Fault Detection Model Research Articles

Development of a Machine Learning Based Fault Detection Model for Received Signal Level in Telecommunication Enterprise Infrastructure

Development of a Machine Learning Based Fault Detection Model for Received Signal Level in Telecommunication Enterprise Infrastructure

Non-intrusive fault detection in shipboard power systems using wavelet graph neural networks

Naval shipboard power systems (SPS) are rapidly embracing electrification, resulting in loads that generate pulsation currents and encounter substantial transients. However, conventional time-based features alone are inadequate for effectively monitoring and safeguarding these loads against faults. This highlights the critical requirement for advanced machine learning based methods to discern and differentiate between the various transient stages within the load profile. In this paper, we propose a Wavelet Graph Neural Network (WGNN) model for non-intrusive fault detection in SPS. The fault detection system leverages the dynamic model of the SPS to train and test performance with varying fault scenarios. The underlying structure and the interdependence among component states in the SPS network are effectively captured using the WGNN model, resulting in accuracies over 99% for intrusive fault detection and 97% for non-intrusive fault detection. The developed WGNN model has also shown to be robust in the presence of pulse loads and noise, achieving an accuracy of over 95%. At the end, a real-time simulation of the proposed method is validated on a hardware-in-the-loop system, guaranteeing the high fidelity and low latency of the proposed approach. These findings validate the effectiveness of the proposed WGNN model for fault detection and real-world applications in SPS.

An enhanced fireworks algorithm and its application in fault detection of the displacement sensor

Regarding the fault detection problem of the displacement sensor, an enhanced fireworks algorithm with information crossover and conversion factor (EFWA-IC) is proposed in this paper. In EFWA-IC, an information crossover strategy is proposed to maintain population diversity. This strategy is based on the predatory behavior of carnivores in nature. In addition, a conversion factor is set to control whether the explosion operator is executed or not to provide a more reasonable search. To fully evaluate the performance of EFWA-IC, a range of tests are carried out based on the CEC2017 and 23 classical test functions. The results show that the performance of EFWA-IC is better than other state-of-the-art optimization algorithms in terms of solution accuracy, convergence speed, and stability. Finally, EFWA-IC is utilized to optimize the particle filter (PF) to establish a fault detection model of displacement sensor in the continuous casting mold. The simulation experiment result of field data manifests that EFWA–IC–PF can accurately detect faults in the displacement sensor. For bias faults, the RMSE of the EFWA–IC–PF model is 0.14468, and the false alarm rate (FAR) and missed detection rate (MDR) are 1 % and 0.5 %, respectively. For stuck faults, the RMSE is 1.00148, and the FAR and MDR are 0.88 % and 1 %, respectively.

A propagation path-based interpretable neural network model for fault detection and diagnosis in chemical process systems

Process monitoring through automated fault detection and diagnosis (FDD) plays a crucial role in maintaining a productive and reliable chemical process system. Developments in AI and machine learning have boosted FDD model performances especially with deep learning methods. However, these neural network models are considered black-boxes where the reasoning behind a diagnosis is unclear, preventing industrial adoption. Therefore, in this study, an interpretable neural network model is proposed for FDD in chemical processes. This framework detects and diagnoses faults based on the propagation paths of different faults which are embedded into the architecture through graph convolutional networks. A mechanism for interpreting the node activations which represent process variables is developed for decision verification. The proposed method is evaluated on the benchmark Tennessee Eastman Process where it achieves a 93.56% accuracy on selected faults.

Fault Detection of Urban Wastewater Treatment Process Based on Combination of Deep Information and Transformer Network.

As one of the hot issues of concerns during modern social development, the wastewater treatment process is acknowledged to be a process with complex biochemical reactions and susceptible to an external environment, featuring strong nonlinear and time correlation characteristics, which are difficult for traditional mechanism-based models to tackle. For many classical data-driven fault detection methods, a complete retraining process is necessary to monitor every new fault, and most of the current neural network-based strategies rarely achieve satisfactory monitoring accuracy or robustness either. Giving full consideration to the aforementioned problems, this article takes advantage of position encoding, residual connection, and multihead attention mechanism embedded in the Transformer structure to establish an effective and efficient wastewater treatment process fault detection model, where offline modeling and online monitoring are performed successively to achieve accurate detection of the faults. In the experimental part, the advantages of the proposed method are strongly verified through the simulation monitoring of 27 faults on the benchmark simulation model 1 (BSM1), where the false alarm rate (FAR) and miss alarm rate (MAR) of the established method are proved to be significantly lower than those of the compared state-of-the-art methods.

Sparse deep encoded features with enhanced sinogramic red deer optimization for fault inspection in wafer maps

AbstractDue to the complexity and dynamics of the semiconductor manufacturing processes, wafer bin maps (WBM) present various defect patterns caused by various process faults. The defect type detection on wafer maps provides information about the process and equipment in which the defect occurred. Recently, automatic inspection has played a vital role in meeting the high-throughput demand, especially with deep convolutional neural networks (DCNN) which shows promising efficiency. At the same time, the need for a large amount of labeled and balanced datasets limits the performance of such approaches. In addition, complex DCNN in recognition tasks can provide redundant features that cause overfitting and reduce interpretability. In this paper, a new hybrid deep model for wafer map fault detection to get over these challenges is proposed. Firstly, a new convolutional autoencoder (CAE) is employed as a synthetization model to fix the high imbalance problem of the dataset. Secondly, for efficient dimensionality reduction, an embedding procedure is applied to the synthesized maps to get sparse encoded wafer maps by reinforcing a sparsity regularization in an encoder-decoder network to form a sparsity-boosted autoencoder (SBAE). The sparse embedding of wafer maps guarantees more discriminative features with 50% reduction in spatial size compared to the original wafer maps. Then, the 2D encoded sparse maps are converted to 1D sinograms to be fed later into another aggressive feature reduction stage using a new modified red deer algorithm with a new tinkering strategy. The resultant feature pool is reduced to ~ 25 1D feature bases, i.e., ~ 1.5% of the initial size of the 2D wafer maps. Finally, for the prediction stage, a simple 1DCNN model is introduced. The proposed inspection model is tested via different experiments on real-world wafer map dataset (WM-811K). Compared to state-of-the-art techniques, the proposed model outperforms their performance even with small-sized 1D feature pool. The average testing accuracy are 98.77% and 98.8% for 9 and 8 types of faults, respectively.

Data-driven fault detection framework for offshore wind-hydrogen systems

Offshore wind-hydrogen systems operate in harsh marine environments for extended periods, posing risks of low accessibility and high failure rates. This paper proposes a data-driven fault detection framework for offshore wind-hydrogen systems, aiming to promptly detect potential faults based on the system's physical parameters. The research establishes a comprehensive model based on the operating principles of offshore wind-hydrogen systems. The study uses fault injection techniques to simulate common partial faults in offshore wind-hydrogen systems and collects relevant physical parameters (such as wind turbine power generation, energy storage battery charging/discharging current, and electrolyzer hydrogen production rate). A fault detection model was constructed using a combination of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) to enable precise detection of potential faults in the system. The established model provides theoretical support for designing, optimizing, and operating offshore wind-hydrogen systems, reducing reliance on actual experiments and lowering project risks and costs. Introducing artificial faults can evaluate the system's performance in different fault scenarios. This paper proposes a CNN-BiLSTM fault detection method that achieves automatic feature extraction and high-precision classification of time-series fault data, confirming the practicality and feasibility of offshore wind-hydrogen systems. This investigation realizes the integration of the offshore wind-hydrogen system model and deep learning, as well as a fully automated learning process from data to fault detection. By calculating and comparing results, it is verified that the framework has a high accuracy of 96.9%. This innovative research offers new methods and perspectives for enhancing the reliability and efficiency of fault detection in offshore wind-hydrogen systems.

Blade fouling fault detection based on shaft orbit generative adversarial network

To address the challenges of accuracy and interpretability in mechanical fault detection models, this study proposes a shaft orbit generative adversarial network (SOGAN) and applies it to detect blade fouling faults. Variational autoencoder (VAE) is used as the foundational network architecture for extracting high-dimensional latent features from the shaft orbit images. Concurrently, the invariant moments of the shaft orbit images are extracted and embedded in a bypass within the generator, thereby enhancing the accuracy of fault detection. Two sets of real-world blade fouling fault data are collected and meticulously analyzed. The proposed SOGAN model demonstrates significant performance improvements, with average increases of 18.91%, 10.20%, and 26.79% in accuracy compared to the autoencoder, VAE, and GANomaly algorithms, respectively. The F1 scores for both the groups exceed 0.98. The data generated by the proposed SOGAN model exhibit a trend-wise correspondence with the finite element modeling data. In addition, the use of gradient information for the localization and visual analysis of anomalies dynamically tracks the spatial evolution of the rotor shaft orbit throughout its lifecycle. The data generation capability and interpretability of the proposed model can effectively support digital twin modeling and health management of rotating machinery.

Transfer learning for servomotor bearing fault detection in the industrial robot

In consequence of their superior performance and durability, industrial robots have enjoyed widespread adoption across a variety of industries. However, despite their sturdy build, they are susceptible to malfunction. The servomotor is a fundamental component of industrial robots, and to ensure smooth and uninterrupted functioning, it is essential to detect any defects it may develop. Although research has addressed methods for detecting bearing failure, diagnosis of a servomotor bearing failure in the industrial robot remains difficult and requires intensive research. In this paper, a novel method for detecting servomotor bearing defects in the industrial robot is provided by integrating knowledge transfer via transfer learning. Initially, current signals of the servomotor are transformed to scalogram images. This processed data is utilized to build the model for fault detection. Applying transfer learning eliminates model training from scratch and streamlined operations. The purported approach shows an average accuracy of more than 99 %.

Unsupervised fault detection approach based on depth auto-encoder for photovoltaic power generation system

Fault detection for photovoltaic power generation system is a challenging problem in condition monitoring and troubleshooting, which aims to maintain the safe operation of equipment and improve the benefit of photovoltaic industry. Aiming at the problems of frequent failures of photovoltaic power generation system, large amount of operating data and difficult to obtain fault samples, we propose an unsupervised fault detection approach for photovoltaic power generation system via bidirectional long/short memory deep auto-encoder which combines the auto-encoder in deep learning with the Bi-directional Long Short-Term Memory (BiLSTM). Specifically, We first take the statistical feature enhanced as the input of an auto-encoder based on BiLSTM. Then, we build a simulation model of Grid-connected PV system. Finally, we use the operation results under normal conditions to train the fault detection model to obtain the reconstruction error and determine the fault detection threshold, so as to judge the anomalies of the photovoltaic power generation system. We simulate the shadow occlusion fault and verify the effectiveness of the proposed method, and the fault detection accuracy of 0.95 is achieved. Compare with other models, the results show that it could set up better dependence on multi-dimensional data in time sequences, effectively testing solar panel failures and solving insufficient data labels problems.

Fault Detection and Interactive Multiple Models Optimization Algorithm Based on Factor Graph Navigation System

Accurate and stable positioning is significant for vehicle navigation systems, especially in complex urban environments. However, urban canyons and dynamic interference make vehicle sensors prone to disturbance, leading to vehicle positioning errors and even failures. To address these issues, an adaptive loosely coupled IMU/GNSS/LiDAR integrated navigation system based on factor graph optimization with sensor weight optimization and fault detection is proposed. First, the factor nodes and system framework are constructed based on error models of sensors, and the optimization method principle is derived. Second, the interactive multiple-model algorithm based on factor graph optimization (IMMFGO) is utilized to calculate and adjust sensor weights for global optimization, which will reduce the impact of disturbed sensors. Finally, a multi-stage fault detection, isolation, and recovery (MSFDIR) strategy is implemented based on the IMMFGO results and IMU pre-integration measurements, which can detect significant sensor faults and optimize the system structure. Vehicle experiments show that our IMMFGO method generally obtains better performance in positioning accuracy by 23.7% compared to adaptive factor graph optimization (AFGO) methods, and the MSFDIR strategy possesses the capability of fault sensor detection, which provides an essential reference for multi-source vehicle navigation systems in urban canyons.

Arc-1DCNN: An enhanced model for series arc fault detection

Series Arc Faults (SAFs) represent a prominent cause of electrical fires in low-voltage distribution systems, often arising from faulty connections or deteriorated insulation. These SAFs occurrences generate high-temperature arcs that endanger electrical system safety. As a result, detecting and accurately identifying SAFs have become crucial concerns. However, the line noise interference and the complexity of the electrical environment make SAFs detection challenging. In this paper, we propose a novel method that combines Wiener filtering with the Arc-1DCNN model to enhance SAFs detection. The method leverages Wiener filtering to enhance current signal, effectively reducing noise interference and providing a more robust dataset for training. To fully exploit the rich high-frequency characteristics of SAFs, Arc-1DCNN incorporates a High-Frequency-Feature-Attention module, enabling the model to capture subtle SAFs anomalies and significantly improving detection accuracy. Experimental validation demonstrates Arc-1DCNN's exceptional performance with 99.94% detection accuracy for SAFs, showcasing its potential for addressing SAFs detection challenges.

Sparse linear parameter-varying autoregressive moving average modelling of non-stationary gearbox vibration signals

Gearboxes frequently operate under variable speed conditions, leading to the non-stationarity of collected monitoring signals. This paper proposes a sparse linear parameter-varying autoregressive moving average (Spa LPV-ARMA) model for fault detection of gearboxes under variable speed conditions. The Spa LPV-ARMA model integrates the advantages of LPV concepts, sparse models, and ARMA models. The proposed model has a more compact structure compared to the reported Spa LPV-AR model, which results in a lower ratio of parameter number to data amount, and the compact model structure also allows the Spa LPV-ARMA model to have higher computational efficiency during the testing phase. A simulation study was conducted to validate the performance of the proposed method. The results demonstrate that the Spa LPV-ARMA model exhibits superior modeling accuracy compared to the reported Spa LPV-AR model. Additionally, the fault detection method based on the Spa LPV-ARMA model achieves a higher fault detection rate when contrasted with a model that solely considers the autoregressive component.

ARMA time series prediction model for fault detection of launch vehicle

Spaceflight is a high-risk activity, especially for launch vehicles, and the losses caused by launch failures are considerable. Real-time fault detection is a prerequisite to ensure that future launch vehicles can detect and isolate faults in a timely manner, and ultimately reduce the hazard of fault. In this article, a time series prediction model of axial overload and three-axis angular rate is established using ARMA (Auto Regressive Moving Average) time series prediction model, and the residuals of the prediction model are analyzed and combined with the fault determination decision strategy to determine whether the system has a fault, and a fault tree can be built to further locate the fault location.

Interpretable Recurrent Variational State-Space Model for Fault Detection of Complex Systems Based on Multisensory Signals

It is necessary to develop a health monitoring system (HMS) for complex systems to improve safety and reliability and prevent potential failures. Time-series signals are collected from multiple sensors installed on the equipment that can reflect the health condition of them. In this study, a novel interpretable recurrent variational state-space model (IRVSSM) is proposed for time-series modeling and anomaly detection. To be specific, the deterministic hidden state of a recursive neural network is used to capture the latent structure of sensor data, while the stochastic latent variables of a nonlinear deep state-space model capture the diversity of sensor data. Temporal dependencies are modeled through a nonlinear transition matrix; an automatic relevance determination network is introduced to selectively emphasize important sensor data. Experimental results demonstrate that the proposed algorithm effectively captures vital information within the sensor data and provides accurate and reliable fault diagnosis during the steady-state phase of liquid rocket engine operation.

Systems Reliability and Data Driven Analysis for Marine Machinery Maintenance Planning and Decision Making

Understanding component criticality in machinery performance degradation is important in ensuring the reliability and availability of ship systems, particularly considering the nature of ship operations requiring extended voyage periods, usually traversing regions with multiple climate and environmental conditions. Exposing the machinery system to varying degrees of load and operational conditions could lead to rapid degradation and reduced reliability. This research proposes a tailored solution by identifying critical components, the root causes of maintenance delays, understanding the factors influencing system reliability, and recognising failure-prone components. This paper proposes a hybrid approach using reliability analysis tools and machine learning. It uses dynamic fault tree analysis (DFTA) to determine how reliable and important a system is, as well as Bayesian belief network (BBN) availability analysis to assist with maintenance decisions. Furthermore, we developed an artificial neural network (ANN) fault detection model to identify the faults responsible for system unreliability. We conducted a case study on a ship power generation system, identifying the components critical to maintenance and defects contributing to such failures. Using reliability importance measures and minimal cut sets, we isolated all faults contributing over 40% of subsystem failures and related events. Among the 4 MDGs, the lubricating system had the highest average availability of 67%, while the cooling system had the lowest at 38% using the BBN availability outcome . Therefore, the BBN DSS recommended corrective action and ConMon as maintenance strategies due to the frequent failures of certain critical parts. ANN found overheating when MDG output was above 180 kVA, linking component failure to generator performance. The findings improve ship system reliability and availability by reducing failures and improving maintenance strategies.

Neural networks and particle swarm for transformer oil diagnosis by dissolved gas analysis

The lifetime of power transformers is closely related to the insulating oil performance. This latter can degrade according to overheating, electric arcs, low or high energy discharges, etc. Such degradation can lead to transformer failures or breakdowns. Early detection of these problems is one of the most important steps to avoid such failures. More efficient diagnostic systems, such as artificial intelligence techniques, are recommended to overcome the limitations of the classical methods. This work deals with diagnosing the power transformer insulating oil by analysis of dissolved gases using new techniques. For this, we have proposed intelligent techniques based on Multilayer artificial neural networks (ANN). Thus, a multi-layer ANN-based model for fault detection is presented. To improve its classification rate, this one was optimized by a meta-heuristic technique as the particle swarm optimization (PSO) technique. Optimized ANNs have never been used in transformer insulating oil diagnostics so far. The robustness and effectiveness of the proposed model is demonstrated, and high accuracy is obtained.

A Small Deep Learning Model for Fault Detection of a Broken Rotor Bar of an Induction Motor

A Small Deep Learning Model for Fault Detection of a Broken Rotor Bar of an Induction Motor

Dirichlet probability navigated fault detection via key-group memory auto-encoder under non-stationary working conditions

Real-time condition monitoring is the foundation of prognostics and health management (PHM) for mechanical systems. Constraint by extravagant cost and insurmountable obstacles to simulate real faults in actual working conditions, establishing fault detection models with historical normal data is the most promising way. Meanwhile, non-stationary fault detection is rarely studied in the literature but fits most in real working conditions. Thus, an innovative method named KGMem-DirAE is proposed to conduct real-time fault detection under non-stationary working conditions using normal data only. In the training stage, normal patterns with different semantics are recorded in the developed key-group memory module (KGMem) combined with auto-encoder. Considering the matching probabilities of encoded latent features and recorded memory units (normal patterns), a statistical anomaly score defined by aggregated negative log-likelihood of Dirichlet distributions is proposed to detect incipient failures. In order to deal with time-varying working conditions and capture fault degradation trends concurrently, normalized time-frequency maps containing fault-evolving information are obtained from vibration data. Both widely studied non-stationary and stationary run-to-failure data sets are deeply researched using the proposed KGMem-DirAE and the experimental results proved its superiority against other comparative anomaly detection methods.

Bearing fault detection technology for automated machinery based on acoustic analysis

Traditional fault detection methods in acoustic signal feature extraction of rolling bearings often make the signal denoising process complex due to low signal-to-noise ratio and weak fault features, making this method difficult to meet real-time requirements. Therefore, a fault detection model based on Fast-Renoriented SIFT feature extraction is proposed, which can quickly extract a large number of features from the original signal without the need for noise reduction processing and can effectively improve the efficiency and accuracy of fault detection. At the same time, to adapt to the fault detection of rolling bearings under multiple working conditions, this study also proposes an adaptive extended word bag model that combines local kurtosis and local 2-dimensional information entropy features, improving the adaptability and flexibility of the new model. It obtained a 100% overall recognition rate and a fault detection time of no more than 0.5 seconds in a 5-fold cross-validation experiment, verifying the excellent recognition accuracy, stability, and operational efficiency of the detection model. Its recognition accuracy in the multi-working condition rolling bearing fault detection experiment was above 97%, which was improved by about 21.25% compared to the traditional word bag model and had significant advantages in fault recognition accuracy and computational efficiency.