International Journal of Production Research最新文献

{"title":"An approximate dynamic programming approach to network-based scheduling of chemotherapy treatment sessions","authors":"Arturo Wenzel, Antoine Sauré, Alejandro Cataldo, Pablo A. Rey, César Sánchez","doi":"10.1080/00207543.2023.2259502","DOIUrl":"https://doi.org/10.1080/00207543.2023.2259502","url":null,"abstract":"AbstractA solution approach is proposed for the interday problem of assigning chemotherapy sessions at a network of treatment centres with the goal of increasing the cost-efficiency of system-wide capacity use. This network-based scheduling procedure is subject to the condition that both the first and last sessions of a patient's treatment protocol are administered at the same centre the patient is referred to by their oncologist. All intermediate sessions may be administered at other centres. It provides a systematic way of identifying effective multi-appointment scheduling policies that exploit the total capacity of a networked system, allowing patients to be treated at centres other than their home centre. The problem is modelled as a Markov decision process which is then solved approximately using techniques of approximate dynamic programming. The benefits of the approach are evaluated and compared through simulation with the existing manual scheduling procedures at two treatment centres in Santiago, Chile. The results suggest that the approach would obtain a 20% reduction in operating costs for the whole system and cut existing first-session waiting times by half. A key conclusion, however, is that a network-based scheduling procedure brings no real benefits if it is not implemented in conjunction with a proactive assignment policy like the one proposed in this paper.Keywords: OR in health serviceschemotherapy schedulingmarkov decision processesapproximate dynamic programminglinear programmingsimulation AcknowledgmentsThe authors would like to thank the Adult Chemotherapy Unit of the Red de Salud UC CHRISTUS (CECA) for generously supplying the necessary data to carry out the practical application discussed in this paper.Disclosure statementNo potential conflict of interest was reported by the authors.Data availability statementThe authors confirm that most of the data supporting the findings of this study are available within the article. Additional information is available from the corresponding author, AS, upon reasonable request.Additional informationFundingThis research was partially supported by the Chilean National Agency for Research and Development (ANID-Fondecyt) [grant number Regular 2023-1231320] and the Natural Sciences and Engineering Research Council of Canada (NSERC) [grant number RGPIN-2018-05225].Notes on contributorsArturo WenzelArturo Wenzel has a professional degree in Engineering with specialisation in Operations Research and Hydraulics and a master's degree in engineering sciences from the Pontificia Universidad Católica de Chile. His professional interests include the development and implementation of decision support systems for practical problems including chemotherapy scheduling.Antoine SauréAntoine Sauré is an associate professor at the Telfer School of Management at the University of Ottawa. His research interests include stochastic modelling, dynamic optimisation, and decision-making under uncertainty. He has man","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136235664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Environmental aspects in supplier networks-a bi-objective just-in-time truck routing problem","authors":"Julian Baals","doi":"10.1080/00207543.2023.2258237","DOIUrl":"https://doi.org/10.1080/00207543.2023.2258237","url":null,"abstract":"AbstractFreight transportation, including just-in-time (JIT) supplier networks, accounts for a substantial part of the global carbon dioxide (CO2) emissions. The JIT truck routing problem (TRP-JIT) presented in the recent literature consists of several suppliers serving a single original equipment manufacturer (OEM). A logistics provider organises the milk-run routes. The shipments are available after their release dates at the suppliers and should be delivered on their due dates at the OEM with minimal total earliness-tardiness penalties (first objective). Unlike previous research on the TRP-JIT, we focus on its environmental impact: (1) We include the weight-distance (second objective), depending on the truck's curb weight, the load, and the transportation distance. (2) We adapt a state-of-the-art large neighbourhood search (LNS) from the literature considering both objectives. (3) The LNS is embedded in bi-criterial frameworks, i.e. ε-constraint and weighted sum methods. Thereby, we estimate Pareto frontiers with at least 60 solutions in less than 25 min for instances with 99 shipments. From a managerial perspective, increasing the difference between the release and due dates for a better JIT performance may worsen the environmental impact. Lighter trucks can reduce the environmental costs without affecting the JIT performance, whereas a smaller fleet negatively affects both objectives.Keywords: Logisticsjust-in-timeenvironmentvehicle routinglarge neighbourhood search Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementThe data that support the findings of this study (instances used in the computational study) are available on GitHub at https://github.com/jbaals/envtrpjit. These data were derived from the following resources available in the public domain:Instances of Demir, Bektaş, and Laporte (Citation2012) at http://www.apollo.management.soton.ac.uk/prplib.htm.Additional informationNotes on contributorsJulian BaalsJulian Baals received a B.Sc. and M.Sc. degree in Engineering Management/Industrial Engineering from the University of Technology in Darmstadt, Germany in 2016 and 2019 respectively. Between 2020 and 2022, he was enrolled as a Ph.D. fellow at Aarhus University, Denmark. Since 2022, he is continuing his Ph.D. studies at Friedrich Schiller University Jena, Germany. His focus is on just-in-time logistics especially the optimisation in transportation networks by developing metaheuristic solution procedures.","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135014299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Load prediction of parcel pick-up points: model-driven vs data-driven approaches","authors":"Thi-Thu-Tam Nguyen, Adnane Cabani, Iyadh Cabani, Koen De Turck, Michel Kieffer","doi":"10.1080/00207543.2023.2253475","DOIUrl":"https://doi.org/10.1080/00207543.2023.2253475","url":null,"abstract":"ABSTRACTPick-Up Points (PUPs) represent an alternative delivery option for online purchases. Parcels are delivered at a reduced cost to PUPs and wait until being picked up by customers or returned to the original warehouse if their sojourn time is over. When the chosen PUP is overloaded, the parcel may be refused and delivered to the next available PUP on the carrier tour. This paper presents and compares forecasting approaches for the load of a PUP to help PUP management companies balance delivery flows and reduce PUP overload. The parcel life-cycle has been taken into account in the forecasting process via models of the flow of parcel orders, the parcel delivery delays, and the pick-up process. Model-driven and data-driven approaches are compared in terms of load-prediction accuracy. For the considered example, the best approach (which makes use of the relationship of the load with the delivery and pick-up processes) is able to predict the load up to 4 days ahead with mean absolute errors ranging from 3.16 parcels (1 day ahead) to 8.51 parcels (4 days ahead) for a PUP with an average load of 45 parcels.KEYWORDS: Count time seriesload predictionparcel deliveryparcel pick-uppick-up point management AcknowledgmentsWe thank Professor Valdério Anselmo Reisen for his valuable comments.Data Availability StatementThe data that support the findings of this study are openly available in Github at https://github.com/cabani/ForecastingParcels.Disclosure statementNo potential conflict of interest was reported by the author(s).Notes1 Based on the statistical analysis in Appendix A, 80 % of the parcels are picked up two days after their delivery, and only 1 % are still in the PUP six days after their delivery. The considered simplifying assumption about smax only marginally impacts the load prediction results.Additional informationNotes on contributorsThi-Thu-Tam NguyenTam Nguyen received her PhD degree in Computer Science from Paris Saclay University, Orsay, France in 2023. Her research interests include statistical and machine learning based models applied to time series analysis and forecasting.Adnane CabaniAdnane Cabani received his Ph.D. degree in Computer Science from INSA Rouen Normandie in December 2007. He obtained his HDR, French Accreditation to Direct Research, in March 2021 from University of Rouen Normandy. He is a Professor of Computer Science at ESIGELEC/IRSEEM. Currently, he is the head of the Software Engineering & Digital Transformation Master's programme and a member of the steering committee of the federative structure in logistics SFLog FED 4230. He has co-authored 70 research papers, conference proceedings, books, and standards in the areas of Intelligent Transport Systems and Logistics.Iyadh CabaniIyadh Cabani received his Ph.D. degree in Computer Science from INSA Rouen Normandie in 2007. He obtained the Executive Certificate, BigData for Digital Business from CentraleSupelec in 2022. He has been a reviewer for several years in IEEE c","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135307155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A cooperative iterated greedy algorithm for the serial distributed permutation flowshop scheduling problem","authors":"Biao Han, Quan-Ke Pan, Liang Gao","doi":"10.1080/00207543.2023.2255681","DOIUrl":"https://doi.org/10.1080/00207543.2023.2255681","url":null,"abstract":"AbstractThis paper addresses a serial distributed permutation flowshop scheduling problem (SDPFSP) inspired by a printed circuit board assembly process that contains two production stages linked by a transportation stage, where the scheduling problem in each production stage can be seen as a distributed permutation flowshop scheduling problem (DPFSP). A sequence-based mixed-integer linear programming model is established. A solution representation consisting of two components, one component per stage, is presented and a makespan calculation method is given for the representation. Two suites of accelerations based on the insertion neighbourhood are proposed to reduce the computational complexity. A cooperative iterated greedy (CIG) algorithm is developed with two subloops, each of which optimises a component of the solution. A collaboration mechanism is used to conduct the collaboration of the two subloops effectively. Problem-specific operators including the NEH-based heuristics, destruction, reconstruction and three local search procedures, are designed. Extensive computational experiments and statistical analysis verify the validity of the model, the effectiveness of the proposed CIG algorithm and the superiority of the proposed CIG over the existing methods for solving the problem under consideration.KEYWORDS: Distributed schedulingiterated greedymakespanpermutation flowshopaccelerations Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementThe data that support the findings of this study are available from the corresponding author upon reasonable request.Additional informationFundingThis research is partially supported by the National Science Foundation of China 62273221 and 61973203, and Program of Shanghai Academic/Technology Research Leader 21XD1401000.Notes on contributorsBiao HanBiao Han received the BS degree from Shanghai Ocean University, Shanghai, China, in 2020. He is currently working toward the MA degree at Shanghai University, China. His research focuses on algorithm design of distributed flowshop scheduling.Quan-Ke PanQuan-ke Pan received the BSc degree and the PhD degree from Nanjing university of Aeronautics and Astronautics, Nanjing, China, in 1993 and 2003, respectively. From 2003 to 2011, he was with School of Computer Science Department, Liaocheng University, where he became a Full Professor in 2006. From 2011 to 2014, he was with State Key Laboratory of Synthetical Automation for Process Industries (Northeastern University), Shenyang, China. From 2014 to 2015, he was with State Key Laboratory of Digital Manufacturing and Equipment Technology (Huazhong University of Science & Technology). He has been with School of Mechatronic Engineering and Automation, Shanghai University since 2015. His current research interests include intelligent optimisation and scheduling algorithms.Liang GaoLiang Gao received the BSc degree in mechatronic engineering from Xidian University, ","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135304898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Delivery network design of a locker-drone delivery system","authors":"Bipan Zou, Siqing Wu, Yeming Gong, Zhe Yuan, Yuqian Shi","doi":"10.1080/00207543.2023.2254402","DOIUrl":"https://doi.org/10.1080/00207543.2023.2254402","url":null,"abstract":"AbstractDrones are increasingly used for last-mile delivery due to their speed and cost-effectiveness. This study focuses on a novel locker-drone delivery system, where trucks transport parcels from the warehouse to lockers, and drones complete the final delivery. This system is ideal for community and intra-facility logistics. The research optimises the network design by determining the location of lockers, the number of drones at each locker, and the assignment of demands to lockers, minimising operating costs. Both single-parcel and multi-parcel capacity drones are examined. We build an optimisation model for each system, considering drone service capacity as a critical constraint. We design an algorithm combining average sample approximation and a genetic algorithm to address demand uncertainty. The algorithm's efficiency is validated through comparative analysis with Gurobi. Numerical experiments, using real and generated data, optimise the network design. Results show that the multi-capacity drone system requires fewer lockers and drones than the single-capacity system. Although the single-capacity system yields lower drone delivery costs, it incurs higher truck delivery costs. Additionally, a comprehensive cost analysis compares the cost-efficiency of the locker-drone system with a conventional drone delivery system, revealing the cost-saving advantage of the locker-drone system.Keywords: Dronelogisticssample average approximationgenetic algorithmlast-mile delivery AcknowledgmentsThe authors would like to thank the attendees of the IFAC MIM 2022 conference for constructive revision comments, as well as the invitation of this paper as a possible publication in IJPR from the organisers of the IFAC MIM 2022 conference.Data availability statementThe data supporting this study's findings are available on request from the authors. The data in the Sao Paulo case that support the findings of this study are openly available in Kaggle at http://doi.org/10.34740/kaggle/dsv/195341. The raw data in the Wuhan case were generated at OpenStreetMap. Derived data supporting the findings of this study are available from the corresponding author on request.Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis research is partially supported by the National Natural Science Foundation of China (grant number 72171233, 71801225) and the Hubei Provincial Natural Science Foundation of China [grant number 2022CFB390]. Yeming Gong is supported by Artificial Intelligence in Management Institute and BIC Center at emlyon.Notes on contributorsBipan ZouBipan Zou is a Professor of the School of Business Administration of Zhongnan University of Economics and Law. He received his PhD degree from Huazhong University of Science and Technology. His main research interests include design and operating policies analysis of intelligent warehousing systems, such as the robotic mobile fulfillment system, the robotic com","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134912802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-objective discrete differential evolution algorithm for energy-efficient distributed blocking flow shop scheduling problem","authors":"Fuqing Zhao, Hui Zhang, Ling Wang, Tianpeng Xu, Ningning Zhu, Jonrinaldi Jonrinaldi","doi":"10.1080/00207543.2023.2254858","DOIUrl":"https://doi.org/10.1080/00207543.2023.2254858","url":null,"abstract":"ABSTRACTThe energy problem in green manufacturing has attracted enormous attention from researchers and practitioners in the manufacturing domain with the global energy crisis and the aggravation of environmental pollution. The distributed blocking flow shop scheduling problem (DBFSP) has considerable application scenarios in connection with its widespread application in the industry under the background of intelligent manufacturing. A multi-objective discrete differential evolution (MODE) algorithm is proposed to solve the energy-efficient distributed blocking flow shop scheduling problem (EEDBFSP) with the objectives of the makespan and total energy consumption (TEC) in this paper. The cooperative initialisation strategy is proposed to generate the initial population of the EEDBFSP. The mutation, crossover, and selection operators are redesigned to enable the MODE algorithm as applied to discrete space. A local search strategy based on the knowledge of five operators is introduced to enhance the exploitation capability of the MODE algorithm in the EEDBFSP. The non-critical path energy-efficient strategy is proposed to reduce energy consumption according to the specific constraints in the EEDBFSP. The effectiveness of each strategy in the MODE algorithm is verified and compared with the state-of-the-art algorithms. The numerical results demonstrate that the MODE algorithm is the efficient optimiser for solving the EEDBFSP.KEYWORDS: Energy-efficient distributed schedulingblocking flow shopmulti-objectivediscrete differential evolutiontotal energy consumption (TEC) Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementThe data are openly available in ‘CSDN’ at https://download.csdn.net/download/weixin_45627438/85802283.Additional informationFundingThis work was financially supported by the National Natural Science Foundation of China under grant 62063021. It was also supported by the Key Program of National Natural Science Foundation of Gansu Province under Grant 23JRRA784, the High-level Foreign Experts Project of Gansu Province under Grant 22JR10KA007, the Key Research Programs of Science and Technology Commission Foundation of Gansu Province (21YF5WA086), Lanzhou Science Bureau project (2018-rc-98), and Project of Gansu Natural Science Foundation (21JR7RA204), respectively.Notes on contributorsFuqing ZhaoFuqing Zhao received the B.Sc. and Ph.D. degrees from the Lanzhou University of Technology, Lanzhou, China, in 1994 and 2006, respectively. Since 1998, he has been with the School of Computer Science Department, Lanzhou University of Technology, Lanzhou, China, where he became a Full Professor in 2012. He has been as the post Doctor with the State Key Laboratory of Manufacturing System Engineering, Xi’an Jiaotong University, Xi’an, China in 2009. He has been as a visiting scholar in Exeter Manufacturing Enterprise Center in Exeter University and Georgia Tech Manufacturing Institute in Geo","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"213 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134910651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel carbon reduction engineering method-based deep Q-learning algorithm for energy-efficient scheduling on a single batch-processing machine in semiconductor manufacturing","authors":"Min Kong, Weizhong Wang, Muhammet Deveci, Yajing Zhang, Xuzhong Wu, D'Maris Coffman","doi":"10.1080/00207543.2023.2252932","DOIUrl":"https://doi.org/10.1080/00207543.2023.2252932","url":null,"abstract":"AbstractThe semiconductor industry is a resource-intensive sector that heavily relies on energy, water, chemicals, and raw materials. Within the semiconductor manufacturing process, the diffusion furnace, ion implantation machine, and plasma etching machine exhibit high energy demands or operate at extremely high temperatures, resulting in significant electricity consumption, which is usually carbon-intensive. To address energy conservation concerns, the industry adopts batch production technology, which allows for the simultaneous processing of multiple products. The energy-efficient parallel batch scheduling problem arises from the need to optimise product grouping and sequencing. In contrast to existing heuristics, meta-heuristics, and exact algorithms, this paper introduces the Deep Q-Network (DQN) algorithm as a novel approach to address the proposed problem. The DQN algorithm is built upon the agent’s systematic learning of scheduling rules, thereby enabling it to offer guidance for online decision-making regarding the grouping and sequencing of products. The efficacy of the algorithm is substantiated through extensive computational experiments.KEYWORDS: Semiconductor manufacturingdeep reinforcement learningparallel batch schedulingless is morecarbon reduction engineering AcknowledgmentsThis research has received financial support from various sources, including the Ministry of Education of Humanities and Social Science Project [grant number 22YJC630050], the China Postdoctoral Science Foundation [grant number 2022M710996], the Educational Commission of Anhui Province [grant number KJ2020A0069], the Natural Science Foundation of Anhui Province [grant numbers 2108085QG291 and 2108085QG287], Anhui Province University Collaborative Innovation Project [grant number GXXT-2021-021], Science and Technology Plan Project of Wuhu [grant number 2021yf49, 2022rkx07], National Natural Science Foundation of China [grant numbers 72101071 and 72071056], the Key Research and Development Project of Anhui Province [grant number 2022a05020023].Data availability statementThe data that support the findings of this study are available from the authors upon reasonable request.Disclosure statementNo potential conflict of interest was reported by the author(s).Additional informationFundingThis research has received financial support from various sources, including the National Natural Science Foundation of China [grant numbers 72301004, 72301005, 72101071, and 72071056], Ministry of Education of Humanities and Social Science Project [grant number 22YJC630050], the China Postdoctoral Science Foundation [grant number 2022M710996], the Educational Commission of Anhui Province [grant number KJ2020A0069], the Natural Science Foundation of Anhui Province [grant numbers 2108085QG291 and 2108085QG287], Anhui Province University Collaborative Innovation Project [grant number GXXT-2021-021], Science and Technology Plan Project of Wuhu [grant number 2021yf49, 2022rkx07] , the ","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134970671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimal and simple approximate solutions to a production-inventory system with two production rates","authors":"Julia Miyaoka, Katy S. Azoury","doi":"10.1080/00207543.2023.2254851","DOIUrl":"https://doi.org/10.1080/00207543.2023.2254851","url":null,"abstract":"We consider a production-inventory system in which the facility produces continuously, switching between two production rates: one faster and one slower than the average demand rate. Demand follows a compound Poisson process, and the size of each demand request is an exponential random variable. Unsatisfied demand is backordered. The production-inventory system is controlled by a two-critical number policy (r,R), whereby production switches from the slower rate to the faster rate when inventory drops below level r and from the faster rate to the slower rate when inventory reaches level R. A fixed cost occurs whenever production switches rates. Our analysis covers two cases: r≥0 and the less studied case of r≤0. We use a level crossing approach to derive the steady-state distribution of the inventory level. Using the steady-state distribution of the inventory level, we calculate the total expected inventory holding, backorder, and switchover costs for each of the two cases. We outline how to obtain the optimal policy through a search of the expected cost functions. We also propose heuristics that give simple closed-form solutions with near-optimal performance. Through a numerical study, we illustrate the importance of considering the r≤ 0 case.","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135740002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knowledge graph driven credit risk assessment for micro, small and medium-sized enterprises","authors":"Rony Mitra, Ayush Dongre, Piyush Dangare, Adrijit Goswami, Manoj Kumar Tiwari","doi":"10.1080/00207543.2023.2257807","DOIUrl":"https://doi.org/10.1080/00207543.2023.2257807","url":null,"abstract":"Micro, Small, and Medium-sized Enterprises (MSMEs) are essential for the growth and development of the country's economy, as they create jobs, generate income, and foster production and innovation. In recent years, credit risk assessment (CRA) has been an essential process used by financial institutions to evaluate the creditworthiness of MSMEs and determine the likelihood of default. Traditionally, CRA has relied on credit scores and financial statements, but with the advent of machine learning (ML) algorithms, lenders have a new tool at their disposal. By and large, ML algorithms are designed to classify borrowers based on their credit history and transactional data while leveraging the entity relationship involved in credit transactions. This study introduces an innovative knowledge graph-driven credit risk assessment model (RGCN-RF) based on the Relational Graph Convolutional Network (RGCN) and Random Forest (RF) algorithm. RGCN is employed to identify topological structures and relationships, which is currently nascent in traditional credit risk assessment methods. RF categorises MSMEs based on the enterprise embedding vector generated from RGCN. Extensive experimentation is conducted to assess model performance utilising the Indian MSMEs database. The balanced accuracy of 92% obtained using the RGCN-RF model demonstrates a considerable advancement over prior techniques in identifying risk-free enterprises.","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135830096","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel control strategies and iterative approaches to order various COVID-19 vaccines to prevent shortages and immunisation expansion","authors":"Seyyed-Mahdi Hosseini-Motlagh, Mohammad Reza Ghatreh Samani, Parnian Farokhnejad","doi":"10.1080/00207543.2023.2254394","DOIUrl":"https://doi.org/10.1080/00207543.2023.2254394","url":null,"abstract":"This paper suggests control strategies for ordering various COVID-19 vaccines and assigning vaccine recipients to immunisation stations in order to minimise shortages. To determine the optimal quantity of multiple vaccines to order, a fuzzy periodic review model is proposed. Furthermore, vaccine recipients are prioritised into different groups based on their occupation (e.g. essential workers), age cohort, co-morbidities, and pre-existing diseases. To model vaccine recipients’ waiting and improve vaccination effectiveness by reducing congestion in immunisation stations, a queuing framework is utilised. Due to the suppliers’ lack of commitment to the mass production of vaccines during the COVID-19 pandemic, the number of orders delivered to the cross-docking facility is considered uncertain. A rolling planning horizon approach is implemented using an iterative method to prevent vaccine shortages. To validate the proposed model, a case study is conducted using data from Arak City in Iran, and sensitivity analysis is performed on the model parameters. The analysis of the results indicates that the rolling planning horizon approach and the possibilistic chance-constrained programming improve network performance against operational risks, including the COVID-19 pandemic. Moreover, implementing this method reduces costs and vaccine shortages in the network compared to the current situation.","PeriodicalId":14307,"journal":{"name":"International Journal of Production Research","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135830257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}