Fault Prediction Research Articles

Digital Twin of Space Environment: Development, Challenges, Applications, and Future Outlook

This paper explores and discusses the revolutionary applications of digital twin technology in space environments and its profound impact on future space exploration activities. Originating from a proposal by the National Aeronautics and Space Administration (NASA) in 2002, digital twin technology aims to enhance the safety and reliability of space missions by creating precise virtual models. As the technology has evolved, its applications have successfully expanded beyond aerospace to include Industry 4.0, healthcare, and urban management, demonstrating remarkable cross-industry adaptability and broad impact. In space applications, digital twin technology can not only improve spacecraft design and maintenance processes but also enhance the efficiency of mission planning and execution. It plays a crucial role in astronaut training and emergency response as well. Particularly in extreme space conditions, this technology provides real-time monitoring and fault prediction, significantly enhancing mission safety and success rates. However, despite its recognized potential, the implementation of digital twins in space environments faces numerous challenges, including data transmission delays, model accuracy, and the design of user–system interactions. In the future, as artificial intelligence (AI) and machine learning (ML) technologies become mature and integrated, the digital twin will play a more central role in space missions, especially in remote operations, complex system management, and deep space exploration. This article is to overview key technical features, application examples, and challenges of digital twin technology, aiming to provide a comprehensive reference framework for researchers and developers while inspiring further in-depth studies and innovative applications.

Design of Power Outage Monitoring and Warning System Based on Internet of Things

With the rapid development of distribution network and the high popularity of distributed generation, the research on risk assessment of distribution network is accelerated. When quantifying the degree of harm caused by abnormal situations, it is necessary to consider the severity of the harm and the impact on society to measure the severity of power failure and reduce the loss caused by power risk. To provide data support for the fine perception of the situation and its development trend, the monitoring system constructed by the power microservice further improves the ability and accuracy of sudden fault prediction. In this paper, through the monitoring system information to explore the transmission line fault early warning, the data analysis model is established. The particle swarm optimization algorithm and BP neural network are used to build the early warning model to predict the potential fault situation and cause analysis of the power grid under various indicators in a certain period in the future, which is to provide more scientific and reasonable risk management and control for the power grid. Through the statistical analysis of all kinds of information data collected by the power microservice, a power monitoring system based on early warning of power outage risk is established to enhance the operation adaptability of the power grid system under uncertain conditions and prevent the occurrence of tripping blackouts so that this study has an important function of intelligent decision-making. The experimental results show the feasibility and high efficiency of this study. The comparison of algorithm results shows that the performance of this method is improved by more than 10%. The stability is improved by 17%. The response time to various situations is shortened by 32% to judge the abnormal operation state of the power grid more efficiently. It can make emergency preparations in time, reduce the damage caused by accidents to the power grid and provide practical tools for the power grid to further enhance the disaster prevention ability of transmission equipment and effectively resist risk events.

A study on cross-project fault prediction through resampling and feature reduction along with source projects selection

A study on cross-project fault prediction through resampling and feature reduction along with source projects selection

Research on Fault Prediction of Nuclear Safety-Class Signal Conditioning Module Based on Improved GRU

Research on Fault Prediction of Nuclear Safety-Class Signal Conditioning Module Based on Improved GRU

A Dataset and a Comparison of Classification Methods for Valve Plate Fault Prediction of Piston Pump

A Dataset and a Comparison of Classification Methods for Valve Plate Fault Prediction of Piston Pump

Deep learning-based vehicular engine health monitoring system utilising a hybrid convolutional neural network/bidirectional gated recurrent unit

Vehicles play a pivotal role in the current era of Industry 4.0 by providing passengers with excellent mobility, comfort, and safety while strengthening national and international economies. Unanticipated vehicular engine issues can hinder performance and lead to costly maintenance. As analytics processes become faster, more accurate, and more reliable, intelligent fault prediction and diagnosis for vehicles, particularly engines, is becoming increasingly popular. To date, hybrid deep learning approaches to vehicle engine diagnostics have been limited, and none have used engine health monitoring and categorisation based on vulnerability assessment and vehicle structural information. This paper introduces a hybrid deep learning-based vehicular engine health monitoring system (VEHMS) decision model using Deep CNN (convolutional neural network)-BiGRU (bi-directional gated recurrent unit). This model monitors a vehicle’s engine health in real-time and classifies its status as good, critical, moderate, or minor condition. Several advanced and hybrid deep learning algorithms were applied to monitor engine health and categorise its status by integrating sensor data with evaluated vulnerability information from an infrastructure vulnerability assessment model. The Deep CNN-BiGRU-based VEHMS decision model outperformed other techniques with an accuracy of 0.8897, ensuring minimal decision losses while classifying engine conditions. This study aims to contribute to developing comprehensive vehicle health monitoring systems and advance the automotive industry by incorporating more intelligent features. The proposed approach can enhance vehicle performance, reliability, and efficiency in the transportation sector by improving engine health monitoring.

Intelligent Grid Optimization and Fault Prediction Based on Machine Learning

Intelligent Grid Optimization and Fault Prediction Based on Machine Learning

Real-Time Simulation of Tube Hydroforming by Integrating Finite-Element Method and Machine Learning

The real-time, full-field simulation of the tube hydroforming process is crucial for deformation monitoring and the timely prediction of defects. However, this is rather difficult for finite-element simulation due to its time-consuming nature. To overcome this drawback, in this paper, a surrogate model framework was proposed by integrating the finite-element method (FEM) and machine learning (ML), in which the basic methodology involved interrupting the computational workflow of the FEM and reassembling it with ML. Specifically, the displacement field, as the primary unknown quantity to be solved using the FEM, was mapped onto the displacement boundary conditions of the tube component with ML. To this end, the titanium tube material as well as the hydroforming process was investigated, and a fairly accurate FEM model was developed based on the CPB06 yield criterion coupled with a simplified Kim–Tuan hardening model. Numerous FEM simulations were performed by varying the loading conditions to generate the training database for ML. Then, a random forest algorithm was applied and trained to develop the surrogate model, in which the grid search method was employed to obtain the optimal combination of the hyperparameters. Sequentially, the principal strain, the effective strain/stress, as well as the wall thickness was derived according to continuum mechanics theories. Although further improvements were required in certain aspects, the developed FEM-ML surrogate model delivered extraordinary accuracy and instantaneity in reproducing multi-physical fields, especially the displacement field and wall-thickness distribution, manifesting its feasibility in the real-time, full-field simulation and monitoring of deformation states.

Size-biased Hybrid Model for Software Defect Prediction

Size-biased Hybrid Model for Software Defect Prediction

Defect monitoring method for Al-CFRTP UFSW based on BWO–VMD–HHT and ResNet

Underwater friction stir welding (UFSW) achieves reliable joining between dissimilar materials and meets the welding demand for function and properties in lightweight structures of modern engineering. A defect monitoring method based on Variational Mode Decomposition optimized by Beluga Whale Optimization and Hilbert–Huang Transform (BWO–VMD–HHT) is proposed to solve the unclear feature of AE signal in UFSW due to the aqueous medium. UFSW experiments on Al alloy and carbon fiber reinforced thermoplastic (CFRTP) are carried out with AE signals measured. The time–frequency domain features of AE signals are extracted by BWO–VMD–HHT. The experimental results show that the main frequency of the AE signal is 22.5 kHz, and surface crack defects, shallow hole defects, and deep hole defects are accompanied by the transfer phenomena of different frequency components. Then, the feature vectors are built by frequency components in the BWO–VMD–HHT spectrum and reduced by principal component analysis, including 22.5 kHz, 24 kHz, 20.6 kHz, 18.4 kHz, 17.3 kHz, and 15.6 kHz. The feature vectors are divided into the train and test sets, and the welding defect prediction model (ResNet18-attention) is built by ResNet18 and trained by feature vectors. In the test set, the ResNet18-attention is compared with the BP, SVM, and RBF. Test results show that the precision of models has improved by at least 10%, which are trained by BWO–VMD–HHT features vector. Also, ResNet18-attention has achieved an average precision of 0.906 and recognizes the category of weld defect accurately, and this method can be applied to the defect monitoring of UFSW.

Machine Learning-based Fault Prediction and Diagnosis of Brushless Motors

Machine Learning-based Fault Prediction and Diagnosis of Brushless Motors

CfExplainer: Explainable just-in-time defect prediction based on counterfactuals

Just-in-time (JIT) defect prediction helps rationally allocate testing resources and reduce testing costs. However, most JIT defect prediction models lack explainability, which significantly affects their credibility. Recently, the local interpretable model-agnostic explanations (LIME) method has been used widely in model-explainable research, and many improved LIME-based methods have been proposed. However, problems with respect to explanation effectiveness and reliability remain, which seriously affects the practical use of LIME. To address this problem, CfExplainer, a local rule-based model-agnostic approach, is proposed. The approach first applies counterfactuals to generate synthetic instances. It then mines weighted class association rules based on synthetic instances, and it optimises the process of generating, ranking, pruning, and predicting the class association rules. Next, it employs the rules with the highest priority to explain the prediction results of the model. Experiments were conducted using the public datasets employed in related studies. Compared to other state-of-the-art methods, in terms of explanation effectiveness, CfExplainer's instance similarity improves by 26.5 %-31.2 %, and local model fittness improves by 2.0 %-3.5 %, 2.3 %-3 %, and 0.7 %-7.5 % on the AUC, F1-score, and Popt metrics, respectively. In terms of the reliability of the explanation, explanations that are 2.6 %-4.7 % more unique and 2.5 %-5.9 % more consistent with the actual characteristics of defect-introducing commits than other state-of-the-art methods. Thus, the explanations of the proposed approach can enhance the model credibility and help guide developers in fixing defects and reducing the risk of introducing them.

Photodiode-based porosity prediction in laser powder bed fusion considering inter-hatch and inter-layer effects

Laser powder bed fusion, while promising, faces hurdles in certifying fabricated parts due to cost and complexity, with in-process monitoring emerging as a potential solution. Existing models focus on predicting defects at a given location using the monitoring signals from solely that same location. Hence, these models treat each track or layer independently of the previous and subsequent ones, neglecting potential interdependencies. This study proposed an in-situ, photodiode-based monitoring approach considering inter-hatch and inter-layer effects on porosity formation - factors often overlooked in existing research. Two Ti-6Al-4 V cuboids (10×10×5 mm3) were built with optimized process parameters, with the melt pool continuously monitored at 20 kHz via a co-axially mounted photodiode. The monitoring system captured the integral radiation in the near-infrared spectrum within a field of view centered on the melt pool. The porosity is assessed by X-ray computed tomography (X-CT), serving as ground truth to build supervised machine learning (ML) models. This study considered physical phenomena occurring during the printing process, including remelting of lack of fusion pores by the subsequent layer, keyholes penetrating the current layer hence introducing pores in the layer below, and overlap between adjacent scan tracks. These considerations are critical for a holistic understanding of pore formation mechanisms. Photodiode signals and computed tomography volumes were cropped using windows of four sizes to test the model's pore localization capability. A machine learning model, specifically a Convolutional Neural Network (CNN) - Long Short-Term Memory (LSTM) network, was trained to predict porosities using these window sequences. The CNN extracted spatial features from photodiode signals, addressing inter-hatch effects, while the LSTM captured temporal dependencies across layers, addressing inter-layer effects. The results, with the Area Under the Receiver Operating Characteristic curve (AUC) of 0.91 for pores exceeding 8000 μm3 in volume and 100 μm2 in cross-sectional area, demonstrate the feasibility of the proposed model in detecting pores-level defects. This high defect prediction and positioning accuracy are essential for process control, providing real-time status of the region of interest and informing the controller of pore positions, thus facilitating intra-layer or inter-layer correction.

EffiMultiOrthoBearNet: An Efficient Lightweight Architecture for Bearing Fault Diagnosis

Amidst the advent of Industry 4.0 and the rapid advancements in smart manufacturing, the imperative for developing resource-efficient condition monitoring and fault prediction technologies tailored for industrial equipment in resource-limited settings has become increasingly evident. This study puts forward EffiMultiOrthoBearNet, an innovative, lightweight, deep learning model specifically designed for the accurate identification and classification of bearing faults. Central to EffiMultiOrthoBearNet’s architecture is the integration of multi-scale convolutional layers and orthogonal attention mechanisms—key innovations that significantly enhance the model’s performance. Leveraging advanced feature extraction capabilities, EffiMultiOrthoBearNet meticulously processes Continuous Wavelet Transform (CWT) images from the CWRU dataset, ensuring the precise delineation of essential bearing signal traits through its multi-scale and attention-enhanced mechanisms. Optimized for supreme operational efficiency in resource-deprived environments, EffiMultiOrthoBearNet achieves unmatched classification accuracy—up to 100% under ideal circumstances and consistently above 90% amidst significant noise and operational complexities. Demonstrating remarkable adaptability and efficiency, EffiMultiOrthoBearNet provides a pioneering and practical fault diagnosis solution for industrial machinery across a wide range of application scenarios, even under stringent resource limitations.

IRJIT: A simple, online, information retrieval approach for just-in-time software defect prediction

IRJIT: A simple, online, information retrieval approach for just-in-time software defect prediction

Unveiling the impact of unchanged modules across versions on the evaluation of within‐project defect prediction models

Unveiling the impact of unchanged modules across versions on the evaluation of within‐project defect prediction models

Research on the HHO improved BP neural network fault prediction algorithm for distribution networks based on weather factors

Abstract Weather factors have a substantial impact on the operation and maintenance of the distribution network, but the current system fault prediction platform mainly focuses on the operating characteristics of the system, that is, the internal parameters, and rarely considers the external parameters. Firstly, by studying the fault data of the distribution network in a city in northern China caused by weather factors, this paper obtains the main weather factors affecting the reliability of power supply in this area. Then, the Harris Hawks optimization (HHO) improved BP neural network algorithm is used to establish the main reliability evaluation models suitable for this region, and based on this, the fault probability of this region is predicted under the target weather. Finally, the prediction results are compared with the actual fault data caused by weather factors in this area. The results show that both the PSO-BP algorithm and HHO-BP neural network algorithm achieve better prediction accuracy than the BP neural network algorithm, and the HHO-BP algorithm has better convergence speed.

Physically Interpretable Wavelet-Guided Networks With Dynamic Frequency Decomposition for Machine Intelligence Fault Prediction

Physically Interpretable Wavelet-Guided Networks With Dynamic Frequency Decomposition for Machine Intelligence Fault Prediction

Multi-Objective Software Defect Prediction via Multi-Source Uncertain Information Fusion and Multi-Task Multi-View Learning

Multi-Objective Software Defect Prediction via Multi-Source Uncertain Information Fusion and Multi-Task Multi-View Learning

The impact of software metrics in NASA metric data program dataset modules for software defect prediction

The impact of software metrics in NASA metric data program dataset modules for software defect prediction