Computers in Industry最新文献_第3页

A triple semantic-aware knowledge distillation network for industrial defect detection

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-30 DOI: 10.1016/j.compind.2025.104252

Zhitao Wen, Jinhai Liu, He Zhao, Qiannan Wang

{"title":"A triple semantic-aware knowledge distillation network for industrial defect detection","authors":"Zhitao Wen, Jinhai Liu, He Zhao, Qiannan Wang","doi":"10.1016/j.compind.2025.104252","DOIUrl":"10.1016/j.compind.2025.104252","url":null,"abstract":"<div><div>Knowledge distillation (KD) is a powerful model compression technique that aims to transfer knowledge from heavy teacher networks to compact student networks via distillation. However, effectively transferring semantic knowledge in industrial settings poses significant challenges. On one hand, the appearance of defects (e.g., size and shape) may vary considerably due to the influence of the industrial site, which potentially weakens the semantic associations between class-specific features. On the other hand, agnostic background interference (e.g., spike anomalies and low light) may foster semantic ambiguity of class-specific features. As such, the weakened semantic associations and fostered semantic ambiguities hinder the efficacy and adequacy of knowledge transfer in KD. To mitigate these limitations, we propose a triple semantic-aware knowledge distillation (TSKD) network for industrial defect detection. TSKD contains three refinements, i.e., dual-relation distillation (DRD), decoupled expert distillation (DED), and cross-response distillation (CRD). Specifically, DRD employs graph reasoning networks to strengthen semantic associations at both the instance and pixel levels, DED enhances semantic explicitness by decoupling foreground and background features while injecting expert priors, and CRD further captures task-specific semantic response knowledge. By integrating these components, TSKD can effectively perceive triple semantic knowledge of relations, features, and responses, ensuring more robust and comprehensive knowledge transfer. Experimental evaluations on two challenging industrial datasets show that TSKD can significantly improve detector performance (MFL-DET: 98.9% mAP; NEU-DET: 81.0% mAP) and compress computation (MFL-DET: 19.7M Params and 105 FPS; NEU-DET: 19.7M Params and 116 FPS).</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"166 ","pages":"Article 104252"},"PeriodicalIF":8.2,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143125033","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

Collaborative fault tolerance for cyber–physical systems: The detection stage

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-30 DOI: 10.1016/j.compind.2025.104253

Luis Piardi , André Schneider de Oliveira , Pedro Costa , Paulo Leitão

{"title":"Collaborative fault tolerance for cyber–physical systems: The detection stage","authors":"Luis Piardi , André Schneider de Oliveira , Pedro Costa , Paulo Leitão","doi":"10.1016/j.compind.2025.104253","DOIUrl":"10.1016/j.compind.2025.104253","url":null,"abstract":"<div><div>In the era of Industry 4.0, fault tolerance is essential for maintaining the robustness and resilience of industrial systems facing unforeseen or undesirable disturbances. Current methodologies for fault tolerance stages namely, detection, diagnosis, and recovery, do not correspond with the accelerated technological evolution pace over the past two decades. Driven by the advent of digital technologies such as Internet of Things, cloud and edge computing, and artificial intelligence, associated with enhanced computational processing and communication capabilities, local or monolithic centralized fault tolerance methodologies are out of sync with contemporary and future systems. Consequently, these methodologies are limited in achieving the maximum benefits enabled by the integration of these technologies, such as accuracy and performance improvements. Accordingly, in this paper, a collaborative fault tolerance methodology for cyber–physical systems, named Collaborative Fault * (CF*), is proposed. The proposed methodology takes advantage of the inherent data analysis and communication capabilities of cyber–physical components. The proposed methodology is based on multi-agent system principles, where key components are self-fault tolerant, and adopts collaborative and distributed intelligence behavior when necessary to improve its fault tolerance capabilities. Experiments were conducted focusing on the fault detection stage for temperature and humidity sensors in warehouse racks. The experimental results confirmed the accuracy and performance improvements under CF* compared with the local methodology and competitiveness when compared with a centralized approach.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"166 ","pages":"Article 104253"},"PeriodicalIF":8.2,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143125026","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

Automated construction contract analysis for risk and responsibility assessment using natural language processing and machine learning

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-25 DOI: 10.1016/j.compind.2025.104251

Irem Dikmen , Gorkem Eken , Huseyin Erol , M. Talat Birgonul

{"title":"Automated construction contract analysis for risk and responsibility assessment using natural language processing and machine learning","authors":"Irem Dikmen , Gorkem Eken , Huseyin Erol , M. Talat Birgonul","doi":"10.1016/j.compind.2025.104251","DOIUrl":"10.1016/j.compind.2025.104251","url":null,"abstract":"<div><div>Construction contracts contain critical risk-related information that requires in-depth examination, yet tight schedules for bidding limit the possibility of comprehensive review of extensive documents manually. This research aims to develop models for automating the review of construction contracts to extract information on risk and responsibility that will provide inputs for risk management plans. Models were trained on 2268 sentences from International Federation of Consulting Engineers templates and tested on an actual construction project contract containing 1217 sentences. A taxonomy classified sentences into Heading, Definition, Obligation, Risk, and Right categories with related parties of Contractor, Employer, and Shared. Twelve models employing diverse Natural Language Processing vectorization techniques and Machine Learning algorithms were implemented and benchmarked based on accuracy and F1 score. Binary classification of sentence types and an ensemble method integrating top models were further applied to improve performance. The best model achieved 89 % accuracy for sentence types and 83 % for related parties, demonstrating the capabilities of automated contract review for identification of risk and responsibilities. Adopting the proposed approach can significantly expedite contract reviews to support risk management activities, bid preparation processes and prevent disputes caused by overlooking risks and responsibilities.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"166 ","pages":"Article 104251"},"PeriodicalIF":8.2,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143055234","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

Domain ontology to integrate building-integrated photovoltaic, battery energy storage, and building energy flexibility information for explicable operation and maintenance

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-23 DOI: 10.1016/j.compind.2025.104250

Xiaoyue Yi , Llewellyn Tang , Reynold Cheng , Mengtian Yin , Yu Zheng

{"title":"Domain ontology to integrate building-integrated photovoltaic, battery energy storage, and building energy flexibility information for explicable operation and maintenance","authors":"Xiaoyue Yi , Llewellyn Tang , Reynold Cheng , Mengtian Yin , Yu Zheng","doi":"10.1016/j.compind.2025.104250","DOIUrl":"10.1016/j.compind.2025.104250","url":null,"abstract":"<div><div>Building-integrated photovoltaics (BIPV) incorporated with battery energy storage (BES) and building energy flexibility (BEF) system is nowadays increasingly prevalent. During the operation and maintenance (O&M) of BIPV, BES, and BEF, various knowledge is contained and generated. This highlights information interaction among systems and the demand for incorporating diverse domain knowledge. However, these systems remain relatively isolated during O&M and suffer from inadequate machine-readable knowledge representation. In the era of semantic web technology, ontology-based methods are promising to integrate heterogeneous information. This study developed a domain ontology named “BIPV-BES-BEF” to integrate BIPV, BES, and BEF O&M information by enriching ontology semantics through relevant standards and leveraging existing ontology resources. In the process ontology construction, classes associated with BIPV, BES, and BEF were initially identified from relevant ontologies based on concepts in authorized codes. The classes with high cosine similarity within these recognized classes were subsequently integrated. Concepts and rules concerning the O&M of BIPV, BES, and BEF from relevant standards were then incorporated to the ontology and semantic web rules. The resulting ontology consists of a total of 2595 axioms and 649 classes, encompassing comprehensive concepts related to BIPV, BES, and BEF components, system specifics, assessment criteria, as well as O&M elements. The built ontology was assessed to be coherent and capable of reasoning through the built knowledge. This study contributes to an ontology purposing BIPV, BES, and BEF O&M, highlighting the potential of ontology-based approaches in BIPV, BES, and BEF data integration and knowledge inference.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"166 ","pages":"Article 104250"},"PeriodicalIF":8.2,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143055236","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

Acoustic signal-based wear monitoring for belt grinding tools with pyramid-structured abrasives using BO-KELM 基于声信号的金字塔结构磨料带磨具磨损监测

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-03 DOI: 10.1016/j.compind.2024.104235

Yingjie Liu , Wenxi Wang , Xiaoyu Zhao , Shudong Zhao , Lai Zou , Chao Wang

引用次数: 0

Predictive analysis-based sustainable waste management in smart cities using IoT edge computing and blockchain technology 利用物联网边缘计算和区块链技术在智慧城市中进行基于预测分析的可持续废物管理

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-03 DOI: 10.1016/j.compind.2024.104234

C. Anna Palagan , S. Sebastin Antony Joe , S.J. Jereesha Mary , E. Edwin Jijo

{"title":"Predictive analysis-based sustainable waste management in smart cities using IoT edge computing and blockchain technology","authors":"C. Anna Palagan , S. Sebastin Antony Joe , S.J. Jereesha Mary , E. Edwin Jijo","doi":"10.1016/j.compind.2024.104234","DOIUrl":"10.1016/j.compind.2024.104234","url":null,"abstract":"<div><div>Effective waste management has become the key challenge in developing smart cities with the increase in population. Traditional waste management systems are often inefficient, which leads to unnecessary trips, high operational costs, difficulties in tracking waste, and the inefficient use of resources. The proposed work aims to integrate real-time predictive analysis-based waste collection and disposal processes using federated learning with blockchain, overcoming the challenges specified. Initially, IoT sensors were installed in waste bins across different sites to monitor the depth of waste accumulated. Local edge gateways preprocess the collected data, which the random forest model analyzes to determine the bin status. The aggregated data is sent to a global model that predicts overall waste generation trends. Furthermore, the processed data is securely recorded on a blockchain network combined with smart contracts, accessed through a decentralized application called D-App, which gives real-time updates for scheduling waste collection, performs efficient communication with users and stakeholders to access real-time data to monitor bin status, and track waste collection trucks. As a result, the model predicts bin status with 99.25 % accuracy using an RF algorithm and blockchain helped achieve a user trust level by 95 %. Thus, the proposed work reduces operational expenses, optimizes waste collection routes, makes better decisions, and provides a scalable solution for sustainable waste management.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"166 ","pages":"Article 104234"},"PeriodicalIF":8.2,"publicationDate":"2025-01-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142936017","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

Human Digital Twins: A systematic literature review and concept disambiguation for industry 5.0 人类数字孪生：工业5.0的系统文献回顾和概念消歧

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2025-01-02 DOI: 10.1016/j.compind.2024.104230

Ben Gaffinet , Jana Al Haj Ali , Yannick Naudet , Hervé Panetto

{"title":"Human Digital Twins: A systematic literature review and concept disambiguation for industry 5.0","authors":"Ben Gaffinet , Jana Al Haj Ali , Yannick Naudet , Hervé Panetto","doi":"10.1016/j.compind.2024.104230","DOIUrl":"10.1016/j.compind.2024.104230","url":null,"abstract":"<div><div>Human Digital Twins (HDTs) are an emerging concept with the potential to create human-centric systems for Industry 5.0. The concept has rapidly spread to new application domains, most notably Healthcare, leading to diverging conceptual interpretations. This Systematic Literature Review analyses the conceptual understanding of HDTs across all application domains to clarify the conceptual foundation. Our review reveals a consensus that an HDT’s twinned entity is a human individual. However, there is little agreement on the data flows between the individual and their HDT. We address this shortcoming by proposing three categories based on the level of data integration: Human Digital Models, Human Digital Shadows, and Human Digital Twins. Finally, we synthesise our findings in a domain-agnostic general definition for HDT. We highlight an edge case where the twinned entity is a human individual alongside a strongly coupled technical system, and name it augmented Human Digital Twin (aHDT). The definition and categorisation scheme provide the needed conceptual clarity for inter-disciplinary collaboration to address open challenges. Notable challenges are sensing human data, reliable data transfers and modelling, especially behavioural modelling. Additional ethical issues concerning security, privacy and consent are central to successful HDT adoption. We call for cross-disciplinary efforts to establish a standardised framework and ethical guidelines to enable future developments.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"166 ","pages":"Article 104230"},"PeriodicalIF":8.2,"publicationDate":"2025-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142936018","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

An approach for adaptive filtering with reinforcement learning for multi-sensor fusion in condition monitoring of gearboxes 用于变速箱状态监测的多传感器融合强化学习自适应滤波方法

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-11-27 DOI: 10.1016/j.compind.2024.104214

Shahis Hashim, Sitesh Kumar Mishra, Piyush Shakya

{"title":"An approach for adaptive filtering with reinforcement learning for multi-sensor fusion in condition monitoring of gearboxes","authors":"Shahis Hashim, Sitesh Kumar Mishra, Piyush Shakya","doi":"10.1016/j.compind.2024.104214","DOIUrl":"10.1016/j.compind.2024.104214","url":null,"abstract":"<div><div>Condition monitoring of gearboxes is integral to maintaining floor safety, system stability, and inventory management. Capturing vibration response using sensors and subsequent response analysis is the standard procedure for gearbox fault detection. However, the sensors are susceptible to non-constant reliability due to the convolution of vibration responses from multiple sources, background noise interference, and transfer-path effect. The problem is multi-fold when ideal sensor attachment locations are unavailable due to spatial constraints of industrial floors. The response component reflective of the fault information must be enhanced for adequate fault severity estimations. The present study addresses this hurdle by proposing a multi-sensor framework with available sensor attachment locations for gearbox condition monitoring. Adaptive filtering is done in the framework with parameters optimised to enhance fault information. A proximal policy optimisation agent is trained with a reinforcement learning environment for parameter refinement. Further, fault severity estimation is achieved by a weighted fusion of spectral features reflective of the side-band excitation effect caused by gear fault. The proposed method is applied to datasets acquired from an in-house seeded fault test bed. The proposed method underscores superior performance compared to conventional single-sensor-based fault severity analysis and alternate fusion approaches.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104214"},"PeriodicalIF":8.2,"publicationDate":"2024-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142718530","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

Wasserstein distributionally robust learning for predicting the cycle time of printed circuit board production 用于预测印刷电路板生产周期的瓦瑟斯坦分布稳健学习法

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-11-19 DOI: 10.1016/j.compind.2024.104213

Feng Liu , Yingjie Lu , Debiao Li , Raymond Chiong

{"title":"Wasserstein distributionally robust learning for predicting the cycle time of printed circuit board production","authors":"Feng Liu , Yingjie Lu , Debiao Li , Raymond Chiong","doi":"10.1016/j.compind.2024.104213","DOIUrl":"10.1016/j.compind.2024.104213","url":null,"abstract":"<div><div>This paper proposes a Wasserstein distributionally robust learning (WDRL) model to predict the production cycle time of highly mixed printed circuit board (PCB) orders on multiple production lines. The PCB production cycle time is essential for optimizing production plans. However, the design of the PCB, production line configuration, order combinations, and personnel factors make the prediction of the PCB production cycle time difficult. In addition, practical production situations with significant disturbances in feature data make traditional prediction models inaccurate, especially when there is new data. Therefore, we establishe a WDRL model, derive a tight upper bound for the expected loss function, and reformulate a tractable equivalent model based on the bound. To demonstrate the effectiveness of this method, we collected data related to surface mounted technology (SMT) production lines from a leading global display manufacturer for our computational experiments. In addition, we also designed experiments with perturbations in the training and testing datasets to verify the WDRL model’s ability to handle perturbations. This proposed method has also been compared with other machine learning methods, such as the support vector regression combined with symbiotic organism search, decision tree, and kernel extreme learning machine, among others. Experimental results indicate that the WDRL model can make robust predictions of PCB cycle time, which helps to effectively plan production capacity in uncertain situations and avoid overproduction or underproduction. Finally, we implement the WDRL model for the actual SMT production to predict the production cycle time and set it as the target for production. We observed a 98–103 % achievement rate in the last 20 months since the implementation in September 2022.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104213"},"PeriodicalIF":8.2,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142673318","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

BRepQL: Query language for searching topological elements in B-rep models BRepQL：用于搜索 B-rep 模型拓扑元素的查询语言

IF 8.2 1区计算机科学

Computers in Industry Pub Date : 2024-11-18 DOI: 10.1016/j.compind.2024.104207

Seungeun Lim , Changmo Yeo , Byung Chul Kim , Kyung Cheol Bae , Duhwan Mun

{"title":"BRepQL: Query language for searching topological elements in B-rep models","authors":"Seungeun Lim , Changmo Yeo , Byung Chul Kim , Kyung Cheol Bae , Duhwan Mun","doi":"10.1016/j.compind.2024.104207","DOIUrl":"10.1016/j.compind.2024.104207","url":null,"abstract":"<div><div>Topological elements form the basis for tasks such as geometric calculations, feature analysis, and direct modeling in 3D CAD systems. Handling these elements is also essential in various automated systems. This study proposes a method to search for topological elements within a boundary representation (B-rep) model by employing topological queries. To address complex scenarios that are difficult to handle using a single query, a topological query procedure that sequentially executes a predefined set of topological queries is used. To verify the effectiveness of the proposed method, experiments were conducted on Test Cases 1, 2, and 3, confirming the successful search of all target topological elements. Furthermore, tests on modified Snap-fit hook A and Bridge B models demonstrated that the same queries remained effective, provided the topological relationships and geometric constraints expressed in the query were preserved. In addition, a search time comparison showed that the proposed method reduced search time by over 90 % compared to manual processes. Finally, in an experiment involving participants with varying levels of programming proficiency, the results indicated that, for a developer with high programming skills, writing topological queries reduced the time required to search for a single topological element by more than 95 % compared to writing the program code.</div></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"164 ","pages":"Article 104207"},"PeriodicalIF":8.2,"publicationDate":"2024-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142673319","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