Computers in Industry最新文献_第7页

Remaining useful life prediction model of cross-domain rolling bearing via dynamic hybrid domain adaptation and attention contrastive learning 通过动态混合域适应和注意力对比学习建立跨域滚动轴承剩余使用寿命预测模型

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-10 DOI: 10.1016/j.compind.2024.104172

Xingchi Lu , Xuejian Yao , Quansheng Jiang , Yehu Shen , Fengyu Xu , Qixin Zhu

{"title":"Remaining useful life prediction model of cross-domain rolling bearing via dynamic hybrid domain adaptation and attention contrastive learning","authors":"Xingchi Lu , Xuejian Yao , Quansheng Jiang , Yehu Shen , Fengyu Xu , Qixin Zhu","doi":"10.1016/j.compind.2024.104172","DOIUrl":"10.1016/j.compind.2024.104172","url":null,"abstract":"<div><p>Performance degradation and remaining useful life (RUL) prediction are of great significance in improving the reliability of mechanical equipment. Existing cross-domain RUL prediction methods usually reduce data distribution discrepancy by domain adaptation, to overcome domain shift under cross-domain conditions. However, the fine-grained information between cross-domain degradation features and the specific characteristics of the target domain are often ignored, which limits the prediction performance. Aiming at these issues, a RUL prediction method based on dynamic hybrid domain adaptation (DHDA) and attention contrastive learning (A-CL) is proposed for the cross-domain rolling bearings. In the DHDA module, the conditional distribution alignment is achieved by the designed pseudo-label-guided domain adversarial network, and is assigned with a dynamic penalty term to dynamically adjust the conditional distribution when aligning the joint distribution, for improving the fine-grainedness of domain adaptation. The A-CL module aims to help the prediction model actively extract the degradation information of the target domain, to generate the degradation features that match the characteristics of the target domain, for improving the robustness of RUL prediction. Then, the proposed method is verified by the ablation and comparison experiments conducted on PHM2012 and XJTU-SY datasets. The results show that the proposed method performs high accuracy for cross-domain RUL prediction with good generalization performance under three different cross-domain scenarios.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104172"},"PeriodicalIF":8.2,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142164253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detecting coagulation time in cheese making by means of computer vision and machine learning techniques 利用计算机视觉和机器学习技术检测奶酪制作过程中的凝固时间

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-09 DOI: 10.1016/j.compind.2024.104173

Andrea Loddo , Cecilia Di Ruberto , Giuliano Armano , Andrea Manconi

{"title":"Detecting coagulation time in cheese making by means of computer vision and machine learning techniques","authors":"Andrea Loddo , Cecilia Di Ruberto , Giuliano Armano , Andrea Manconi","doi":"10.1016/j.compind.2024.104173","DOIUrl":"10.1016/j.compind.2024.104173","url":null,"abstract":"<div><p>Cheese production, a globally cherished culinary tradition, faces challenges in ensuring consistent product quality and production efficiency. The critical phase of determining cutting time during curd formation significantly influences cheese quality and yield. Traditional methods often struggle to address variability in coagulation conditions, particularly in small-scale factories. In this paper, we present several key practical contributions to the field, including the introduction of CM-IDB, the first publicly available image dataset related to the cheese-making process. Also, we propose an innovative artificial intelligence-based approach to automate the detection of curd-firming time during cheese production using a combination of computer vision and machine learning techniques. The proposed method offers real-time insights into curd firmness, aiding in predicting optimal cutting times. Experimental results show the effectiveness of integrating sequence information with single image features, leading to improved classification performance. In particular, deep learning-based features demonstrate excellent classification capability when integrated with sequence information. The study suggests the suitability of the proposed approach for integration into real-time systems, especially within dairy production, to enhance product quality and production efficiency.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104173"},"PeriodicalIF":8.2,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0166361524001015/pdfft?md5=049ee78fc600c8a36c293c17fd46e748&pid=1-s2.0-S0166361524001015-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142164254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prior knowledge embedding convolutional autoencoder: A single-source domain generalized fault diagnosis framework under small samples 先验知识嵌入卷积自动编码器：小样本下的单源域广义故障诊断框架

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-07 DOI: 10.1016/j.compind.2024.104169

Feiyu Lu , Qingbin Tong , Xuedong Jiang , Xin Du , Jianjun Xu , Jingyi Huo

{"title":"Prior knowledge embedding convolutional autoencoder: A single-source domain generalized fault diagnosis framework under small samples","authors":"Feiyu Lu , Qingbin Tong , Xuedong Jiang , Xin Du , Jianjun Xu , Jingyi Huo","doi":"10.1016/j.compind.2024.104169","DOIUrl":"10.1016/j.compind.2024.104169","url":null,"abstract":"<div><p>The proposed transfer learning-based fault diagnosis models have achieved good results in multi-source domain generalization (MDG) tasks. However, research on single-source domain generalization (SDG) is relatively scarce, and the limited availability of small training samples is seldom considered. Therefore, to address the insufficient feature extraction capability and poor generalization performance of existing models on single-source domain small sample data, a novel single-source domain generalization fault diagnosis (SDGFD) framework, the prior knowledge embedded convolutional autoencoder (PKECA), is proposed. During the training phase, first, single-source domain data are used to construct prior features based on the time domain, frequency domain, and time-frequency domain. Second, a prior knowledge embedding structure based on the convolutional autoencoder is built, which compresses the prior knowledge and original vibration data into a high-dimensional space of consistent dimensions, embedding the prior knowledge into the features corresponding to the vibration data using a mean squared error loss function. Subsequently, the proposed centroid-based self-supervised learning (CBSSL) strategy further constrains high-dimensional features, improving the generalization ability. The designed sparse regularized activation (SRA) function significantly enhances the regularization effect on features. During the testing phase, it is only necessary to input the data from the unknown domain to identify the fault types. The experimental results show that the proposed method achieves superior performance in fault diagnosis tasks involving cross-speed, time-varying speed, and small sample data in SDGFD, demonstrating that PKECA has strong generalizability. The code can be found here: https://github.com/John-520/PKECA. © 2024 Elsevier Science. All rights reserved</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104169"},"PeriodicalIF":8.2,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142144022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Computers as co-creative assistants. A comparative study on the use of text-to-image AI models for computer aided conceptual design 作为共同创作助手的计算机。关于在计算机辅助概念设计中使用文本到图像人工智能模型的比较研究

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-07 DOI: 10.1016/j.compind.2024.104168

Jorge Alcaide-Marzal, Jose Antonio Diego-Mas

{"title":"Computers as co-creative assistants. A comparative study on the use of text-to-image AI models for computer aided conceptual design","authors":"Jorge Alcaide-Marzal, Jose Antonio Diego-Mas","doi":"10.1016/j.compind.2024.104168","DOIUrl":"10.1016/j.compind.2024.104168","url":null,"abstract":"<div><p>This preliminary research presents a comparative study between Text-to-Image AI models and Shape Grammars, one of the main generative approaches to Computer Aided Conceptual Design. The goal is to determine to which extent AI models can reproduce or complement the performance of grammar algorithms as creative support tools for shape exploration in conceptual product design. Workflows, advantages and limitations are identified through a comprehensive practical comparison example. The results show many similarities regarding generative capabilities and highlight several advantages of Text-to-Image AI models, including an easier way of capturing product grammars and a wider and more immediate range of further applications. In contrast, Shape Grammars approach proved more solid in aspects related to exploration workflows and cognitive stimulation. These results encourage the research on new ways to address the interaction between designers and AI generative models, combining the AI potential with well-established generative strategies.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104168"},"PeriodicalIF":8.2,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0166361524000964/pdfft?md5=1f56acc9291a1170ec8ff973996755fd&pid=1-s2.0-S0166361524000964-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142144024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive early initial degradation point detection and outlier correction for bearings 轴承自适应早期初始退化点检测和离群值校正

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-07 DOI: 10.1016/j.compind.2024.104166

Qichao Yang, Baoping Tang, Lei Deng, Zihao Li

{"title":"Adaptive early initial degradation point detection and outlier correction for bearings","authors":"Qichao Yang, Baoping Tang, Lei Deng, Zihao Li","doi":"10.1016/j.compind.2024.104166","DOIUrl":"10.1016/j.compind.2024.104166","url":null,"abstract":"<div><p>This paper delves into the accurate detection of the early initial degradation point (IDP) in bearings, and proposes, for the first time, a comprehensive adaptive IDP detection framework for bearings under variable operating conditions, along with an outlier data repair strategy. First, this study introduces the adaptive early initial degradation point detection (AEIDPD) method, which incorporates least-squares fitting to compute the slope and intercept of health indicators, and t-tests are used to construct the “sum-of-slopes” indicator. An adaptive IDP threshold construction method that adapts to variable operating conditions is proposed, establishing a strategy for IDP detection based on sum-of-slopes and adaptive thresholds. To enhance the robustness of AEIDPD in variable operating conditions, this paper introduces synchronized wavelet transform to obtain the \"synchronous pseudo-speed\" signal of bearing vibration, and constructs a condition interference elimination strategy based on velocity and sliding window averaging to mitigate the effects of variable operating conditions. Additionally, the study constructs upper and lower bounds for the root mean square feature of vibration signals using empirical parameters to correct outliers, providing more accurate data to support bearing life predictions. Experimental results demonstrate the effectiveness and robustness of the proposed methods.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104166"},"PeriodicalIF":8.2,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142144026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fusing multichannel autoencoders with dynamic global loss for self-supervised fault diagnosis 融合具有动态全局损失的多通道自动编码器，实现自我监督故障诊断

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-07 DOI: 10.1016/j.compind.2024.104165

Chuan Li , Manjun Xiong , Hongmeng Shen , Yun Bai , Shuai Yang , Zhiqiang Pu

{"title":"Fusing multichannel autoencoders with dynamic global loss for self-supervised fault diagnosis","authors":"Chuan Li , Manjun Xiong , Hongmeng Shen , Yun Bai , Shuai Yang , Zhiqiang Pu","doi":"10.1016/j.compind.2024.104165","DOIUrl":"10.1016/j.compind.2024.104165","url":null,"abstract":"<div><p>Engineering fault diagnosis often needs to be implemented without prior knowledge of labels. Considering the randomness and drift of fault features, this paper proposes fusing multichannel autoencoders with dynamic global loss (FMA-DGL) to enhanc<u>e</u> self-supervised fault diagnosis. Multiple autoencoders are employed to represent the fault features of multichannel vibration signals. A dynamic global loss function is utilized to self-supervise the generation of pseudo-labels, thereby integrating multichannel feature information together. The proposed dynamic global loss controls the degree of conflict of samples from different channels to construct clustering centers, allowing the clustering process to converge more smoothly. By leveraging both the common and complementary information across different channels, the randomness and drift issues of self-supervised pseudo-labels are addressed, effectively enhancing the fault diagnosis performance through multichannel fusion. Experiments were carried out using a public bearing dataset and a rotating machinery experimental setup, respectively. Results show that the proposed FMA-DGL outperforms the state-of-the-art peer methods, exhibiting good results and applicability in self-supervised fault diagnosis based on multichannel vibration signals.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104165"},"PeriodicalIF":8.2,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142144025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Intelligent crude oil price probability forecasting: Deep learning models and industry applications 智能原油价格概率预测：深度学习模型和行业应用

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-04 DOI: 10.1016/j.compind.2024.104150

Liang Shen , Yukun Bao , Najmul Hasan , Yanmei Huang , Xiaohong Zhou , Changrui Deng

{"title":"Intelligent crude oil price probability forecasting: Deep learning models and industry applications","authors":"Liang Shen , Yukun Bao , Najmul Hasan , Yanmei Huang , Xiaohong Zhou , Changrui Deng","doi":"10.1016/j.compind.2024.104150","DOIUrl":"10.1016/j.compind.2024.104150","url":null,"abstract":"<div><p>The crude oil price has been subject to periodic fluctuations because of seasonal changes in industrial demand and supply, weather, natural disasters and global political unrest. An accurate forecast of crude oil prices is of utmost importance for decision makers and industry players in the energy sector. Despite this, the volatility of crude oil prices contributes to the uncertainty of the energy industry, which was particularly challenging following the recent global spread of the COVID-19 epidemic and the Russia–Ukraine conflict. This paper proposes a hybrid deep learning (DL) modelling framework to deal with the volatility of crude oil prices, applying ensemble empirical mode decomposition (EEMD), convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) integrated with quantile regression (QR); named EEMD-CNN-BiLSTM-QR. Two real-world datasets on crude oil prices from the West Texas Intermediate and Brent Crude Oil markets were employed to validate the EEMD-CNN-BiLSTM-QR hybrid modelling framework. Given that the probability density forecast can capture uncertainty, an in-depth analysis was carried out and prediction accuracy calculated. The findings of this study demonstrate that the proposed EEMD-CNN-BiLSTM-QR DL modelling framework, which uses the probability density forecast method, is superior to other tested models in terms of its ability to forecast crude oil prices. The novelty of this study stems mainly from its use of QR, which allows for the description of the conditional distribution of predicted variables and the extraction of more uncertain information for probability density forecasts.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"163 ","pages":"Article 104150"},"PeriodicalIF":8.2,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142129477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detecting visual anomalies in an industrial environment: Unsupervised methods put to the test on the AutoVI dataset 检测工业环境中的视觉异常：在 AutoVI 数据集上测试无监督方法

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-02 DOI: 10.1016/j.compind.2024.104151

Philippe Carvalho , Meriem Lafou , Alexandre Durupt , Antoine Leblanc , Yves Grandvalet

{"title":"Detecting visual anomalies in an industrial environment: Unsupervised methods put to the test on the AutoVI dataset","authors":"Philippe Carvalho , Meriem Lafou , Alexandre Durupt , Antoine Leblanc , Yves Grandvalet","doi":"10.1016/j.compind.2024.104151","DOIUrl":"10.1016/j.compind.2024.104151","url":null,"abstract":"<div><p>The methods for unsupervised visual inspection use algorithms that are developed, trained and evaluated on publicly available datasets. However, these datasets do not reflect genuine industrial conditions, and thus current methods are not evaluated in real-world industrial production contexts. To answer this shortcoming, we introduce AutoVI, an industrial dataset of visual defects that can be encountered on automotive assembly lines. This dataset, comprising six inspection tasks, was designed as a benchmark to assess the performance of defect detection methods under realistic acquisition conditions. We analyze the performance of current state-of-the-art methods and discuss the difficulties specifically encountered in the industrial context. Our results show that current methods leave considerable room for improvement. We make AutoVI publicly available to develop unsupervised detection methods that will be better suited to real industrial tasks.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"163 ","pages":"Article 104151"},"PeriodicalIF":8.2,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0166361524000794/pdfft?md5=b20367b293bf15a589dd0934b0e45c85&pid=1-s2.0-S0166361524000794-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142122001","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Digitally enhanced development of customised lubricant: Experimental and modelling studies of lubricant performance for hot stamping 数字化增强型定制润滑剂开发：热冲压润滑剂性能的实验和建模研究

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-09-01 DOI: 10.1016/j.compind.2024.104152

Xiao Yang , Heli Liu , Vincent Wu , Denis J. Politis , Haochen Yao , Jie Zhang , Liliang Wang

{"title":"Digitally enhanced development of customised lubricant: Experimental and modelling studies of lubricant performance for hot stamping","authors":"Xiao Yang , Heli Liu , Vincent Wu , Denis J. Politis , Haochen Yao , Jie Zhang , Liliang Wang","doi":"10.1016/j.compind.2024.104152","DOIUrl":"10.1016/j.compind.2024.104152","url":null,"abstract":"<div><p>Digitally enhanced technologies are transforming every aspect of the manufacturing sector towards the era of digital manufacturing. Traditional lubricant development methods involving systematic but time-consuming iterative processes is still extensively used in the metal forming industry. In the present study, a novel digitally enhanced lubricant development scheme was proposed by leveraging a mechanism-based interactive friction modelling framework and quantitative and comprehensive evaluation of lubricant performance via the data-centric lubricant limit diagrams. By predicting transient lubricant behaviour following the complex contact condition evolution experienced in actual forming operations, a close association and quantified relation between the lubricant performance and its properties such as viscosity, evaporation rate and fraction of dry matter was established. This can facilitate the optimisation efficiency of lubricant parameters and minimise the experimental cost for iterative lubricant trials. A case study was conducted in this work to develop a customised lubricant using this digitally enhance scheme for the target hot stamping process based on a benchmark lubricant as a reference. Further industrial forming tests of an automotive component were conducted to validate the ideal performance of the customised lubricant.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"163 ","pages":"Article 104152"},"PeriodicalIF":8.2,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0166361524000800/pdfft?md5=720c572a424101129d0be812521a5372&pid=1-s2.0-S0166361524000800-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142117566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A digital twin system for centrifugal pump fault diagnosis driven by transfer learning based on graph convolutional neural networks 基于图卷积神经网络的迁移学习驱动的离心泵故障诊断数字孪生系统

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-08-30 DOI: 10.1016/j.compind.2024.104155

Zifeng Xu , Zhe Wang , Chaojia Gao , Keqi Zhang , Jie Lv , Jie Wang , Lilan Liu

{"title":"A digital twin system for centrifugal pump fault diagnosis driven by transfer learning based on graph convolutional neural networks","authors":"Zifeng Xu , Zhe Wang , Chaojia Gao , Keqi Zhang , Jie Lv , Jie Wang , Lilan Liu","doi":"10.1016/j.compind.2024.104155","DOIUrl":"10.1016/j.compind.2024.104155","url":null,"abstract":"<div><p>In industrial sectors such as shipping, chemical processing, and energy production, centrifugal pumps often experience failures due to harsh operational environments, making it challenging to accurately identify fault types. Traditional fault diagnosis methods, which heavily rely on existing fault datasets, suffer from limited generalization capabilities, especially when substantial labeled and specific fault sample data are lacking. This paper proposes a novel fault diagnosis approach for centrifugal pumps, utilizing a digital twin (DT) framework powered by a graph transfer learning model to address this issue. Firstly, a high-fidelity DT model is constructed to simulate the flow-induced vibration response of the impeller under different health states to enrich the type and scale of the dataset. Secondly, a graph convolutional neural networks (GCN) model is constructed to learn the knowledge of simulation data, and the Wasserstein distance between simulation data and measured data is optimized for adversarial domain adaptation, thereby achieving efficient cross-domain fault diagnosis. Experimental results demonstrate that the proposed algorithm delivers effective fault diagnosis with minimal prior knowledge and outperforms comparable models. Furthermore, the DT system developed using the proposed model enhances the operational reliability of centrifugal pumps, reduces maintenance costs, and presents an innovative application of DT technology in industrial fault diagnosis.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"163 ","pages":"Article 104155"},"PeriodicalIF":8.2,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142094663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0