short due to a lack of physical constraints like mass conservation; PSMs address this issue by training deep neural networks with sensor data and physics-informing using components’ Partial Differential Equations (PDEs), resulting in a physics-constrained, end-to-end differentiable forward dynamics model. Through two in silico experiments – a heated channel and a cooling system loop – we demonstrate that PSMs offer a more accurate approach than a purely data-driven model. In the former experiment, PSMs demonstrated significantly lower average root-mean-square errors across test datasets compared to a purely data-driven neural network, with reductions of 44 %, 48 %, and 94 % in predicting pressure, velocity, and temperature, respectively.Beyond accuracy, PSMs demonstrate a compelling multitask capability, making them highly versatile. In this work, we showcase two: supervisory control of a nonlinear system through a sequentially updated state-space representation and the proposal of a diagnostic algorithm using residuals from each of the PDEs. The former demonstrates PSMs’ ability to handle constant and time-dependent constraints, while the latter illustrates their value in system diagnostics and fault detection.

Optimal Artificial Neural Network-based Fabric Defect Detection and Classification

Automated Fabric Defect (FD) detection plays a crucial role in industrial automation within fabric production. Traditionally, the identification of FDs heavily relies on manual assessment, facilitating prompt repairs of minor defects. However, the efficiency of manual recognition diminishes significantly as labor working hours increase. Consequently, there is a pressing need to introduce an automated analysis method for FD recognition to reduce labor costs, minimize errors, and improve fabric quality. Many researchers have devised defect detection systems utilizing Machine Learning (ML) approaches, enabling swift, accurate, and efficient identification of defects. This study presents the Optimal Artificial Neural Network-based Fabric Defect Detection and Classification (OANN-FDDC) technique. The OANN-FDDC technique exploits handcrafted features with a parameter-tuning strategy for effectively detecting the FD process. To obtain this, the OANN-FDDC technique employs CLAHE and Bilateral Filtering (BF) model-based contrast augmentation and noise removal. Besides, the OANN-FDDC technique extracts shape, texture, and color features. For FD detection, the ANN method is utilized. To improve the detection results of the ANN method, the Root Mean Square Propagation (RMSProp) optimization technique is used for the parameter selection process. The simulation outputs of the OANN-FDDC technique were examined on an open fabric image database. The experimental results of the OANN-FDDC technique implied a better outcome than the 96.97% of other recent approaches.

Optimal Fault Detection for Stochastic Linear Time-Varying Systems by $\chi ^{2}$ Test

Optimal Fault Detection for Stochastic Linear Time-Varying Systems by $\chi ^{2}$ Test

A New Approach for Single-Phase-to-Ground Fault Detection in Mid-Voltage Systems Using Low-Voltage Sensors

Single-phase-to-ground fault in low-current grounding systems represents a serious public safety concern. Low-voltage (LV) sensors, with their growing maturity, can now monitor multiple points of the mid-voltage (MV) distribution network. This paper proposes a new method for identifying single-phase-to-ground line faults and locating them using LV sensors deployed on the LV side of distribution transformers. We analyze the characteristics of the negative-sequence signal on the LV side after a single-phase grounding fault occurs on the MV side. The negative-sequence current can distinguish between fault and non-fault lines. By setting the ratio coefficient of negative-sequence voltage and positive-sequence voltage, we can use multi-point collaborative calculation and comparison to determine the section of the fault point. We consider the unbalanced load on the LV side and the special case of a fault point on one end of the line. Through simulation of combined MV and LV distribution systems in MATLAB software and dynamic model experiments, we verify that the proposed method has good robustness and accuracy. Monitoring the status information of the MV distribution network through LV sensors has great potential in practical application and implementation for realizing the fault detection of low-current grounding systems.

Unified Solutions to Optimal Fuzzy Observer-Based Fault Detection for Discrete-Time Nonlinear Systems

Unified Solutions to Optimal Fuzzy Observer-Based Fault Detection for Discrete-Time Nonlinear Systems

An energy‐aware software fault detection system based on hierarchical rule approach for enhancing quality of service in internet of things‐enabled wireless sensor network

AbstractOf late, the Internet of Things (IoT) has progressed in its pervasiveness across the globe for diverse applications. Wireless Sensor Network (WSN) is one of the prominent technologies employed in IoT environments where multiple tiny sensor nodes are distributed to sense real‐time observations about unforeseeable areas for control and managerial purposes. Owing to the presence of sensors in inaccessible regions and their battery restrictions, different types of software faults occur in IoT‐enabled WSNs (IWSNs). These faults create uncertainty in data reading which causes serious damage to the sensor network. Hence, the IWSN necessitates an effective fault‐detection methodology to continue optimal activity despite the existence of software faults. This work proposes a novel Energy‐Aware Hierarchical Rule‐based Software Fault Detection (HRSFD) model to identify various software faults with minimum energy depletion in the IWSN environment. Primarily, the proposed model extracts antecedent attributes from the characteristics of the sensed data. Its abnormal values can be identified based on the obtained antecedent attributes. Subsequently, the category of the software fault is determined by applying a hierarchical rule strategy. Finally, from the simulation results, it is apparent that the fault detection accuracy rate of the proposed HRSFD model attains 99.12% for dense networks. The lifetime of the network is also prolonged by 18% as compared to the existing state‐of‐the‐art models.

Machine Learning Approaches for In-Vehicle Failure Prognosis in Automobiles: A Review

The automobile industry has a growing need for reliable and safe health monitoring systems equipped with low-cost sensor networks and intelligent algorithms. This paper provides an overview of approaches already exist, used in on-board health monitoring systems for vehicles. It focuses on the methodologies, theories, and applications employed in the data measurement and data analysis systems of vehicle (cars) on-board health monitoring systems. A fault detection and diagnosis system, which is accurate, plays a vital role in ensuring the safety of autonomous vehicles by preventing potentially dangerous situations. This study focuses on emphasizing a fault diagnosis system that utilizes hybrid methods. Among the various options considered in this analysis, internal sensors emerge as the preferred choice due to their numerous benefits, including affordability, durability, widespread availability, ease of access, and low energy consumption. Model-based methods require various techniques that may introduce errors to estimation results, while signal-based methods necessitate a time-consuming process of including all possible conditions in a pre-built database. Based on this review, future development trends in designing new low-cost health monitoring systems for vehicles are also discussed.

Innovative Approaches for Dynamic System Monitoring: Signal Processing and Parameter Estimation Strategies

Dynamic system monitoring is essential for ensuring the optimal performance and reliability of various systems across multiple domains. This Abstract introduces innovative approaches focusing on signal processing and parameter estimation strategies for dynamic system monitoring. Signal processing techniques such as wavelet transform and adaptive filtering are utilized for noise reduction and feature extraction from sensor data. Additionally, parameter estimation strategies including Kalman filtering and Bayesian inference aid in accurately estimating system parameters and states in real-time. These advanced methods, integrating machine learning and statistical inference, promise enhanced monitoring capabilities, facilitating proactive maintenance and fault detection in complex dynamic systems. Through case studies and simulation results, the effectiveness and versatility of these approaches in addressing real-world challenges are demonstrated, illustrating their potential for advancing the field of dynamic system monitoring.

Predictive maintenance in oil and gas facilities, leveraging ai for asset integrity management

This paper explores the application of AI in predictive maintenance within oil and gas facilities, discussing its benefits, challenges, and future prospects. Through the integration of AI-driven analytics and real-time data monitoring, oil and gas companies can enhance their asset integrity management practices, ultimately driving cost savings and operational excellence. Predictive maintenance has become indispensable in the oil and gas industry, serving as a pivotal strategy to uphold operational efficiency and preserve asset integrity. This paper delves into the profound impact of artificial intelligence (AI) technologies on predictive maintenance, ushering in a new era of proactive equipment management. By harnessing AI capabilities, oil and gas companies can preempt equipment failures, curtail downtime, and refine maintenance protocols, thereby optimizing overall operational performance. The integration of AI in predictive maintenance marks a paradigm shift, offering a proactive approach to asset management. Leveraging AI-driven analytics and real-time data monitoring, oil and gas facilities can fortify their asset integrity management practices. Through predictive algorithms and machine learning models, these technologies empower companies to forecast equipment malfunctions with unprecedented accuracy, allowing for timely interventions and mitigating potential risks the benefits of AI-powered predictive maintenance in the oil and gas sector are multifaceted the future of predictive maintenance in the oil and gas industry is brimming with promise. As AI technologies continue to evolve, we can anticipate further advancements in predictive analytics, fault detection, and decision support systems. By embracing innovation and collaboration, oil and gas companies can harness the full potential of AI-driven predictive maintenance, cementing their position as industry leaders in asset management and operational efficiency.

IOT based smart street light fault detection management system

In the contemporary landscape of urbanization and technological progress, efficient resource management, particularly in energy consumption, is paramount. Street lighting stands out as a significant energy consumer in urban environments. This paper proposes a Smart Street Light Fault Detection System utilizing Internet of Things (IoT) technology, a NodeMCU microcontroller, Light Dependent Resistor (LDR), street lights, and the ThingSpeak. The system employs the NodeMCU microcontroller to monitor ambient light conditions through the LDR sensor, enabling automatic control of street lights to optimize energy usage. Furthermore, it integrates fault detection mechanisms to identify abnormalities in street light operations, such as constant light levels amidst changing environmental conditions, indicative of potential faults. Through the ThingSpeak, users can remotely monitor real-time LDR readings, receive notifications about detected faults, and take necessary actions, empowering city authorities or maintenance personnel with timely information for addressing issues and ensuring smooth infrastructure operation. This smart system offers advantages like energy efficiency, automated control, and proactive fault detection, facilitating significant energy savings, reduced maintenance costs, and enhanced sustainability in urban environments, thereby showcasing a practical implementation of IoT technology for smarter and more sustainable cities.

Hierarchical spatial–temporal autocorrelation graph neural network for online wind turbine pitch system fault detection

The advancement of low-cost, non-manually labeled big data technologies for fault detection in wind turbines is crucial to guarantee their safe and efficient operation. In this context, Normal Behavior Modelling (NBM) is a prevalent approach. However, existing NBM methods for wind turbine fault detection inadequately utilize complex spatial–temporal correlations within the Supervisory Control and Data Acquisition (SCADA) during the normal behavior prediction stage. To cope with this limitation, this paper propose a hierarchical spatial-temporal autocorrelation graph neural network method for online wind turbine pitch system fault detection. This approach integrates a dynamic graph network with an adaptive structure for spatial correlation learning and a transformer model with autocorrelation attention to identify periodic time-distance correlations. Furthermore, a hierarchical neural network, specifically designed for wind turbine physical structure, enhances local information extraction through seven latent graph neural networks and a probsparse attention mechanism. The proposed method demonstrates significant effectiveness in real-world applications, as evidenced by data from a Shanghai wind farm.