Types Of Faults Research Articles

Investigation of co-seismic stress and aftershock distribution along the Sumatra–Andaman subduction zone

AbstractThis study aimed to investigate co-seismic stress and aftershock distribution along the Sumatra–Andaman subduction zone (SASZ). The fault parameters of six major earthquakes with an M ≥ 7 that occurred during 2010–2022 along the SASZ, were utilized to determine the Coulomb stress change using numerical modeling techniques calculated on the receiver faults with similar focal mechanisms of the mainshock, strike-slip, thrust, and normal faulting, respectively. The earthquake events were then classified to analyze the aftershocks of major earthquakes in the area. These aftershocks were mapped in order to determine the relationship between the aftershock distribution and the areas of increased or decreased stress. The relationship between the co-seismic stress and distribution of aftershocks in the SASZ was found to mainly depend on the focal mechanism of major earthquakes and the type of receiver fault used for calculation. After a major earthquake in the SASZ, there are two possible patterns that most aftershocks will be generated from in the areas of increased stress. First, a major earthquake is a type of thrust fault calculated on the receiver fault using the focal mechanism of the mainshock. Second, a major earthquake is a type of strike-slip fault calculated on the receiver fault with an optimum-oriented strike-slip fault. This relationship is likely to represent the specific pattern of the seismotectonic stress in the SASZ that can be used to evaluate the risk areas of aftershocks after a major earthquake has occurred. Furthermore, two earthquake events with large magnitudes were generated following the respective major earthquake in the SASZ that were located around the areas of increased stress, indicating that these two earthquake events were likely triggered in areas of increased stress following the respective major earthquake. Therefore, this study concluded that after a major earthquake occurrence in the SASZ, the areas of increased stress have a higher risk of generating both a large number of aftershocks and a new large-magnitude mainshock event. The investigation of co-seismic stress is very important to estimate areas of increased stress after a major earthquake, as this can be useful for monitoring both earthquake and tsunami hazards in the area.

Simulation of Faults in the Yeywa-Thaphaywa High Voltage Transmission Line using Fuzzy Logic

Faults in transmission networks frequently undermine the reliability and stability of electrical power supply, causing load shedding and posing risks to power system equipment. Effective fault classification is crucial to minimize power outages and ensure timely restoration. This study presents a fault classification method for transmission lines using fuzzy logic. The classification utilizes three-phase feeder currents, neutral current, and phase voltages as inputs to the Fuzzy Inference System (FIS). The proposed method accurately classifies the various types of faults in a high voltage transmission network, including line-to-ground fault, double line-to-ground fault, line-to-line fault, and three-phase faults. Numerous test cases demonstrate the technique's high accuracy. The simulations are carried out in MATLAB/SIMULINK using Sim Power Systems and the Fuzzy Logic Toolbox (MATLAB 2016a).

IG‐YOLOv8: Insulator Guardian Based on YOLO for Insulator Fault Detection

AbstractInsulators have an extremely important role in transmission lines, and they are important components for ensuring the safe operation of transmission lines. In order to solve the difficult problem of insulator fault detection under complex background, IG‐YOLOv8 insulator fault detection algorithm is proposed in this paper. First, the Wise‐IoU (WIoU) loss function is introduced to mitigate the adverse impact of low‐quality images by employing a dynamic non‐monotonic focusing mechanism, thereby enhancing the detection performance of the entire model. Second, a novel C2f network is constructed by integrating the receptive field coordination attention (RFCA) convolutional module to address the parameter‐sharing issue associated with large convolutional kernels. Additionally, the data set has been reorganized using k‐fold cross‐validation to ensure that each subset undergoes training and testing, consequently reducing generalization errors. Finally, a deformable attention (DA) mechanism is employed to augment the feature extraction capability pertaining to insulator fault region information. In order to evaluate the detection performance of the improved IG‐YOLOv8 algorithm, this study constructed an insulator target detection data set containing four fault types: Normal, Defect, Dirty, and Aging. The experimental results show that the average accuracy of the improved model is increased from 89.7% to 96.9%, and the Recall value of the Aging type insulator is increased from 71.8% to 89.1%. The occurrence of missed detection is greatly reduced, and the accuracy of detection is improved. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Study of conveyor belt deviation detection based on improved YOLOv8 algorithm

Conveyor belt deviation is a commmon and severe type of fault in belt conveyor systems, often resulting in significant economic losses and potential environment pollution. Traditional detection methods have obvious limitations in fault localization precision and analysis accuracy, unable to meet the demands of efficient and real-time fault detection in complex industrial scenarios. To address these issues, this paper proposes an improved detection algorithm based on YOLOv8, aiming to achieve efficient and accurate detection during the operation of the belt. Firstly, an Enhanced Squeeze-and-Excitation (ESE) module is incorporated into C2f to boost feature extraction for rollers and belts. Secondly, the construction of the BiFPN_DoubleAttention module in the neck network enhances bidirectional feature fusion and attention mechanism, thereby improving multi-scale object localization accuracy under complex environments. Then, a Multi-Head Self-Attention (MHSA) mechanism is introduced in the head network, better capturing positional features of small roller targets and belt areas in various environments, thus enhancing detection performance. Finally, extensive experiments are conducted on a self-built dataset, achieving an accuracy of 98.1%, mAP0.5 of 99.0%, and a detection speed of 46 frames per second (FPS). This method effectively handles variations and disturbances in the conveyor belt transportation environment, meeting real-time diagnostic needs for belt misalignment in the industry.

Diagnosis of solar panels using Fuzzy logic with a recursive method

The article presents an innovative methodology for diagnosing faults in solar panels using an approach that combines fuzzy logic and recursive least squares (RLS). The main objective of the study is to develop a robust and accurate diagnostic system capable of detecting and locating faults in solar panels. The proposed method uses fuzzy logic to model the complex relationships between the parameters of the solar panel, such as brightness, temperature, voltage, current, and the operating state of the solar panel. Recursive least squares (RLS) are integrated into the diagnostic system to dynamically update the fuzzy parameters of the model based on new observations and real data from the solar panel. This approach allows continuous adaptation of the diagnostic model to changes in environmental conditions and the operation of the solar panel. The results demonstrate the effectiveness and accuracy of the proposed diagnostic system, with a high capability to detect and locate different types of faults in solar panels.

Switch monitoring algorithm for 220 kV terminal substation startup process based on multi time scale graph model

The switch monitoring in the startup process of 220 kV terminal substation is a dynamic and changeable process, which has obvious characteristics of diversified scales in time, so as to solve the problem of switch monitoring under multivariable and multi-scale interference. The switch monitoring framework for the startup process of 220KV terminal substation is built. The process layer uses the graphic configuration software and combines the internal and external models of the substation to build the objective function for the generation of the substation graphic model. The particle swarm optimization algorithm is used to solve it to generate the optimal substation graphic model. Through the online monitoring device, the signals such as sensors, normally open and normally closed contacts are collected in real time, and the status of the switchgear is obtained through processing, the reduced half trapezoidal cloud model multivariable multi-scale sample entropy similarity tolerance criterion is used for softening treatment, and the multivariable multi-scale cloud sample entropy is determined to achieve the extraction of multiple time scale switch fault feature vectors, which are used as the input of the SE-DSCNN fault diagnosis model. Combined with the substation diagram, the switch fault identification during the startup process of the substation is realized, and the fault switch position is located. The experimental results show that the algorithm can accurately generate the substation model, which includes all the equipment in the substation, accurately describes the connection relationship and operation status of the equipment, and has high accuracy, integrity and aesthetics; The algorithm can effectively extract and analyze the MMCES entropy characteristics of different types of switch faults; The algorithm can realize the switch monitoring during the startup of substation C, and determine the fault switch and fault location.

A Hybrid Data-Driven Method for Main Circuit Gound Faults Diagnosis in Electrical Traction Drive Systems

A main circuit ground fault (MCGF) is a typical system fault in an electrical traction drive system (ETDS). When two or more MCGFs occur, it will cause serious accidents. Therefore, it is particularly important to detect and handle MCGFs in a timely manner. To improve the efficiency of train operation and ensure driving safety, this paper proposes a hybrid data-driven MCGF diagnosis method. First, the voltage signals related to the fault are selected according to the mechanism analysis of the MCGF, and then the initial feature variables are constructed according to these voltage signals. Secondly, the initial feature variables of different types of MCGF are analyzed in the time and frequency domains by wavelet transform, and four feature indicators are calculated. Finally, the fault feature indicators are trained by random forest to obtain a model for subsequent fault diagnosis. After comparative experiments using various machine learning methods, it was found that the RF used in the proposed method has a better diagnostic effect, and the correct isolation rate exceeds 99%.

Exploring frictional properties of upper plate fault reactivation in subduction zones: The Atacama Fault System in northern Chile

The Maule 2010 and Tohoku-Oki 2011 earthquakes demonstrated how dormant upper plate faults can be reactivated as normal faults by plate margin relaxation following megathrust slip. However, the reactivation mechanisms of these types of faults are yet unexplored. To provide a better understanding of these mechanisms, we collected fault core samples from fault segments of the Atacama Fault System in northern Chile. The sampled fault segments have clear morphological evidence of Quaternary reactivation as normal fault. We performed laboratory experiments to measure the fault strength, stability and dynamic weakening. We consider low-velocity tests for exploring the frictional strength and velocity dependence of friction via a double-direct shear apparatus and ii) high-velocity tests for investigating the frictional properties at seismic velocities via a rotary shear apparatus. The experiments revealed that fault cores have low frictional strength, velocity-strengthening behaviour and strong dynamic weakening. Additionally, a novel experimental procedure that simulates stress relaxation by stepwise reducing of the normal stress on the sample assembly showed: 1. Accelerating creep towards dynamic weakening in chlorite-rich gouges and 2. oscillatory sliding in fault gouges enriched in illite. By extrapolating our experimental observations to natural conditions, we conclude that stable sliding is favoured during the interseismic phase of the subduction earthquake cycle, whereas unstable sliding is favoured during the coseismic and postseismic phases. The latter occurs via normal stress reduction during the shift from interseismic compression to co- and postseismic tension at the plate margin.

Power grid accident warning based on real-time analysis of hazard sources and weights

Abstract The power grid system has diverse structures consisting of multiple subnets, equipment, and components that are interrelated and mutually influential. At the same time, there are various types of power grid accidents, including short circuits, open circuits, overloads, grounding faults, etc. Each type of fault may have its specific cause and manifestation. This complexity and diversity make establishing a comprehensive and accurate early warning model difficult. Therefore, this study proposes an adaptive warning method based on hazard sources and weighted coefficients for power grid accidents. To transform raw data containing a large amount of redundant information and noise into data with targeted features for representation, power grid accident information feature labels are generated based on weighted coefficients. Based on this, based on the improved YOLOv3, potential risks in the power grid are identified and assessed. Identification based on implementing risk prevention and control measures defines multiple warning levels to achieve adaptive warning of power grid accidents. Test data validation shows that the proposed solution has an accuracy up to 97.85%. There is also a significant improvement in other indicators, all of which remain above 98%. Indicator validation shows that the research method meets the actual process standards. For the entire day period, the precision and recall of the research method remained stable at over 90%.

Vibration source inversion-based fault diagnosis: approach and application

The gear transmission system of industrial equipment is characterized by a highly integrated structure, non-stationary operating conditions, and large loads. Therefore, the attenuation of fault signal characteristics and the complexity of operating conditions in gear transmission systems significantly affect the effectiveness of vibration signal-based fault diagnosis. This paper proposes a unified diagnostic framework based on vibration source inversion for two typical transmission component fault signal phenomena: meshing frequency modulation sidebands and equally spaced fault characteristic frequency interval harmonic clusters. This approach incorporates the vibration transfer path analysis of passive subsystems and identifies bearing dynamic forces, followed by their decomposition, reconstruction, and sensitive frequency band localization. It enables accurate diagnosis of complex gear transmission systems under non-stationary conditions with limited vibration testing. The effectiveness and advantages of this method over existing mainstream signal processing techniques are validated through actual cases of gear and weak bearing fault diagnosis on a complex planetary gear transmission system test bench.

Fault Detection in Transmission Line

Abstract: This project focuses on the design and implementation of an advanced fault detection system for overhead transmission lines, utilizing key components such as the ESP 8266 microcontroller, current sensors, a GPS module, and IoT integration. The system is capable of detecting and classifying four major fault types: single line to ground (L-G), line to line (LL), double line to ground (L-L-G), and three-phase faults (L-L-LG). By placing current sensors at the transmission line's sending end, the system identifies faults and accurately determines their location through GPS coordinates .Simulations using protect us software were conducted to verify the system’s performance prior to building a hardware prototype. Upon fault detection, the system provides alerts via an LCD display and a buzzer, while real-time fault data is transmitted to an Android app and web server through the arduino IoT cloud. Testing confirmed the system’s precision in fault identification and location tracking, ensuring timely notifications for control room and remote device operators. This successful implementation highlights the system's potential for improving safety and efficiency in power transmission networks. the project lays the groundwork for further exploration into advanced fault detection and real-time monitoring solutions in electrical engineering.

Development of a Hybrid AI Model for Fault Prediction in Rod Pumping System for Petroleum Well Production

Rod pumping systems are widely used in oil wells. Accurate fault prediction could reduce equipment fault rate and has practical significance in improving oilfield production efficiency. This paper analyzed the production journal of rod pumping wells in block X of Xinjiang Oilfield. According to the production journal, oil well maintenance operations are primarily caused by five types of faults: scale, wax, corrosion, fatigue, and wear. These faults make up approximately 90% of all faults. 1354 oil wells in the block that experienced workover operations as a result of the aforementioned factors were chosen as the research objects for this paper. To lower the percentage of data noise, wavelet threshold denoising and variational mode decomposition were used. Based on the bidirectional long short-term memory network, an intelligent model for fault prediction was built. It was trained and verified with the help of the sparrow search algorithm. Its efficacy was demonstrated by testing various deep learning models in the same setting and with identical parameters. The results show that the prediction accuracy of the model is the highest compared with other 11 models, reaching 98.61%. It is suggested that the model using artificial intelligence can provide an accurate fault warning for the oilfield and offer guidance for the maintenance of the rod pumping system, which is meant to reduce the occurrence of production stagnation and resource waste.

Spark: A Statistical Comparison and Evaluation of Classification Algorithms for Fault Prediction in Electrical Secondary Distribution Network

Managing faults in the electrical secondary distribution network is a challenging task given the nature, size, and complexity. Predicting faults early before they occur helps in increasing the safety and reliability of the power distribution system. Various statistical and machine learning techniques are being used to predict different types of faults. This study applies classification algorithms available in the big data framework Apache Spark through its python interface PySpark to predict electrical secondary distribution network faults. The study evaluates and compares nine algorithms: Decision tree, Gradient-boosted tree, Logistic regression, Naïve Bayes, Multilayer perceptron, Random forest, Linear Support Vector Machine, One-versus-rest and Factorization machines. The research uses Friedman’s test followed by the Nemenyi post hoc test to find the significance of performance differences among the algorithms. The results show significant differences among the algorithms. Gradient-boosted tree and One-versus-rest with Gradient-boosted tree had the best performance for binary and multiclass classification, respectively, while Naïve Bayes had the worst performance.

Diagnosis and prognosis of soybean roaster failures using particle swarms

In industry, the monitoring and diagnosis of production processes are crucial issues in ensuring plant reliability, performance and quality. In particular, food processing operations, such as coffee roasting, are subject to numerous risks of failure that can impact on productivity and the quality of the final product. In this context, the main objective of this study was to develop an innovative method for the diagnosis and prognosis of failures in a coffee roasting process. The proposed method differs from standard approaches by using the particle swarm optimization (PSO) algorithm applied to the analysis of signatures of key process variables. This new approach has improved fault detection, with a recognition rate of over 90% for the main types of fault identified, such as heating problems, air obstructions or leaks. In addition to diagnostics, the method has also demonstrated its effectiveness in prognosticating the state of health of the process, with an average error on the prediction of remaining service life reduced to 15%, compared with 35% for fixed-threshold methods. This work has therefore enabled us to develop an innovative method offering superior performance to standard approaches for the diagnosis and prognosis of failures in the roasting process.

Weak Compound Fault Identification of Gearboxes Based on Improved Symplectic Geometric Mode Decomposition and Optimized Cyclic Kurtosis Deconvolution

Abstract Given the complex and harsh operating conditions of gear transmission systems, gearboxes are prone to compound faults. These faults, involving multiple types, often couple together, causing the weak fault pulse characteristics to be entirely masked by strong environmental noise. This significantly complicates the extraction of relevant fault information from the gearbox. To address these issues, this paper proposes a method for extracting compound fault features based on improved symplectic geometric mode decomposition (SGMD) and optimized cyclic bispectrum deconvolution (CYCBD). Firstly, considering the periodic impact characteristics of different fault types, morphological envelope cyclic bispectrum is proposed to cluster the initial components obtained from SGMD decomposition, thereby adaptively separating different fault features contained in the compound fault signals. An adaptive filter length search strategy is subsequently introduced to optimize the CYCBD by deconvolving each initial fault component, thereby eliminating the interference caused by complex transmission paths and substantial environmental noise, which, in turn, enhances weak periodic fault pulses. Following this, the enhanced signals are subjected to envelope demodulation to extract fault characteristic frequencies, enabling the identification of various types of faults. The effectiveness and feasibility of the proposed method are demonstrated through both simulation signals and actual experimental data related to gearbox compound faults. Compared with existing methods, the proposed method demonstrates superior performance in identifying weak compound faults under strong environmental noise.

Advanced Methods for Monitoring and Fault Diagnosis of Control Loops in Common Rail Systems

Common rail systems are a key component of modern diesel engines and highly increase their performance. During their working lifetime, there could be critical damages or failures related to aging, like backlash or friction, or out-of-spec operating conditions, like low-quality fuel with, e.g., the presence of water or particles or a high percentage of biodiesel. In this work, suitable data-driven methods are adopted to develop an automatic procedure to monitor, diagnose, and estimate some types of faults in common rail systems. In particular, the pressure control loop operating within the engine control unit is investigated; the system is described using a Hammerstein model composed of a nonlinear model for the control valve behavior and an extended linear model for the process dynamics, which also accounts for the presence of external disturbances. Three different sources of oscillations can be successfully detected and quantified: valve stiction, aggressive controller tuning, and external disturbance. Selected case studies are used to demonstrate the effectiveness of the developed methodology.

Transformer fault identification based on GWO-optimized Dual-channel M-A method.

In order to improve the accuracy of the transformer fault identification using nature-inspired algorithms, an identification method based on the GWO (Grey Wolf Optimizer)-optimized Dual-channel MLP (Multilayer Perceptron)-Attention is proposed. First, a Dual-channel model is constructed by combining the AM (Attention Mechanism) and MLP. Subsequently, the GWO algorithm is used to optimize the number and the nodes of the hidden layer in the Dual-channel MLP-Attention model. Typical transformer faults are simulated using DDRTS (Digital Dynamic Real-Time Simulator) system. Experiments showed that the GWO- optimized method has an accuracy rate of 95.3%-96.7% in identifying the transformer faults. Compared with BP, SVM, MLP, and single-channel M-A models, the proposed method improved the accuracy by14.1%, 9.6%, 9.3%, and 3.3% respectively. This result indicates the rationality and effectiveness of the proposed method in transformer fault identification.

Interaction law between mining stress and fault activation and the effect of fault dip angle in longwall working face

Study of the interaction between fault activation and mining stress evolution in the longwall working face is helpful to provide a targeted area for fault type heavy mine pressure disaster control. Combining theoretical analysis, physical and numerical simulation, the mechanical mechanism of fault activation is analyzed, the interaction law between mining stress and fault activation is studied, and the influence of fault dip angle on the evolution of fault activation and mining stress is discussed. The minimum critical dip angles α of normal and reverse fault activation are π/4 + φ/2 and π/4-φ/2, respectively. During the mining process, the activation position of the fault surface, the peak values of stress and displacement gradually increase and transfer from the high position of the fault to the low position, and the peak value of the advance abutment pressure reaches the maximum at the fault. The advancing distance of the working face required for fault activation gradually decreases with the decrease of the fault dip angle, and the peak elevation area of the working face gradually increases with the decrease of the fault dip angle. Combined with the on-site microseismic monitoring results, it can be seen that when the working face is about 20 m away from the fault, the stress and energy increase sharply, which is the main control area of the impact disaster.

Quantitative detection of refrigerant charge faults in multi-unit air conditioning systems based on machine learning algorithms

Refrigerant charging discrepancies constitute the predominant malfunctions in air conditioning systems. Achieving the optimal charging level is crucial for system performance, underscoring the importance of precise refrigerant level prediction. This study introduces an algorithm designed for the quantitative detection of refrigerant charging errors by integrating the Markov Transition Field (MTF), Convolutional Neural Networks (CNN), and Multi-head Self-Attention (MSA) mechanisms. A high-precision enthalpy difference chamber was employed to establish a Variable Refrigerant Flow (VRF) refrigerant charging test bench. This setup facilitated the analysis of system parameter sensitivity to charging faults and aided in the creation of a training dataset for the algorithm. Comparative analysis was conducted against Support Vector Machines (SVM), Random Forests (RF), CNN with Self-Attention (AT), and MTF-CNN-MSA. The findings reveal that our method adeptly captures temporal dependencies and dynamic shifts in time series as visual representations, offering novel insights for discerning fault patterns within such data. Notably, the maximum pressure variations at high-pressure and low-pressure points were 0.25 MPa and 0.07 MPa, respectively, with temperature shifts of 12 °C and 3.5 °C at the high and low-temperature points. The high-pressure and high-temperature points are particularly sensitive to changes in refrigerant charging, and parameters from these sections were utilized to construct the dataset. The CNN-MSA algorithm demonstrates consistent performance across various fault types, effectively delineating fault characteristics. The accuracies achieved by SVM, RF, CNN-AT, and MTF-CNN-MSA were 84.38 %, 73.75 %, 88.13 %, and 93.75 %, respectively. In comparison, the CNN-MSA algorithm was able to more accurately detect refrigerant charge faults at different levels.

Calibration of a hybrid model for HVAC systems for fault data generation

The application of automated fault detection and diagnosis algorithms has proven to be an effective way to increase the energy efficiency of buildings. While data-driven strategies have demonstrated their potential in developing such algorithms, they require a set of historical data that represents both healthy and faulty equipment operation, which is not a common scenario in real facilities. This article presents a methodology for the generation of synthetic data on both healthy and faulty operation for building heating and air conditioning equipment, which is especially useful for supervision and failure detection in the case of replication and expansion of buildings in tertiary or residential building planning programmes. This work investigates the automatic calibration of a typical air-handling unit hybrid model, composed of the detailed parametric representation of the system components and its control sequence coupled with a simplified thermal load. The model is then extended with fault models that resemble commonly encountered component faults to generate operation data in faulty scenarios. The proposed framework is validated in a real use case with the calibration of an air-handling unit system and its control sequence using 15 days of data gathered from the building management system. The results obtained from the injection of seven typical faults are then compared with the fault-free simulations to highlight and validate their impact on key operating variables. The results prove the capabilities of this methodology to support database generation in the fields of fault detection and advanced maintenance of buildings’ air conditioning systems for building replicas.