Pub Date : 2024-09-24DOI: 10.1016/j.cie.2024.110603
Project delays are common in construction due to unavoidable factors such as severe weather and human factors such as poor planning. These delays originate from the constituent activities within the project. A critical challenge in project management is accurately assigning delays to specific activities. However, this issue remains poorly understood. This study aims to address the allocation of delays to constituent activities by developing a mechanism using the Shapley value. We also propose solution methods to effectively solve the delay allocation problem. Moreover, we conduct numerical experiments that demonstrate the efficiency and applicability of the proposed mechanism and solution methods. This study can provide guidelines for allocating project delays (e.g., identifying the activity that contributes most to project delay) and project appraisal. Overall, this study contributes to a better understanding of the allocation of project delays, providing reference for project management and decision-making in the construction industry.
{"title":"Mechanism for allocating delay to constituent activities in project management","authors":"","doi":"10.1016/j.cie.2024.110603","DOIUrl":"10.1016/j.cie.2024.110603","url":null,"abstract":"<div><div>Project delays are common in construction due to unavoidable factors such as severe weather and human factors such as poor planning. These delays originate from the constituent activities within the project. A critical challenge in project management is accurately assigning delays to specific activities. However, this issue remains poorly understood. This study aims to address the allocation of delays to constituent activities by developing a mechanism using the Shapley value. We also propose solution methods to effectively solve the delay allocation problem. Moreover, we conduct numerical experiments that demonstrate the efficiency and applicability of the proposed mechanism and solution methods. This study can provide guidelines for allocating project delays (e.g., identifying the activity that contributes most to project delay) and project appraisal. Overall, this study contributes to a better understanding of the allocation of project delays, providing reference for project management and decision-making in the construction industry.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358326","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}
Pub Date : 2024-09-24DOI: 10.1016/j.cie.2024.110601
Unmanned Aerial Vehicles (UAVs) are playing an increasingly critical role in military surveillance missions. However, due to safety and economic issues, it is necessary to validate the UAV performance and algorithms in a semi-physical simulation environment before the real flights. In this study, the mechanical structure and control system of the semi-physical simulation system is developed for the UAVs. In order to better simulate the attitude of the UAV during a flight, the flight attitude simulator is designed. Also, a sand table of the mountainous scenery from real inspection tasks is developed to work with the simulation system. Path planning algorithms are embedded in the platform, and improvements and evaluations of traditional algorithms are carried out. Then, an improved adaptive particle swarm optimization (IAPSO) algorithm is proposed to improve the accuracy of the path of UAVs. An energy-consumption prediction model is established for the platform. By combining the IAPSO algorithm with the energy-consumption prediction model, the best path with low energy consumption can be obtained. Finally, the effectiveness of the simulation system is verified by comparison experiments of the mathematical simulation, semi-physical simulation, and real flight.
{"title":"Construction of an improved semi-physical simulation system for UAV with integrated energy-consumption prediction model and its evaluation of the path planning algorithms in mountainous scenery","authors":"","doi":"10.1016/j.cie.2024.110601","DOIUrl":"10.1016/j.cie.2024.110601","url":null,"abstract":"<div><div>Unmanned Aerial Vehicles (UAVs) are playing an increasingly critical role in military surveillance missions. However, due to safety and economic issues, it is necessary to validate the UAV performance and algorithms in a semi-physical simulation environment before the real flights. In this study, the mechanical structure and control system of the semi-physical simulation system is developed for the UAVs. In order to better simulate the attitude of the UAV during a flight, the flight attitude simulator is designed. Also, a sand table of the mountainous scenery from real inspection tasks is developed to work with the simulation system. Path planning algorithms are embedded in the platform, and improvements and evaluations of traditional algorithms are carried out. Then, an improved adaptive particle swarm optimization (IAPSO) algorithm is proposed to improve the accuracy of the path of UAVs. An energy-consumption prediction model is established for the platform. By combining the IAPSO algorithm with the energy-consumption prediction model, the best path with low energy consumption can be obtained. Finally, the effectiveness of the simulation system is verified by comparison experiments of the mathematical simulation, semi-physical simulation, and real flight.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358327","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}
Pub Date : 2024-09-24DOI: 10.1016/j.cie.2024.110602
The increasing adoption of additive manufacturing (AM) in the industrial sector is leading to an imbalance between supply and demand of additively manufactured subcomponents: companies demanding AM services require very specific products and AM suppliers differ widely in their capabilities. Some existing proposals aim to help match supply and demand by merely making customer–supplier allocations. Only a few recent works go beyond allocation issues and propose market mechanisms to also address pricing aspects. However, we observe that these mechanisms do not fully exploit the potential of additive manufacturing techniques. The aim of this paper is to design a market mechanism that considers the particularity of AM techniques, wherein suppliers can benefit from manufacturing multiple heterogeneous parts from multiple customers in the same build area to increase production throughput. This market mechanism has been implemented as an iterative combinatorial double auction that adapts to this feature of the AM market: customers will bid to get their orders produced and suppliers will submit asking quotes to win the production of combinations of those orders. The mechanism solves the allocation and pricing of AM orders while seeking the maximization of social welfare. The procedure is simulated in a theoretical environment to evaluate its performance and to identify the most appropriate conditions for its implementation in a real environment. Unlike other existing proposals for client-supplier allocation mechanisms in additive manufacturing, the proposed mechanism allows a single supplier to produce a combination of orders from different clients, leading to a pricing system that maximizes social welfare without participants disclosing sensitive information.
工业部门越来越多地采用增材制造（AM）技术，导致增材制造子部件的供需失衡：要求提供增材制造服务的公司需要非常特殊的产品，而增材制造供应商的能力却大相径庭。现有的一些建议旨在仅通过客户与供应商之间的分配来帮助实现供需匹配。近期只有少数著作超越了分配问题，提出了同时解决定价问题的市场机制。然而，我们注意到这些机制并没有充分利用增材制造技术的潜力。本文旨在设计一种考虑到增材制造技术特殊性的市场机制，供应商可以从在同一构建区域制造来自多个客户的多个异构部件中获益，从而提高生产吞吐量。该市场机制以迭代组合式双重拍卖的形式实现，以适应自动机械加工市场的这一特点：客户通过竞标获得订单生产，供应商通过报价赢得订单组合的生产。该机制在寻求社会福利最大化的同时，解决了 AM 订单的分配和定价问题。该程序在理论环境中进行了模拟，以评估其性能，并确定在真实环境中实施该程序的最合适条件。与其他现有的增材制造客户-供应商分配机制建议不同的是，所建议的机制允许单一供应商生产来自不同客户的订单组合，从而在参与者不披露敏感信息的情况下实现社会福利最大化的定价系统。
{"title":"An iterative price-based combinatorial double auction for additive manufacturing markets","authors":"","doi":"10.1016/j.cie.2024.110602","DOIUrl":"10.1016/j.cie.2024.110602","url":null,"abstract":"<div><div>The increasing adoption of additive manufacturing (AM) in the industrial sector is leading to an imbalance between supply and demand of additively manufactured subcomponents: companies demanding AM services require very specific products and AM suppliers differ widely in their capabilities. Some existing proposals aim to help match supply and demand by merely making customer–supplier allocations. Only a few recent works go beyond allocation issues and propose market mechanisms to also address pricing aspects. However, we observe that these mechanisms do not fully exploit the potential of additive manufacturing techniques. The aim of this paper is to design a market mechanism that considers the particularity of AM techniques, wherein suppliers can benefit from manufacturing multiple heterogeneous parts from multiple customers in the same build area to increase production throughput. This market mechanism has been implemented as an iterative combinatorial double auction that adapts to this feature of the AM market: customers will bid to get their orders produced and suppliers will submit asking quotes to win the production of combinations of those orders. The mechanism solves the allocation and pricing of AM orders while seeking the maximization of social welfare. The procedure is simulated in a theoretical environment to evaluate its performance and to identify the most appropriate conditions for its implementation in a real environment. Unlike other existing proposals for client-supplier allocation mechanisms in additive manufacturing, the proposed mechanism allows a single supplier to produce a combination of orders from different clients, leading to a pricing system that maximizes social welfare without participants disclosing sensitive information.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142328065","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}
Pub Date : 2024-09-23DOI: 10.1016/j.cie.2024.110590
Optimizing supplier selections is an open ended problem, relevant to the operational performance of both individual companies and entire supply chains. Considering the prediction of future occurrences of delays in the optimization of supplier selections is still an under covered problem. Unlike existing literature, this article suggests a more collaborative and integrated workflow to improve the visibility and involvement of multiple stakeholders in the supplier selection decision-making processes. This is achieved through enhanced collaboration between multiple stakeholders (suppliers, customers, decision-makers from different departments, in addition to data sources from information systems), and better integration between data analysis and decision-making, through data-driven-machine-learning and optimization. The specificities of a French company in the furniture industry are considered. A workflow model is designed to support information sharing and to streamline knowledge and interactions between multiple stakeholders from different expertise domains. A Collaborative Predictive Optimization System (CPOS) is designed to classify expected occurrences of delays, to optimize order allocations, and to enable stakeholder collaboration. Delay prediction involves Decision Trees, Random Forests, and eXtreme Gradient Boosting (XGBoost). Supplier selection is solved using mathematical programming, while considering the classification of expected occurrences of delays. Stakeholder collaboration relies on information systems and uses prediction and optimization to support finding satisfactory agreements. The approach is validated using a real 3.5-year dataset, including 139 suppliers, 7,934 products and 89,080 purchase orders. A detailed experimentation, including sensitivity analysis, best–worst case analysis, and a larger scale analysis on company datasets, shows that the suggested approach enhances collaboration and achieves delay reduction and total procurement cost savings. Valuable managerial insights are collected, including the necessity to adopt digital technologies, to adapt company workflows, and to improve upstream negotiations and supplier commitments to yearly plannings.
{"title":"Collaborative and integrated data-driven delay prediction and supplier selection optimization: A case study in a furniture industry","authors":"","doi":"10.1016/j.cie.2024.110590","DOIUrl":"10.1016/j.cie.2024.110590","url":null,"abstract":"<div><div>Optimizing supplier selections is an open ended problem, relevant to the operational performance of both individual companies and entire supply chains. Considering the prediction of future occurrences of delays in the optimization of supplier selections is still an under covered problem. Unlike existing literature, this article suggests a more collaborative and integrated workflow to improve the visibility and involvement of multiple stakeholders in the supplier selection decision-making processes. This is achieved through enhanced collaboration between multiple stakeholders (suppliers, customers, decision-makers from different departments, in addition to data sources from information systems), and better integration between data analysis and decision-making, through data-driven-machine-learning and optimization. The specificities of a French company in the furniture industry are considered. A workflow model is designed to support information sharing and to streamline knowledge and interactions between multiple stakeholders from different expertise domains. A Collaborative Predictive Optimization System (CPOS) is designed to classify expected occurrences of delays, to optimize order allocations, and to enable stakeholder collaboration. Delay prediction involves Decision Trees, Random Forests, and eXtreme Gradient Boosting (XGBoost). Supplier selection is solved using mathematical programming, while considering the classification of expected occurrences of delays. Stakeholder collaboration relies on information systems and uses prediction and optimization to support finding satisfactory agreements. The approach is validated using a real 3.5-year dataset, including 139 suppliers, 7,934 products and 89,080 purchase orders. A detailed experimentation, including sensitivity analysis, best–worst case analysis, and a larger scale analysis on company datasets, shows that the suggested approach enhances collaboration and achieves delay reduction and total procurement cost savings. Valuable managerial insights are collected, including the necessity to adopt digital technologies, to adapt company workflows, and to improve upstream negotiations and supplier commitments to yearly plannings.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358325","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}
Pub Date : 2024-09-23DOI: 10.1016/j.cie.2024.110596
Digital and simulation models support the design and management of complex systems. However, system modelling is a time-demanding and knowledge-intensive activity. Moreover, modern manufacturing systems are subjected to frequent changes in production plans and subsequent reconfigurations. Therefore, the quick regeneration of the digital models is necessary to align digital twins and cyber-physical systems. This paper proposes a novel event-centric process mining paradigm, a process discovery algorithm, and a set of Key Performance Indicators for the fast and automated generation of digital models and their benchmarking. The discovery algorithm is based on the Event Relationship Graph of the conceptual model of the physical line. The algorithm is tested in four realistic systems of increasing complexity to verify the accuracy in modelling multi-product systems with re-entrant flows and random reworks in the presence of the assembly, disassembly, and split processes beyond the processing operations, and multi-operation workstations. The Event Relationship Graphs of the four systems are presented through the equivalent Petri nets models. The proposed approach is suitable for systems where the sensor positions are known and meaningful, like manufacturing systems, and it is effective for the quick automated generation of digital models for the activities of production planning and control as it requires a few seconds of computation time and a few hours of system observation.
数字模型和仿真模型支持复杂系统的设计和管理。然而，系统建模是一项需要大量时间和知识的工作。此外，现代制造系统的生产计划经常发生变化，随后还要进行重新配置。因此，数字模型的快速再生对于数字孪生和网络物理系统的协调是非常必要的。本文提出了一种新颖的以事件为中心的流程挖掘范式、一种流程发现算法和一套关键性能指标，用于快速自动生成数字模型及其基准。发现算法基于物理线路概念模型的事件关系图。该算法在四个复杂度不断增加的现实系统中进行了测试，以验证其在多产品系统建模中的准确性，这些系统具有重入流和随机返工，并且存在加工操作之外的装配、拆卸和拆分过程以及多操作工作站。四个系统的事件关系图通过等效的 Petri 网模型呈现。所提出的方法适用于传感器位置已知且有意义的系统，如制造系统，它能有效地为生产计划和控制活动快速自动生成数字模型，因为它只需要几秒钟的计算时间和几个小时的系统观察。
{"title":"Automated generation of digital models for manufacturing systems: The event-centric process mining approach","authors":"","doi":"10.1016/j.cie.2024.110596","DOIUrl":"10.1016/j.cie.2024.110596","url":null,"abstract":"<div><div>Digital and simulation models support the design and management of complex systems. However, system modelling is a time-demanding and knowledge-intensive activity. Moreover, modern manufacturing systems are subjected to frequent changes in production plans and subsequent reconfigurations. Therefore, the quick regeneration of the digital models is necessary to align digital twins and cyber-physical systems. This paper proposes a novel event-centric process mining paradigm, a process discovery algorithm, and a set of Key Performance Indicators for the fast and automated generation of digital models and their benchmarking. The discovery algorithm is based on the Event Relationship Graph of the conceptual model of the physical line. The algorithm is tested in four realistic systems of increasing complexity to verify the accuracy in modelling multi-product systems with re-entrant flows and random reworks in the presence of the assembly, disassembly, and split processes beyond the processing operations, and multi-operation workstations. The Event Relationship Graphs of the four systems are presented through the equivalent Petri nets models. The proposed approach is suitable for systems where the sensor positions are known and meaningful, like manufacturing systems, and it is effective for the quick automated generation of digital models for the activities of production planning and control as it requires a few seconds of computation time and a few hours of system observation.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142328025","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}
Pub Date : 2024-09-23DOI: 10.1016/j.cie.2024.110597
This study examines the dynamic evolution of business models in intelligent manufacturing enterprises, focusing on their adaptation to market demands and technological advancements. While business model transformation in intelligent manufacturing has garnered academic attention, there remains a gap in effectively measuring and analyzing the dynamic evolution and inherent characteristics of these models. To address this gap, we apply machine learning techniques, specifically combining convolutional neural networks with gated recurrent units, to develop a text analysis approach that reduces noise and analyzes the evolutionary process of business models in intelligent manufacturing enterprises. We validate our approach using annual report texts from intelligent manufacturing enterprises, covering the period from 2011 to 2021. The results demonstrate that our machine learning approach effectively classifies business models within complex, unstructured text data. Our analysis identifies three key stages in the evolution of business models: “efficiency driven,” “novelty boom,” and “ novelty renaissance.” Additionally, we explore the underlying characteristics and trends of these business models, shedding light on the factors driving their evolution.
{"title":"Leveraging machine learning to uncover the dynamic evolution of business models in intelligent manufacturing","authors":"","doi":"10.1016/j.cie.2024.110597","DOIUrl":"10.1016/j.cie.2024.110597","url":null,"abstract":"<div><div>This study examines the dynamic evolution of business models in intelligent manufacturing enterprises, focusing on their adaptation to market demands and technological advancements. While business model transformation in intelligent manufacturing has garnered academic attention, there remains a gap in effectively measuring and analyzing the dynamic evolution and inherent characteristics of these models. To address this gap, we apply machine learning techniques, specifically combining convolutional neural networks with gated recurrent units, to develop a text analysis approach that reduces noise and analyzes the evolutionary process of business models in intelligent manufacturing enterprises. We validate our approach using annual report texts from intelligent manufacturing enterprises, covering the period from 2011 to 2021. The results demonstrate that our machine learning approach effectively classifies business models within complex, unstructured text data. Our analysis identifies three key stages in the evolution of business models: “efficiency driven,” “novelty boom,” and “ novelty renaissance.” Additionally, we explore the underlying characteristics and trends of these business models, shedding light on the factors driving their evolution.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142358329","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}
Pub Date : 2024-09-21DOI: 10.1016/j.cie.2024.110586
The hospitality industry generates significant food waste, leading to adverse environmental and economic impacts, social and ethical concerns, legal and regulatory issues, and operational challenges. The lack of traceability and trust among stakeholders in the hospitality industry exacerbates the expensive and difficult nature of food waste management. This work proposes a blockchain-based solution that aims to minimize food waste generated in hospitality outlets, thereby fostering a sustainable food ecosystem. Within this context, the term ’sustainable food ecosystem’ refers to the interconnected network of stakeholders involved in the responsible management of food resources within the hospitality industry. In this context, we categorize these stakeholders under the umbrella of ’food resource management entities,’ encompassing both food donation organizations and recycling companies, recognizing their distinct roles in the effective management of surplus food resources. With our proposed solution, businesses can track and verify the origin, movement, and disposal of food items in real-time, facilitating streamlined inventory planning, waste reduction, and heightened operational efficiency. Additionally, the proposed system ensures transparency and accountability, guaranteeing the proper and efficient disposal of food waste. Using a permissioned Ethereum network, our solution establishes seamless connectivity between food and beverage outlets and various food resource management entities. We present a generalized system for secure information sharing, integrating advanced algorithms tailored to capture and enhance trust among participating stakeholders. Furthermore, our thorough security analysis underscores the robustness of our proposed solution, effectively addressing various security vulnerabilities. Lastly, the proposed blockchain-based solution is commercially viable, enabling the hospitality industry to operate with enhanced efficiency while providing improved information connectivity for various stakeholders in the food supply chain.
{"title":"Using blockchain technology to achieve sustainability in the hospitality industry by reducing food waste","authors":"","doi":"10.1016/j.cie.2024.110586","DOIUrl":"10.1016/j.cie.2024.110586","url":null,"abstract":"<div><div>The hospitality industry generates significant food waste, leading to adverse environmental and economic impacts, social and ethical concerns, legal and regulatory issues, and operational challenges. The lack of traceability and trust among stakeholders in the hospitality industry exacerbates the expensive and difficult nature of food waste management. This work proposes a blockchain-based solution that aims to minimize food waste generated in hospitality outlets, thereby fostering a sustainable food ecosystem. Within this context, the term ’sustainable food ecosystem’ refers to the interconnected network of stakeholders involved in the responsible management of food resources within the hospitality industry. In this context, we categorize these stakeholders under the umbrella of ’food resource management entities,’ encompassing both food donation organizations and recycling companies, recognizing their distinct roles in the effective management of surplus food resources. With our proposed solution, businesses can track and verify the origin, movement, and disposal of food items in real-time, facilitating streamlined inventory planning, waste reduction, and heightened operational efficiency. Additionally, the proposed system ensures transparency and accountability, guaranteeing the proper and efficient disposal of food waste. Using a permissioned Ethereum network, our solution establishes seamless connectivity between food and beverage outlets and various food resource management entities. We present a generalized system for secure information sharing, integrating advanced algorithms tailored to capture and enhance trust among participating stakeholders. Furthermore, our thorough security analysis underscores the robustness of our proposed solution, effectively addressing various security vulnerabilities. Lastly, the proposed blockchain-based solution is commercially viable, enabling the hospitality industry to operate with enhanced efficiency while providing improved information connectivity for various stakeholders in the food supply chain.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142316159","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}
Pub Date : 2024-09-20DOI: 10.1016/j.cie.2024.110582
Employee turnover significantly impacts organizations, particularly those with substantial investments in training their workforce. To mitigate these effects, we propose a Prescriptive Human Resources Analytics approach that optimizes employee benefits to minimize total costs, focusing on turnover management The methodology models employee decision-making using a discrete choice model, with parameters estimated through maximum likelihood. We solve the resulting nonlinear optimization problem with a heuristic tailored to the problem’s complexity. We applied this methodology to a hospital case study, which was used to enhance the transportation system as an employee benefit, considering the associated turnover costs. The results demonstrate that our approach can reduce total costs, optimize the usage level of the designed benefits, and increase employee satisfaction. This research provides a robust framework for data-driven decision-making in HR, offering practical tools for improving employee retention strategies.
员工流失对企业，尤其是那些在员工培训方面投入巨大的企业造成了严重影响。为了减轻这些影响，我们提出了一种 "规范性人力资源分析"（Prescriptive Human Resources Analytics）方法，该方法可以优化员工福利，最大限度地降低总成本，重点关注员工流失管理。我们根据问题的复杂程度，采用启发式方法解决由此产生的非线性优化问题。我们将这一方法应用于一家医院的案例研究，考虑到相关的离职成本，该医院将交通系统作为一项员工福利进行了改进。结果表明，我们的方法可以降低总成本，优化所设计福利的使用水平，并提高员工满意度。这项研究为人力资源领域的数据驱动决策提供了一个强大的框架，为改进员工保留战略提供了实用工具。
{"title":"Designing employee benefits to optimize turnover: A prescriptive analytics approach","authors":"","doi":"10.1016/j.cie.2024.110582","DOIUrl":"10.1016/j.cie.2024.110582","url":null,"abstract":"<div><p>Employee turnover significantly impacts organizations, particularly those with substantial investments in training their workforce. To mitigate these effects, we propose a Prescriptive Human Resources Analytics approach that optimizes employee benefits to minimize total costs, focusing on turnover management The methodology models employee decision-making using a discrete choice model, with parameters estimated through maximum likelihood. We solve the resulting nonlinear optimization problem with a heuristic tailored to the problem’s complexity. We applied this methodology to a hospital case study, which was used to enhance the transportation system as an employee benefit, considering the associated turnover costs. The results demonstrate that our approach can reduce total costs, optimize the usage level of the designed benefits, and increase employee satisfaction. This research provides a robust framework for data-driven decision-making in HR, offering practical tools for improving employee retention strategies.</p></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142271554","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}
Pub Date : 2024-09-19DOI: 10.1016/j.cie.2024.110581
This paper presents two novel data-driven multi-objective predictive maintenance scheduling models that integrate remaining useful life (RUL) prediction into maintenance planning. First, we propose a deep learning ensemble model that includes a convolutional neural network and bidirectional long short-term memory network with a temporal self-attentional mechanism and Bayesian optimization method to predict system RUL effectively. Then, two novel multi-objective mixed-integer linear programming (MILP) models are developed based on the system-predicted RUL to deal with the system predictive maintenance problem, which aims to minimize the total maintenance completion time and maintenance-related costs simultaneously. To solve this problem, we design an iteration -constraint method to achieve Pareto solutions. Meanwhile, a fuzzy logic method is proposed to recommend a preferred Pareto solution for decision-makers. Finally, the aircraft engine C-MAPSS dataset from NASA validates that the effectiveness of the proposed data-driven multi-objective predictive maintenance scheduling models are effective. For the predictive maintenance of 20 aircraft engines, both the maintenance completion time and maintenance cost are reduced by more than 40%.
{"title":"Multi-objective predictive maintenance scheduling models integrating remaining useful life prediction and maintenance decisions","authors":"","doi":"10.1016/j.cie.2024.110581","DOIUrl":"10.1016/j.cie.2024.110581","url":null,"abstract":"<div><div>This paper presents two novel data-driven multi-objective predictive maintenance scheduling models that integrate remaining useful life (RUL) prediction into maintenance planning. First, we propose a deep learning ensemble model that includes a convolutional neural network and bidirectional long short-term memory network with a temporal self-attentional mechanism and Bayesian optimization method to predict system RUL effectively. Then, two novel multi-objective mixed-integer linear programming (MILP) models are developed based on the system-predicted RUL to deal with the system predictive maintenance problem, which aims to minimize the total maintenance completion time and maintenance-related costs simultaneously. To solve this problem, we design an iteration <span><math><mi>ϵ</mi></math></span>-constraint method to achieve Pareto solutions. Meanwhile, a fuzzy logic method is proposed to recommend a preferred Pareto solution for decision-makers. Finally, the aircraft engine C-MAPSS dataset from NASA validates that the effectiveness of the proposed data-driven multi-objective predictive maintenance scheduling models are effective. For the predictive maintenance of 20 aircraft engines, both the maintenance completion time and maintenance cost are reduced by more than 40%.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142316158","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}
Pub Date : 2024-09-19DOI: 10.1016/j.cie.2024.110579
The rapid expansion of the electric vehicle (EV) market in recent years has presented manufacturers with the challenge of strategically prioritizing the types of EVs in which to invest under uncertain conditions. This study proposes an enhanced multi-attribute decision-making (MADM) framework to address this issue by leveraging online reviews and expert opinions. The proposed framework combines a novel linguistic representation, called calibrated basic uncertain linguistic information (CBULI), to capture uncertainty, a value function from cumulative prospect theory (CPT) with double reference points to model the manufacturers’ psychological preferences, and the Preference Ranking Organization Method for Enrichment of Evaluations II (PROMETHEE II) for prioritizing EVs for investment. It extracts demand attributes from online reviews, applies CBULI to represent uncertain evaluations, and incorporates CPT to capture risk preferences. A case study of an EV manufacturing enterprise in Sichuan, China, was conducted to validate our framework, and the results demonstrated its effectiveness and practicability in identifying the most promising types of EVs for investment. The results of sensitivity and comparative analyses further confirmed the robustness and superiority of the model in comparison with prevalent methods. The work here contributes to methodological advancements in research on the choice of types of EVs in which to invest, and provides valuable insights for EV enterprises to make informed investment-related decisions that are aligned with user demands and enterprise development. The proposed MADM framework supports the strategic development of the EV industry by enabling manufacturers to prioritize investment in the appropriate types of EVs under uncertainty.
{"title":"Leveraging online reviews and expert opinions for electric vehicle type prioritization","authors":"","doi":"10.1016/j.cie.2024.110579","DOIUrl":"10.1016/j.cie.2024.110579","url":null,"abstract":"<div><div>The rapid expansion of the electric vehicle (EV) market in recent years has presented manufacturers with the challenge of strategically prioritizing the types of EVs in which to invest under uncertain conditions. This study proposes an enhanced multi-attribute decision-making (MADM) framework to address this issue by leveraging online reviews and expert opinions. The proposed framework combines a novel linguistic representation, called calibrated basic uncertain linguistic information (CBULI), to capture uncertainty, a value function from cumulative prospect theory (CPT) with double reference points to model the manufacturers’ psychological preferences, and the Preference Ranking Organization Method for Enrichment of Evaluations II (PROMETHEE II) for prioritizing EVs for investment. It extracts demand attributes from online reviews, applies CBULI to represent uncertain evaluations, and incorporates CPT to capture risk preferences. A case study of an EV manufacturing enterprise in Sichuan, China, was conducted to validate our framework, and the results demonstrated its effectiveness and practicability in identifying the most promising types of EVs for investment. The results of sensitivity and comparative analyses further confirmed the robustness and superiority of the model in comparison with prevalent methods. The work here contributes to methodological advancements in research on the choice of types of EVs in which to invest, and provides valuable insights for EV enterprises to make informed investment-related decisions that are aligned with user demands and enterprise development. The proposed MADM framework supports the strategic development of the EV industry by enabling manufacturers to prioritize investment in the appropriate types of EVs under uncertainty.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":null,"pages":null},"PeriodicalIF":6.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142316157","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号