Fault Detection Algorithm Research Articles

A Visual Fault Detection Algorithm of Substation Equipment Based on Improved YOLOv5

The development of artificial intelligence technology provides a new model for substation inspection in the power industry, and effective defect diagnosis can avoid the impact of substation equipment defects on the power grid and improve the reliability and stability of power grid operation. Aiming to combat the problem of poor recognition of small targets due to large differences in equipment morphology in complex substation scenarios, a visual fault detection algorithm of substation equipment based on improved YOLOv5 is proposed. Firstly, a deformable convolution module is introduced into the backbone network to achieve adaptive learning of scale and receptive field size. Secondly, in the neck of the network, a simple and effective BiFPN structure is used instead of PANet. The multi-level feature combination of the network is adjusted by a floating adaptive weighted fusion strategy. Lastly, an additional small object detection layer is added to detect shallower feature maps. Experimental results demonstrate that the improved algorithm effectively enhances the performance of power equipment and defect recognition. The overall recall rate has increased by 7.7%, precision rate has increased by nearly 6.3%, and mAP@0.5 has improved by 4.6%. The improved model exhibits superior performance.

On the performance comparison of diagnostic techniques in machine monitoring

Predictive maintenance can save a lot of efforts in modern industry and condition monitoring is attracting a lot of attention accordingly. New algorithms for fault detection appear frequently in the technical literature, however an objective, quantitative and widely accepted approach to performance comparison is still lacking. In this paper, we propose a new method leading to a fair and reproducible performance assessment. The proposed solution is based on vibrational analysis and consists of searching and detecting the theoretical cyclic frequencies that appear as a specific “signature” of a fault. Each algorithm for condition monitoring relies on a metric, then the main idea is to quantitatively characterize the peaks of the metric emerging from the machine noise. We think that the wide adoption of the proposed approach could significantly foster the research in the fields of condition monitoring and predictive maintenance.

Research on an Intelligent Piezoelectric Needle Selector System with Closed-Loop Fault Detection Capability

The piezoelectric needle selector is a crucial component of computerized dobby weft knitting machines. With the continuous development of weft knitting machine technology, enhancing the accuracy of piezoelectric needle selector control is essential. Accurate determination of whether the blades are in the correct position would significantly improve the precision of piezoelectric needle selector control. In this study, piezoelectric ceramic sensors were used to collect impact vibration signals when the blades struck the damper baffle. Key hardware circuits were designed for this purpose. A self-learning algorithm was employed to capture the highest point and the time it takes to reach the highest point in the impact vibration signal. A fault detection algorithm was used to implement closed-loop fault detection for piezoelectric needle selectors. Experimental results and practical applications have demonstrated that this research effectively addresses the accurate determination of whether the piezoelectric needle selector blades are in the correct position. It has reduced the defect rate of fabric production in weft knitting, thereby improving the overall efficiency and profitability of businesses.

Empirical Filtering-Based Artificial Intelligence Learning Diagnosis of Series DC Arc Faults in Time Domains

Direct current (DC) networks play a pivotal role in the growing integration of renewable energy sources. However, the occurrence of DC arc faults can introduce disruptions and pose fire hazards within these networks. In order to ensure both safety and optimal functionality, it becomes imperative to comprehend the characteristics of DC arc faults and implement a dependable detection system. This paper introduces an innovative arc fault detection algorithm that leverages current filtering based on the empirical rule in conjunction with intelligent machine learning techniques. The core of this approach involves the sampling and subsequent filtration of current using the empirical rule. This filtering process effectively amplifies the distinctions between normal and arcing states, thereby enhancing the overall performance of the intelligent learning techniques integrated into the system. Furthermore, this proposed diagnosis scheme requires only the signal from the current sensor, which reduces the complexity of the diagnosis scheme. The results obtained from the detection process serve to affirm the effectiveness and reliability of the proposed DC arc fault diagnosis scheme.

IoT-based monitoring and shading faults detection for a PV water pumping system using deep learning approach

One of the major challenges facing photovoltaic (PV) systems is fault detection. Artificial intelligence (AI) is one of the main popular techniques used in error detection due to its ability to extract signal and image features. In this paper, a deep learning approach based on convolutional neural network (CNN) and internet of things (IoT) technology are used to detect and locate shading faults for a PV water pumping system. The current and voltage signals generated by the PV panels as well as temperature and radiation were used to convert them into 3D images and then upload to a deep learning algorithm. The PV system and fault detection algorithms were simulated by MATLAB. The obtained results indicate that the performance of the proposed deep learning approach to detect and locate faults is better than the traditional statistical methods and other machine learning methods.

Real-Time DC Series Arc Fault Detection Based on Noise Pattern Analysis in Photovoltaic System

This paper presents a method for detecting series arc faults based on noise pattern analysis in photovoltaic systems. The arc detection circuit is required to detect the series arc quickly and not falsely detect the system noise as arc noise. This paper proposes noise pattern analysis to distinguish between system noise and arc noise and prevent false detection. First, periodic feature analysis prevents false detection by periodic noise, such as inverter noise, using the difference in periodic characteristics. Second, zero-range density analysis detects series arc noise using the difference in fluctuation characteristics. An integrated arc fault detection algorithm comprising discrete wavelet transform decomposition, periodic feature analysis, zero-range density, and an iterative loop algorithm is developed. The proposed methods are verified using noise distinction experiments, wherein the injected signal and arc noise are distinguished with high classification precision using the proposed noise pattern analysis method. The developed arc detection algorithm is applied to a real-time series arc detection board based on the TMS320F28335 DSP, and the performance of the series arc detection and false detection prevention is verified using the UL1699B arc detection test circuit and a real PV system.

Energy-aware and Context-aware Fault Detection Framework for Wireless Sensor Networks

Wireless sensor networks (WSNs) consist of many sensor nodes that are densely deployed throughout a randomized geographical area to monitor, detect, and analyze various physical phenomena. The primary obstacle encountered in WSNs pertains to the significant reliance of sensor nodes on finite battery power for wireless data transfer. Sensors as a crucial element inside Cyber-Physical Systems (CPS) renders them vulnerable to failures arising from intricate surroundings, substandard manufacturing, and the passage of time. Various anomalies can appear within WSNs, mostly attributed to defects such as hardware and software malfunctions and anomalies and assaults initiated by unauthorized individuals. These anomalies significantly impact the overall integrity and completeness of the data gathered by the networks. Therefore, it is imperative to provide a critical mechanism for the early detection of faults, even in the presence of constraints imposed by the sensor nodes. Machine Learning (ML) techniques encompass a range of approaches that may be employed to identify and diagnose sensor node faults inside a network. This paper presents a novel Energy-aware and Context-aware fault detection framework (ECFDF) that utilizes the Extra-Trees algorithm (ETA) for fault detection in WSNs. To assess the effectiveness of the suggested methodology for identifying context-aware faults (CAF), a simulated WSN scenario is created. This scenario consists of data from humidity and temperature sensors and is designed to emulate severe low-intensity problems. This study examines six often-seen categories of sensor fault, including drift, hard-over/bias, spike, erratic/precision, stuck, and data loss. The ECFDF approach utilizes an Energy-Efficient Fuzzy Logic Adaptive Clustering Hierarchy (EE-FLACH) algorithm to select a Super Cluster Head (SCH) within WSNs. The SCH is responsible for achieving optimal energy consumption within the network, and this selection process facilitates the early detection of faults. The results of the simulation indicate that the ECFDF technique has superior performance in terms of Fault Detection Accuracy (FDA), False-Positive Rate (FPR), and Mean Residual Energy (MRE) when compared to other detection and classification methods.

Improving kernel PCA-based algorithm for fault detection in nonlinear industrial process through fractal dimension

Principal Component Analysis (PCA) is a widely used technique for fault detection and diagnosis. PCA works well when the data set has linear characteristics. However, most industrial processes have nonlinear characteristics in their data. Kernel PCA (KPCA) is an alternative solution for such types of data sets. This solution doesn’t come without a cost since one of KPCA’s disadvantages is a large number of observations which results in more occupied storage space and more execution time than the PCA technique. Furthermore, if the data is too large it may minimize the monitoring performance of the KPCA model. Reduced KPCA (RKPCA) is a solution for the conventional KPCA limitations. Firstly, RKPCA can deal with nonlinear characteristics without crucial problems because it is based on the KPCA algorithm with a data reduction part where it keeps most of the data’s information. Thus, by reducing the number of observations RKPCA reduces the occupied storage space and execution time while preserving tolerable monitoring performance. The proposed RKPCA algorithm consists of two parts. First, the large-sized training data set is reduced using the fractal dimension technique (correlation dimension). Afterward, the KPCA model is developed through the obtained reduced training data set. The proposed scheme is applied to the Tennessee Eastman Process and the Cement Plant Rotary Kiln data sets to evaluate its performance in comparison with other algorithms.

An Improved Algorithm for Topology Identification of Distribution Networks Using Smart Meter Data and Its Application for Fault Detection

This paper proposes a new method for estimating the topology of radial distribution networks and a novel data-driven fault detection technique using smart meter data. An improved method to estimate voltage sensitivity coefficients from smart meter data is proposed that takes into account the variability of the transformer voltage. These coefficients are used in both the topology estimation and the fault detection algorithms. In the topology estimation algorithm, an improved graph learning algorithm, which iteratively constructs the network graph, is devised. In the fault detection algorithm, the objective is to look for sudden changes in the estimated voltage sensitivity coefficients. The performance of the proposed methods is first assessed on randomly generated topologies under various noise conditions. Then, the performance of the algorithms is validated using real smart meter measurements obtained from Australian distribution networks. The results show a significant improvement in the accuracy of estimated topologies compared to the state-of-the-art methods while the fault detection technique is successful in detecting faults using real smart meter data.

On the Assessment of Sampling Rate Impacts on Responses of Digital Protective Relays

Power systems (including industrial and commercial power systems) widely utilize digital protective relays for component and system protection. These protective devices have shown numerous operational advantages over conventional electromagnetic protective devices. Such operational advantages include the accuracy, reliability, response speed, interoperability, weight, and size. Performance and operational advantages of digital protective relays are typically dependent on the resolution of their input data, as well as their algorithms for fault detection and identification. This paper assesses the performance of time-based, frequency-based, and time-frequency-based digital protective relays, when operated at different sampling rates. Tested sampling rates include low, medium, and high sampling rates that range from 16 to 288 samples per cycle. In this paper, the three digital protective relays are tested when deployed as the digital 87 T transformer digital protection. Performance of the time-based, frequency-based, and time-frequency-based digital protective relays is assessed in terms of their accuracy and response speed. Test results show that low sampling rates can deteriorate the accuracy and response speed of the three tested digital protective relays. Obtained performance results also reveal that medium and high sampling rates can effectively improve the accuracy and response speed of the time-based, frequency-based, and time-frequency-based digital protective relays.

Application of non-Gaussian feature enhancement extraction in gated recurrent neural network for fault detection in batch production processes

The nonlinear, time correlation, and non-Gaussian features in data present significant challenges for effective fault detection. While the Gate Recurrent Unit (GRU) network is renowned for its capacity to manage time correlation, it falls short in capturing non-Gaussian features in process data, which can likely lead to suboptimal monitoring results. To address this limitation, the Enhancement Gate Recurrent Unit (ENGRU) is developed to perfect the fault detection accuracy of the network. Specifically, The ENGRU effectively extracts high order statistics information by employing the overcompleted independent component analysis method, thereby augmenting its ability to capture non-Gaussian properties. The extracted features information are then entered into the ENGRU model further to uncover additional hidden features beyond what the GRU can achieve. The ENGRU network, which is built upon the extracted characteristic information, even farther enhances the accuracy of the fault detection. The merits of the proposed model are demonstrated by comparing it with excellent fault detection algorithms on a benchmark platform.

A simple approach for the protection of EHV transmission lines

Due to the geographically widespread nature of the transmission lines, the chances of fault occurrence are more due to outdoor erection. This makes it inevitable to detect and isolate the faulty section of the system as quickly as possible. The existing fault detection and classification algorithms are limited to a specific configuration of transmission lines. This work has proposed a novel and simple methodology to recognize and classify faults on transmission lines by using single-end current data. A Harmonic Phasor Measurement Unit (HPMU) based on a non-recursive DFT algorithm is used to extract the fundamental and second-order harmonic components from current samples. The Equivalent Fundamental Component (EFC) and ΔEFC are estimated from the extracted data. Subsequently, an Index Matrix (P) is derived to recognize the fault. The non-zero value of the determinant of the index matrix detects the occurrence of a fault in the system. Second-order harmonic fault current coefficients are proposed for fault classification based on the second-order harmonic component extracted from HPMU. The proposed method accurately detects and classifies all types of conventional faults and cross-country faults (CCF) for any configuration of transmission network. The proposed method has also been validated under various abnormal conditions in PSCAD/EMTDC to ensure its efficacy.

DCMF-AFNet: An anchor-free photovoltaic hot-spot fault detection network based on deformable context transformer and bi-branch multi-level feature fusion

In the process of photovoltaic hot-spot detection by thermal infrared sensors, the fault features cannot be effectively represented due to low pixel ratios and complex environmental interference, which makes it difficult for the detection network to accurately detect hot-spot faults. Therefore, an anchor-free photovoltaic hot-spot fault detection algorithm based on deformable context Transformer and bi-branch multi-level feature fusion is proposed. First, to improve the feature extraction ability of the backbone network for small-scale hot-spot faults, a deformable context Transformer module is constructed. By building an offset network in a multi-headed self-attention mechanism, dynamic and static context information with small-scale fault features can be explored from shallow feature maps. Second, to solve the problem of low target saliency due to the complex background interference, a bi-branch multi-level feature fusion module is designed to aggregate global and local multi-level features in a parallel fusion manner, enabling the detection network to rapidly focus on the fault target region in complex environments. Then, an anchor-free mechanism is introduced, and a dynamic task alignment prediction module is proposed to avoid feature misalignment in the classification and localization tasks and further improve the algorithm detection accuracy. Finally, to verify the superiority of the proposed network, seven detection algorithms are selected for comparison experiments. The experimental results show that the DCMF-AFNet network can accurately detect multi-scale hot-spot targets under various harsh conditions, and the detection accuracy can reach 87.3%.

Adaptive Actuator Failure Compensation Control: A New Scheme Based on Fault Detection and Isolation

In flight control systems, multiple actuator stuck (or hardover) failures would cause saturation of the remaining healthy actuators and result in system instability. In this article, a new adaptive actuator failure compensation control scheme is proposed for a class of nonlinear systems with multiple redundant inputs. Under a mild assumption on the time interval between two successive failures, an online fault detection and isolation (FDI) algorithm is introduced, with which an actuator failure can be exactly identified in a given finite time without using the persistent excitation (PE) condition. The main advantage of the proposed scheme is that with the help of the FDI algorithm, an actuator with stuck failure (SF) can be deactivated before a new failure occurs and therefore, the drawback of the current adaptive failure compensation control approach that may cause more control effort or even saturation with multiple actuators being stuck can be overcome.

Protection System Architecture for All-Electric Aircraft

To reduce emissions from the aviation industry and meet the targets set by different countries, research has been focused on investigating all-electric aircraft. To make this vision practical, superconducting machines are expected to power the propellers, as they are half the size and a third the weight of conventional machines. The main purpose of this paper is to do a higher-level study of a reliable holistic protection system for all-electric aircraft; that can reduce heat leakage and be able to detect faults reliably. Thus, three main protection systems were investigated; 1) cryogenic voltage source converter superconducting magnetic energy storage system (VSC-SMES), 2) cryogenic dc breaker integrated with superconducting fault current limiter (SFCL), and 3) machine learning algorithm for fault detection. By immersing the protection system at cryogenic temperature, the paper has shown that passive leakage can be eliminated, and thus more energy can be saved for the fuel cell. The paper has also demonstrated that using machine learning for the SFCL-dc-breaker system can consistently eliminate faults and protect the system.

A Fault Detection Algorithm Based on Artificial Neural Network Threshold Selection in Multi-Terminal DC Grids

The DC fault is one of the critical challenges in the High Voltage Multi-Terminal Direct Current (HV-MTDC) grid. The fixed value threshold used in some implementations may be affected by different grid conditions and thus causes errors in the fault detection procedure. This paper offers a two-stage fault detection algorithm based on the integrated Artificial Neural Network (ANN) and Discrete Wavelet Transform (DWT) theory. The main innovations of the proposed method are: 1) Increasing the reliability of the fault detection operation by solving the fixed value threshold problems; 2) Offering high robustness against the wide range of fault resistances; 3) Providing bus protection capability and 4) Setting relays locally, and avoiding the requirement to high-speed communications links. Also, it offers DC fault detection in a short period of time. The performance of the proposed protection scheme has been ascertained via simulations in the MATLAB/Simulink environment. The results prove the robustness of the proposed method against noise disturbance, high resistance fault, and grid parameters variations.

A graph-guided collaborative convolutional neural network for fault diagnosis of electromechanical systems

Collaborative fault diagnosis has become a hot research topic in fault detection and identification, greatly benefiting from emerging multisensory fusion techniques and newly developed convolutional neural network (CNN) models. Existing CNN models take advantage of various fusion techniques to identify machine health status by utilizing multiple sensory signals. Nevertheless, a few of them are able to simultaneously explore modality-specific features and intrinsic shared features among multi-source signals, limiting the capability of the exploration of multisource data. To address this issue, this paper proposes a novel convolutional network called a graph-guided collaborative convolutional neural network (GGCN) for highly-effective fault diagnosis of electromechanical systems. The main contributions of this study include: (1) developing a novel graph-guided CNN algorithm for collaborative fault detection; (2) establishing a graph reasoning fusion module (GRFM) to explore the inherent correlations between multisource signals; and (3) advancing the current approaches by taking into account both the distribution gap and the intrinsic correlation between different signals simultaneously. The developed GGCN is expected to shed new light on collaborative fault diagnosis using the graph-convolution-based intermediate fusion scheme. Two experimental datasets namely, the cylindrical rolling bearing dataset and the planetary gearbox dataset, are applied in this paper to verify the efficacy of the GGCN. Experimental results demonstrate that GGCN outperforms seven other state-of-the-art approaches, particularly under noisy conditions.

Application of Signal Denoising Technology Based on Improved Spectral Subtraction in Arc Fault Detection

In the research of fault arc detection technology, proper signal denoising can greatly improve the recognition ability of the arc fault detection algorithm. Therefore, this study proposes a current signal enhancement algorithm based on improved spectral subtraction from the statistical law of electrical noise in a low-voltage distribution system and the principle of the arc fault detection algorithm. According to the results of the arc fault detection algorithm, the algorithm selects an appropriate reference current as the basis for noise estimation and further assumes that the types and quantities of power loads are relatively fixed and the current noise is relatively stable in a certain power consumption period in the same power consumption place, so as to obtain the current noise in the current power consumption environment, and then uses improved spectral subtraction to realize the real-time noise reduction of current signals required by the arc fault detection algorithm. The experimental results show that this method and the arc fault detection algorithm complement each other, and the processing of current signal is more targeted, which can make the selected arc fault characteristics more different between the normal state and fault state, eliminate the interference of high-frequency clutter in current signal on arc fault characteristics and greatly improve the sensitivity of the original detection algorithm on the premise of unchanged detection reliability.

Evolving fuzzy prediction interval for fault detection in a heat exchanger

The objective of this work is to design a novel evolving fuzzy prediction interval for modeling a nonlinear system and to implement a novel interval-based algorithm for fault detection. To achieve these goals, three frameworks are studied to provide the basis for the ideas to be proposed. First, the prediction intervals developed in the literature to characterize the uncertainties in modeling systems. Second, the evolving intelligence systems presented in the literature to improve the predictive models through adaptability to temporal changes. Third, the model-based error detection algorithms that detect anomalies in system behavior based on the error of the models. This work proposes a complete recursive design of the evolving fuzzy prediction interval based on interval coverage estimation. This estimation is based on the accumulated number of past time points in which the interval contained the measurements of the modeled system. Additionally, a new interval-based fault detection algorithm is proposed in this work that determines the activation of alarms based on the increment of the proposed interval failure index. This novel index is similar in structure to the interval coverage estimation. The proposed recursively evolving fuzzy prediction interval and interval-based fault detection algorithm were tested on a heat exchanger system whose characteristics were affected by external changes. The experimental results show the effectiveness of the proposed interval model in representing the dynamics of the heat exchanger. Furthermore, the experiment shows that the proposed fault detection algorithm achieves comparable accurate performance to the results of a previous model-based fault detection method.

Fault detection of a reciprocating plunger pump with fault-free data based on an unsupervised feature encoder and minimum covariance determinant

It is well known that complex mechanical equipment has many differnt the failure modes, and monitoring data for fault conditions are scarce. Therefore, research on fault detection for reciprocating plunger pumps with fault-free data is significant for theory and application. Due to the lack of prior knowledge of faults, it is always a great challenge for researchers to extract fault features from signals. In this paper, an innovative fault detection method for a reciprocating plunger pump is proposed based on an unsupervised feature encoder (UFE) and minimum covariance determination (MCD). Firstly, a criterion based on mutual information maximization for local and global features is proposed for unsupervised feature extraction. In addition, an unsupervised training strategy based on negative sampling is proposed to train the encoder, so that the model can converge quickly and improve the stability of model training. A fault detection algorithm for a reciprocating plunger pump is proposed based on a UFE and MCD. Finally, the effectiveness and superiority of the proposed method are verified with the measured data for a reciprocating plunger pump. The results show that the proposed method can accurately detect the faults in the reciprocating plunger pump with a detection accuracy of more than 98%. Compared with other methods, the proposed fault detection algorithm has better applicability and accuracy for fault detection with fault-free data.