Neural Network Based Fault Detection Research Articles

Artificial Neural Network-Based Fault Detection on Nigerian 330kv Power Transmission Line

In Nigeria, there will inevitably be ongoing difficulties with 330kv power transmission lines. This drop in insulation strength between the phase conductors and the earthed screen encircling the conductors may be the cause of the difficulties that have emerged on the electric transmission circuit. Many scholars have approached these problems in different ways. Fast Fourier Transform (FFT), Wavelet Transform, Fourier Transform, S-Transform, and Fourier Series are a few of the techniques utilized to address these transmission line problems. It has not been widely and thoroughly adopted to solve problems in Power System Engineering, according to numerous study studies on artificial neural networks (ANNs). Consequently, the 330kV Power Transmission Line problems have been addressed in this research by using artificial neural networks (ANNs). the training efficacy of any ANN challenges diagnosis system. The MATLAB/Simulink R2018a was utilized to conduct simulations on an ANN challenges detector. The ANN detector was trained with pre-fault and fault signals as inputs, allowing for the identification of different types of line difficulties. Results indicated that at Mean Square Error (MSE) of 1.6856e-5, the best training performance for the challenges was attained. At Regression, it approaches zero (9.8958e-1). Because it met the requirements, the simulation's outcome is acceptable. Keywords: Power System, Transmission Line, Matlab/Simulink, Three Phase, Artificial neural networks, fault detection.

2D-convolutional neural network based fault detection and classification of transmission lines using scalogram images

The reliable operation of power transmission systems is essential for maintaining the stability and efficiency of the electrical grid. Rapid and accurate detection of faults in transmission lines is crucial for minimizing downtime and preventing cascading failures. This research presents a novel approach to fault detection and classification in transmission lines employing 2D Convolutional Neural Networks (2D-CNN).The proposed methodology leverages the inherent spatial characteristics of fault signals, converting them as 2D scalogram images for input to the CNN model. By converting fault signals into scalogram representations, the network can capture both temporal and frequency domain features, enabling a more comprehensive analysis of fault patterns. The 2D-CNN architecture is designed to automatically learn hierarchical features, allowing for effective discrimination between different fault types. To evaluate the performance of the proposed approach, extensive simulations and experiments were conducted using MATLAB/SIMULINK modeled transmission line data. The results demonstrate the superior fault detection accuracy and classification capabilities of the 2D-CNN model. The performance of the proposed model is evaluated using 10-fold cross-validation, and its effectiveness is assessed by comparing it with current state-of-the-art techniques. Proposed 2D-CNN model has evidenced an accuracy of 99.9074 with ideal dataset for 12- class fault classification and performing consistently in presence of noise, having an accuracy of 99.629 %,99.72 % and 99.814 % in 20.30 and 40 dB noises respectively. The proposed model also verified in high resistance fault condition. The model exhibits robustness to noise and is capable of generalizing well to various fault scenarios. The proposed methodology offers a scalable and efficient solution for transmission line fault analysis, paving the way for the integration of advanced machine learning techniques into the operation and maintenance of power transmission infrastructure.

Cyber-Physical Distributed Intelligent Motor Fault Detection.

This research paper explores the realm of fault detection in distributed motors through the vision of the Internet of electrical drives. This paper aims at employing artificial neural networks supported by the data collected by the Internet of distributed devices. Cross-verification of results offers reliable diagnosis of industrial motor faults. The proposed methodology involves the development of a cyber-physical system architecture and mathematical modeling framework for efficient fault detection. The mathematical model is designed to capture the intricate relationships within the cyber-physical system, incorporating the dynamic interactions between distributed motors and their edge controllers. Fast Fourier transform is employed for signal processing, enabling the extraction of meaningful frequency features that serve as indicators of potential faults. The artificial neural network based fault detection system is integrated with the solution, utilizing its ability to learn complex patterns and adapt to varying motor conditions. The effectiveness of the proposed framework and model is demonstrated through experimental results. The experimental setup involves diverse fault scenarios, and the system's performance is evaluated in terms of accuracy, sensitivity, and false positive rates.

A Physics-Based Model-Data-Driven Method for Spindle Health Diagnosis—Part III: Model Training and Fault Detection

Abstract The primary goal of the paper is to monitor the health of the spindle in machine tools to ensure optimal performance and reduce costly downtimes. Spindle health monitoring is essential to detect wear and cracks in spindle bearings, which can be challenging due to their gradual development and hidden locations. The proposed approach combines physics-based modeling and data-driven techniques to monitor spindle health effectively. In Part I and Part II of the paper, mathematical models of bearing faults and spindle imbalance are integrated into the digital model of the spindle. This allows for simulating the operation of the spindle both with and without faults. The integration of fault models enables the generation of vibrations at sensor locations along the spindle shaft. The generated vibration data from the physics-based model are used to train a recurrent neural network-based (RNN) fault detection algorithm. The RNN learns from the labeled vibration spectra to identify different fault conditions. Bayesian optimization is used to automatically tune the hyperparameters governing the accuracy and efficiency of the learning models during the training process. The RNN classifiers are further fine-tuned using a small set of experimentally collected data for the generalization of the model on real-world data. Once the RNN classifier is trained, it can distinguish between different types of damage and identify their specific locations on the spindle assembly. The proposed algorithms achieved an accuracy of 98.43% on experimental data sets that were not used in training the network.

Artificial neural network-based fault detection and isolation in a parabolic-trough solar plant with defocusing strategy

Fault detection is crucial for ensuring optimal operation and maintenance of solar plants. This paper proposes a methodology for fault detection and isolation using artificial neural networks (ANNs) in a model of a 50 MW parabolic-trough solar plant that employs a defocusing strategy. The proposed methodology focuses on detecting three different types of faults in the collector area, namely, faults in the optical efficiency, flow rate, and thermal losses. The methodology is divided into three steps. Firstly, a feedforward dynamic neural network that internally models the concentrated parameter model of the system is used to detect faults and output the fault type. Secondly, information on the defocusing mechanism is added to the inputs of the neural network. Finally, the range of faults considered is adjusted based on the neural networks’ ability to detect each fault size and its impact on the plant’s outlet temperature. The accuracy of fault detection is evaluated through several simulations, and the proposed methodology shows promising results. The accuracy of fault detection is found to be 71.72%, 83.96%, and 90.62% for the first, second, and third approaches, respectively. The proposed methodology based on ANNs has the potential to improve the operational efficiency and reduce maintenance costs of solar plants.

Artificial Neural Network-Based Fault Detection System with Residual Analysis Approach on Centrifugal Pump: A Case Study

Centrifugal pump is an instrument that is widely used in industry and has become the main driving component. A detection system is often needed to prevent damage to these pumps because they can interfere with the overall system performance. Therefore, this study discussed the development of a fault detection system for two centrifugal pump units, namely the Medium Pressure Oil Pump (MPOP) and the Water Injection Pump (WIP). In detecting the operating conditions of the pump, it was used a residual feature extraction technique in the time domain with a statistical approach. Residual was generated by using three sub-systems of a pumping system. Each sub-system was modeled using an artificial neural network with feedforward-back propagation architecture. Based on the feature values, the classifier was designed to classify pump conditions. Then the proposed fault detection system was applied in a condition monitoring system scheme. The test results (using data from the field) show that the fault detection system has an accuracy of 91.67% for MPOP and 94.8% for WIP cases. Meanwhile, the fault detection system has an accuracy above 99% during online monitoring simulations.

Enhancing reliability and lifespan of PEM fuel cells through neural network-based fault detection and classification

In order to maximise fuel cell reliability of operation and useful life span, an accurate online health assessment of the fuel cell system is essential. Existing algorithms for fault detection in fuel cell systems are based on sensing elements, control methods, and statistical/probabilistic models. In this paper, an artificial neural network (ANN) will be developed to detect and classify faults in proton-exchange membrane (PEM) fuel cell systems. As the ANN model developed within the PEM system relies on the input and output current and voltage, additional sensing devices are not required within the system. Based on an experimental setup using a 3-kW fuel cell system, it was found that the proposed model was able to detect faults associated with the reduction/increase of fuel pressure, H2 consumption rate, and voltage regulation changes in the dc-dc converter with >90% accuracy. In the proposed model, historical data is required to train and validate the ANN algorithm, but after this is complete, no human intervention is required afterward.

Fault detection for vaccine refrigeration via convolutional neural networks trained on simulated datasets

In low-and middle-income countries, the cold chain that supports vaccine storage and distribution is vulnerable due to insufficient infrastructure and interoperable data. To bolster these networks, we developed a convolutional neural network-based fault detection method for vaccine refrigerators using datasets synthetically generated by thermodynamic modeling. We demonstrate that these thermodynamic models can be calibrated to real cooling systems in order to identify system-specific faults under a diverse range of operating conditions. If implemented on a large scale, this portable, flexible approach has the potential to increase the fidelity and lower the cost of vaccine distribution in remote communities.

Artificial Bee and Ant Colony-assisted Performance Improvements in Artificial Neural Network-based Rotor Fault Detection

Asynchronous motors are the most commonly used types of motor in the industry. They are preferred because of their ease of control and reasonable cost. Since it is not desirable to suspend production in factories, it is required that motor failures used in production lines be detected quickly and easily. In this article, sound signals were recorded during the operation of the asynchronous motor, which is operational and with a rotor bar crack; and filtering, normalization, and Fast Fourier Transform were performed. The detection of rotor broken bar error was examined using the feed-forward backpropagation Artificial Neural Network (ANN) method. With intuitive algorithms such as the artificial bee colony and artificial ant colony, improvements to the ANN results were investigated. The experimental results verified that intuitive algorithms can improve the estimation performance of the neural network.

Handling Imbalanced Datasets for Robust Deep Neural Network-Based Fault Detection in Manufacturing Systems

Over the recent years, Industry 4.0 (I4.0) technologies such as the Industrial Internet of Things (IIoT), Artificial Intelligence (AI), and the presence of Industrial Big Data (IBD) have helped achieve intelligent Fault Detection (FD) in manufacturing. Notably, data-driven approaches in FD apply Deep Learning (DL) techniques to help generate insights required for monitoring complex manufacturing processes. However, due to the ratio of instances where actual faults occur, FD datasets tend to be imbalanced, leading to training challenges that result in inefficient DL-based FD models. In this paper, we propose Dual Logits Weights Perturbation (DLWP) loss, a method featuring weight vectors for improved dataset generalization in FD systems. The weight vectors act as hyperparameters adjusted on a case-by-case basis to regulate focus accorded to individual minority classes during training. In particular, our proposed method is suitable for imbalanced datasets from safety-related FD tasks as it generates DL models that minimize false negatives. Subsequently, we integrate human experts into the workflow as a strategy to help safeguard the system. A subset of the results, model predictions with uncertainties exceeding a preset threshold, are considered a preliminary output subject to cross-checking by human experts. We demonstrate that DLWP achieves improved Recall, AUC, F1 scores.

Real-Time Fault Detection in Discrete Manufacturing Systems Via LSTM Model based on PLC Digital Control Signals

A lot of sensor and control signals is generated by an industrial controller and related internet-of-things in discrete manufacturing system. The acquired signals are such records indicating whether several process operations have been correctly conducted or not in the system, therefore they are usually composed of binary numbers. For example, once a certain sensor turns on, the corresponding value is changed from 0 to 1, and it means the process is finished the previous operation and ready to conduct next operation. If an actuator starts to move, the corresponding value is changed from 0 to 1 and it indicates the corresponding operation is been conducting. Because traditional fault detection approaches are generally conducted with analog sensor signals and the signals show stationary during normal operation states, it is not simple to identify whether the manufacturing process works properly via conventional fault detection methods. However, digital control signals collected from a programmable logic controller continuously vary during normal process operation in order to show inherent sequence information which indicates the conducting operation tasks. Therefore, in this research, it is proposed to a recurrent neural network-based fault detection approach for considering sequential patterns in normal states of the manufacturing process. Using the constructed long short-term memory based fault detection, it is possible to predict the next control signals and detect faulty states by compared the predicted and real control signals in real-time. We validated and verified the proposed fault detection methods using digital control signals which are collected from a laser marking process, and the method provide good detection performance only using binary values.

Real-Time Hierarchical Neural Network Based Fault Detection and Isolation for High-Speed Railway System Under Hybrid AC/DC Grid

Real-Time Hierarchical Neural Network Based Fault Detection and Isolation for High-Speed Railway System Under Hybrid AC/DC Grid

Neural network-based fault detection for nonlinear networked systems with uncertain medium access constraint: Application to motor systems

The fault detection for a class of continuous-time nonlinear networked control systems with medium access constraint is concerned in this paper, where the occurring probability of transition from one sensor to another is allowed to be partially unknown and uncertain. First of all, a Markovian system approach is adopted to describe the access process of sensors, in which only one sensor is allowed to access the communication channel. A robust filter based residual generator is proposed to generate the residual signal such that it can be used to indicate whether the fault has occurred or not. The nonlinear term is approximated by a neural network, and the Lyapunov–Krasovskii functional is introduced to analyze the fault detection system, three sufficient conditions for the stochastic stability of fault detection error system are given, and the fault detection filter gains are calculated via solving some matrix inequalities. In the simulation, a second-order DC motor system is used to validate of the main results, which shows the effectiveness of the fault detector design.

Sensor Failure Management in Liquid Rocket Engine using Artificial Neural Network

This paper presents a novel Artificial Neural Network based Fault Detection, Isolation and Substitution (ANN-FDIS)algorithm for faulty sensor measurement in Liquid Rocket Engine (LRE). Fault detection and isolation are done by residual and fault flag logics and the trained multilayer perceptron model Artificial Neural Network (ANN) substitutes faulty sensor measurement. Data for ANN training, testing and validation are extracted from qualification and validation hot tests of LRE. Regression (R) and Mean Square Error (MSE) are considered for evaluating the ANN. During validation of this study, the faulty sensor is identified, isolated and data substituted from other input parameters with an error less than ±0.7%. This unique scheme does not require accurate modeling of the complicated LRE as well as sensor hardware redundancy which adds weight, space and power to rockets.

Recurrent Neural Networks Based Fault Detection for Synchronous Generator Stator Windings Protection. (Dept. E.)

This paper presents a proposed approach for fault detection and faulty phase(s) identification for synchronous generator protection-based om artificial neural networks. In order to perform this approach: the protection system is subdivided into different neural network modules for fault detection and classification. The proposed approach uses Recurrent Neural Network (RNN) to detect and classify the synchronous generator internal faults. The RNN uses the three-phase current measurements from both sides of the synchronous generator stator winding as its input data. RNN was trained using various sets of data available from the simulation results of the selected synchronous model under different fault scenarios (fault type, fault location, fault resistance and fault inception angle). Simulation results of the proposed RNN based synchronous generator stator winding protection provide a great performance; in terms of accuracy, speed and reliability.

Real-Time Hierarchical Neural Network Based Fault Detection and Isolation for High-Speed Railway System Under Hybrid AC/DC Grid

Reliable and comfortable high-speed railway (HSR) has skyrocketed in popularity as a transportation medium for traveling around the world. High-voltage direct current (HVDC) electrification system has been introduced to the HSR gradually. However, the coexistence of AC and DC systems will last for a long time because AC railway systems are still in the dominant position. A detailed HSR traction system transient model operating under the hybrid AC/DC grid was established in PSCAD/EMTDC. We proposed a real-time fault detection and isolation (FDI) method for the simulated model using neural network (NN). Hierarchical structure of the monitoring system has been employed. Low-level sub-monitors supervised the conditions of their local regions and the top-level monitor collected all the feedback from sub-monitors making the final evaluation of the entire HSR system based on a voting strategy. Both off-line and real-time experiments were conducted to validate the effectiveness of the proposed method. In the experiments, the sub-monitors were designed based on Gated Recurrent Unit (GRU) algorithm and implemented on the Xilinx VCU128 FPGA board. For the off-line experiment, the sub-monitors used the training and testing dataset both from PSCAD/EMTDC to construct the architecture of their individual GRU networks and to verify how great the networks can be. For the real-time task, the sub-monitors interfaced with a real-time HSR system emulator running on the Xilinx VCU118 FPGA board to test the performance in the real-time application. The results proved that our proposed FDI method has the capability of real-time detection and can achieve better accuracy within reasonable time and resource consumption than other NN-based methods. Moreover, the method was capable of standing against noises from measured signals to some extent.

Long short-term memory neural network based fault detection and isolation for electro-mechanical actuators

In the new generation of aircraft, electro-mechanical actuators (EMA) have been replacing the conventional hydraulic versions. Despite the fact that a failure of this system can seriously affect the safety of vehicles and their operators, there are few studies that focus on fault diagnosis for the units. In this paper, we present an innovative fault detection and isolation method for the EMA. Our method is tested and verified against three types of failures. This novel fault diagnosis method works by creating a model for sensor data by using the known time series. It utilizes an advanced Long Short-term Memory (LSTM) neural network, which can effectively handle time series data in this domain. A modification to the LSTM network is applied in order to take advantage of the correlation between sensors. In addition, the algorithm uses a sliding window to improve performance of LSTM applied to fault isolation. Our research has revealed that the proposed algorithm is better able to detect faults when compared to traditional neural networks. We also compare our performance with the support vector machine algorithm and the typical LSTM algorithm. Ultimately, the proposed method performs superiorly for the task of fault isolation.

Neural Network Based Adaptive Actuator Fault Detection Algorithm for Robot Manipulators

In order to improve the reliability of robotic systems, various fault detection and isolation (FDI) algorithms have been proposed. However, most of these algorithms are model-based and thus, an accurate model of the robot is required although it is hard to obtain and often time-varying. Acceleration estimation is an additional challenge in dynamic model-based algorithms as it is hard to measure accurately in practice. In this study, a neural network based fault detection algorithm that does not require the use of physical robot model and acceleration is proposed. By utilizing neural network, the fault torque can be estimated, which allows effective fault detection and diagnosis. The feasibility of the proposed fault detection algorithm is validated through various simulations and experiments.

A Feed‐Forward Wavelet Neural Network Adaptive Observer‐Based Fault Detection Technique for Spacecraft Attitude Control Systems

This paper presents a novel neural network-based fault detection technique applicable to a class of nonlinear systems. The adaptive observer was designed for fault detection based on a single hidden layer feed-forward wavelet neural network. In order to guarantee network convergence, the network weights are updated according to a modified back-propagation algorithm, and the Lyapunov function is introduced to ensure stability. The proposed fault detection scheme was tested on the actuators of a typical spacecraft attitude control system, and the results demonstrated the effectiveness and feasibility of the proposed observer in detecting nonlinear system failure.

Deep Neural Network Based Fault Detection for Three-Phase Induction Motor

The three-phase induction motor is known as one of the most widely-used machine in the manufacturing industry. Electrical and mechanical fault of this machine is able to cause breaking down the plant facilities that leads significant productivity losses. In this paper, we will propose the fault detection method of induction motor by using deep neural network with measurement data of the electrical current signals to provide supervised classification of 2 types ofmotor fault, rotor broken and stator conductor fault. We also studied the size of data-set in faulty state to train the model for fault detection.