Fault Diagnosis System Research Articles

Research on Fault Section Location in an Active Distribution Network Based on Improved Subtraction-Average-Based Optimizer

The high penetration of distributed generation (DG) in the distribution system poses a challenge to the protection techniques and strategies of active distribution networks, making it difficult to adapt traditional methods to the fault diagnosis of the new power system. A method based on the improved subtractive optimiser algorithm for fault diagnosis is proposed to address this situation. Firstly, a fault localization model applicable to DG grid connection is constructed, which can effectively deal with the impact of the dynamic switching of DGs on the system and make up for the shortcomings of the traditional single-power network model; secondly, to solve the model, the original algorithm is improved using multi-strategy fusion, and the improved subtraction-average-based optimizer (ISABO) is obtained. Through the test of classical functions, its excellent solving performance and decoupling ability are verified; finally, the ISABO algorithm is applied to the 33-node test system to make it operate in various complex fault conditions. The results show that the ISABO algorithm is feasible in solving the fault location problem and can adapt to the connect/disconnect state of the interconnection switch and the dynamic casting and cutting of multiple DGs. Compared with the original SABO algorithm, its positioning accuracy can always be maintained at 100%, and the positioning speed is increased by 46.68%, symmetrically improving positioning speed, positioning accuracy, and fault tolerance.

Explainable artificial intelligence of tree-based algorithms for fault detection and diagnosis in grid-connected photovoltaic systems

A grid-connected photovoltaic system integrates solar panels with the utility grid through a power inverter unit, allowing them to operate in parallel with the grid. Commonly known as grid-tied or on-grid solar systems, these configurations enable panels to feed electrical energy back into the grid, offering simplicity, low operating and maintenance costs, and reduced electricity bills. Despite these advantages, this environmentally friendly energy solution is still susceptible to downtimes and faults. This study utilizes advanced machine learning tree-based algorithms for fault detection and diagnosis in such systems with the goal of maintaining reliability, improving performance, and ensuring optimal energy generation. Specifically, the research investigates the effectiveness of Extra Trees as a fault detection and diagnosis algorithm through an efficient two-phase framework that consists of a binary fault detection phase followed by a multi-class fault diagnosis phase, achieving respective accuracies of 99.5% and 98.7%. In addition, the study underscores the importance of oversampling in improving results, particularly for imbalanced datasets. Moreover, explainable artificial intelligence is employed to enhance transparency in the model’s output and sensitivity to specific features in a given order. Remarkably, the findings align directly with results obtained from techniques such as feature importance averaging and incremental feature accuracy tracking. The research unveils a highly scalable, lightweight, and simple framework for fault detection and diagnosis in grid-connected photovoltaic systems.

Modeling and fault diagnosis of the PID-controlled electro-hydraulic system based on LSTM

Modeling and fault diagnosis of the PID-controlled electro-hydraulic system based on LSTM

Fault diagnosis of multi-sensor oil system of road header based on convolution neural network

Fault diagnosis of multi-sensor oil system of road header based on convolution neural network

Condition monitoring and multi-fault classification of hydraulic systems using multivariate functional data analysis.

Condition monitoring and fault classification in engineering systems is a critical challenge within the scope of Prognostics and Health Management (PHM). The fault diagnosis of complex nonlinear systems, such as hydraulic systems, has become increasingly important due to advancements in big data analytics, machine learning (ML), Industry 4.0, and Internet of Things (IoT) applications. Multi-sensor data provides opportunities to predict component conditions; however, environments characterized by multiple sensors and diverse fault states across various components complicate the fault classification process. To address these challenges, this study introduces a novel multivariate Functional Data Analysis (FDA) framework based on Multivariate Functional Principal Component Analysis (MFPCA) for classifying failure conditions in hydraulic systems. The proposed method systematically tackles condition-based diagnostics and addresses fundamental issues in multi-fault classification. Experimental results demonstrate that this approach achieves high classification accuracy using raw multi-sensor data, establishing multivariate FDA as a powerful tool for fault diagnosis in complex systems.

Improving fault diagnosis in elevator systems with GAN-based synthetic data

Improving fault diagnosis in elevator systems with GAN-based synthetic data

Out-of-Distribution Fault Diagnosis of Industrial Cyber-Physical Systems Based on Orthogonal Anchor Clustering With Adaptive Balance

Out-of-Distribution Fault Diagnosis of Industrial Cyber-Physical Systems Based on Orthogonal Anchor Clustering With Adaptive Balance

Fault Diagnosis for Electric Vehicle Battery Pack Interconnection System Using Real-World Driving Data

Fault Diagnosis for Electric Vehicle Battery Pack Interconnection System Using Real-World Driving Data

Fine-grained fault diagnosis of photovoltaic systems based on DMAD-GAN and IFD-FGIF

Abstract In the field of photovoltaic (PV) system monitoring, fault detection faces two critical challenges: data imbalance and fault diversity, as well as incomplete complex fault information. To tackle these issues, this paper proposes a dual-mechanism anomaly detection with generative adversarial network (DMAD-GAN) and an integrated fault diagnosis with fine-grained information fusion (IFD-FGIF). DMAD-GAN utilizes GAN to integrate dual mechanisms for anomaly detection in PV datasets, with coordinate-space attention enhancing the perception of subtle features and differences in PV panels. The anomaly scoring mechanism utilizes an improved loss function to compute anomaly scores, assessing the degree of anomaly for each sample. In the IFD-FGIF method, t-SNE is used to visualize features for fault pre-classification to determine the presence of new faults. A fine-grained information fusion module is designed, leveraging ResNet50 to extract features from fault key areas and original images. This module integrates fine-grained features, original features, and fine-grained attributes. Fault attributes and categories are determined using an attribute classifier and Euclidean distance. If a new fault is identified during pre-classification, the network undergoes transfer learning to recognize and adapt to the new fault. The experimental results demonstrate that the proposed method outperforms other networks, achieving an anomaly detection accuracy of 95.86%. The fault fine-grained recognition accuracy is 95.62%. The accuracy of fine-grained information fusion has improved by 4%, and unsupervised learning of new faults has been successfully achieved. The proposed method can enhance the intelligent operation and maintenance capability of PV power plants, reduce false alarm rates in fault detection, and minimize operational risks caused by potential faults, thus effectively shortening downtime and lowering maintenance costs.

Photovoltaic Array Fault Diagnosis and Localization Method Based on Modulated Photocurrent and Machine Learning.

Photovoltaic arrays are exposed to outdoor conditions year-round, leading to degradation, cracks, open circuits, and other faults. Hence, the establishment of an effective fault diagnosis system for photovoltaic arrays is of paramount importance. However, existing fault diagnosis methods often trade off between high accuracy and localization. To address this concern, this paper proposes a fault identification and localization approach for photovoltaic arrays based on modulated photocurrent and machine learning. By irradiating different frequency-modulated light, this method separates photocurrent and directly measures the photoelectric conversion efficiency of each panel, achieving both high accuracy and localization. Through machine learning classification algorithms, the current amplitude and frequency of each photovoltaic panel are identified to achieve fault identification and localization. Compared to other methods, the strengths of this method lie in its ability to achieve high-speed and high-accuracy fault identification and localization by measuring only the short-circuit current. Additionally, the equipment cost is low. The feasibility of the proposed method is demonstrated through practical experimentation. It is determined that when utilizing a neural network algorithm, the fault identification speed meets measurement requirements (5800 obs/s), and the fault diagnosis accuracy is optimal (97.8%).

Fault diagnosis of elevator systems based on multidomain feature extraction and SHAP feature selection

In smart buildings, elevator faults may affect the traveling efficiency and the safety of passengers. It is important to find a quick and accurate method for fault diagnosis to minimize disruption time. Most existing fault diagnosis methods are for gear systems, which ignore the characteristics of elevators and need adaptations before applying them to the elevators. This study presents a novel multidomain feature extraction method for elevator fault diagnosis. It calculates the time domain features and wavelet packet energy and then extracts the elevator frequency features. These multidomain features are utilized as the input of a support vector machine to diagnose elevator faults. Subsequently, SHapley Additive exPlanations is used to select features to remove redundant features without reducing diagnosis accuracy. Comparative experiments show that multidomain feature extraction based on triaxial data improves diagnosis accuracy. Additionally, the elevator frequency feature extraction method further enhances diagnosis accuracy. In addition, experiments demonstrate that SHapley Additive exPlanations feature selection can be effectively applied to remove redundant features in different fault diagnoses, which improves the training efficiency and reduces the risk of overfitting. Practical applications In this paper, we present a practical solution for elevator fault diagnosis in intelligent buildings. By the proposed method, maintainers can find elevator faults based on objective evidence rather than intuitive feeling. We utilize a phone instead of the vulnerable and expensive equipment to collect and analyze signals, which makes the cost for this solution inexpensive and propagable. Thus, this solution can be applied to most practical elevator maintenance to reduce the elevator downtime.

Knowledge Graph-Based In-Context Learning for Advanced Fault Diagnosis in Sensor Networks.

This paper introduces a novel approach for enhancing fault diagnosis in industrial equipment systems through the application of sensor network-driven knowledge graph-based in-context learning (KG-ICL). By focusing on the critical role of sensor data in detecting and isolating faults, we construct a domain-specific knowledge graph (DSKG) that encapsulates expert knowledge relevant to industrial equipment. Utilizing a long-length entity similarity (LES) measure, we retrieve relevant information from the DSKG. Our method leverages large language models (LLMs) to conduct causal analysis on textual data related to equipment faults derived from sensor networks, thereby significantly enhancing the accuracy and efficiency of fault diagnosis. This paper details a series of experiments that validate the effectiveness of the KG-ICL method in accurately diagnosing fault causes and locations of industrial equipment systems. By leveraging LLMs and structured knowledge, our approach offers a robust tool for condition monitoring and fault management, thereby improving the reliability and efficiency of operations in industrial sectors.

Data-driven fault diagnosis for aero-engine gas path systems with unknown system parameters

This paper is concerned with the fault diagnosis problem for aero-engine gas path systems. Due to the complexity of the aero-engine structure, it is hard to establish an accurate model with known system parameters to describe its physical characterisations. To tackle this problem, two neural networks are introduced to learn the input–output relationship for both fault-free and faulty cases. Specifically, the first neural network is mainly constructed to generate residual signals for fault detection, and the second one is designed by extracting features of different fault types such that the fault isolation problem is solved based on the extracted data. Meanwhile, considering the weak fault features, a fuzzy logic system incorporating expert knowledge is embedded to enhance the isolation accuracy. Moreover, a data-driven fault estimator is designed by using Markov parameters identification and optimisation method, and it is shown that the estimation performance is improved compared with the existing results.

Applied fault diagnosis with distributed monitoring systems: Bridging theory with practice

We address the feasibility of the pragmatic implementation of monitoring systems for real-time distributed fault diagnosis in complex processes. We delve into the integration of theoretical distributed estimation methods and practical distributed embedded systems. This study emphasizes the merger of distributed computing and signal processing to augment fault diagnosis in dynamic systems. We introduce a generic mathematical model for distributed fault diagnosis algorithms, laying the groundwork for a reference network computing architecture that details the essential components, organization, and operational characteristics necessary for distributed monitoring systems. Subsequently, we evaluate existing software and hardware solutions that facilitate the realization of these systems. The theoretical framework and system design are empirically validated through an experimental setup involving a liquid-level control system, demonstrating the efficacy and applicability of our approach.

Research on the Detection Method for Feeding Metallic Foreign Objects in Coal Mine Crushers Based on Reflective Pulsed Eddy Current Testing

In response to the difficulties and poor timeliness in detecting feeding metallic foreign objects during high-yield continuous crushing operations in coal mines, this paper proposes a new method for detecting metallic foreign objects, combining pulsed eddy current testing with the Truncated Region Eigenfunction Expansion (TREE) method. This method is suitable for the harsh working conditions in coal mine crushing stations, which include high dust, strong vibration, strong electromagnetic interference, and low temperatures in winter. A model of the eddy current field of feeding metallic foreign objects in the truncated region is established using a coaxial excitation and receiving coil with a Hall sensor. The full-cycle time-domain analytical solution for the induced voltage and magnetic induction intensity of the reflective field under practical square wave signals is obtained. Simulation and experimental results show that the effective time range, peak value, and time to peak of the received voltage and magnetic induction signals can be used to classify and identify the size, thickness, conductivity, and magnetic permeability of feeding metallic foreign objects. Experimental results meet the actual needs for removing feeding metallic foreign objects in coal mine sites. This provides core technical support for the establishment of a predictive fault diagnosis system for crushing equipment.

Data imbalanced fault diagnosis of gearbox transmission system under various speeds based on dynamic dual-scale normalized fusion network

Abstract Gearboxes play a pivotal role in industrial production, and their reliability and safety are essential for production safety and efficiency. However, gearboxes frequently encounter challenges such as variable rotational speeds and unknown operating conditions. Unfortunately, most existing traditional fault diagnosis methods face the following issues: (1) They heavily rely on expert experience and pre-existing knowledge bases, making them unable to tackle fault diagnosis in unknown working conditions. (2) While addressing various speed issues, they seldom consider the problem of data imbalance in real-world industrial environments. (3) Many transfer learning methods primarily focus on global distribution alignment and knowledge transfer between source and target domains, neglecting the importance of fine-grained distribution alignment between subdomains. To address these issues, a dynamic dual-scale normalization fusion network (DSNFNet) is proposed for cross-domain fault diagnosis under variable speed and data imbalance. Firstly, the two parallel graph convolution frameworks constructed are used to extract multi-scale fault features. Subsequently, a dual-scale normalization fusion module is adopted to integrate the global and local fault feature information within the subdomains of both the source and target domains, thereby aligning their fine-grained distributions to obtain domain-invariant features. Finally, a dynamic soft threshold feedback strategy is introduced, which assigns pseudo labels to the target domain data, enabling the model to give equal attention to each class of data samples, even under data imbalance conditions, thereby improving the recognition accuracy of minority fault classes. Validating the proposed method on two real cases, our method achieved the highest accuracy compared to other advanced approaches.

Learning criteria of normalized regressor-based adaptive observer for actuator fault diagnosis of disturbed systems

Learning criteria of normalized regressor-based adaptive observer for actuator fault diagnosis of disturbed systems

Study on the Characteristics of Turn-to-Turn Short Circuit Faults in the Primary Windings of the Generator Terminal Voltage Transformer

Turn-to-turn short circuit faults in the primary winding of generator terminal voltage transformers can lead to erroneous operation of stator grounding protection systems. This paper analyzes the fault characteristics associated with such failures and derives formulas for the fault phase current and zero-sequence voltage during a turn-to-turn short circuit in the primary winding. A 3D finite element model of the generator terminal voltage transformer is established by using Altair Flux 3D, and the accuracy of the model is verified. Based on this model, simulation tests were conducted to investigate turn-to-turn short circuits in the primary winding. The results reveal that as the number of shorted turns increases, the voltage of the fault phase decreases continuously while the voltages of the other two phases increase. The current in the short-circuited phase rises significantly, accompanied by an increase in zero-sequence voltage. Visualizations of magnetic field parameters indicate that as the number of shorted turns increases, the magnetic induction magnitude of the fault phase rises steadily and approaches saturation, resulting in heightened magnetic field intensity near the shorted turns. This analysis of fault characteristics through simulation contributes to the advancement of fault diagnosis systems for generator terminal voltage transformers.

Fault diagnosis in hydropower units based on chaotic Kepler optimization algorithm-enhanced BiLSTM model

Safe and stable operation of hydropower units is the cornerstone of the whole hydroelectric power generation system. This paper proposes a deep learning model based on the chaotic Kepler optimization algorithm (CKOA) for fault diagnosis of hydropower units. The Tent chaotic function is introduced to initialize the initial population of KOA, which accelerates the convergence speed of the KOA algorithm and improves the global search capability by improving the uniformity and uncertainty of the population. CKOA is used to optimize the hyperparameters of Bidirectional Long Short-term Memory (BiLSTM) to improve the robustness and generalization ability of the model, making it suitable for dealing with complex nonlinear fault signals of hydropower units. The experimental results show that the training accuracy and testing accuracy of the CKOA-BiLSTM model are 97.6% and 98.3%, respectively, which are better than those of the LSTM, BiLSTM, and KOA-BiLSTM models. Meanwhile, diagnosing faults from the acoustic point of view, the accuracy of impact faults in hydropower units is much higher than that of wear and tear faults. This study can serve as a valuable supplement to the existing hydropower units condition monitoring and fault diagnosis system.

Simplified Kernel-Based Cost-Sensitive Broad Learning System for Imbalanced Fault Diagnosis

Simplified Kernel-Based Cost-Sensitive Broad Learning System for Imbalanced Fault Diagnosis