Pub Date : 2023-01-01DOI: 10.5267/j.ijiec.2023.5.003
Guangyan Xu, Z. Guan, L. Yue, Jabir Mumtaz
Production plans based on Material Requirement Planning (MRP) frequently fall short in reflecting actual customer demand and coping with demand fluctuations, mainly due to the rising complexity of the production environment and the challenge of making precise predictions. At the same time, MRP is deficient in effective adjustment strategies and has inadequate operability in plan optimization. To address material management challenges in a volatile supply-demand environment, this paper creates a make-to-stock (MTS) material production planning model that is based on customer demand and the demand-driven production planning and control framework. The objective of the model is to optimize material planning output under resource constraints (capacity and storage space constraints) to meet the fluctuating demand of customers. To solve constrained optimization problems, the demand-driven material requirements planning (DDMRP) management concept is integrated with the grey wolf optimization (GWO) algorithm and proposed the DDMRP-GWO algorithm. The proposed DDMRP-GWO algorithm is used to optimize the inventory levels, shortage rates, and production line capacity utilization simultaneously. To validate the effectiveness of the proposed approach, two sets of customer demand data with different levels of volatility are used in experiments. The results demonstrate that the DDMRP-GWO algorithm can optimize the production capacity allocation of different types of parts under the resource constraints, enhance the material supply level, reduce the shortage rate, and maintain a stable production process.
{"title":"An efficient production planning approach based demand driven MRP under resource constraints","authors":"Guangyan Xu, Z. Guan, L. Yue, Jabir Mumtaz","doi":"10.5267/j.ijiec.2023.5.003","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.5.003","url":null,"abstract":"Production plans based on Material Requirement Planning (MRP) frequently fall short in reflecting actual customer demand and coping with demand fluctuations, mainly due to the rising complexity of the production environment and the challenge of making precise predictions. At the same time, MRP is deficient in effective adjustment strategies and has inadequate operability in plan optimization. To address material management challenges in a volatile supply-demand environment, this paper creates a make-to-stock (MTS) material production planning model that is based on customer demand and the demand-driven production planning and control framework. The objective of the model is to optimize material planning output under resource constraints (capacity and storage space constraints) to meet the fluctuating demand of customers. To solve constrained optimization problems, the demand-driven material requirements planning (DDMRP) management concept is integrated with the grey wolf optimization (GWO) algorithm and proposed the DDMRP-GWO algorithm. The proposed DDMRP-GWO algorithm is used to optimize the inventory levels, shortage rates, and production line capacity utilization simultaneously. To validate the effectiveness of the proposed approach, two sets of customer demand data with different levels of volatility are used in experiments. The results demonstrate that the DDMRP-GWO algorithm can optimize the production capacity allocation of different types of parts under the resource constraints, enhance the material supply level, reduce the shortage rate, and maintain a stable production process.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"34 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87645821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2023.1.003
Pradeep Jangir, P. Manoharan, Sundaram B. Pandya, R. Sowmya
This paper recommends a new Many-Objective Teaching-Learning-Based Optimizer (MaOTLBO) to handle the Many-Objective Optimal Power Flow (MaO-OPF) problem of modern complex power systems while meeting different operating constraints. A reference point-based mechanism is utilized in the basic version of Teacher Learning-Based Optimizer (TLBO) to formulate the MaOTLBO algorithm and directly applied to DTLZ test benchmark functions with 5, 7, 10-objectives and IEEE-30 bus power system with six different objective functions, namely the minimization of the voltage magnitude deviation, total fuel cost, voltage stability indicator, total emission, active power loss, and reactive power loss. The results obtained from the MaOTLBO optimizer are compared with the well-known standard many-objective algorithms, such as the Multi-Objective Evolutionary Algorithm based on Decomposition with Dynamical Resource Allocation (MOEA/D-DRA) and Non-Dominated Sorting Genetic Algorithm-version-III (NSGA-III) presented in the literature. The results show the ability of the proposed MaOTLBO to solve the MaO-OPF problem in terms of convergence, coverage, and well-Spread Pareto optimal solutions. The experimental outcomes indicate that the suggested MaOTLBO gives improved individual output and compromised solutions than MOEA/D-DRA and NSGA-III algorithms.
针对现代复杂电力系统在满足不同运行约束条件下的多目标最优潮流问题，提出了一种新的多目标教学优化器(MaOTLBO)。在基于教师学习的优化器(TLBO)基础版中，利用基于参考点的机制制定了MaOTLBO算法，并直接应用于具有5、7、10个目标的DTLZ测试基准函数和具有电压幅值偏差最小、总燃油成本最小、电压稳定指标最小、总排放最小、有功损耗最小、无功损耗最小六个不同目标函数的IEEE-30母线电力系统。将MaOTLBO优化器得到的结果与文献中提出的基于动态资源分配分解的多目标进化算法(MOEA/D-DRA)和非支配排序遗传算法-版本- iii (NSGA-III)等知名标准多目标算法进行了比较。实验结果表明，与MOEA/D-DRA和NSGA-III算法相比，所提出的MaOTLBO算法具有更好的个体输出和折衷解。
{"title":"MaOTLBO: Many-objective teaching-learning-based optimizer for control and monitoring the optimal power flow of modern power systems","authors":"Pradeep Jangir, P. Manoharan, Sundaram B. Pandya, R. Sowmya","doi":"10.5267/j.ijiec.2023.1.003","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.1.003","url":null,"abstract":"This paper recommends a new Many-Objective Teaching-Learning-Based Optimizer (MaOTLBO) to handle the Many-Objective Optimal Power Flow (MaO-OPF) problem of modern complex power systems while meeting different operating constraints. A reference point-based mechanism is utilized in the basic version of Teacher Learning-Based Optimizer (TLBO) to formulate the MaOTLBO algorithm and directly applied to DTLZ test benchmark functions with 5, 7, 10-objectives and IEEE-30 bus power system with six different objective functions, namely the minimization of the voltage magnitude deviation, total fuel cost, voltage stability indicator, total emission, active power loss, and reactive power loss. The results obtained from the MaOTLBO optimizer are compared with the well-known standard many-objective algorithms, such as the Multi-Objective Evolutionary Algorithm based on Decomposition with Dynamical Resource Allocation (MOEA/D-DRA) and Non-Dominated Sorting Genetic Algorithm-version-III (NSGA-III) presented in the literature. The results show the ability of the proposed MaOTLBO to solve the MaO-OPF problem in terms of convergence, coverage, and well-Spread Pareto optimal solutions. The experimental outcomes indicate that the suggested MaOTLBO gives improved individual output and compromised solutions than MOEA/D-DRA and NSGA-III algorithms.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"51 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89802015","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2023.7.001
Parames Chutima
Industry 4.0 encourages industries to digitise the manufacturing system to facilitate human-robot collaboration (HRC) to foster efficiency, agility and resilience. This cutting-edge technology strikes a balance between fully automated and manual operations to maximise the benefits of both humans and assistant robots (known as cobots) working together on complicated and prone-to-hazardous tasks in a collaborative manner in an assembly system. However, the introduction of HRC poses a significant challenge for assembly line balancing since, besides typical assigning tasks to workstations, the other two important decisions must also be made regarding equipping workstations with appropriate cobots as well as scheduling collaborative tasks for workers and cobots. In this article, the cobot assembly line balancing problem (CoALBP), which just initially emerged a few years ago, is thoroughly reviewed. The 4M1E (i.e., man, machine, material, method and environment) framework is applied for categorising the problem to make the review process more effective. All of the articles reviewed are compared, and their key distinct features are summarised. Finally, guidelines for additional studies on the CoALBP are offered.
{"title":"Assembly line balancing with cobots: An extensive review and critiques","authors":"Parames Chutima","doi":"10.5267/j.ijiec.2023.7.001","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.7.001","url":null,"abstract":"Industry 4.0 encourages industries to digitise the manufacturing system to facilitate human-robot collaboration (HRC) to foster efficiency, agility and resilience. This cutting-edge technology strikes a balance between fully automated and manual operations to maximise the benefits of both humans and assistant robots (known as cobots) working together on complicated and prone-to-hazardous tasks in a collaborative manner in an assembly system. However, the introduction of HRC poses a significant challenge for assembly line balancing since, besides typical assigning tasks to workstations, the other two important decisions must also be made regarding equipping workstations with appropriate cobots as well as scheduling collaborative tasks for workers and cobots. In this article, the cobot assembly line balancing problem (CoALBP), which just initially emerged a few years ago, is thoroughly reviewed. The 4M1E (i.e., man, machine, material, method and environment) framework is applied for categorising the problem to make the review process more effective. All of the articles reviewed are compared, and their key distinct features are summarised. Finally, guidelines for additional studies on the CoALBP are offered.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135784220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2022.9.004
Zhengmin Zhang, Z. Guan, L. Yue
This research focuses on production releasing and routing allocation problems in re-entrant mixed-flow shops. Since re-entrant mixed flow shops are complex and dynamic, many studies evaluate release plans by developing discrete event simulation models and selecting the optimal solution according to the estimation results. However, a high-accurate discrete event simulation model requires a lot of computation time. In this research, we develop an effective multi-fidelity optimization method to address product release planning problems for re-entrant mixed-flow shops. The proposed method combines the advantages of rapid evaluation of analytical models and accurate evaluation of simulation models. It conducts iterative optimization using a low-fidelity mathematical estimation model to find good solutions and searches for the optimal solution via a high-fidelity simulation estimation model. Computational results of large-scale production releasing and routing allocation problems illustrate that the proposed approach is good at addressing large-scale problems in re-entrant mixed-flow shops.
{"title":"Multi-fidelity simulation optimization for production releasing in re-entrant mixed-flow shops","authors":"Zhengmin Zhang, Z. Guan, L. Yue","doi":"10.5267/j.ijiec.2022.9.004","DOIUrl":"https://doi.org/10.5267/j.ijiec.2022.9.004","url":null,"abstract":"This research focuses on production releasing and routing allocation problems in re-entrant mixed-flow shops. Since re-entrant mixed flow shops are complex and dynamic, many studies evaluate release plans by developing discrete event simulation models and selecting the optimal solution according to the estimation results. However, a high-accurate discrete event simulation model requires a lot of computation time. In this research, we develop an effective multi-fidelity optimization method to address product release planning problems for re-entrant mixed-flow shops. The proposed method combines the advantages of rapid evaluation of analytical models and accurate evaluation of simulation models. It conducts iterative optimization using a low-fidelity mathematical estimation model to find good solutions and searches for the optimal solution via a high-fidelity simulation estimation model. Computational results of large-scale production releasing and routing allocation problems illustrate that the proposed approach is good at addressing large-scale problems in re-entrant mixed-flow shops.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"8 3 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78386982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2022.9.001
Yuan-Shyi P. Chiu, Zhongsheng Zhao, Fan-Yun Pai, Tiffany Chiu
This study examines the collective impact of postponement, scrap, and subcontracting standard components on the multiproduct replenishing decisions. Rapid response, desirable quality, and various goods guide the client’s demands in today’s competitive market. Therefore, many manufacturing firms search for alternative fabrication and outsourcing strategies during the production planning stage to satisfy the client’s expectations, minimize fabrication-inventory costs, and smoothen machine utilization. To effectively help producers meet today's client's needs and enhance their competitive advantage, we develop a two-stage multiproduct replenishing system incorporating scraps, standard parts subcontracting, commonality, and delayed differentiation. To reduce the production uptime, stage one has a hybrid fabrication process for the common components (i.e., a partial outsourcing strategy), and stage two manufactures the finished multiproduct. In-house fabrication processes in both stages are imperfect; a screening process detects and removes scraps to maintain the finished batch quality. We determine the cost-minimized operating cycle. The findings reveal the collective impact of postponement, scrap, and external suppliers on this multi-product replenishment problem and can be used to facilitate production planning and decision-making.
{"title":"Investigating the collective impact of postponement, scrap, and external suppliers on multiproduct replenishing decision","authors":"Yuan-Shyi P. Chiu, Zhongsheng Zhao, Fan-Yun Pai, Tiffany Chiu","doi":"10.5267/j.ijiec.2022.9.001","DOIUrl":"https://doi.org/10.5267/j.ijiec.2022.9.001","url":null,"abstract":"This study examines the collective impact of postponement, scrap, and subcontracting standard components on the multiproduct replenishing decisions. Rapid response, desirable quality, and various goods guide the client’s demands in today’s competitive market. Therefore, many manufacturing firms search for alternative fabrication and outsourcing strategies during the production planning stage to satisfy the client’s expectations, minimize fabrication-inventory costs, and smoothen machine utilization. To effectively help producers meet today's client's needs and enhance their competitive advantage, we develop a two-stage multiproduct replenishing system incorporating scraps, standard parts subcontracting, commonality, and delayed differentiation. To reduce the production uptime, stage one has a hybrid fabrication process for the common components (i.e., a partial outsourcing strategy), and stage two manufactures the finished multiproduct. In-house fabrication processes in both stages are imperfect; a screening process detects and removes scraps to maintain the finished batch quality. We determine the cost-minimized operating cycle. The findings reveal the collective impact of postponement, scrap, and external suppliers on this multi-product replenishment problem and can be used to facilitate production planning and decision-making.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"38 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73618028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2023.1.001
Yuan-Shyi Peter Chiu, Tingting Yan, S. Chiu, Hui-Chi Wang, Tiffany Chiu
This study examines the joint impact of outsourcing, overtime, multi-delivery, rework, and postponement on a multiproduct fabrication problem. A growing/clear trend in today’s customer requirements turned into rapid response and desired quality of multi-merchandises and multiple fixed-amount deliveries in equal-interval time. To satisfy customers’ expectations, current manufacturing firms must effectively design/plan their multiproduct production scheme with minimum fabrication-inventory-shipping expenses and under confined capacity. Motivated by assisting manufacturing firms in making the right production decision, this study develops a decision-support delayed-differentiation model considering multi-shipment, rework, and dual uptime-reducing strategies (namely, overtime and outsourcing). Our delayed-differentiation model comprises stage one, which makes all common/standard parts of multi-end-merchandises, and stage two, which produces multiple end merchandise. For cutting making times, the study proposes subcontracting a portion of the common/standard part’s lot size and adopting overtime-making end merchandise in stage two. The screening and reworking tasks identify and repair faulty items to ensure customers’ desired quality. The finished lots of end merchandise are divided into a few equal-amount shipments and distributed to customers in equal-interval time. We employ mathematical derivation and optimization methodology to derive the annual expected fabrication- inventory-shipping expense and the cost-minimized production-shipping policy. A numerical demonstration is presented to exhibit our research scheme’s applicability and exposes the studied problem’s critical managerial insights, which help the management make beneficial decisions.
{"title":"Impact of dual uptime-reducing strategies, postponement, multi-delivery, and rework on a multiproduct fabrication-shipping problem","authors":"Yuan-Shyi Peter Chiu, Tingting Yan, S. Chiu, Hui-Chi Wang, Tiffany Chiu","doi":"10.5267/j.ijiec.2023.1.001","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.1.001","url":null,"abstract":"This study examines the joint impact of outsourcing, overtime, multi-delivery, rework, and postponement on a multiproduct fabrication problem. A growing/clear trend in today’s customer requirements turned into rapid response and desired quality of multi-merchandises and multiple fixed-amount deliveries in equal-interval time. To satisfy customers’ expectations, current manufacturing firms must effectively design/plan their multiproduct production scheme with minimum fabrication-inventory-shipping expenses and under confined capacity. Motivated by assisting manufacturing firms in making the right production decision, this study develops a decision-support delayed-differentiation model considering multi-shipment, rework, and dual uptime-reducing strategies (namely, overtime and outsourcing). Our delayed-differentiation model comprises stage one, which makes all common/standard parts of multi-end-merchandises, and stage two, which produces multiple end merchandise. For cutting making times, the study proposes subcontracting a portion of the common/standard part’s lot size and adopting overtime-making end merchandise in stage two. The screening and reworking tasks identify and repair faulty items to ensure customers’ desired quality. The finished lots of end merchandise are divided into a few equal-amount shipments and distributed to customers in equal-interval time. We employ mathematical derivation and optimization methodology to derive the annual expected fabrication- inventory-shipping expense and the cost-minimized production-shipping policy. A numerical demonstration is presented to exhibit our research scheme’s applicability and exposes the studied problem’s critical managerial insights, which help the management make beneficial decisions.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"103 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79205860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2022.10.001
Yuanshyi Peter Chiu, S. Chiu, Fan-Yun Pai, Victoria Chiu
Production management operating in recent competitive marketplaces must satisfy the client desired quality and shorter order lead-time and avoid internal fabricating disruption caused by inevitable defects and stochastic equipment failures. Achieving these operational tasks without undesirable quality goods, missing due dates, and fabrication interruption help the management minimize operating expenditures. Motivated by assisting manufacturing firms in the situations mentioned this study explores a manufacturing system that features quality reassurances through reworking or removal of defectives, correction of probabilistic failures, and partial overtime and outsourcing options for reducing uptime. This study finds the function of system operating expenditures through model building, mathematical formulations, optimization approaches, and algorithm proposition, shows its convexity, and derives the optimal batch time for the studied manufacturing model. Finally, this study offers numerical illustrations to confirm our work’s applicability and disclose its capability to provide various profound crucial system information that helps the management make strategic operating decisions.
{"title":"Minimizing operating expenditures for a manufacturing system featuring quality reassurances, probabilistic failures, overtime, and outsourcing","authors":"Yuanshyi Peter Chiu, S. Chiu, Fan-Yun Pai, Victoria Chiu","doi":"10.5267/j.ijiec.2022.10.001","DOIUrl":"https://doi.org/10.5267/j.ijiec.2022.10.001","url":null,"abstract":"Production management operating in recent competitive marketplaces must satisfy the client desired quality and shorter order lead-time and avoid internal fabricating disruption caused by inevitable defects and stochastic equipment failures. Achieving these operational tasks without undesirable quality goods, missing due dates, and fabrication interruption help the management minimize operating expenditures. Motivated by assisting manufacturing firms in the situations mentioned this study explores a manufacturing system that features quality reassurances through reworking or removal of defectives, correction of probabilistic failures, and partial overtime and outsourcing options for reducing uptime. This study finds the function of system operating expenditures through model building, mathematical formulations, optimization approaches, and algorithm proposition, shows its convexity, and derives the optimal batch time for the studied manufacturing model. Finally, this study offers numerical illustrations to confirm our work’s applicability and disclose its capability to provide various profound crucial system information that helps the management make strategic operating decisions.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"15 1","pages":""},"PeriodicalIF":3.3,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73075837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2023.6.003
Minghao Xia, Haibin Liu, Mingfei Li, Long Wang
In modern industrial manufacturing, there are uncertain dynamic disturbances between processing machines and jobs which will disrupt the original production plan. This research focuses on dynamic multi-objective flexible scheduling problems such as the multi-constraint relationship among machines, jobs, and uncertain disturbance events. The possible disturbance events include job insertion, machine breakdown, and processing time change. The paper proposes a conv-dueling network model, a multidimensional state representation of the job processing information, and multiple scheduling objectives for minimizing makespan and delay time, while maximizing the completion punctuality rate. We design a multidimensional state space that includes job and machine processing information, an efficient and complete intelligent agent scheduling action space, and a compound scheduling reward function that combines the main task and the branch task. The unsupervised training of the network model utilizes the dueling-double-deep Q-network (D3QN) algorithm. Finally, based on the multi-constraint and multi-disturbance production environment information, the multidimensional state representation matrix of the job is used as input and the optimal scheduling rules are output after the feature extraction of the conv-dueling network model and decision making. This study carries out simulation experiments on 50 test cases. The results show the proposed conv-dueling network model can quickly converge for DQN, DDQN, and D3QN algorithms, and has good stability and universality. The experimental results indicate that the scheduling algorithm proposed in this paper outperforms DQN, DDQN, and single scheduling algorithms in all three scheduling objectives. It also demonstrates high robustness and excellent comprehensive scheduling performance.
{"title":"A dynamic scheduling method with Conv-Dueling and generalized representation based on reinforcement learning","authors":"Minghao Xia, Haibin Liu, Mingfei Li, Long Wang","doi":"10.5267/j.ijiec.2023.6.003","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.6.003","url":null,"abstract":"In modern industrial manufacturing, there are uncertain dynamic disturbances between processing machines and jobs which will disrupt the original production plan. This research focuses on dynamic multi-objective flexible scheduling problems such as the multi-constraint relationship among machines, jobs, and uncertain disturbance events. The possible disturbance events include job insertion, machine breakdown, and processing time change. The paper proposes a conv-dueling network model, a multidimensional state representation of the job processing information, and multiple scheduling objectives for minimizing makespan and delay time, while maximizing the completion punctuality rate. We design a multidimensional state space that includes job and machine processing information, an efficient and complete intelligent agent scheduling action space, and a compound scheduling reward function that combines the main task and the branch task. The unsupervised training of the network model utilizes the dueling-double-deep Q-network (D3QN) algorithm. Finally, based on the multi-constraint and multi-disturbance production environment information, the multidimensional state representation matrix of the job is used as input and the optimal scheduling rules are output after the feature extraction of the conv-dueling network model and decision making. This study carries out simulation experiments on 50 test cases. The results show the proposed conv-dueling network model can quickly converge for DQN, DDQN, and D3QN algorithms, and has good stability and universality. The experimental results indicate that the scheduling algorithm proposed in this paper outperforms DQN, DDQN, and single scheduling algorithms in all three scheduling objectives. It also demonstrates high robustness and excellent comprehensive scheduling performance.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135784222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2023.8.002
Junyuan Xiao, Guoyi Liu, Min Huang, Zhihua Yin, Zheming Gao
With a view to overcoming a few shortcomings resulting from the kernel-based SVM models, these kernel-free support vector machine (SVM) models are newly promoted and researched. With the aim of deeply enhancing the classification accuracy of present kernel-free quadratic surface support vector machine (QSSVM) models while avoiding computational complexity, an emerging kernel-free ν-fuzzy reduced QSSVM with L1 norm regularization model is proposed. The model has well-developed sparsity to avoid computational complexity and overfitting and has been simplified as these standard linear models on condition that the data points are (nearly) linearly separable. Computational tests are implemented on several public benchmark datasets for the purpose of showing the better performance of the presented model compared with a few known binary classification models. Similarly, the numerical consequences support the more elevated training effectiveness of the presented model in comparison with those of other kernel-free SVM models. What`s more, the presented model is smoothly employed in lung cancer subtype diagnosis with good performance, by using the gene expression RNAseq-based lung cancer subtype (LUAD/LUSC) dataset in the TCGA database.
{"title":"A kernel-free L1 norm regularized ν-support vector machine model with application","authors":"Junyuan Xiao, Guoyi Liu, Min Huang, Zhihua Yin, Zheming Gao","doi":"10.5267/j.ijiec.2023.8.002","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.8.002","url":null,"abstract":"With a view to overcoming a few shortcomings resulting from the kernel-based SVM models, these kernel-free support vector machine (SVM) models are newly promoted and researched. With the aim of deeply enhancing the classification accuracy of present kernel-free quadratic surface support vector machine (QSSVM) models while avoiding computational complexity, an emerging kernel-free ν-fuzzy reduced QSSVM with L1 norm regularization model is proposed. The model has well-developed sparsity to avoid computational complexity and overfitting and has been simplified as these standard linear models on condition that the data points are (nearly) linearly separable. Computational tests are implemented on several public benchmark datasets for the purpose of showing the better performance of the presented model compared with a few known binary classification models. Similarly, the numerical consequences support the more elevated training effectiveness of the presented model in comparison with those of other kernel-free SVM models. What`s more, the presented model is smoothly employed in lung cancer subtype diagnosis with good performance, by using the gene expression RNAseq-based lung cancer subtype (LUAD/LUSC) dataset in the TCGA database.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135784226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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 : 2023-01-01DOI: 10.5267/j.ijiec.2023.9.005
Somayé Ghandi, Ellips Masehian
As the simple assembly line balancing problem type 1 (SALBP1) has been proven to be NP-hard, heuristic and metaheuristic approaches are widely used for solving middle to large instances. Nevertheless, the characteristics (fitness landscape) of the problem’s search space have not been studied so far and no rigorous justification for implementing various metaheuristic methods has been presented. Aiming to fill this gap in the literature, this study presents the first comprehensive and in-depth Fitness Landscape Analysis (FLA) study for SALBP1. The FLA was performed by generating a population of 1000 random solutions and improving them to local optimal solution, and then measuring various statistical indices such as average distance, gap, entropy, amplitude, length of the walk, autocorrelation, and fitness-distance among all solutions, to understand the complexity, structure, and topology of the solution space. We solved 83 benchmark problems with various cycle times taken from Scholl’s dataset which required 83000 local searches from initial to optimal solutions. The analysis showed that locally optimal assembly line balances in SALBP1 are distributed nearly uniformly in the landscape of the problem, and the small average difference between the amplitudes of the initial and optimal solutions implies that the landscape was almost plain. In addition, the large average gap between local and global solutions showed that global optimum solutions in SALBP1 are difficult to find, but the problem can be effectively solved using a single-solution-based metaheuristic to near-optimality. In addition to the FLA, a new mathematical formulation for the entropy (diversity) of solutions in the search space for SALBP1 is also presented in this paper.
{"title":"Fitness landscape analysis of the simple assembly line balancing problem type 1","authors":"Somayé Ghandi, Ellips Masehian","doi":"10.5267/j.ijiec.2023.9.005","DOIUrl":"https://doi.org/10.5267/j.ijiec.2023.9.005","url":null,"abstract":"As the simple assembly line balancing problem type 1 (SALBP1) has been proven to be NP-hard, heuristic and metaheuristic approaches are widely used for solving middle to large instances. Nevertheless, the characteristics (fitness landscape) of the problem’s search space have not been studied so far and no rigorous justification for implementing various metaheuristic methods has been presented. Aiming to fill this gap in the literature, this study presents the first comprehensive and in-depth Fitness Landscape Analysis (FLA) study for SALBP1. The FLA was performed by generating a population of 1000 random solutions and improving them to local optimal solution, and then measuring various statistical indices such as average distance, gap, entropy, amplitude, length of the walk, autocorrelation, and fitness-distance among all solutions, to understand the complexity, structure, and topology of the solution space. We solved 83 benchmark problems with various cycle times taken from Scholl’s dataset which required 83000 local searches from initial to optimal solutions. The analysis showed that locally optimal assembly line balances in SALBP1 are distributed nearly uniformly in the landscape of the problem, and the small average difference between the amplitudes of the initial and optimal solutions implies that the landscape was almost plain. In addition, the large average gap between local and global solutions showed that global optimum solutions in SALBP1 are difficult to find, but the problem can be effectively solved using a single-solution-based metaheuristic to near-optimality. In addition to the FLA, a new mathematical formulation for the entropy (diversity) of solutions in the search space for SALBP1 is also presented in this paper.","PeriodicalId":51356,"journal":{"name":"International Journal of Industrial Engineering Computations","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135784227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：