Journal of Intelligent Manufacturing最新文献

{"title":"Digital twin-driven smelting process management method for converter steelmaking","authors":"Tianjie Fu, Shimin Liu, Peiyu Li","doi":"10.1007/s10845-024-02366-7","DOIUrl":"https://doi.org/10.1007/s10845-024-02366-7","url":null,"abstract":"<p>The converter is an indispensable key equipment in the steel manufacturing industry. With the increasing demand for high-quality steel, there is an increasing demand for monitoring and controlling the status of the converter during the smelting process. Compared to other manufacturing industries, such as food processing and textile, converter steelmaking requires a larger keep-out zone due to its ultra-high temperatures and harsh smelting environment. This makes it difficult for personnel to fully understand, analyze, and manage the smelting process, resulting in low production efficiency and the inability to achieve consistently high-quality results. Aiming at the low virtual visualization level and insufficient monitoring ability of the converter steelmaking process, a process management method based on digital twin technology is proposed. Firstly, a digital twin system framework for full-process monitoring of converter steelmaking is proposed based on the analysis of the process characteristics of converter steelmaking. The proposed framework provides critical enabling technologies such as point cloud-based digital twin model construction, visual display, and steel endpoint analysis and prediction, to support full-process, high-fidelity intelligent monitoring. After conducting experiments, a digital twin-driven smelting process management system was developed to manage the entire smelting process. The system has proven to be effective as it increased the monthly production capacity by 77.7%. The waste of smelting materials has also been greatly reduced from 34% without the system to 7.8% with the system. Based on these results, it is evident that this system significantly enhances smelting efficiency and reduces both the costs and waste associated with the process.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"19 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140802912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A transfer regression network-based adaptive calibration method for remaining useful life prediction considering individual discrepancies in the degradation process of machinery","authors":"Jiaxian Chen, Dongpeng Li, Ruyi Huang, Zhuyun Chen, Weihua Li","doi":"10.1007/s10845-024-02386-3","DOIUrl":"https://doi.org/10.1007/s10845-024-02386-3","url":null,"abstract":"<p>Transfer learning (TL)-based remaining useful life (RUL) prediction has been extensively studied and plays a crucial role under cross-working conditions. While previous works have made great efforts to realize domain adaptation, existing methods still suffer from two key limitations: (1) Most feature-based TL methods focus on learning shared domain-independent features and fail to capture private domain information. (2) Model-based TL methods typically use all features to pre-train an RUL prediction model without accounting for the negative effect of private features in the source domain to the target domain. To tackle these challenges, a transfer regression network-based adaptive calibration (TRNAC) method is proposed to execute accurate RUL prediction for different machines where shared domain-independent features and private individual features in the target domain are fully considered to enhance the feature representation for RUL prediction. Specifically, the constructed TRNAC model includes a set of feature extractors where one is to learn shared domain-independent features in both domains and another is to extract individual domain features in the target domain, a shared RUL regressor to learn a mapping relationship between the shared features and the RUL values, a domain discriminator to distinguish which domain the feature comes from. Most importantly, an error regressor is customized by designing a dynamic calibration factor to revise the prediction error caused by the shared RUL regressor and achieve accurate prediction. The comprehensive experimental results on the aero-engine dataset and bearing dataset indicate that the proposed method performs better than other state-of-the-art RUL prediction methods.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"57 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140802919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid intelligence failure analysis for industry 4.0: a literature review and future prospective","authors":"Mahdi Mokhtarzadeh, Jorge Rodríguez-Echeverría, Ivana Semanjski, Sidharta Gautama","doi":"10.1007/s10845-024-02376-5","DOIUrl":"https://doi.org/10.1007/s10845-024-02376-5","url":null,"abstract":"<p>Industry 4.0 and advanced technology, such as sensors and human–machine cooperation, provide new possibilities for infusing intelligence into failure analysis. Failure analysis is the process of identifying (potential) failures and determining their causes and effects to enhance reliability and manufacturing quality. Proactive methodologies, such as failure mode and effects analysis (FMEA), and reactive methodologies, such as root cause analysis (RCA) and fault tree analysis (FTA), are used to analyze failures before and after their occurrence. This paper focused on failure analysis methodologies intelligentization literature applied to FMEA, RCA, and FTA to provide insights into expert-driven, data-driven, and hybrid intelligence failure analysis advancements. Types of data to establish an intelligence failure analysis, tools to find a failure’s causes and effects, e.g., Bayesian networks, and managerial insights are discussed. This literature review, along with the analyses within it, assists failure and quality analysts in developing effective hybrid intelligence failure analysis methodologies that leverage the strengths of both proactive and reactive methods.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"102 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140637455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Combining physics-based and data-driven methods in metal stamping","authors":"Amaia Abanda, Amaia Arroyo, Fernando Boto, Miguel Esteras","doi":"10.1007/s10845-024-02374-7","DOIUrl":"https://doi.org/10.1007/s10845-024-02374-7","url":null,"abstract":"<p>This work presents a methodology for combining physical modeling strategies (FEM), machine learning techniques, and evolutionary algorithms for a metal stamping process to ensure process quality during production. Firstly, a surrogate model or metamodel is proposed to approximate the behavior of the simulation model for different outputs in a fraction of time. Secondly, based on the surrogate model, multiple soft sensors that estimate different quality measures of the stamped part departing from the draw-ins are proposed, which enables their integration into the process. Lastly, evolutionary algorithms are used to estimate the latent blank characteristics and for the prescriptions of process parameters that maximize the quality of the stamped part. The obtained numerical results are promising, with relative errors around 2 2% in most cases and outperforming a naive method. This methodology aims to be a decision support system that moves towards zero defects in the stamping process from the process conception phase.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"40 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140624326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated assembly quality inspection by deep learning with 2D and 3D synthetic CAD data","authors":"Xiaomeng Zhu, Pär Mårtensson, Lars Hanson, Mårten Björkman, Atsuto Maki","doi":"10.1007/s10845-024-02375-6","DOIUrl":"https://doi.org/10.1007/s10845-024-02375-6","url":null,"abstract":"<p>In the manufacturing industry, automatic quality inspections can lead to improved product quality and productivity. Deep learning-based computer vision technologies, with their superior performance in many applications, can be a possible solution for automatic quality inspections. However, collecting a large amount of annotated training data for deep learning is expensive and time-consuming, especially for processes involving various products and human activities such as assembly. To address this challenge, we propose a method for automated assembly quality inspection using synthetic data generated from computer-aided design (CAD) models. The method involves two steps: automatic data generation and model implementation. In the first step, we generate synthetic data in two formats: two-dimensional (2D) images and three-dimensional (3D) point clouds. In the second step, we apply different state-of-the-art deep learning approaches to the data for quality inspection, including unsupervised domain adaptation, i.e., a method of adapting models across different data distributions, and transfer learning, which transfers knowledge between related tasks. We evaluate the methods in a case study of pedal car front-wheel assembly quality inspection to identify the possible optimal approach for assembly quality inspection. Our results show that the method using Transfer Learning on 2D synthetic images achieves superior performance compared with others. Specifically, it attained 95% accuracy through fine-tuning with only five annotated real images per class. With promising results, our method may be suggested for other similar quality inspection use cases. By utilizing synthetic CAD data, our method reduces the need for manual data collection and annotation. Furthermore, our method performs well on test data with different backgrounds, making it suitable for different manufacturing environments.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"13 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140614072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of image acquisition by automated white-light interferometers during the inspection of object surfaces","authors":"Björn Schwarze, Stefan Edelkamp","doi":"10.1007/s10845-023-02306-x","DOIUrl":"https://doi.org/10.1007/s10845-023-02306-x","url":null,"abstract":"<p>This paper considers the efficient quality assurance of diverse geometric objects through the use of a white-light interferometer, with a primary focus on minimizing the number of required image captures. The motivation behind such an algorithm stems from the extended recording times associated with various free-form sheet metal parts. Given that capturing images with a microscope typically consumes 30–40 s, maintaining high-quality assurance is imperative. A reduction in the number of images not only expedites part throughput but also enhances the economic efficiency. A unique aspect in this context is the requirement for focus points to consistently align with the part’s surface. We formulate this challenge in a mathematical framework, necessitating a comprehensive literature review to identify potential solutions, and introduce an algorithm designed to optimize the image acquisition process for inspecting object surfaces. The proposed algorithm enables efficient coverage of large surfaces on objects of various sizes and shapes using a minimal number of images. The primary objective is to create the most concise list of points that comprehensively encompass the entire object surface. Subsequently, the paper conducts a comparative analysis of various strategies to identify the most effective approach.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"97 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140617819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-supervised fusion of deep soft assignments for multi-view diagnosis of machine faults","authors":"Chuan Li, Yifan Wu, Manjun Xiong, Shuai Yang, Yun Bai","doi":"10.1007/s10845-024-02360-z","DOIUrl":"https://doi.org/10.1007/s10845-024-02360-z","url":null,"abstract":"<p>Fault patterns are often unavailable for machine fault diagnosis without prior knowledge. This makes it challenging to diagnose the existence of machine faults and their types. To address this issue, a novel scheme of deep soft assignments fusion network (DSAFN) is proposed for the self-supervised multi-view diagnosis of machine faults. To enhance the robustness of the model and prevent overfitting, random noise is added to the collected signals. In each view, vibration features are extracted by a denoising autoencoder. Using the extracted deep features, a soft assignment fusion strategy is proposed to fully utilize both the public and complementary information of multiple views. Critical diagnosis missions, including novel fault detection and fault clustering, are accomplished through binary clustering and multi-class clustering of DSAFN, respectively. Two diagnostic experiments are conducted to validate the proposed method. The results indicate that the proposed method performs better than state-of-the-art peer methods in terms of diagnostic accuracy and noise robustness.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"87 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140578552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Manufacturing process selection based on similarity search: incorporating non-shape information in shape descriptor comparison","authors":"Zhichao Wang, Xiaoliang Yan, Jacob Bjorni, Mahmoud Dinar, Shreyes Melkote, David Rosen","doi":"10.1007/s10845-024-02368-5","DOIUrl":"https://doi.org/10.1007/s10845-024-02368-5","url":null,"abstract":"<p>Given a part design, the task of manufacturing process selection chooses an appropriate manufacturing process to fabricate it. Prior research has traditionally determined manufacturing processes through direct classification. However, an alternative approach to select a manufacturing process for a new design involves identifying previously produced parts with comparable shapes and materials and learning from them. Finding similar designs from a large dataset of previously manufactured parts is a challenging problem. To solve this problem, researchers have proposed different spatial and spectral shape descriptors to extract shape features including the D2 distribution, spherical harmonics (SH), and the Fast Fourier Transform (FFT), as well as the application of different machine learning methods on various representations of 3D part models like multi-view images, voxel, triangle mesh, and point cloud. However, there has not been a comprehensive analysis of these different shape descriptors, especially for part similarity search aimed at manufacturing process selection. To remedy this gap, this paper presents an in-depth comparative study of these shape descriptors for part similarity search. While we acknowledge the importance of factors like part size, tolerance, and cost in manufacturing process selection, this paper focuses on part shape and material properties only. Our findings show that SH performs the best among non-machine learning methods for manufacturing process selection, yielding 97.96% testing accuracy using the proposed quantitative evaluation metric. For machine learning methods, deep learning on multi-view image representations is best, yielding 99.85% testing accuracy when rotational invariance is not a primary concern. Deep learning on point cloud representations excels, yielding 99.44% testing accuracy when considering rotational invariance.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"49 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140614013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of laser annealing parameters based on bayesian reinforcement learning","authors":"Chung-Yuan Chang, Yen-Wei Feng, Tejender Singh Rawat, Shih-Wei Chen, Albert Shihchun Lin","doi":"10.1007/s10845-024-02363-w","DOIUrl":"https://doi.org/10.1007/s10845-024-02363-w","url":null,"abstract":"<p>Developing new semiconductor processes consumes tremendous time and cost. Therefore, we applied Bayesian reinforcement learning (BRL) with the assistance of technology computer-aided design (TCAD). The fixed or variable prior BRL is tested where the TCAD prior is fixed or is changed by the experimental sampling and decays during the entire RL procedure. The sheet resistance (<i>R</i>_s) of the samples treated by laser annealing is the optimization target. In both cases, the experimentally sampled data points are added to the training dataset to enhance the RL agent. The model-based experimental agent and a model-free TCAD Q-Table are used in this study. The results of BRL proved that it can achieve lower R_s minimum values and variances at different hyperparameter settings. Besides, two action types, i.e., point to state and increment of levels, are proven to have similar results, which implies the method used in this study is insensitive to the different action types.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"17 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140578550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Visual coating inspection framework via self-labeling and multi-stage deep learning strategies","authors":"Changheon Han, Jiho Lee, Martin B. G. Jun, Sang Won Lee, Huitaek Yun","doi":"10.1007/s10845-024-02372-9","DOIUrl":"https://doi.org/10.1007/s10845-024-02372-9","url":null,"abstract":"<p>An instantaneous and precise coating inspection method is imperative to mitigate the risk of flaws, defects, and discrepancies on coated surfaces. While many studies have demonstrated the effectiveness of automated visual inspection (AVI) approaches enhanced by computer vision and deep learning, critical challenges exist for practical applications in the manufacturing domain. Computer vision has proven to be inflexible, demanding sophisticated algorithms for diverse feature extraction. In deep learning, supervised approaches are constrained by the need for annotated datasets, whereas unsupervised methods often result in lower performance. Addressing these challenges, this paper proposes a novel deep learning-based automated visual inspection (AVI) framework designed to minimize the necessity for extensive feature engineering, programming, and manual data annotation in classifying fuel injection nozzles and discerning their coating interfaces from scratch. This proposed framework comprises six integral components: It begins by distinguishing between coated and uncoated nozzles through gray level co-occurrence matrix (GLCM)-based texture analysis and autoencoder (AE)-based classification. This is followed by cropping surface images from uncoated nozzles, and then building an AE model to estimate the coating interface locations on coated nozzles. The next step involves generating autonomously annotated datasets derived from these estimated coating interface locations. Subsequently, a convolutional neural network (CNN)-based detection model is trained to accurately localize the coating interface locations. The final component focuses on enhancing model performance and trustworthiness. This framework demonstrated over 95% accuracy in pinpointing the coating interfaces within the error range of ± 6 pixels and processed at a rate of 7.18 images per second. Additionally, explainable artificial intelligence (XAI) techniques such as t-distributed stochastic neighbor embedding (t-SNE) and the integrated gradient substantiated the reliability of the models.</p>","PeriodicalId":16193,"journal":{"name":"Journal of Intelligent Manufacturing","volume":"44 1","pages":""},"PeriodicalIF":8.3,"publicationDate":"2024-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140578722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}