Early Fault Detection Research Articles

Early Fault Detection and Operator-Based MIMO Fault-Tolerant Temperature Control of Microreactor

A microreactor is a chemical reaction device that mixes liquids in a very narrow channel and continuously generates reactions. They are attracting attention as next-generation chemical reaction devices because of their ability to achieve small-scale and highly efficient reactions compared to the conventional badge method. However, the challenge is to design a control system that is tolerant of faults in some of the enormous number of sensors in order to achieve parallel production by numbering up. In a previous study, a simultaneous control system for two different temperatures was proposed in an experimental system that imitated the microreactor cooled by Peltier devices. In addition, a fault-tolerant control system for one area has also been proposed. However, the fault-tolerant control system could not be applied to the control system of two temperatures in the previous study. In this paper, we extend it to a two-input, two-output fault-tolerant control system. We also use a fault detection system that combines ChangeFinder, a time-series data analysis method, and One-Class SVM, an unsupervised learning method. Finally, the effectiveness of the proposed method is confirmed by experiments.

Deep learning-based anomaly detection using one-dimensional convolutional neural networks (1D CNN) in machine centers (MCT) and computer numerical control (CNC) machines

Computer numerical control (CNC) and machine center (MCT) machines are mechanical devices that manipulate different tools using computer programming as inputs. Predicting failures in CNC and MCT machines before their actual failure time is crucial to reduce maintenance costs and increase productivity. This study is centered around a novel deep learning-based model using a 1D convolutional neural network (CNN) for early fault detection in MCT machines. We collected sensor-based data from CNC/MCT machines and applied various preprocessing techniques to prepare the dataset. Our experimental results demonstrate that the 1D-CNN model achieves a higher accuracy of 91.57% compared to traditional machine learning classifiers and other deep learning models, including Random Forest (RF) at 89.71%, multi-layer perceptron (MLP) at 87.45%, XGBoost at 89.67%, logistic regression (LR) at 75.93%, support vector machine (SVM) at 75.96%, K-nearest neighbors (KNN) at 82.93%, decision tree at 88.36%, naïve Bayes at 68.31%, long short-term memory (LSTM) at 90.80%, and a hybrid 1D CNN + LSTM model at 88.51%. Moreover, our proposed 1D CNN model outperformed all other mentioned models in precision, recall, and F-1 scores, with 91.87%, 91.57%, and 91.63%, respectively. These findings highlight the efficacy of the 1D CNN model in providing optimal performance with an MCT machine’s dataset, making it particularly suitable for small manufacturing companies seeking to automate early fault detection and classification in CNC and MCT machines. This approach enhances productivity and aids in proactive maintenance and safety measures, demonstrating its potential to revolutionize the manufacturing industry.

In situ monitoring of defects in steel structures using a robot‐assisted ultrasonic inspection technique

AbstractIncidents in extreme environments can bring unprecedented consequences that would endanger the lives of many humans. Real‐time and early detection of cracks and defects in the steel used for the construction of industrial sites can bring many benefits to remote operators and site managers. Although different methods and systems have been proposed in the past, they are not suitable for real‐time fault detection or long‐term operation in harsh environments. Therefore, this paper proposes a low‐power robotic platform with a magnetic actuator mechanism which is capable of wireless inspection of steel structures using the ultrasonic method. The proposed magnetic motion uses the inertia force generated by the piston vibration and the difference in frictional force during movement. The paper evaluates the performance of the steel structure defect detection system from four different perspectives: sensing principle, wireless communication network, driving part, and power supply.

Deep learning-based proactive fault detection method for enhanced quadrotor safety

The early detection of faults in advanced technological systems is imperative for ensuring operational reliability and safety. While there is a growing interest in using artificial intelligence for fault detection, current methodologies often exhibit limitations in utilizing comprehensive system information and sensor data. Hidden faults within collected data further highlight the need for advanced analysis techniques. This study introduces a novel deep learning-based framework designed to predict faults and extract insights from complex system datasets. The model, consisting of LSTM-autoencoder and BiLSTM classification components, effectively reduces feature dimensions, thereby enhancing fault detection accuracy. The autoencoder’s latent layer identifies prominent features across various dimensions, while BiLSTM classification conducts bidirectional analysis using these features from both healthy and faulty states, facilitating early fault detection. Experimental results demonstrate the model’s efficacy, achieving an accuracy of 79.48% in predicting incipient faults 30 seconds before a serious malfunction occurs. This underscores the significant potential of the proposed framework in enhancing operational safety and reliability in complex systems. Moreover, the study emphasizes the importance of leveraging comprehensive data and advanced analysis techniques for early fault detection.

Void detection in structural adhesive joints using a k-Nearest Neighbors model with features from Electromechanical Impedance Spectroscopy

Electromechanical Impedance Spectroscopy (EMIS) is a promising Structural Health Monitoring (SHM) method which allows the early detection of defects by analyzing the structure response to an AC electrical signal swept through a range of high frequencies. In this work, EMIS measurements of pristine and damaged adhesive joints were performed, and features were extracted from the experimental measurements. These features were inputted to a k-Nearest Neighbors (kNN) model for damage detection. Results show that only one type of features is enough for damage detection. Furthermore, the use of the Manhattan Distance in the kNN enables a better classification.

Efficient Estimation of Synthetic Indicators for the Assessment of Nonlinear Systems Quality

The availability of synthetic indicators of the degree and type of nonlinearity in systems is used in various fields to assess system quality or to highlight possible malfunctions. Different distortion or damage indexes are synthetic measures designed (and standardized) to evaluate the frequency trend of specific aspects resulting from the nonlinear behavior of the system under consideration. The different measures of deviation from linear behavior quantitatively consider the system and its nonlinearity characteristics; they were defined according to practically feasible measurement methodologies and the various aspects of the system’s nonlinearity that needed to be highlighted. In parallel, techniques for representing and modeling nonlinear systems have been defined, capable of describing the system in a more general way, attempting to capture its input–output characteristics by varying the level of stress to which the system is subjected. Numerous modeling techniques have been proposed, aimed at representing the nonlinear behavior of physical devices. In this paper, after an extensive description of the Hammerstein model identification technique based on swept sinusoidal signals, we show how the nonlinear model of the system can be used to obtain accurate estimates of the parameter aimed at describing the nonlinearity characteristics of the system. This extensive description makes it possible to point out that the same Hammerstein model can be obtained not only from a single type of excitation, but it is shown that the identification technique can be extended to input signals of different types. The description of the method also makes clear the motivation behind the introduction of the proposed original technique for estimating, from a single measurement, the model parameters of the nonlinear system—and from these the synthetic estimators—relative to multiple values of the input signal amplitude, thus enabling a considerable increase in the estimation efficiency of these parameters. The proposed technique is verified with both synthetic and laboratory experiments, demonstrating the effectiveness of the method in evaluating nonlinear system parameters, distortion estimates, and parameters defined for an early detection of defects of the structure.

Time Frequency Analysis Based Fault Detection in PV Array Using Scaling Basis Chirplet Transform

ABSTRACTPhotovoltaic (PV) arrays have gained significant attention in recent years due to their potential for sustainable energy generation. However, the reliable operation of PV arrays is crucial for optimal performance and long‐term durability. The early detection of faults in PV arrays is vital to prevent further damage, improve maintenance strategies, and ensure uninterrupted energy production. In this study, we propose a novel fault detection method based on Time Frequency Analysis (TFA) using the Scaling Basis Chirplet Transform (SBCT). In this proposed fault detection method, PV array signal is decomposed into a set of chirplets using the SBCT. The chirplets represent localized time‐frequency components that can capture the dynamic behavior of the PV array signal. To evaluate the effectiveness of the proposed method, extensive simulations and experiments are conducted using real‐world PV array data. The SBCT with combination of various machine learning algorithms is proposed to detect faults in PV array. SBCT in combination with Support Vector Machine, Decision Tree, Random Forest, and ANN classifiers are able to detect faults in PV array with 99%, 98.5%, 99.2%, and 99.5% accuracies in no shading condition and 88%, 85%, 89%, and 89.5% accuracies in severe shading condition. The proposed method achieves high accuracy and robustness in detecting various types of faults in PV arrays, even in the presence of noise and uncertainties. The proposed fault detection method using TFA based on the SBCT offers a promising solution for efficient and reliable fault detection in PV arrays. It enables early fault detection, facilitating timely maintenance and minimizing energy losses. The proposed approach can contribute to enhancing the overall performance, reliability, and lifespan of PV arrays, thereby advancing the adoption of renewable energy sources and promoting sustainable development.

Defective Pennywort Leaf Detection Using Machine Vision and Mask R-CNN Model

Demand and market value for pennywort largely depend on the quality of the leaves, which can be affected by various ambient environment or fertigation variables during cultivation. Although early detection of defects in pennywort leaves would enable growers to take quick action, conventional manual detection is laborious and time consuming as well as subjective. Therefore, the objective of this study was to develop an automatic leaf defect detection algorithm for pennywort plants grown under controlled environment conditions, using machine vision and deep learning techniques. Leaf images were captured from pennywort plants grown in an ebb-and-flow hydroponic system under fluorescent light conditions in a controlled plant factory environment. Physically or biologically damaged leaves (e.g., curled, creased, discolored, misshapen, or brown spotted) were classified as defective leaves. Images were annotated using an online tool, and Mask R-CNN models were implemented with the integrated attention mechanisms, convolutional block attention module (CBAM) and coordinate attention (CA) and compared for improved image feature extraction. Transfer learning was employed to train the model with a smaller dataset, effectively reducing processing time. The improved models demonstrated significant advancements in accuracy and precision, with the CA-augmented model achieving the highest metrics, including a mean average precision (mAP) of 0.931 and an accuracy of 0.937. These enhancements enabled more precise localization and classification of leaf defects, outperforming the baseline Mask R-CNN model in complex visual recognition tasks. The final model was robust, effectively distinguishing defective leaves in challenging scenarios, making it highly suitable for applications in precision agriculture. Future research can build on this modeling framework, exploring additional variables to identify specific leaf abnormalities at earlier growth stages, which is crucial for production quality assurance.

High-accuracy gearbox fault detection using deep learning on vibrational data

Abstract In the face of escalating demands for reliability in industrial machinery, this study introduces an advanced deep-learning model aimed at the early detection of faults in rotating gear systems. Addressing the need for timely fault diagnosis to prevent operational disruptions and financial setbacks, our work utilizes a novel neural network approach applied to vibrational data from Kaggle’s Gearbox Fault Diagnosis Dataset. The methodology involves data preprocessing steps, including normalization and one-hot encoding, followed by training a sequential neural network with multiple dense layers and dropout for regularization. The model, trained using the Adam optimizer and evaluated over 50 epochs, significantly outperforms traditional machine learning techniques, achieving a remarkable 98.63% accuracy in distinguishing between healthy and compromised gear conditions. This research marks a significant stride in predictive maintenance, providing a robust foundation for future development toward prognostic health management systems that anticipate maintenance needs and ensure uninterrupted industrial productivity.

Prediction of spatter-related defects in metal laser powder bed fusion by analytical and machine learning modelling applied to off-axis long-exposure monitoring

Laser powder bed fusion of metals is increasingly used for fabricating complex parts requiring good mechanical properties. Simultaneously, researchers in the field are intensifying the efforts to reduce defects, such as internal porosities, which hinder a wider industrial adoption of this technology, urging process monitoring to a pivotal role in defect identification and mitigation. Therefore, understanding the correlation between in-process monitoring signals and post-process actual defects is fundamental to taking informed decisions and potential corrective actions during the process.This work focuses on developing models to predict spatter-related defects from specific process signatures detected through off-axis long-exposure imaging. Layer-wise images were properly aligned with corresponding cross-sections from tomographic reconstructions to investigate the relationship between spatter-related signatures and actual defects measured by X-ray computed tomography. This relationship was used as a knowledge basis to develop an analytical image-processing approach and a machine learning-based methodology, which were then compared in terms of their correlation performances. The advantages and limitations of both methods are discussed in the paper.Both approaches led to promising results in the prediction of lack-of-fusion defects caused by spatters, with the machine learning approach showing a prediction accuracy in the order of 90% for defects with equivalent diameter above 90µm, while the analytical model needed equivalent diameters larger than 130µm to reach a prediction accuracy in the order of 80%. Furthermore, the machine learning method led to strong results regarding early defect detection, with most of the investigated defects properly predicted by analysing two consecutive layers after the signature detection.

CRDS‐based measurement of CO/CO2 concentration ratios for assessing transformer insulation aging

AbstractA gas analyzer has been developed using cavity ring‐down spectroscopy (CRDS) technology, designed to simultaneously measure the concentrations of CO2 and CO. These gases are critical indicators of transformer insulation degradation. The analyzer covers a CO2 concentration range from a few ppm to several thousand ppm and can measure CO/CO2 concentration ratios from 0.076 to 0.8. The selected absorption lines for CO and CO2 are centered at 6337.99 and 6338.59 cm−1, respectively. The two candidate lines are proximate to each other and nonoverlapping. The experimental results indicate that the system accurately fits the measured and calculated signals, enabling concentration measurements at the ppm level. This confirms its ability to measure the gas concentrations and ratios critical for assessing the condition of transformer insulation. This CRDS‐based system offers a reliable and sensitive method for early detection of potential transformer faults.

Enhancing efficiency and quality control: The impact of Digital Twins in drinking water networks.

This paper showcases the successful development and implementation of two Digital Twin prototypes within the Lab Digital Twins project, designed to enhance the efficiency and quality control of Aigües de Barcelona's drinking water network. The first prototype focuses on asset management, using (near) real-time data and statistical models, and achieving a 70% success rate in predicting pump station failures 137 days in advance. The second prototype addresses water quality monitoring, leveraging machine learning to accurately forecast trihalomethane levels at key points in the distribution system, and enabling proactive water quality management strategies, ensuring compliance with stringent safety standards and safeguarding public health. The paper details the methodology of both prototypes, highlighting their potential to revolutionize water network management. PRACTITIONER POINTS: Digital representation of assets and processes in the drinking water treatment network Early fault detection in assets, and predictions of trihalomethane formation in the drinking water distribution network Reduction on monitoring time and incident response for target assets by means of Digital Twins Improvement in visualization, prediction, and proactive measures for asset management and water quality control Contribution to the growing knowledge on Digital Twins and their potential to revolutionize water network operations.

Alarm management approach for supervision of Green Hydrogen Plants

Amid the increasing significance of renewable energy sources, Green Hydrogen Plants (GHPs) have emerged as pivotal contributors to sustainable energy solutions. However, efficient and reliable alarm management in such complex systems remains a significant challenge. This paper presents a novel methodology called V-nets-based alarm management (VBAM), designed to improve supervision by addressing the intricacies of discrete event management in industrial applications such as GHPs. VBAM offers a powerful formalism that integrates visual modeling and temporal patterns, enabling the precise detection and handling of alarms. The proposed methodology is applied to a case study in a GHP, where critical operational parameters are continuously monitored. By analyzing discrete events and their temporal patterns, V-nets facilitate early fault detection, minimize false positives, and optimize alarm response. The theoretical application of VBAM demonstrates its efficacy in improving system safety, reducing downtime, and enhancing overall operational efficiency within GHPs. The contributions of this work to the state of the art include the development of a comprehensive VBAM methodology tailored to GHPs, as well as the theoretical and practical demonstration of its potential impact on alarm management within GHP operations. The outcomes from the experiments showcase the adaptability and effectiveness of VBAM in addressing the complexities of alarm management in GHPs, thereby contributing to enhanced safety, efficiency, and resilience in the operation of GHPs.

IoT Enabled Motor Drive Vehicle for the Early Fault Detection in New EnergyConservation

An IoT-enabled motor drive vehicle integrates Internet of Things (IoT) technology with traditional vehicle systems to enhance control, monitoring, and automation. Sensors and connected devices within the vehicle collect real-time data on parameters such as speed, battery status, motor performance, and environmental conditions. This data is transmitted to cloud-based platforms for analysis, enabling remote diagnostics, predictive maintenance, and optimization of vehicle performance. IoT integration also facilitates features like vehicle tracking, smart navigation, and user-specific adjustments, improving overall efficiency, safety, and user experience. This paper investigates the utilization of IoT enabled Programmable Logic Controller (PLC) technology to enhance fault detection in new energy vehicle (NEV) motor drive systems. With the increasing adoption of electric vehicles, ensuring the safety and reliability of motor drive systems becomes paramount. The study begins with a comprehensive review of existing literature, examining various fault detection methodologies and technologies. Subsequently, simulation analyses are conducted to evaluate the performance of IOT enabled PLC-based fault detection algorithms under different operating conditions. This paper presents the numerical results of fault detection in new energy vehicle (NEV) motor drive systems using Programmable Logic Controller (IOT enabled PLC) technology. Through comprehensive simulations and experimental validations, the IOT enabled PLC-based fault detection algorithms achieved an average detection accuracy of 93% across various fault scenarios. The response time of the fault detection system.

DCW-YOLO: An Improved Method for Surface Damage Detection of Wind Turbine Blades

Wind turbine blades (WTBs) are prone to damage from their working environment, including surface peeling and cracks. Early and effective detection of surface defects on WTBs can avoid complex and costly repairs and serious safety hazards. Traditional object detection methods have disadvantages of insufficient detection capabilities, extended model inference times, low recognition accuracy for small objects, and elongated strip defects within WTB datasets. In light of these challenges, a novel model named DCW-YOLO for surface damage detection of WTBs is proposed in this research, which leverages image data collected by unmanned aerial vehicles (UAVs) and the YOLOv8 algorithm for image analysis. Firstly, Dynamic Separable Convolution (DSConv) is introduced into the C2f module of YOLOv8, allowing the model to more effectively focus on the geometric structural details associated with damage on WTBs. Secondly, the upsampling method is replaced with the content-aware reassembly of features (CARAFE), which significantly minimizes the degradation of image characteristics throughout the upsampling process and boosts the network’s ability to extract features. Finally, the loss function is substituted with the WIoU (Wise-IoU) strategy. This strategy allows for a more accurate regression of the target bounding boxes and helps to improve the reliability in the localization of WTBs damages, especially for low-quality examples. This model demonstrates a notable superiority in surface damage detection of WTBs compared to the original YOLOv8n and has achieved a substantial improvement in the mAP@0.5 metric, rising from 91.4% to 93.8%. Furthermore, in the more rigorous mAP@0.5–0.95 metric, it has also seen an increase from 68.9% to 71.2%.

Drone-based inspection of wind turbine blades: a comparative study of deep learning models

Maintaining wind turbine blades is a challenging task, often marked by high costs, safety risks, time inefficiency, and the possibility of incorrect diagnosis. A promising approach to support preventive maintenance involves the use of drones and deep learning for inspection and early fault detection. This paper offers a comparative study of five advanced deep learning models: Residual Networks (ResNet), Inception Networks (InceptionV3), YOLO (You Only Look Once), EfficientNet, and Vision Transformers (ViTs) applied to the DTU Drone Inspection Images of Wind Turbine dataset. The objective is to determine the most effective model for detecting defects in wind turbine blades, which is critical for ensuring the efficiency and safety of wind energy systems. The models were assessed using key performance metrics, such as accuracy, precision, recall, F1-score, and inference time. EfficientNet emerged as the top performer with the highest accuracy and balanced efficiency, while YOLO demonstrated the fastest inference time, making it ideal for real-time applications. ResNet and InceptionV3 also performed well, particularly in detecting subtle defects, whereas ViTs showed strong capabilities in capturing complex global features despite longer processing times. The findings provide valuable insights for selecting appropriate deep learning models in drone-based wind turbine inspections, contributing to more effective and reliable maintenance practices.

Structural damage detection of floating offshore wind turbine blades based on Conv1d-GRU-MHA network

Due to the global commitment to mitigate climate warming by replacing fossil fuels, the global wind power installed capacity continues to increase. The reliability of wind turbines is a vital factor in ensuring their safety and profitability. Early fault detection can significantly reduce the maintenance costs of wind farms. This paper constructs a Conv1d-GRU-MHA model for detecting blade structural damage in floating offshore wind turbines (FOWTs) operating under complex conditions. This model combines a one-dimensional convolutional neural network (Conv1d), gated recurrent units (GRU), and multi-head attention mechanism (MHA) to provide accurate detection of blade structural damage. This amalgamation enables the model to comprehend diverse scales of sequence data, effectively capturing intricate patterns and abstract features. The NREL OpenFAST software was used to model a 5 MW wind turbine, where structural damage was introduced on the blades. Acceleration data was collected from blades and tower in different directions and under different wind turbulence intensities (WTI). The Conv1d-GRU-MHA network predicts blade health with an accuracy of up to 97.58 % under the 5 % turbulence level background, with both precision and recall being superior to the comparative models.

Rotating machinery early fault detection integrating variational mode decomposition and multiscale singular value decomposition

Abstract Security and reliability are important issues that must be paid attention to during the operation of rotating machinery. If defects can be found in the early stage, there will be enough time to take maintenance measures and realize the stable operation of equipment. However, the presence of noise, shaft rotation signals, gear meshing signals, and other interfering factors often obfuscate fault signals, rendering the early detection of defects an arduous undertaking. Against this backdrop, this study presents an advanced approach for early defect detection, integrating the virtues of variational mode decomposition (VMD) and multiscale singular value decomposition (MSVD). Initially, a novel evaluation index is constructed by combining envelope entropy and envelope spectrum sparsity. Based on this a method is proposed to adaptively determine the critical parameters of VMD, enabling the adaptive decomposition of vibration signals into a series of modal components. The optimal sensitive components are then discerned utilizing the characteristic frequency intensity coefficient index. Subsequently, to address the limitations of single VMD methods in effectively suppressing low-frequency noise, the MSVD method is proposed for effective noise reduction, which reconstructs the signal after SVD of the signal within each segment through the operation of successive signal segmentation. Ultimately, envelope spectrum analysis is conducted on the reconstructed signal, facilitating the precise extraction of fault characteristic frequency information and enabling early fault identification. The efficacy of this novel methodology is evaluated through simulations and actual vibration signals, successfully discerning early faults afflicting rotating machinery.

Predictive framework for remaining useful life of roller bearings: Utilizing fractional generalized Pareto degradation model in performance evaluation

Research on predictive frameworks for the Remaining Useful Life (RUL) of mechanical systems is limited. This study proposes a comprehensive RUL prediction framework for roller bearings, integrating early failure assessment, adaptive failure threshold determination, and an adaptive drift fractional-order Pareto degradation model. To tackle data insufficiency, multi-sensor fusion combines time-domain, frequency-domain, and time–frequency features. The framework normalizes the health indicator (HI) using Mahalanobis distance and a sigmoid function, and employs the MD-CUSUM technique for early fault detection. Dynamic threshold updating is achieved through BOX-COX transformation and Chebyshev inequality, establishing confidence intervals. The model demonstrates significant results: lowest RMSE of 5.4267, MAE of 3.7857, highest SOR of 0.90936, HD of 0.93543, PICP of 57.143%, and the narrowest MPIW of 9.45, showing enhanced accuracy and reduced uncertainty. Validation with the XJTU-SY bearing dataset confirms improved performance.

Small-sample health indicator construction of rolling bearings with wavelet scattering network: An empirical study from frequency perspective

As a critical issue of diagnostics and health management (PHM), health indicator (HI) construction aims to describe the degradation process of bearings and can provide essential support of domain knowledge for early fault detection and remaining useful life prediction. In recent years, various deep neural networks, with end-to-end modeling capability, have been successfully applied to the HI construction for rolling bearings. In small-sample environment, however, the degradation features would not be extracted well by deep learning techniques, which may raise insufficient tendency and monotonicity characteristics in the obtained HI sequence. To address this concern, this paper proposes a HI construction method based on wavelet scattering network (WSN) and makes an empirical evaluation from frequency perspective. First, degradation features in different frequency bands are extracted from vibration signals by using WSN to expand the feature space with different scales and orientations. Second, the frequency band with the optimal scale and orientation parameters is selected by calculating the dynamic time wrapping (DTW) distance between the feature sequences of each frequency band and the root mean square (RMS) sequence. With the feature subset from the determined frequency band, the HI sequence can be built by means of principal component analysis (PCA). Experimental results on the IEEE PHM Challenge 2012 bearing dataset show that the proposed method can work well with only a small amount of bearing whole-life data in obtaining the HI sequences with high monotonicity and correlation characteristics. More interestingly, the critical frequency band whose information supports decisively the HI construction can be clarified, raising interpretability in a frequency sense and enhancing the credibility of the obtained HI sequence as well.