{"title":"MUH: Maximum-uncertainty-heuristic method of modeling belief function","authors":"Zihan Yu , Zhen Li , Guohui Zhou , Yong Deng","doi":"10.1016/j.cie.2025.111067","DOIUrl":"10.1016/j.cie.2025.111067","url":null,"abstract":"<div><div>Modeling of belief functions is the basic step for using belief function theory to deal with uncertainty. Transformation method for belief functions from different information representation has always been an important method of building belief function, which can integrate multi-source information and vary diverse modeling approaches. Additionally, building belief functions with constraints under maximum uncertainty is a promising way due to various forms of uncertainty measures. However, their drawbacks such as low flexibility and high computational complexity restrict their widespread application. To address these issues, a normalized dynamic total uncertainty measure is proposed, which has a simple and flexible form to obtain belief functions with constraints. Then, a heuristic method is proposed to solve the problem of high computational complexity. The proposed method is validated based on numerous experimental results compared to other methods.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111067"},"PeriodicalIF":6.7,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738623","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":"The generalized energy-aware flexible job shop scheduling model: A constraint programming approach","authors":"Hajo Terbrack , Thorsten Claus","doi":"10.1016/j.cie.2025.111065","DOIUrl":"10.1016/j.cie.2025.111065","url":null,"abstract":"<div><div>Taking up the ongoing shift towards green production, this article addresses energy-oriented flexible job shop scheduling. Existing approaches mainly focus on single objectives in terms of energy utilization such as minimizing energy consumption. However, production control can affect multiple energy-related criteria. Therefore, we propose a flexible job shop scheduling model to minimize real-time pricing-related energy costs, peak demand and energy-related emissions. Motivated by the reported preeminence of Constraint Programming (CP) for a variety of scheduling problems, we extend a CP formulation for our study. To evaluate potential contradictory between energy objectives, we present nine objective functions by means of different lexicographic orders. In addition, we enhance the proposed scheduling model to account for sequence-dependent setup and due dates. To analyze and compare the effectiveness of the different model formulations, we present computational experiments for 20 small-, medium- and large-sized problem instances. Our study indicates that productivity can be maximized while, on average, energy costs are reduced by 5.3%, peak demand by 11.8%, emissions by 8.3% compared to traditional job scheduling. However, partly conflicting objectives require the decision maker to select the objective function most suitable to the individual needs. Including setup effort and due date compliance into energy-aware scheduling is possible and needed to make the concept of energy-aware scheduling applicable to industrial practice. We show that the additional aspects limit the potential improvement. Hence, it is crucial to understand such complex scheduling systems combining energy awareness, setup and due date compliance.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111065"},"PeriodicalIF":6.7,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738620","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":"Two-phase optimization modelling with swarm computation and biomimetic intelligence learning for neural network training","authors":"Zhen-Yao Chen","doi":"10.1016/j.cie.2025.111058","DOIUrl":"10.1016/j.cie.2025.111058","url":null,"abstract":"<div><div>This study aims to enhance the tuning efficiency of radial basis function neural network (RNt) through the self-organized map (SOM) neural network (SOMnt) mode and several swarm intelligence (SI) algorithms. Next, ant colony optimization (ACO)-inspired approach and artificial immune system (AIS)-inspired approaches is integrated into the integration of ACO-inspired and AIS-inspired approaches (IACI) algorithm, which is then applied to RNt for modulation. The proposed two-phase hybrid of SOMnt mode and IACI algorithm (HSACI) method, offers diversity and incorporates intensive solutions to achieve optimized explication. The population variety characteristic demonstrates a higher success rate in reaching global extreme values in the five nonlinear function problems, replacing restricted local extreme values. The verification results indicate that the combination of SOMnt mode, ACO-inspired, and AIS-inspired approaches is a distinctive method and accordingly a two-phase HSACI method is proposed, which is capable to adjust to the best precision among relevant algorithms in this paper. The method is then evaluated on five nonlinear function problems as well as the results from an actual laptop demand forecasting exercise in Taiwan. The results demonstrate that the proposed two-phase HSACI method outperforms the relevant algorithms and the Box-Jenkins models in term of precision.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111058"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724474","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 novel nonlinear time-varying grey prediction framework for green transformation of manufacturing industry: Modeling of a non-equidistant perspective","authors":"Shiwei Zhou , Yufeng Zhao , Xuemei Li , Rui Han","doi":"10.1016/j.cie.2025.111068","DOIUrl":"10.1016/j.cie.2025.111068","url":null,"abstract":"<div><div>This study proposes a multi-dimensional nonlinear time-varying grey prediction framework, NEMTDNGM(1,1), to address the challenges of modeling non-equidistant effects in the green transformation of land and marine manufacturing industries (LMMIGT). Using technological innovation as an input, NEMTDNGM(1,1) effectively identifies its non-equidistant drivers within LMMIGT. By introducing dual time-varying effects through grey action and development coefficients, the model thoroughly examines LMMIGT’s nonlinear features characterized by energy consumption. Robustness is tested with Monte Carlo simulations based on the Marine Predator Algorithm, employing β-convergence and kernel density estimation. Empirical results demonstrate that NEMTDNGM(1,1) achieves the training and test MAPEs below 3%, significantly outperforming other models, underscoring its potential to support sustainable development of land and marine manufacturing systems.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111068"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143724475","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":"Joint optimization of route and frequency with flexible rail pricing in a container intermodal","authors":"Xichun Chen, Xiaopeng Tian, Shiya Cheng, Huimin Niu","doi":"10.1016/j.cie.2025.111070","DOIUrl":"10.1016/j.cie.2025.111070","url":null,"abstract":"<div><div>This paper focuses on how to optimize road-rail-combined routes and container-train-associated frequencies for effectively delivering freight demands from origins to destinations in a container intermodal network. Unlike common single-rate rail pricing contracts, we employ a flexible rail pricing (FRP) contract which depends on freight carrying volumes and average loading rates within the corresponding rail subnetwork. With the help of the formulated FRP requirements, a bi-objective integer programming model is developed for this problem, aiming to minimize the total freight transportation cost and maximize the total rail net profit. Further, we tackle the nonlinear constraints caused by FRP through the big-M method. The model, with the purpose of enhancing applicability and flexibility, is then extended to incorporate actual route selection rules. By using the ε-constraint method, the obtained bi-objective models are transformed into single-objective forms, which are addressed with state-of-the-art commercial solvers and heuristic strategies. Finally, we perform several different-sized numerical experiments to validate the efficiency and effectiveness of the proposed approach.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111070"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143767848","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}
Yan Ge , Hao Ding , Aimin Wang , Haigen Yang , Yinlu Wang
{"title":"Scheduling for hybrid flow shop with energy-efficiency and machine preventive maintenance in sheet metal manufacturing system","authors":"Yan Ge , Hao Ding , Aimin Wang , Haigen Yang , Yinlu Wang","doi":"10.1016/j.cie.2025.111050","DOIUrl":"10.1016/j.cie.2025.111050","url":null,"abstract":"<div><div>Hybrid flow shop scheduling (HFSS) is widely used in actual workshop production processes and is an important means of reducing delivery time, increasing cost savings, and improving production efficiency and quality. In this study, a HFSS with machining-speed-based energy efficiency and machine preventive maintenance (HFSE-PM) was investigated in the context of sheet metal processing, filling the gap in existing related researches. Based on the characteristics of HFSE-PM, the concepts of virtual machines, conventional machine maintenance, and effective machine maintenance were applied, and a linear programming model was established to minimize the makespan and total energy consumption of the machines. An improved teaching- and learning-based optimization (I-TLBO) algorithm framework was designed, in which a two-stage encoding operator, a decoding operator based on scenario evaluation, five types of neighborhood search operators in three phases, and a phased large-scale mutation strategy were also designed to generate initial solutions, avoid poor quality solutions, perform local optimization, and perform global optimization, respectively. Computational experiments demonstrated the effectiveness of the proposed model and the superiority of the proposed neighborhood search operators. In a comparison with three other excellent algorithms for solving similar problems, the superiority of I-TLBO in providing HFSE-PM was demonstrated. The model and research method constructed are not only applicable to production scheduling problems in the sheet metal processing industry but also to all practical production scheduling applications that can be modeled as HFSE-PM, HFSE, HFSS-PM, and HFSS.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111050"},"PeriodicalIF":6.7,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748594","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":"E-retail platform or wholesale strategy for a manufacturer developing a market channel","authors":"Heng Du","doi":"10.1016/j.cie.2025.111078","DOIUrl":"10.1016/j.cie.2025.111078","url":null,"abstract":"<div><div>Compared with the conventional wholesale mode, the e-retail platform has been regarded as an important alternative for a manufacturer building a market channel. Motivated by the observation, this paper develops two models to investigate a manufacturer’s e-retail platform and wholesale strategies by the methods of mathematics optimization and game theory. We first focus on the issue of whether to enter an e-retail platform for an upstream manufacturer. The manufacturer’s decisions and profits under two scenarios are contrasted. Next, a supply chain with a third party logistics provider, a manufacturer and an e-commerce platform is considered. We further explore how a third party logistics and channel power affect the manufacturer’s strategy motivation. Three strategies are examined including the wholesale strategy, the manufacturer-led e-commerce strategy, and the e-commerce strategy led by the third party. It is found that: (i) even though the online platform charge is large, the manufacturer should still insist on the e-retail strategy; (ii) if the manufacturer’s logistics service is provided by a third party, the platform charge and the logistics service cost simultaneously affect the manufacturer’s strategy choice motivation; (iii) in the e-retail environment, the manufacturer should utilize his own channel power to extract more channel profits if the platform fee is not large; otherwise, the manufacturer should give up the channel influence advantage.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111078"},"PeriodicalIF":6.7,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738621","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}
Bin Wang, Hao Tang, Shurun Wang, Zhaowu Ping, Qi Tan
{"title":"Hierarchical decision and control method for the human–exoskeleton collaborative packaging system based on deep reinforcement learning","authors":"Bin Wang, Hao Tang, Shurun Wang, Zhaowu Ping, Qi Tan","doi":"10.1016/j.cie.2025.111063","DOIUrl":"10.1016/j.cie.2025.111063","url":null,"abstract":"<div><div>The packaging process is an important part of the production and transportation process, and many companies have introduced exoskeleton robots to mitigate worker fatigue in the packaging process. Therefore, a human–exoskeleton collaborative packaging system with random product arrivals is studied, focusing on the operation decision and assistive force control of the system. A hierarchical decision and control policy is proposed to prevent the worker’s fatigue level from crossing a threshold while improving the energy efficiency of the exoskeleton and the system’s productivity. First, a hierarchical decision and control architecture is designed, in which the upper layer makes decisions on operations and the lower layer controls the assistive forces. Second, the optimal hierarchical decision and control policy is solved by combining the double DQN (DDQN) for discrete actions and the deep deterministic policy gradient (DDPG) for continuous actions. Finally, the proposed policy is validated in the constructed visualization virtual platform. The simulation results show that the proposed policy can effectively control worker fatigue and improve the energy efficiency of the equipment and the productivity of the system.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111063"},"PeriodicalIF":6.7,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143748596","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}
Md Mizanur Rahman , Faycal Bouhafs , Sayed Amir Hoseini , Frank den Hartog
{"title":"UNSW HomeNet: A network traffic flow dataset for AI-based smart home device classification","authors":"Md Mizanur Rahman , Faycal Bouhafs , Sayed Amir Hoseini , Frank den Hartog","doi":"10.1016/j.cie.2025.111041","DOIUrl":"10.1016/j.cie.2025.111041","url":null,"abstract":"<div><div>The emergence of the Internet of Things (IoT) has introduced a variety of devices into smart homes, making smart home networks increasingly complex and insecure. However, many IoT device manufacturers prioritize functionality, time-to-market, and performance over security, leaving IoT devices and networks vulnerable. Automatic device classification techniques are crucial for applying various network management approaches to ensure both performance and security. Despite the considerable research effort devoted to device classification, very few datasets are publicly available for in-depth investigation. This paper identifies the currently available public datasets for smart home device classification and highlights their limitations. These limitations encouraged us to develop a new, large-scale network traffic flow dataset for AI-Based smart home device classification dataset comprising more than 200 million data points stemming from 105 different IoT and non-IoT devices. This dataset is now publicly available to the research community, and in this paper we present and describe its properties. Furthermore, we evaluated the effectiveness of different Machine Learning algorithms in classifying these devices. Our results indicate that the Random Forest algorithm achieves the highest accuracy at 0.906 with recall, precision, and F1 scores of 0.877, 0.901, and 0.887, respectively. Finally, we investigated the importance of the features and found that only 12 features are largely responsible for the observed levels of accuracy.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"204 ","pages":"Article 111041"},"PeriodicalIF":6.7,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143738624","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":"Harnessing heterogeneous graph neural networks for Dynamic Job-Shop Scheduling Problem solutions","authors":"Chien-Liang Liu , Po-Hao Weng , Chun-Jan Tseng","doi":"10.1016/j.cie.2025.111060","DOIUrl":"10.1016/j.cie.2025.111060","url":null,"abstract":"<div><div>Manufacturing firms increasingly face the challenge of managing production complexity in the face of global competition and evolving customer demands. A critical component for maintaining efficiency and profitability in such an environment is the ability to solve the Job-Shop Scheduling Problem (JSSP) effectively. Traditional methods often fail in dynamic manufacturing settings, where unpredictability and the need for real-time adaptability can render static approaches obsolete. This study introduces a novel framework that uses Deep Reinforcement Learning (DRL) to address these limitations and navigate the intricacies of dynamic JSSP. By integrating heterogeneous graph neural networks (HGNNs) with DRL, we develop a model that not only captures the complex interconnections inherent in JSSP, but also dynamically adapts to the evolving nature of real-world manufacturing systems. Our proposed model is size-agnostic, meaning that it can deal with JSSPs with variable problem sizes. In addition, we introduce a new training method called Bootstrap Curriculum Learning (BCL) that enhances the model’s resilience and adaptability by training it in stages, progressively introducing the model to more challenging scheduling problem cases. The performance of the proposed model, evaluated against public benchmarks and synthetic datasets, shows superior performance and generalizability, offering a robust solution to dynamic scheduling challenges in smart manufacturing.</div></div>","PeriodicalId":55220,"journal":{"name":"Computers & Industrial Engineering","volume":"203 ","pages":"Article 111060"},"PeriodicalIF":6.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715648","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}