Fault Conditions Research Articles

Explainable fault diagnosis method for process flow based on data augmentation with system graph relationship

The main objective of process industrial systems is to ensure safe operation. Signal fluctuations resulting from equipment failures and variable abnormalities can progressively propagate over the entire system, potentially resulting in fault conditions. However, the sporadic occurrence of fault conditions leads to a scarcity of data samples for diagnosis models. A fault diagnosis method for process flow based on data augmentation with system graph relationships is proposed. Propagation paths of fault signals are generated through graph relationships of systems. Simultaneously, the data of multiple nodes in paths is transformed to generate augmentation samples. To ensure comprehensive learning of the information included in augmentation samples, a large number of samples are generated for pre-training based on real-world data from a system. The explainability analysis method is used to analyze the focus area of diagnostic networks on samples with and without augmentation. The experimental results demonstrate that the proposed method can substantially improve diagnostic accuracy and explainability, hence offering advantages for diagnosis tasks in small sample cases.

Aileron fault detection with dynamic resampling based on fuzzy entropy and multi-branch neural network

The complex movements of unmanned aerial vehicles (UAVs) and feature loss at low resampling rates will result in the misidentification of aileron damage. In this paper, a fault detection method based on fuzzy entropy and a multi-branch neural network (MBNN) is proposed to shorten the fault detection time by reducing the resampling rate. The optimal size of the sliding window sampler is determined by analysing the UAV’s movement using fuzzy entropy, ensuring that the captured flight data segments reflect the UAV’s flight status with a smaller size. The multi-branch structure and feature-sharing mechanism in the network are used to adapt to feature loss at low sampling rates. The resampling rate is dynamically adjusted in accordance with the change in the UAV’s fault status, which is calculated from MBNN’s output using the Kullback Leibler (KL) divergence. Experimental results show that the proposed method can improve the real-time performance of UAV fault detection and maintain high accuracy.

A Multi-Model Architecture Based on Deep Learning for Longitudinal Available Overload Prediction of Commercial Subsonic Aircraft with Actuator Faults

Assessing the real-time longitudinal available overload onboard under fault conditions offers vital insights for the fault-tolerant reconfiguration and trajectory planning of commercial subsonic aircraft. After actuator failures in a commercial subsonic aircraft, its aerodynamic model undergoes changes. Traditional methods based on analytical models rely on precise aerodynamic models. However, due to the complexities of the flight environment and uncertainties in disturbances, establishing an accurate aerodynamic model after actuator failures is often challenging. Consequently, traditional methods can yield significant errors when evaluating the available overload under actuator faults. To address this, we introduce a multi-model architecture based on deep learning for the longitudinal available overload prediction of a commercial subsonic aircraft with actuator faults. For flight state data under different working conditions and different faults, Spearman correlation coefficient analysis and the gradient boosting decision tree (GBDT) algorithm are used to remove redundant feature parameters, thereby enhancing the training and prediction speed of the model while reducing the risk of overfitting. To meet prediction accuracy and speed demands, we employ the multi-layer perceptron (MLP) deep learning network to fully explore the environmental features, including uncertainties and disturbances, within the flight state, and the mapping relationships between the flight state and the available overload variations. We incorporate the light gradient boosting machine (LightGBM) and the categorical boosting (CatBoost) algorithms to enhance the model’s prediction speed and fuse it with a longitudinal available overload analytical model to elevate the model’s prediction accuracy, thereby achieving the real-time estimation of the commercial subsonic aircraft’s longitudinal available overload with actuator faults. The results demonstrate that the proposed method achieves a higher accuracy than traditional methods, with a relative error of less than 5%.

Intelligent Fault Diagnosis Method for Constant Pressure Variable Pump Based on Mel-MobileViT Lightweight Network

The sound signals of hydraulic pumps contain abundant key information reflecting their internal mechanical states. In environments characterized by high temperatures or high-speed rotation, or where sensor deployment is challenging, acoustic sensors offer non-contact and flexible arrangement features. Therefore, this study aims to develop an intelligent fault diagnosis method for hydraulic pumps based on acoustic signals. Initially, the Adaptive Chirp Mode Decomposition (ACMD) method is employed to remove environmental noise from the acoustic signals, enhancing the feature signals. Subsequently, the Mel spectrum is extracted as the acoustic fingerprint features of various fault states of the hydraulic pump, and these features are used to train the MobileViT network, achieving accurate identification of the different fault modes. The results indicate that the proposed Mel-MobileViT model effectively identifies and classifies various faults in constant pressure variable pumps, outperforming other models. This study not only provides an efficient and reliable intelligent method for the fault diagnosis of critical industrial equipment such as hydraulic pumps, but also offers new perspectives on the application of deep learning in acoustic pattern analysis.

Optimal power flow in hybrid AC-DC systems considering N-k security constraints in the preventive-corrective control stage

The optimal power flow methods for AC-DC systems containing VSC-HVDC generally only consider the economy during normal operation, overlooking the distribution of line transmission power in fault conditions. As a result, lines that continue to operate after a fault may experience overloading or operate at full capacity. Thus, a method for optimal power flow calculation is proposed that incorporates N-k security constraints in the preventive-corrective control stage for secure and economic operation of hybrid AC-DC systems. This method ensures that the line transmission power in the system meets the limits in the normal, short-term fault, and long-term fault states. In addition to the optimal power flow in the normal state, the method incorporates the system's imbalance as an indicator to evaluate system resilience. It combines this indicator with the economic, network loss, and performance metrics of the system, forming a two-stage bi-level multi-objective optimization model. Furthermore, to address the curse of dimensionality in anticipating system fault sets, a method for generating the anticipated fault set using non-sequential Monte Carlo simulation is proposed, along with a fault scenario search approach based on robust thinking to identify the most severe faults. Finally, the traditional IEEE 30-bus system was improved, and simulation verification was conducted using examples of an AC/DC system with a three-terminal DC network and a wind-solar-storage hybrid AC/DC system with a three-terminal DC network. The simulation results indicate that the proposed optimal power flow method considering the preventive-corrective control stage with N-k security constraints can effectively enhance system resilience. Furthermore, it improves the economic efficiency while ensuring the secure operation of the system.

Recent advances in journal bearings: wear fault diagnostics, condition monitoring and fault diagnosis methodologies

Recent advances in journal bearings: wear fault diagnostics, condition monitoring and fault diagnosis methodologies

Intelligent Framework Design for Quality Control in Industry 4.0

This research aims to develop an intelligent framework for quality control and fault detection in pre-production and post-production systems in Industry 4.0. In the pre-production system, the health of the manufacturing machine is monitored. In this study, we examine the gear system of induction motors used in industries. In post-production, the product is tested for quality using a machine vision system. Gears are fundamental components in countless mechanical systems, ranging from automotive transmissions to industrial machinery, where their reliable operation is vital for overall system efficiency. A faulty gear system in the induction motor directly affects the quality of the manufactured product. Vibration data, collected from the gear system of the induction motor using vibration sensors, are used to predict the motor’s health condition. The gear system is monitored for six different fault conditions. In the second part, the quality of the final product is inspected with the machine vision system. Faults on the surface of manufactured products are detected, and the product is classified as a good or bad product. The quality control system is developed with different deep learning models. Finally, the quality control framework is validated and tested with the evaluation metrics.

Modeling of Grid Tied PV Inverter to Improve its Performance During Unbalanced Load and Unbalance Fault

Integrating solar through inverter brings about various challenges in the microgrids and the inverter itself. This paper aims to the study of problems in the operation of inverter during unbalance load and unbalance fault condition along with the possible control measures to mitigate those problems to ensure the safe and reliable operation of the inverter. A grid connected PV inverter is modeled using hysteresis band controller and implementing the MPPT of the PV system with the buck boost converter. During unbalance load and unbalance fault condition, the negative and zero sequence components of current exists. All the zero-sequence component of current is delivered by the grid. The negative sequence component of current also flows through the inverter resulting in high value of current and loss of stability. Also, the voltage across the dc link capacitor increases during fault. The high value of current flowing through the inverter and high voltage across dc link capacitor may damages the inverter and capacitor respectively. An inverter dual current controller is introduced replacing the hysteresis band control such that the negative sequence component of current flowing through the inverter is almost mitigated from 600A to 10A and positive sequence current is also reduced relatively to a tolerable value 150A from 550A. The total current flowing through the inverter is limited to 200A from 950A and voltage across dc link capacitor is limited to 700V from 1050V during LG fault at the inverter side thus ensuring safe operation of the inverter during voltage dip condition. A further study can be done on limiting the positive sequence component of current to a rated value and improving the performance while operating in islanded mode.

Restoration of the current transformer secondary current under core saturation conditions based on ANN

Relay protection and emergency automation is an integral part of electric power systems. The algorithms of the relay protection and emergency automation are based on the use of analysis of the parameters of the electrical mode - current and voltage - obtained from current and voltage instrument transformers. As a rule, these transformers operate on the basis of the laws of electromagnetism. Operational experience shows that the magnetic core of current transformers under fault conditions can be saturated. As a result, the shape of the measured current is distorted which can lead to false operation of the relay protection and emergency automation system. In this paper a comparative analysis of the existing methods is presented. The advantages and disadvantages of them are described. The problem of current transformer core saturation is reduced to a regression problem. To solve the problem an artificial neural networks-based method is proposed. Computational experiments for both proposed and existing methods are performed. The results of experiments show that the efficiency of the proposed method is 1.25 times higher relative to the most effective existing method. The method of re-scaling data at real-time work applied to the restoration of the distorted shape of current is proposed.

Traveling wave network location method based on adaptive waveform similarity

High-voltage transmission technology can effectively address the issue of uneven spatial and temporal energy distribution, leading to its rapid development in recent years. To address the challenge of accurately identifying the source of the second traveling wave head in complex transmission network scenarios with existing single-ended fault location methods, a traveling wave network fault location method based on adaptive waveform similarity is proposed. The paper analyzes the propagation process of traveling waves in transmission lines and quantitatively derives the time-domain expression of the traveling wave waveform. The BFS algorithm is enhanced by incorporating the propagation characteristics of traveling waves, allowing for the determination of all paths from any location in the topological network to the measurement points. Based on the path information and the derived expression, the traveling wave waveform at the measurement points for the fault location is calculated. An optimization algorithm is used to iteratively solve for unknown parameters such as fault location, traveling wave speed, and fault point information, with the objective of maximizing the similarity between the adaptive waveform and the real waveform by adaptively adjusting the waveform shape. When the similarity between the adaptive waveform and the real waveform is maximized, the adaptive fault location is identified as the actual fault location. Verified through the PSCAD simulation platform, this method can achieve accurate location under different fault conditions.

Improved fault detection and classification in PV arrays using stockwell transform and data mining techniques

The growing integration of photovoltaic (PV) systems into the power grid necessitates reliable fault detection and classification mechanisms to ensure operational efficiency and safety. Fault detection in photovoltaic (PV) arrays is crucial for maintaining optimal system performance and ensuring the reliability of solar power generation. This paper proposes a novel approach for fault detection in PV arrays by employing the Stockwell transform in combination with various data mining techniques. The Stockwell transform is an advanced time-frequency analysis tool that allows for enhanced feature extraction from time-series data. By applying the Stockwell transform to the PV array's operational data, valuable frequency-domain information is extracted, enabling the identification of subtle fault signatures. To effectively detect and classify various faults, different data mining techniques, such as support vector machines, decision trees, random forests, and k-nearest neighbours, are applied to the transformed data. Each technique's effectiveness in identifying faults is evaluated and compared, enabling the selection of the most suitable algorithm for the specific application. Experimental results demonstrate the effectiveness of the proposed fault detection approach, exhibiting high accuracy, sensitivity, and specificity in identifying various types of faults in PV arrays. Extensive simulations and experimental validations were conducted on various fault conditions, including partial shading, open-circuit faults, and degradation. The results demonstrate the proposed method's superior performance, achieving an accuracy of 99.61 %, precision of 99.75 % and F1 score of 98.73 %. These metrics significantly surpass traditional fault detection techniques, highlighting the method's potential for real-world deployment. The approach not only enhances the reliability of PV systems but also contributes to reducing maintenance costs and improving system efficiency. The combination of the Stockwell transforms with data mining techniques proposed here provides a robust and efficient framework for early detection of faults, enabling timely maintenance and minimizing energy losses.

Data-Driven Multi-Fault Detection in Pipelines Utilizing Frequency Response Function and Artificial Neural Networks

This research presents a data-driven structural health monitoring (SHM) approach for pipeline systems that leverages frequency response function (FRF) signals and artificial neural network (ANN) algorithms to accurately identify and classify diverse pipeline fault conditions. The study focuses on three specific faults: bolt looseness, scale deposits, and crack occurrence at pipeline supports, which were replicated on a pipeline segment located at the Sound and Vibration Research Group (SVRG) at University Putra Malaysia (UPM). The FRF signals were captured using accelerometers to monitor the structural health of the pipeline. The data acquisition stage involved collecting FRF signals from the accelerometers to capture vibrations and responses related to the identified faults using a Siemens LMS SCADAS data acquisition unit. The data underwent preprocessing, including the application of principal component analysis (PCA) for feature selection. The subsequent data processing stage involved the application of an artificial neural network (ANN) algorithm for pattern recognition to analyze and classify the acquired data, identifying patterns associated with the replicated fault conditions. The proposed methodology demonstrated exceptional performance, with the ANN model achieving consistently high overall accuracy (above 99.7%) and remarkably low mean squared error (in the range of 0.0088×10−3to0.3062×10−3) across multiple iterations and sensor datasets. The detailed class-specific metrics, including accuracy, precision, sensitivity, and F1-score, further substantiated the model's effectiveness in identifying the individual fault types with near-perfect or perfect results for the majority of the fault scenarios. The location-invariant performance of the ANN model across different sensor placements demonstrates the robustness of the proposed data-driven SHM methodology. This research highlights the transformative potential of integrating state-of-the-art data-driven techniques to revolutionize the monitoring and assessment of critical pipeline infrastructure, ultimately enhancing the safety, reliability, and longevity of these vital systems.

A smooth switching strategy for steady-state operation control and fault transient control of doubly fed induction generator

Abstract As the proportion of wind power generation systems in power systems continues to rise, their dynamic response during system malfunctions has gained significant importance. As the grid short-circuit ratio continues to decrease, traditional fault ride-through algorithms for wind power generators may no longer be applicable. This is evidenced by voltage oscillations under significant disturbances and overvoltage issues during low-voltage ride-through, which are further aggravated during asymmetric fault conditions. Therefore, this paper focuses on the low-voltage ride-through issues of doubly fed induction wind power generators in weak power grids. It investigates the steady-state operation and transient control schemes and proposes a smooth transition strategy for steady-state and fault transient operations of doubly fed wind power generators. This approach guarantees the synchronization of active and reactive power, mitigates steady-state reactive power imbalance, and prevents voltage fluctuations triggered by recurring low-voltage ride-through occurrences. Furthermore, during fault recovery, a ramped active power restoration approach is employed to mitigate the coupling of active and reactive power introduced by the phase-locked loop, enabling rapid and stable restoration of active and reactive power outputs. As a result, superior dynamic performance is achieved during both symmetric and asymmetric fault processes. Finally, the superiority of the proposed smooth transition strategy under different fault scenarios is validated through simulations with the RTLAB platform.

Motor fault diagnosis based on multisensor-driven visual information fusion

To need of accurate motor fault diagnosis in industrial system, we propose a fault diagnosis framework that utilizes motor current and electromagnetic signals, combining them with a self-attention-enhanced capsule network for enhanced signal analysis and accuracy. Firstly, the original signal extracted by multiple sensors is constructed into a symmetric point mode (SDP) image, and the visual fault information of different sensors and fusion signals of different motion health states are obtained by the proposed multi-channel image fusion method. Then, the capsule network, combined with self-attention, extracts spatial features from the high-dimensional tensor of the multi-channel fused image for adaptive recognition and extraction. Subsequently, advanced feature vector information is obtained through softmax for diagnosis. Diagnosis results of several datasets indicate that the developed diagnosis framework with compressed image information can availably identify 8 kinds of motor fault states under various loads, and the fault diagnosis rate is as high as 99.95 %, it is helpful for low cost and high-speed diagnosis of motors. In addition, by learning multiple sensor signals in the same state, it obtains stronger robustness and effectiveness than a single signal model.

A fault diagnosis method for analog circuits based on EEMD-PSO-SVM

Analog circuit is an crucial component of electronic equipment, and the ability to diagnose its fault state quickly and accurately is essential for ensuring the safety and reliability of these electronic equipment. This paper addresses the problems of low diagnostic accuracy and the difficulties associated with model parameter selection in traditional fault diagnosis methods, particularly when dealing with nonlinear and non-stationary fault signals. A fault diagnosis method for analog circuits is proposed, which utilizes Ensemble Empirical Mode Decomposition (EEMD) for features extraction, the Maximum Information Coefficient algorithm (MIC) for features selection, and Particle Swarm Optimization (PSO) for optimizing Support Vector Machine (SVM) classification. Firstly, EEMD is used to adaptively decompose the fault signals in the circuit to extract multi-scale fault features. Secondly, the extracted features are quantitatively evaluated using the Pearson correlation coefficient and energy value analysis, leading to the construction of a fault feature vector is constructed. On this basis, the MIC feature selection algorithm is applied to further optimize the feature vector. Finally, an efficient fault classification model is developed by optimizing the hyperparameters of the SVM model using PSO. The simulation results show that the proposed method effectively overcome the problems of model complexity and low classification accuracy caused by improper selection of wavelet basis function. The accuracy of fault diagnosis and the efficiency of model training are significantly superior to those of traditional methods.

Research on Classification Maintenance Strategy for More Electric Aircraft Actuation Systems Based on Importance Measure

In this paper, a practical maintenance algorithm is proposed to improve the reliability of actuation systems and their components, specifically addressing the consistency degradation caused by faults in the symmetric actuation system components of more electric aircraft (MEA). By integrating important measures with traditional genetic algorithms, the accuracy of the algorithm is improved. Prior to maintenance, a reasonable classification of components is built to mitigate the adverse effects of extreme fault conditions on the algorithm. This approach improves both the effectiveness and efficiency of the algorithm, rendering the overall maintenance strategy better suited for real-world needs. Finally, comparative simulations confirm the algorithm’s superior performance in reliability improvement, demonstrating its substantial contribution to the field of MEA maintenance and reliability.

Multi-level monitoring method based on slow independent component analysis-tensor decomposition for industrial batch processes

Industrial batch processes employ similar or identical equipment to manufacture various specification products, hence multi-batch data exhibit common characteristics. Additionally, complex characteristics exist within each batch. In this paper, a multi-level monitoring method based on slow independent component analysis-tensor decomposition (SICA-TD) is proposed considering the characteristics of industrial batch processes. In the first-level monitoring model, SICA is used to identify whether the current batch is faulty. An integrated control limit is constructed to enhance robustness. When a fault is detected, fault and normal data features are combined into a tensor. Subsequently, the second-level monitoring model extracts common features through TD. The disparity in common feature distribution between normal and fault conditions is measured via Bhattacharyya distance (BD) statistics to ascertain whether the fault affects all batches. The method is validated through an actual hot strip mill process (HSMP) and implemented in a process monitoring platform for a steel manufacturing company.

Fault diagnosis of photovoltaic array with multi-module fusion under hyperparameter optimization

Photovoltaic (PV) arrays’ random and intermittent output characteristics impact power system safety. To improve the performance of the PV array fault diagnosis model, a novel online fault monitoring technique is introduced. (1) Fault diagnostic model construction: Significant differences in PV arrays’ I-V and P-V curves under various fault conditions led to constructing a 3D channel feature map based on I, V, and P features. (2) Multi-source information fusion network (MSIFN): this multi-module fusion model includes a time–frequency domain fusion module (TDFM), a multi-feature shuffle expansion convolution module (MSECM), a parameter-free parallel hybrid attention enhancement module, and a multi-scale mixed pooling fusion classification module (MMPCM). (3) Multi-strategy fusion whale optimization algorithm (MSFWOA): addressing the original WOA’s deficiencies, we designed time control, parameter modification, and greedy control strategies based on lens imaging to optimize MSIFN’s hyper-parameters. Experimental results show that the MSFWOA-MSIFN model excels in PV array fault diagnosis (Paccuracy=Pprecision=Precall = 99.92 %). In three types of noise experiments with 15 dB, 25 dB, and 30 dB, the average performance index remained above 99 %. In practical experiments, the average performance indices werePaccuracy = 97.53 %, Pprecision = 97.32 %, andPrecall = 97.41 %, further demonstrating its excellent diagnostic performance. This model effectively diagnoses various faults in PV arrays, providing scientific and theoretical support for PV system operations.

Innovative protection schemes through hardware-in-the-loop dynamic testing.

In microgrid environments, the behaviour of Distributed Generation (DG) during fault conditions varies significantly based on DG types and penetration levels. Conventional Overcurrent Relays (OCRs) with standard time-current characteristics may exhibit limitations during excessive fault scenarios, leading to OCR operating delays and mis-coordination within the microgrid. This study proposes a novel constraint on the maximum Current Multiplier Setting (CMS) and utilizes Water Cycle Algorithm (WCA) and Particle Swarm Optimization (PSO) techniques to optimize the Time Multiplier Setting (TMS). Comparative dynamic analysis through real-time validation shows that the non-standard OCR approach outperforms the standard IEC scheme across all grid operation modes with different type, size and location of DGs. For instance, under F1 conditions, the tripping time of OCR1 was reduced from 0.0226 seconds (IEC) to 0.000981 seconds (non-standard). HIL results further affirm the efficacy of the proposed scheme. The optimization process, implemented in MATLAB and validated using ATP/EMTP simulations and SIPROTEC 7SJ62 relays, demonstrates enhanced microgrid protection coordination, improving system reliability and performance.

MRCFN: A multi-sensor residual convolutional fusion network for intelligent fault diagnosis of bearings in noisy and small sample scenarios

Bearing fault diagnosis is of great importance to ensure the safe and stable operation of mechanical equipment. The actual collected bearing fault signals are susceptible to strong noise interference and bearing samples for each fault state may be insufficient, which increases the difficulty of capturing effective features. Most of the existing diagnostic methods extract features from a single sensor signal for pattern recognition and fault diagnosis. The fault information provided by a single sensor is limited and incomplete, which is usually very difficult to meet the demand for accurate and reliable fault diagnosis in complex scenarios. To solve these problems, this paper proposes a multi-sensor residual convolutional fusion network (MRCFN) for intelligent fault diagnosis of bearings. Firstly, a convolutional pooling module (CPM) is coupled with the designed double ring residual module (DRRM) to rough feature extraction and deep feature mining, which not only captures the discriminative fault features from multi-sensor signal, but also avoids the performance degradation of network. Secondly, a spatial channel reconstruction module (SCRM) is further introduced to eliminate redundant information in the features and improve the network training efficiency. Finally, the presented global interactive perception fusion module (GIPFM) is connected with a classification block (CB) to globally fuse the features extracted from the acoustic and vibration signals and conduct automatic fault identification, which both can realize the complementarity and calibration of multi-sensor feature information and high precision diagnosis. The experiments and a series of comparisons are implemented on two datasets to efficaciously verify the superiority of the proposed method over five existing representative multi-sensor fusion diagnosis methods (i.e., FAC-CNN, MB-CNN, MsACNN, MRSDF, and IMSFDFL) under strong noise and small samples.