Computers & Industrial Engineering最新文献

{"title":"An investigation of mixed-model assembly line balancing problem with uncertain assembly time in remanufacturing","authors":"","doi":"10.1016/j.cie.2024.110676","DOIUrl":"10.1016/j.cie.2024.110676","url":null,"abstract":"<div><div>In recent decades, remanufacturing has emerged as an effective way to address resource crises and environmental pollution issues. Unlike traditional manufacturing, remanufacturing production is filled with various variable factors, especially in the assembly phase. Due to changes in part types, quality conditions, and assembly methods, the assembly time becomes highly uncertain. Assembly line balancing is a key challenge to achieve the stable operation of remanufacturing system. This study proposes an evaluation method for remanufacturing assembly time and establishes a multi-objective mathematical model for balancing remanufacturing mixed-model assembly (RMMA) line. The evaluation method utilizes the Fuzzy Graphical Evaluation Review Technique (FGERT) network to predict expected assembly time for each operation. The balancing model aims to optimize remanufacturing takt time and comprehensive balance rate (CBR). To effectively solve this model, an adaptive double-layer genetic algorithm (ADGA) is designed, where layer I ensures production efficiency and layer II optimizes assembly line balance. Finally, an assemble example of high-pressure common rail fuel pumps (HCRFP) is used to validate the effectiveness of the proposed method. The results demonstrate notable improvements compared to traditional single-product assembly (TSPA) line in scenarios with workstation numbers 4, 5, 6, and 7. Specifically, the production takt time is reduced by 4.19% to 9.56%, and CBR is enhanced by approximately 50%. Further comparison with three other classic algorithms confirms the superiority of ADGA. Additionally, it is observed that remanufacturability (proportion of remanufactured parts) has a significant impact on assembly performance. As remanufacturability increases, both takt time and CBR increase, reaching their maximum values when remanufacturability is around 0.5.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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 3D multiobjective multi-item eco-routing problem for refrigerated fresh products delivery using NSGA-II with hybrid chromosome","authors":"","doi":"10.1016/j.cie.2024.110644","DOIUrl":"10.1016/j.cie.2024.110644","url":null,"abstract":"<div><div>In a developing countries, say India, about 40 percent fresh foods are wasted during transportation and $14 billion of post harvest products are lost due to inefficiency of cold supply chain such as using non-refrigerated vehicle during last mile transport. Hence, temperature control through refrigerated transportation is very essential. But, the by-product of this process i.e., carbon emission (CE) due to transportation and refrigeration is detrimental for the world. Only logistic transportation contributes about 25 percent of global CE. Due to the world wide infrastructural development, there are several available routes for the road transportation among different cities. For the maintenance of these routes, there are some toll plazas for collection of money. Some routes also cross the rail lines. For maximum profit, a supplier distributes the products at the earliest as the retailers fix the product’s price with respect to its freshness. Again, this process generates more CE. With these realities, a 3D multiobjective multi-item eco-routing problems for refrigerated fresh products (3DMOMIERPsfRFPs) are developed, where a refrigerated vehicle starts from a depot (refrigerated) and comes back after distributing the fresh products to retailers as per their demands. The optimal routing plan, vehicle’s velocity and preservation rate are determined so that total profit and CE are respectively maximized and minimized simultaneously. For solution, an NSGA-II with different modified operators (NSGA-IIwDOs) is developed with hybrid chromosomes having discrete and continuous variables together, probabilistic selection, problem-specific crossover and generation-dependent mutation. Some performance metrics are presented through NSGA-IIwDOs on the standard TSPLIB problems. Results of 3DMOMIERPsfRFPs without and with specific delivery time slots, road-dependent vehicle velocity and time constraints are evaluated. Pareto front for multiobjective are depicted. As a particular case, results of a previous investigation are obtained. Some of the managerial decisions are observed.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539729","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A predictive model for the estimation of industrial PM2.5 emissions for IoT-based devices","authors":"","doi":"10.1016/j.cie.2024.110662","DOIUrl":"10.1016/j.cie.2024.110662","url":null,"abstract":"<div><div>The paper is devoted to solving the problem, associated with increasing the forecasting accuracy of pollutant concentration level based on <span><math><mrow><mi>P</mi><msub><mrow><mi>M</mi></mrow><mrow><mn>2</mn><mo>.</mo><mn>5</mn></mrow></msub></mrow></math></span> dust. The LANN model (LANN – Lagrange powered Artificial Neuron Network), proposed in the paper, allows you to take into account the mutual influence of pollution sources on the concentration level at monitoring points, which, on the one hand, allows to manage the volume of emissions from industrial enterprises in such a way as to avoid penalties and, on the other hand, allows the regulatory agencies to determine points for environmental control, at which permissible standards will be most likely exceeded. The suggested solution makes it possible to use low-cost IoT-based air quality monitoring devices, which were primarily considered not applicable due to their low accuracy and exposure to the influence of short-term stochastic factors; besides, no models were available, which would be capable to provide the necessary accuracy and forecast horizon on the base of IoT data. At the same time, the obtained model has low requirements for computing resources compared to dispersion models and is dependent on the accuracy of weather information; besides, the model allows you to take into account trends and obtain better forecast values in terms of accuracy than the models, that use regression methods, neural network models and ML models, stochastic models and their ensembles. The application of the model improves well-known pollutant dispersion estimation calculation techniques through the use of measurement data flow and dynamic adaptation to changing conditions. The model was trained on the dataset over the period 2022–2023 collected from 5 monitoring devices, which were installed in the catchment area of the group, incl. 13 industrial points of <span><math><mrow><mi>P</mi><msub><mrow><mi>M</mi></mrow><mrow><mn>2</mn><mo>.</mo><mn>5</mn></mrow></msub></mrow></math></span> pollutant sources.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive budget allocation in simheuristics applied to stochastic home healthcare routing and scheduling","authors":"","doi":"10.1016/j.cie.2024.110651","DOIUrl":"10.1016/j.cie.2024.110651","url":null,"abstract":"<div><div>The organization of home care is of pivotal importance in response to the trend of delivering more care directly to clients’ residences. With more vulnerable clients residing at home, variability in care durations needs careful consideration. This paper addresses the operational home healthcare routing and scheduling problem (HHCRSP) with uncertainty in travel and service times. The quality of the routes is evaluated based on the expected objective function, incorporating travel time, waiting time, and shift overtime. Due to the complexity of the problem, a simheuristic approach is applied that carefully integrates the optimization of the deterministic HHCRSP with simulation. This study proposes a new framework, based on optimal computing budget allocation and the expected opportunity costs, to dynamically determine when to employ optimization and when to use simulation. A practical case study demonstrates the effectiveness of the approach and reveals the substantial impact of accounting for randomness in the HHCRSP.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-criteria decision making beyond consistency: An alternative to AHP for real-world industrial problems","authors":"","doi":"10.1016/j.cie.2024.110661","DOIUrl":"10.1016/j.cie.2024.110661","url":null,"abstract":"<div><div>The Analytic Hierarchy Process (AHP) is a widely used method for multi-criteria decision-making that relies on consistency in pairwise comparisons. However, decision-makers often struggle to provide fully consistent judgments in real-world scenarios. This article introduces a decision-making framework that operates independently of consistency. Utilizing the Skew-Symmetric Bilinear representation of preferences allows decision-makers to more accurately evaluate alternatives and criteria, making this framework more applicable in practical settings. The proposed method is validated through practical examples and an in-depth case study in the textile industry, effectively resolving a complex decision-making problem related to acquiring a data analytics tool for supplier selection. The results underscore the robustness and flexibility of this consistency-independent technique as an alternative to traditional AHP methods.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552140","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing long-term carpooling with fairness: A collaborative Jaya algorithm","authors":"","doi":"10.1016/j.cie.2024.110663","DOIUrl":"10.1016/j.cie.2024.110663","url":null,"abstract":"<div><div>Inspired by Japan’s unique regulatory framework, this study addresses the Long-Term Carpooling Problem with Fairness (LTCPF), with a focus on enhancing sustainable urban transport. We investigate this issue by optimizing carpooling arrangements to balance travel time, ensure inclusive rider participation, and reduce detour time discrepancies. At the core of our approach is the Collaborative Jaya Algorithm (CJA), a modification of the existing Jaya algorithm with improved computational efficiency and reduced hyperparameter dependency. Our model assigns explicitly fixed roles to participants as drivers or riders, promoting efficient and equitable carpooling. The practical efficacy of the CJA is validated through rigorous simulation experiments across various scenarios. The simulation results demonstrate that the proposed algorithm is superior to existing counterparts.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552136","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing internal supply chain management in manufacturing through a simulation-based digital twin platform","authors":"","doi":"10.1016/j.cie.2024.110670","DOIUrl":"10.1016/j.cie.2024.110670","url":null,"abstract":"<div><div>Digital Twin (DT) technology is profoundly changing the manufacturing landscape and supply chain management with its ability to create real-time digital replicas of physical processes, allowing for enhanced monitoring and optimized decision-making. However, the analysis of scientific literature reveals that further efforts are needed to spread the use of Industry 4.0 technologies, in the specific context of Internal Supply Chains (ISCs). The main aim of this study is to design, develop test and validate a multi-plant Simulation-Based DT production planning platform for ISCs management. A modular architecture is adopted, and the focus is on a Simulation-Based Digital Twin module, which uses an object-oriented structure and enables what-if analyses, involving several scheduling rules and ISC configurations. The proposed solution ensures flexibility and scalability, two crucial features in a constantly evolving market environment. The platform is tested and validated through a case study, involving a corporate group in the Oil &amp; Gas manufacturing sector, which needs to improve the ISC performance, under a Make-To-Order production strategy. The comparison with a baseline scenario, where the platform is not adopted, shows that the proposed approach can significantly reduce the average flow time, the average tardiness, the number of late orders. This study has important practical implications because enables proactive and smart decision-making, aimed at resource optimization and continuous improvement, through predictive analytics and scenario analysis.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning-based production, maintenance, and quality optimization in smart manufacturing systems: A literature review and trends","authors":"","doi":"10.1016/j.cie.2024.110656","DOIUrl":"10.1016/j.cie.2024.110656","url":null,"abstract":"<div><div>With the introduction of manufacturing paradigms, including Industry 4.0, production research has shifted its focus to enabling intelligent manufacturing systems within industrial environments. These systems can efficiently schedule and control processes and operations using artificial intelligence methods, including machine learning and deep learning. Since 1995, relevant literature has presented several examples of such implementations, addressing topics, for example equipment fault diagnosis and quality inspections. To this end, the present paper strives to present a state-of-the-art review of the learning-based scheduling and control frameworks, which are exploited in the production research. The review is limited to the relevant research between the years 1995 and 2024, surveying approaches in the domains of manufacturing, maintenance, and quality control. To this end, the paper follows a <em>meta</em>-analysis method for the selection and evaluation of relevant research articles. Moreover, research questions are formulated to analyze the obtained findings and seek out insights on aspects of the relevant research, including the inclusion of decision-making models and dissemination of literature. The provided answers, among others, reveal trends and limitations of the state-of-the art research in relation to learning-based scheduling and control.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unmasking phishers: ML for malicious certificate detection","authors":"","doi":"10.1016/j.cie.2024.110652","DOIUrl":"10.1016/j.cie.2024.110652","url":null,"abstract":"<div><div>Phishing attacks increasingly use digital certificates to appear safe to users, and the frequency of such attacks has surged in recent years. As an example, around 80% of the 2021 phishing attacks used digital certificates to appear legitimate. The most common methods today for detecting phishing websites rely on users reporting the websites to phishing repositories, where they are then confirmed. This process can be slow, allowing the attacker to have time to have their phishing attack out on the Internet. Newer methods that implement machine learning models for the detection of phishing websites based on their digital certificate have been shown to be effective. This paper presents a system that uses certificate and domain name related features along with machine learning methods for the detection of phishing websites. To develop the system, data was collected from PhishTank and Tranco for domain names, and Censys was used for certificate retrieval. The domain related features are partly engineered using a time-series based deep learning model to get a vector representation of the domain name. Using the features engineered from the certificate and domain name, classical machine learning classifiers are trained and compared. Enriching the feature set with the vector representation of the domain names results in higher performance in distinguishing suspicious certificates from benign ones, going from an F1-score of 0.77 for a feature set solely based on certificate-related features to a performance of 0.89 with the enriched feature set. A time-based evaluation reflects the same performance with an F1-score of 0.88, which is an improvement compared to existing approaches to feature engineering.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring the impact of EU tendering operations on future AI governance and standards in pharmaceuticals","authors":"","doi":"10.1016/j.cie.2024.110655","DOIUrl":"10.1016/j.cie.2024.110655","url":null,"abstract":"<div><div>This research examines the incorporation of artificial intelligence (AI) into the domain of tender management (TM) within the pharmaceutical industry, with a particular emphasis on operational efficiency, governance, and compliance with European regulatory standards. A comparative analysis of four companies—two that have adopted AI and two that have not—reveals significant discrepancies in the management of TM processes between AI-driven and traditional companies.</div><div>The study employs the Delphi method to ascertain expert consensus on eight critical areas of AI governance, including data privacy, transparency, and ethical AI use. The findings indicate that companies integrating AI demonstrate enhanced decision-making capabilities, accelerated processing times, and enhanced stakeholder engagement. However, they also encounter challenges pertaining to ethical governance and regulatory compliance.</div><div>The research highlights the necessity of aligning the adoption of AI with the latest European directives, such as the AI Act and General Data Protection Regulation (GDPR), to ensure both operational efficiency and adherence to ethical standards. The broader implications of the study underscore the necessity for pharmaceutical companies to develop robust governance frameworks, prioritize ethical considerations, and maintain regulatory compliance to fully leverage the potential of AI. Additionally, the study contributes to the ongoing scholarly discourse by providing empirical evidence on the interplay between AI, ethics, and governance, thereby encouraging further interdisciplinary research. This work emphasizes the critical role of strategic AI adoption in maintaining competitive advantage while safeguarding societal trust and adhering to legal requirements.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142539726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}