Applied Sciences

Editorial

Jump to: Research, Review

4 pages, 657 KiB

Open AccessEditorial

Artificial Intelligence in Fault Diagnosis and Signal Processing

by Andres Bustillo and Athanasios Karlis

Appl. Sci. 2025, 15(7), 3922; https://doi.org/10.3390/app15073922 - 3 Apr 2025

Viewed by 445

Abstract

Industry 4 [...] Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

Research

Jump to: Editorial, Review

18 pages, 3840 KiB

Open AccessArticle

An Enhanced Contrastive Ensemble Learning Method for Anomaly Sound Detection

by Jingneng Liao, Fei Yang and Xiaoqing Lu

Appl. Sci. 2025, 15(3), 1624; https://doi.org/10.3390/app15031624 - 5 Feb 2025

Viewed by 1441

Abstract

This paper proposes an enhanced contrastive ensemble learning method for anomaly sound detection. The proposed method achieves approximately 6% in the AUC metric in some categories and achieves state-of-the-art performance among self-supervised models on multiple benchmark datasets. The proposed method is effective in [...] Read more.

This paper proposes an enhanced contrastive ensemble learning method for anomaly sound detection. The proposed method achieves approximately 6% in the AUC metric in some categories and achieves state-of-the-art performance among self-supervised models on multiple benchmark datasets. The proposed method is effective in automatically monitoring the operating conditions of the production equipment by detecting the sounds emitted by the machine, to provide an early warning of potential production accidents. This method can significantly reduce industrial monitoring costs and increase monitoring efficiency to improve manufacturing facility productivity effectively. Existing detection methods face challenges with data imbalance caused by the scarcity of anomalous samples, leading to performance degradation. This paper proposes an enhanced data augmentation method that improves model robustness by allowing the data to retain the original features while adding noise close to the real environment through a simple operation. Secondly, model feature extraction is enhanced by using channel attention to fuse time-frequency features. Thirdly, this paper proposes a simple anomaly sample generation method, which can automatically generate real pseudo anomaly samples to help the model gain anomaly detection capability and reduce the impact of data imbalance. Finally, this paper proposes a statistical-based bias compensation that further mitigates the impact of data imbalance by distributing samples through statistical induction. Experimental verification confirms that these changes enhance anomalous sound detection capability. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

15 pages, 2797 KiB

Open AccessArticle

DVCW-YOLO for Printed Circuit Board Surface Defect Detection

by Pei Shi, Yuyang Zhang, Yunqin Cao, Jiadong Sun, Deji Chen and Liang Kuang

Appl. Sci. 2025, 15(1), 327; https://doi.org/10.3390/app15010327 - 31 Dec 2024

Viewed by 1053

Abstract

The accurate and efficient detection of printed circuit board (PCB) surface defects is crucial to the electronic information manufacturing industry. However, current approaches to PCB defect detection face challenges, including large model sizes and difficulties in balancing detection accuracy with speed. To address [...] Read more.

The accurate and efficient detection of printed circuit board (PCB) surface defects is crucial to the electronic information manufacturing industry. However, current approaches to PCB defect detection face challenges, including large model sizes and difficulties in balancing detection accuracy with speed. To address these challenges, this paper proposes a novel PCB surface defect detection algorithm, named DVCW-YOLO. First, all standard convolutions in the backbone and neck networks of YOLOv8n are replaced with lightweight DWConv convolutions. In addition, a self-designed C2fCBAM module is introduced to the backbone network for extracting features. Next, within the neck structure, the C2f module is substituted with the more lightweight VOVGSCSP module, thereby reducing model redundancy, simplifying model complexity, and enhancing detection speed. By enhancing prominent features and suppressing less important ones, this modification allows the model to better focus on key regions, thereby improving feature representation capabilities. Finally, the WIoU loss function is implemented to replace the traditional CIoU function in YOLOv8n. This adjustment addresses issues related to low generalization and poor detection performance for small objects or complex backgrounds, while also mitigating the impact of low-quality or extreme samples on model accuracy. Experimental results demonstrate that the DVCW-YOLO model achieves a mean average precision (mAP) of 99.3% and a detection speed of 43.3 frames per second (FPS), which represent improvements of 4% and 4.08%, respectively, over the YOLOv8n model. These results confirm that the proposed model meets the real-time PCB defect detection requirements of small and medium-sized enterprises. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

13 pages, 5379 KiB

Open AccessArticle

Application of Machine Learning Algorithms in Real-Time Monitoring of Conveyor Belt Damage

by Damian Bzinkowski, Miroslaw Rucki, Leszek Chalko, Arturas Kilikevicius, Jonas Matijosius, Lenka Cepova and Tomasz Ryba

Appl. Sci. 2024, 14(22), 10464; https://doi.org/10.3390/app142210464 - 13 Nov 2024

Cited by 1 | Viewed by 1868

Abstract

This paper is devoted to the real-time monitoring of close transportation devices, namely, belt conveyors. It presents a novel measurement system based on the linear strain gauges placed on the tail pulley surface. These gauges enable the monitoring and continuous collection and processing [...] Read more.

This paper is devoted to the real-time monitoring of close transportation devices, namely, belt conveyors. It presents a novel measurement system based on the linear strain gauges placed on the tail pulley surface. These gauges enable the monitoring and continuous collection and processing of data related to the process. An initial assessment of the machine learning application to the load identification was made. Among the tested algorithms that utilized machine learning, some exhibited a classification accuracy as high as 100% when identifying the load placed on the moving belt. Similarly, identification of the preset damage was possible using machine learning algorithms, demonstrating the feasibility of the system for fault diagnosis and predictive maintenance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

20 pages, 3150 KiB

Open AccessArticle

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

by Yuma Morita and Mingcong Deng

Appl. Sci. 2024, 14(21), 9907; https://doi.org/10.3390/app14219907 - 29 Oct 2024

Viewed by 933

Abstract

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 [...] Read more.

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. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

17 pages, 3111 KiB

Open AccessArticle

Transformer-Based High-Speed Train Axle Temperature Monitoring and Alarm System for Enhanced Safety and Performance

by Wanyi Li, Kun Xie, Jinbai Zou, Kai Huang, Fan Mu and Liyu Chen

Appl. Sci. 2024, 14(19), 8643; https://doi.org/10.3390/app14198643 - 25 Sep 2024

Viewed by 1128

Abstract

As the fleet of high-speed rail vehicles expands, ensuring train safety is of the utmost importance, emphasizing the critical need to enhance the precision of axel temperature warning systems. Yet, the limited availability of data on the unique features of high thermal axis [...] Read more.

As the fleet of high-speed rail vehicles expands, ensuring train safety is of the utmost importance, emphasizing the critical need to enhance the precision of axel temperature warning systems. Yet, the limited availability of data on the unique features of high thermal axis temperature conditions in railway systems hinders the optimal performance of intelligent algorithms in alarm detection models. To address these challenges, this study introduces a novel dynamic principal component analysis preprocessing technique for tolerance temperature data to effectively manage missing data and outliers. Furthermore, a customized generative adversarial network is devised to generate distinct data related to high thermal axis temperature, focusing on optimizing the network’s objective functions and distinctions to bolster the efficiency and diversity of the generated data. Finally, an integrated model with an optimized transformer module is established to accurately classify alarm levels, provide a comprehensive solution to pressing train safety issues, and, in a timely manner, notify drivers and maintenance departments (DEPOs) of high-temperature warnings. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

11 pages, 3974 KiB

Open AccessArticle

Fault Feature Extraction Using L-Kurtosis and Minimum Entropy-Based Signal Demodulation

by Surinder Kumar, Sumika Chauhan, Govind Vashishtha, Sunil Kumar and Rajesh Kumar

Appl. Sci. 2024, 14(18), 8342; https://doi.org/10.3390/app14188342 - 16 Sep 2024

Viewed by 1185

Abstract

The health of mechanical components can be assessed by analyzing the vibration and acoustic signals they produce. These signals contain valuable information about the component’s condition, often encoded within specific frequency bands. However, extracting this information is challenging due to noise contamination from [...] Read more.

The health of mechanical components can be assessed by analyzing the vibration and acoustic signals they produce. These signals contain valuable information about the component’s condition, often encoded within specific frequency bands. However, extracting this information is challenging due to noise contamination from various sources. Narrow-band amplitude demodulation presents a robust technique for isolating fault-related information within the signal. This work proposes a novel approach based on cluster-based segmentation for demodulating the signal and extracting the frequency band of interest. The segmentation process leverages the criteria of maximum L-kurtosis and minimum entropy. L-kurtosis maximizes impulsiveness in the signal, while minimum entropy signifies a low degree of randomness and high cyclo-stationarity, and both characteristics are crucial for identifying the desired frequency band. Simulations and experimental tests using vibration signals from different gears demonstrate the effectiveness of this technique. The processed envelope of the signal exhibits distinct improvements, highlighting the ability to accurately extract the fault-related information embedded within the complex noise-ridden signals. This approach offers a promising solution for accurate and efficient fault diagnosis in mechanical systems, contributing to enhanced reliability and reduced downtime. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

17 pages, 2647 KiB

Open AccessArticle

Machine Learning Use Cases in the Frequency Symbolic Method of Linear Periodically Time-Variable Circuits Analysis

by Yuriy Shapovalov, Spartak Mankovskyy, Dariya Bachyk, Anna Piwowar, Łukasz Chruszczyk and Damian Grzechca

Appl. Sci. 2024, 14(17), 7926; https://doi.org/10.3390/app14177926 - 5 Sep 2024

Viewed by 885

Abstract

This manuscript presents an analysis of machine learning (ML) usage in the Frequency Symbolic Method (FSM) to enhance the diagnosis of faults in parametric circuit analysis and optimization, with a particular focus on Linear Periodically Time-Variable (LPTV) systems. We put forth a few [...] Read more.

This manuscript presents an analysis of machine learning (ML) usage in the Frequency Symbolic Method (FSM) to enhance the diagnosis of faults in parametric circuit analysis and optimization, with a particular focus on Linear Periodically Time-Variable (LPTV) systems. We put forth a few ML-based approaches for fault diagnosis (including anomaly detection), invisible feature detection, and the prediction of FSM output. These methodologies concentrate on identifying and diagnosing faults by evaluating particular ML techniques, extracting pertinent features, and determining the desired diagnostic outputs. The use cases of ML application considered in this paper demonstrate that machine learning can enhance fault detection and diagnosis, reduce human errors and identify previously unnoticed anomalies within the FSM framework. ML has never been used in FSM before, so the key aim of this paper is to consider possible use cases of AI application in FSM. Additionally, feature extraction, required as an input stage for the ML model, is proposed based on FSM peculiarities. This work can be considered a study of ML application in FSM. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

26 pages, 11819 KiB

Open AccessArticle

CNN-Based Damage Identification of Submerged Structure-Foundation System Using Vibration Data

by Ngoc-Lan Pham, Quoc-Bao Ta and Jeong-Tae Kim

Appl. Sci. 2024, 14(17), 7508; https://doi.org/10.3390/app14177508 - 25 Aug 2024

Cited by 2 | Viewed by 1087

Abstract

This study presents a convolutional neural network (CNN) deep learning approach for identifying damage in submerged structure-foundation systems using vibration data. Firstly, foundation damage in a lab-scale caisson-foundation system is simulated to measure time-history responses. Singular value decomposition (SVD) responses are derived from [...] Read more.

This study presents a convolutional neural network (CNN) deep learning approach for identifying damage in submerged structure-foundation systems using vibration data. Firstly, foundation damage in a lab-scale caisson-foundation system is simulated to measure time-history responses. Singular value decomposition (SVD) responses are derived from the time-history responses. Secondly, the 1-D CNN deep learning model is trained using both the time-history responses and SVD responses. Finally, the trained CNN models are implemented to evaluate the foundation damage under conditions of noise contamination and partially untrained data. The experimental results demonstrate the effectiveness of CNN models for damage identification and highlight the comparative strengths of time-history and SVD data. The CNN model trained using SVD data outperforms the other model when under noise contamination conditions, while the CNN model trained using time-history data maintains better accuracy in partially untrained data conditions. Integrating both types of data enhances the accuracy of damage classification. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

18 pages, 1998 KiB

Open AccessArticle

Engine Fault Detection by Sound Analysis and Machine Learning

by Ferit Akbalık, Abdulnasır Yıldız, Ömer Faruk Ertuğrul and Hasan Zan

Appl. Sci. 2024, 14(15), 6532; https://doi.org/10.3390/app14156532 - 26 Jul 2024

Cited by 3 | Viewed by 5663

Abstract

Traditional vehicle fault diagnosis methods rely heavily on the expertise of mechanics or diagnostic tools available at service centers, which can be costly, time-consuming, and may not always provide accurate results. This study presents a comprehensive vehicle fault diagnosis framework, which utilized Mel-Frequency [...] Read more.

Traditional vehicle fault diagnosis methods rely heavily on the expertise of mechanics or diagnostic tools available at service centers, which can be costly, time-consuming, and may not always provide accurate results. This study presents a comprehensive vehicle fault diagnosis framework, which utilized Mel-Frequency Cepstral Coefficients (MFCCs), Discrete Wavelet Transform (DWT)-based features, and the Extreme Learning Machine (ELM) classifier. To address the limitations of previous works, the proposed framework leverages a large, diverse dataset encompassing various vehicle models and real-world operating conditions. Significantly improved robustness and generalizability of the fault diagnosis system were achieved. The results of the experiments demonstrate the superiority of the MFCC-based features combined with the ELM classifier, achieving the highest performance metrics in terms of accuracy, precision, recall, F1-score, macro F1-score, and weighted F1-score, which are 92.17%, 92.24%, 92.22%, 92.10%, and 92.06%, respectively. Slightly lower performance was obtained while employing the DWT-based features compared to employing MFCC-based features. Additionally, frequency analysis was conducted to identify specific frequency bins, which are the most indicative of different fault types in providing valuable guidance for future diagnostic efforts. Overall, the proposed framework provides a reliable and practical solution for accurate vehicle fault detection, paving the way for future advancements in automotive diagnostics. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

18 pages, 13548 KiB

Open AccessArticle

Superficial Defect Detection for Concrete Bridges Using YOLOv8 with Attention Mechanism and Deformation Convolution

by Tijun Li, Gang Liu and Shuaishuai Tan

Appl. Sci. 2024, 14(13), 5497; https://doi.org/10.3390/app14135497 - 25 Jun 2024

Cited by 2 | Viewed by 1688

Abstract

The accuracy of detecting superficial bridge defects using the deep neural network approach decreases significantly under light variation and weak texture conditions. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. [...] Read more.

The accuracy of detecting superficial bridge defects using the deep neural network approach decreases significantly under light variation and weak texture conditions. To address these issues, an enhanced intelligent detection method based on the YOLOv8 deep neural network is proposed in this study. Firstly, multi-branch coordinate attention (MBCA) is proposed to improve the accuracy of coordinate positioning by introducing a global perception module in coordinate attention mechanism. Furthermore, a deformable convolution based on MBCA is developed to improve the adaptability for complex feature shapes. Lastly, the deformable convolutional network attention YOLO (DCNA-YOLO) detection algorithm is formed by replacing the deep C2F structure in the YOLOv8 architecture with a deformable convolution. A supervised dataset consisting of 4794 bridge surface damage images is employed to verify the proposed method, and the results show that it achieves improvements of 2.0% and 3.4% in mAP and R. Meanwhile, the model complexity decreases by 1.2G, increasing the detection speed by 3.5/f·s⁻¹. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

14 pages, 3052 KiB

Open AccessArticle

Time Series Feature Selection Method Based on Mutual Information

by Lin Huang, Xingqiang Zhou, Lianhui Shi and Li Gong

Appl. Sci. 2024, 14(5), 1960; https://doi.org/10.3390/app14051960 - 28 Feb 2024

Cited by 5 | Viewed by 5954

Abstract

Time series data have characteristics such as high dimensionality, excessive noise, data imbalance, etc. In the data preprocessing process, feature selection plays an important role in the quantitative analysis of multidimensional time series data. Aiming at the problem of feature selection of multidimensional [...] Read more.

Time series data have characteristics such as high dimensionality, excessive noise, data imbalance, etc. In the data preprocessing process, feature selection plays an important role in the quantitative analysis of multidimensional time series data. Aiming at the problem of feature selection of multidimensional time series data, a feature selection method for time series based on mutual information (MI) is proposed. One of the difficulties of traditional MI methods is in searching for a suitable target variable. To address this issue, the main innovation of this paper is the hybridization of principal component analysis (PCA) and kernel regression (KR) methods based on MI. Firstly, based on historical operational data, quantifiable system operability is constructed using PCA and KR. The next step is to use the constructed system operability as the target variable for MI analysis to extract the most useful features for the system data analysis. In order to verify the effectiveness of the method, an experiment is conducted on the CMAPSS engine dataset, and the effectiveness of condition recognition is tested based on the extracted features. The results indicate that the proposed method can effectively achieve feature extraction of high-dimensional monitoring data. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

25 pages, 7014 KiB

Open AccessArticle

Machinery Fault Signal Detection with Deep One-Class Classification

by Dosik Yoon and Jaehong Yu

Appl. Sci. 2024, 14(1), 221; https://doi.org/10.3390/app14010221 - 26 Dec 2023

Cited by 2 | Viewed by 1579

Abstract

Fault detection of machinery systems is a fundamental prerequisite to implementing condition-based maintenance, which is the most eminent manufacturing equipment system management strategy. To build the fault detection model, one-class classification algorithms have been used, which construct the decision boundary only using normal [...] Read more.

Fault detection of machinery systems is a fundamental prerequisite to implementing condition-based maintenance, which is the most eminent manufacturing equipment system management strategy. To build the fault detection model, one-class classification algorithms have been used, which construct the decision boundary only using normal class. For more accurate one-class classification, signal data have been used recently because the signal data directly reflect the condition of the machinery system. To analyze the machinery condition effectively with the signal data, features of signals should be extracted, and then, the one-class classifier is constructed with the features. However, features separately extracted from one-class classification might not be optimized for the fault detection tasks, and thus, it leads to unsatisfactory performance. To address this problem, deep one-class classification methods can be used because the neural network structures can generate the features specialized to fault detection tasks through the end-to-end learning manner. In this study, we conducted a comprehensive experimental study with various fault signal datasets. The experimental results demonstrated that the deep support vector data description model, which is one of the most prominent deep one-class classification methods, outperforms its competitors and traditional methods. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

17 pages, 4854 KiB

Open AccessArticle

Delamination Detection Framework for the Imbalanced Dataset in Laminated Composite Using Wasserstein Generative Adversarial Network-Based Data Augmentation

by Sungjun Kim, Muhammad Muzammil Azad, Jinwoo Song and Heungsoo Kim

Appl. Sci. 2023, 13(21), 11837; https://doi.org/10.3390/app132111837 - 29 Oct 2023

Cited by 12 | Viewed by 1705

Abstract

As laminated composites are applied more commonly, Prognostics and Health Management (PHM) techniques for the maintenance of composite systems are also attracting attention. However, applying PHM techniques to a composite system is challenging due to the data imbalance problem from the lack of [...] Read more.

As laminated composites are applied more commonly, Prognostics and Health Management (PHM) techniques for the maintenance of composite systems are also attracting attention. However, applying PHM techniques to a composite system is challenging due to the data imbalance problem from the lack of failure data and unpredictable failure cases. Despite numerous studies conducted to address this limitation, including techniques like data augmentation and transfer learning, significant challenges remain. In this study, the Wasserstein Generative Adversarial Network (WGAN) model using a time-series data augmentation technique is proposed as a solution to the data imbalance problem. To ensure the performance of the WGAN model, time-series data augmentation of experimental data is executed with a frequency analysis. After that, a One-Dimensional Convolutional Neural Network (1D CNN) is used for fault diagnosis in laminated composites, validating the performance improvement after data augmentation. The proposed data augmentation significantly elevated the performance of the 1D CNN classification model compared to its non-augmented counterpart. Specifically, the accuracy increased from 89.20% to 91.96%. The precision improved remarkably from 29.76% to 74.10%, and its sensitivity rose from 33.33% to 94.39%. Collectively, these enhancements highlight the vital role of data augmentation in improving fault diagnosis performance. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

25 pages, 2816 KiB

Open AccessArticle

FPGA-Based Methodology for Detecting Positional Accuracy Degradation in Industrial Robots

by Ervin Galan-Uribe, Luis Morales-Velazquez and Roque Alfredo Osornio-Rios

Appl. Sci. 2023, 13(14), 8493; https://doi.org/10.3390/app13148493 - 23 Jul 2023

Cited by 4 | Viewed by 2005

Abstract

Industrial processes involving manipulator robots require accurate positioning and orienting for high-quality results. Any decrease in positional accuracy can result in resource wastage. Machine learning methodologies have been proposed to analyze failures and wear in electronic and mechanical components, affecting positional accuracy. These [...] Read more.

Industrial processes involving manipulator robots require accurate positioning and orienting for high-quality results. Any decrease in positional accuracy can result in resource wastage. Machine learning methodologies have been proposed to analyze failures and wear in electronic and mechanical components, affecting positional accuracy. These methods are typically implemented in software for offline analysis. In this regard, this work proposes a methodology for detecting a positional deviation in the robot’s joints and its implementation in a digital system of proprietary design based on a field-programmable gate array (FPGA) equipped with several developed intellectual property cores (IPcores). The method implemented in FPGA consists of the analysis of current signals from a UR5 robot using discrete wavelet transform (DWT), statistical indicators, and a neural network classifier. IPcores are developed and tested with synthetic current signals, and their effectiveness is validated using a real robot dataset. The results show that the system can classify the synthetic robot signals for joints two and three with 97% accuracy and the real robot signals for joints five and six with 100% accuracy. This system aims to be a high-speed reconfigurable tool to help detect robot precision degradation and implement timely maintenance strategies. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

22 pages, 563 KiB

Open AccessReview

Generative AI in AI-Based Digital Twins for Fault Diagnosis for Predictive Maintenance in Industry 4.0/5.0

by Emilia Mikołajewska, Dariusz Mikołajewski, Tadeusz Mikołajczyk and Tomasz Paczkowski

Appl. Sci. 2025, 15(6), 3166; https://doi.org/10.3390/app15063166 - 14 Mar 2025

Cited by 3 | Viewed by 2947

Abstract

Generative AI (GenAI) is revolutionizing digital twins (DTs) for fault diagnosis and predictive maintenance in Industry 4.0 and 5.0 by enabling real-time simulation, data augmentation, and improved anomaly detection. DTs, virtual replicas of physical systems, already use generative models to simulate various failure [...] Read more.

Generative AI (GenAI) is revolutionizing digital twins (DTs) for fault diagnosis and predictive maintenance in Industry 4.0 and 5.0 by enabling real-time simulation, data augmentation, and improved anomaly detection. DTs, virtual replicas of physical systems, already use generative models to simulate various failure scenarios and rare events, improving system resilience and failure prediction accuracy. They create synthetic datasets that improve training quality while addressing data scarcity and data imbalance. The aim of this paper was to present the current state of the art and perspectives for using AI-based generative DTs for fault diagnosis for predictive maintenance in Industry 4.0/5.0. With GenAI, DTs enable proactive maintenance and minimize downtime, and their latest implementations combine multimodal sensor data to generate more realistic and actionable insights into system performance. This provides realistic operational profiles, identifying potential failure scenarios that traditional methods may miss. New perspectives in this area include the incorporation of Explainable AI (XAI) to increase transparency in decision-making and improve reliability in key industries such as manufacturing, energy, and healthcare. As Industry 5.0 emphasizes a human-centric approach, AI-based generative DT can seamlessly integrate with human operators to support collaboration and decision-making. The implementation of edge computing increases the scalability and real-time capabilities of DTs in smart factories and industrial Internet of Things (IoT) systems. Future advances may include federated learning to ensure data privacy while enabling data exchange between enterprises for fault diagnostics, and the evolution of GenAI alongside industrial systems, ensuring their long-term validity. However, challenges remain in managing computational complexity, ensuring data security, and addressing ethical issues during implementation. Full article

(This article belongs to the Special Issue Artificial Intelligence in Fault Diagnosis and Signal Processing)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence in Fault Diagnosis and Signal Processing

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (16 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI