Ideally, the solution to job-shop scheduling problem (JSP) should effectively reduce the cost of manpower and materials, thereby enhancing the core competitiveness of the manufacturer. Deep learning (DL) neural networks have certain advantages in handling complex dynamic JSPs with a massive amount of historical data. Therefore, this paper proposes a dynamic job-shop scheduling model based on DL. Firstly, a data prediction model was established for dynamic job-shop scheduling, with long short-term memory network (LSTM) as the basis; the Dropout technology and adaptive moment estimation (ADAM) were introduced to enhance the generalization ability and prediction effect of the model. Next, the dynamic JSP was described in details, and three objective functions, namely, maximum makespan, total device load, and key device load, were chosen for optimization. Finally, the multi-objective problem of dynamic JSP scheduling was solved by the improved multi-objective genetic algorithm (MOGA). The effectiveness of the algorithm was proved experimentally.
{"title":"A dynamic job-shop scheduling model based on deep learning","authors":"W. Tian, H. Zhang","doi":"10.14743/APEM2021.1.382","DOIUrl":"https://doi.org/10.14743/APEM2021.1.382","url":null,"abstract":"Ideally, the solution to job-shop scheduling problem (JSP) should effectively reduce the cost of manpower and materials, thereby enhancing the core competitiveness of the manufacturer. Deep learning (DL) neural networks have certain advantages in handling complex dynamic JSPs with a massive amount of historical data. Therefore, this paper proposes a dynamic job-shop scheduling model based on DL. Firstly, a data prediction model was established for dynamic job-shop scheduling, with long short-term memory network (LSTM) as the basis; the Dropout technology and adaptive moment estimation (ADAM) were introduced to enhance the generalization ability and prediction effect of the model. Next, the dynamic JSP was described in details, and three objective functions, namely, maximum makespan, total device load, and key device load, were chosen for optimization. Finally, the multi-objective problem of dynamic JSP scheduling was solved by the improved multi-objective genetic algorithm (MOGA). The effectiveness of the algorithm was proved experimentally.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2021-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90154933","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}
During material handling processes, automated guided vehicles (AGVs) pose a path conflict problem. To solve this problem, we proposed a multi-objective scheduling model based on total driving distance and waiting time, and used the A* path planning algorithm to search the shortest path of AGV. By using a speed control strategy, we were able to detect the overlap path and the conflict time. Additionally, we adopted an efficient MapReduce framework to improve the speed control strategy execution efficiency. At last, a material handling system of smart electrical connectors workshop was discussed to verify the scheduling model and the speed control strategy combined with the MapReduce framework is feasible and effective to reduce the AGV path conflict probability. The material handling system could be applied in workshop to replace manual handling and to improve production efficiency.
{"title":"Multi-objective automated guided vehicle scheduling based on MapReduce framework","authors":"W. Shi, D. Tang, P. Zou","doi":"10.14743/APEM2021.1.383","DOIUrl":"https://doi.org/10.14743/APEM2021.1.383","url":null,"abstract":"During material handling processes, automated guided vehicles (AGVs) pose a path conflict problem. To solve this problem, we proposed a multi-objective scheduling model based on total driving distance and waiting time, and used the A* path planning algorithm to search the shortest path of AGV. By using a speed control strategy, we were able to detect the overlap path and the conflict time. Additionally, we adopted an efficient MapReduce framework to improve the speed control strategy execution efficiency. At last, a material handling system of smart electrical connectors workshop was discussed to verify the scheduling model and the speed control strategy combined with the MapReduce framework is feasible and effective to reduce the AGV path conflict probability. The material handling system could be applied in workshop to replace manual handling and to improve production efficiency.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2021-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86538463","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}
D. Ciric, M. Delić, B. Lalic, D. Gračanin, T. Lolic
Aligning the project management approach to a particular project is considered to be essential for project success. Based on the literature review, in this research, the project management approach is analyzed through differentiation between agile and traditional approaches within the specific managerial aspects. This research aimed to contrast these two project management approaches and explore their impact on different project success dimensions. The research was conducted on a sample of 227 project management professionals worldwide, using the PLS-SEM method. Research results denounced that, in most cases, the traditional approach is applied in project initiation and planning. It has proven to provide higher-level od project success, while, within all other managerial aspects considered in this research, they gravitate more towards the agile approach. By combining agile and traditional approaches, organizations can take advantage of some benefits of agile development without abandoning the stability provided by a traditional approach. The study is relevant for project management practitioners tailoring down the success-oriented project management approach and developing project management contingency theory for academics.
{"title":"Exploring the link between project management approach and project success dimensions: A structural model approach","authors":"D. Ciric, M. Delić, B. Lalic, D. Gračanin, T. Lolic","doi":"10.14743/APEM2021.1.387","DOIUrl":"https://doi.org/10.14743/APEM2021.1.387","url":null,"abstract":"Aligning the project management approach to a particular project is considered to be essential for project success. Based on the literature review, in this research, the project management approach is analyzed through differentiation between agile and traditional approaches within the specific managerial aspects. This research aimed to contrast these two project management approaches and explore their impact on different project success dimensions. The research was conducted on a sample of 227 project management professionals worldwide, using the PLS-SEM method. Research results denounced that, in most cases, the traditional approach is applied in project initiation and planning. It has proven to provide higher-level od project success, while, within all other managerial aspects considered in this research, they gravitate more towards the agile approach. By combining agile and traditional approaches, organizations can take advantage of some benefits of agile development without abandoning the stability provided by a traditional approach. The study is relevant for project management practitioners tailoring down the success-oriented project management approach and developing project management contingency theory for academics.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2021-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80592310","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}
Generating economies of scale is one of the most desirable goals when developing modular product systems. Since complex products are commonly developed in collaboration between an Original Equipment Manufacturer (OEM) and its suppliers, pursuing this goal inherently establishes interdependencies between the development process, supplier integration and supply chain design. To fully reap the benefits of modular product systems requires a comprehensive approach that encompasses these fields and addresses the inter-dependencies between them via a coherent collaboration between development and purchasing. This is the main focus of this work. In this paper, we first describe how the product development process has to be restructured for the concerted development of modules and overall products within the scope of a modular product system. Secondly, we propose a new collaboration model between the OEM and its suppliers, since OEMs need to collaborate directly with suppliers of lower levels of the value chain in order to facilitate the standardisation of components and modules across different products. Finally, we delineate an awarding process for both development services and production volumes for series supply that resolves the conflicting priorities of economies of scale and avoiding over-dependence on single suppliers. The process models described in this paper have been conceived based on systems engineering principles and have been successfully tested and further refined throughout several industrial projects carried out with two automotive manufacturers. The resulting approach will be demonstrated using a generic example taken from the automotive industry.
{"title":"The implications of product modularisation on the development process, supplier integration and supply chain design in collaborative product development","authors":"F. Koppenhagen, T. Held","doi":"10.14743/APEM2021.1.386","DOIUrl":"https://doi.org/10.14743/APEM2021.1.386","url":null,"abstract":"Generating economies of scale is one of the most desirable goals when developing modular product systems. Since complex products are commonly developed in collaboration between an Original Equipment Manufacturer (OEM) and its suppliers, pursuing this goal inherently establishes interdependencies between the development process, supplier integration and supply chain design. To fully reap the benefits of modular product systems requires a comprehensive approach that encompasses these fields and addresses the inter-dependencies between them via a coherent collaboration between development and purchasing. This is the main focus of this work. In this paper, we first describe how the product development process has to be restructured for the concerted development of modules and overall products within the scope of a modular product system. Secondly, we propose a new collaboration model between the OEM and its suppliers, since OEMs need to collaborate directly with suppliers of lower levels of the value chain in order to facilitate the standardisation of components and modules across different products. Finally, we delineate an awarding process for both development services and production volumes for series supply that resolves the conflicting priorities of economies of scale and avoiding over-dependence on single suppliers. The process models described in this paper have been conceived based on systems engineering principles and have been successfully tested and further refined throughout several industrial projects carried out with two automotive manufacturers. The resulting approach will be demonstrated using a generic example taken from the automotive industry.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2021-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82486637","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}
Combining timber and glass in the wall elements of the building envelope with the proper orientation of such transparent façade elements enables the utilization of solar energy for heating and internal illumination of the building. However, the asymmetrical layout of timber‐glass wall elements in such buildings can result in problems with the horizontal stability of the structure, so their participation to load‐bearing capacity of the structure is usually ne‐ glected. The study deals with solutions for such elements as horizontal load‐ bearing members with proper connection details. First, specifically developed timber‐glass wall elements were experimentally tested under monotonic and cyclic horizontal point load, and further in combination with classical timber‐ framed wall elements implemented into special single and two‐storey box‐ house models, which were further experimentally tested on the shaking table. In the second part as the main goal of the study, a quite simple mathematical model of the box‐house prototypes is developed using a fictive diagonal ele‐ ment for simulating the racking stiffness of the bracing timber‐glass wall element. The calculated results for the 1st vibration period are compared with the previously measured experimental results to prove an accuracy of the developed model. Finally, a linear time‐history calculation is done as a sample presentation of the developed mathematical model using Landers accelera‐ tion spectrum. The developed mathematical model enables a simple and effec‐ tive seismic response calculation of timber buildings considering the devel‐ oped timber‐glass wall elements as load‐bearing bracing elements against horizontal load actions. The model can also be recommended for using in further parametric numerical academic studies analysing the influence of various parameters.
{"title":"Study of load-bearing timber-wall elements using experimental testing and mathematical modelling","authors":"M. Premrov, B. Ber, E. K. Silih","doi":"10.14743/APEM2021.1.385","DOIUrl":"https://doi.org/10.14743/APEM2021.1.385","url":null,"abstract":"Combining timber and glass in the wall elements of the building envelope with the proper orientation of such transparent façade elements enables the utilization of solar energy for heating and internal illumination of the building. However, the asymmetrical layout of timber‐glass wall elements in such buildings can result in problems with the horizontal stability of the structure, so their participation to load‐bearing capacity of the structure is usually ne‐ glected. The study deals with solutions for such elements as horizontal load‐ bearing members with proper connection details. First, specifically developed timber‐glass wall elements were experimentally tested under monotonic and cyclic horizontal point load, and further in combination with classical timber‐ framed wall elements implemented into special single and two‐storey box‐ house models, which were further experimentally tested on the shaking table. In the second part as the main goal of the study, a quite simple mathematical model of the box‐house prototypes is developed using a fictive diagonal ele‐ ment for simulating the racking stiffness of the bracing timber‐glass wall element. The calculated results for the 1st vibration period are compared with the previously measured experimental results to prove an accuracy of the developed model. Finally, a linear time‐history calculation is done as a sample presentation of the developed mathematical model using Landers accelera‐ tion spectrum. The developed mathematical model enables a simple and effec‐ tive seismic response calculation of timber buildings considering the devel‐ oped timber‐glass wall elements as load‐bearing bracing elements against horizontal load actions. The model can also be recommended for using in further parametric numerical academic studies analysing the influence of various parameters.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2021-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77854345","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}
The purpose of this article is to give a general overview of the production technologies of stents with consideration of their design and materials. Since the beginning of the use of stents in medicine for atherosclerosis treatment, their development has changed rapidly. Various stents have also been developed with the development of materials science, treatment techniques and new manufacturing processes. In this way the development has shifted from the initial bare-metal stents (BMS), to drug-eluting stents (DES) and bio-resorbable stents (BRS), which are made of biodegradable polymers or metals. Various studies agree that it will be necessary to further review the experimentally obtained material properties with analytical and numerical studies. Here, the computational modelling (Finite element analysis - FEA and Computational fluid dynamics - CFD) was found as a valuable tool when evaluating stent mechanics and optimizing stent design. The development of the stent manufacturing technologies has also changed and been supplemented over the years. Nowadays, 3D printing could be an exciting manufacturing method to produce polymeric bio-materials, suitable for the latest generation of bio-degradable stents applications.
{"title":"A review of production technologies and materials for manufacturing of cardiovascular stents","authors":"B. Polanec, J. Kramberger, S. Glodež","doi":"10.14743/apem2020.4.373","DOIUrl":"https://doi.org/10.14743/apem2020.4.373","url":null,"abstract":"The purpose of this article is to give a general overview of the production technologies of stents with consideration of their design and materials. Since the beginning of the use of stents in medicine for atherosclerosis treatment, their development has changed rapidly. Various stents have also been developed with the development of materials science, treatment techniques and new manufacturing processes. In this way the development has shifted from the initial bare-metal stents (BMS), to drug-eluting stents (DES) and bio-resorbable stents (BRS), which are made of biodegradable polymers or metals. Various studies agree that it will be necessary to further review the experimentally obtained material properties with analytical and numerical studies. Here, the computational modelling (Finite element analysis - FEA and Computational fluid dynamics - CFD) was found as a valuable tool when evaluating stent mechanics and optimizing stent design. The development of the stent manufacturing technologies has also changed and been supplemented over the years. Nowadays, 3D printing could be an exciting manufacturing method to produce polymeric bio-materials, suitable for the latest generation of bio-degradable stents applications.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74650738","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}
High-speed machining (HSM) maintains a high interest in the preparation of metal parts for optimum results, but with the application of HSM, the sustainability issue becomes important. To overcome the problem, minimum quantity lubrication (MQL) during HSM is one of the innovative and challenging tasks during conventional cutting (milling) to improve quality, productivity, and strength under the umbrella of sustainability. The objective of this research is to achieve sustainable machining by simultaneously optimizing sustainable machining drivers during the HSM of 15CDV6 HSLA steel under MQL and flood lubrication. The response surface methodology has been applied for the development of mathematical models and selecting the best combination of process parameters to optimized responses, i.e. surface roughness, material removal rate, and strength. Optimization associated with sustainability produced compromising optimal results (Min. Ra 0.131 µm, Max. MRR 0.64 cm3/min, and Max. ST 1132 MPa) at the highest cutting speed 270 m/min and the lowest feed rate 0.09 mm/rev and depth of cut 0.15 mm under MQL. The comparative investigation exposed that significant improvement in Ra (1.1-16.6 %) and ST (1.3-2.3 %) of the material using MQL has been witnessed and gives a strong indication that MQL is the best substitute than the flood lubrication. The scientific contribution of the approach is to develop mathematical models under MQL and flood lubrication that will aid practitioners to choose input parameters for desired responses without experimentations. The work would be beneficial in the field of aviation, defense, and aeronautical applications due to the excellent mechanical properties of 15CDV6 HSLA steel.
{"title":"High-speed machining parametric optimization of 15CDV6 HSLA steel under minimum quantity and flood lubrication","authors":"A. H. Khawaja, M. Jahanzaib, T. A. Cheema","doi":"10.14743/apem2020.4.374","DOIUrl":"https://doi.org/10.14743/apem2020.4.374","url":null,"abstract":"High-speed machining (HSM) maintains a high interest in the preparation of metal parts for optimum results, but with the application of HSM, the sustainability issue becomes important. To overcome the problem, minimum quantity lubrication (MQL) during HSM is one of the innovative and challenging tasks during conventional cutting (milling) to improve quality, productivity, and strength under the umbrella of sustainability. The objective of this research is to achieve sustainable machining by simultaneously optimizing sustainable machining drivers during the HSM of 15CDV6 HSLA steel under MQL and flood lubrication. The response surface methodology has been applied for the development of mathematical models and selecting the best combination of process parameters to optimized responses, i.e. surface roughness, material removal rate, and strength. Optimization associated with sustainability produced compromising optimal results (Min. Ra 0.131 µm, Max. MRR 0.64 cm3/min, and Max. ST 1132 MPa) at the highest cutting speed 270 m/min and the lowest feed rate 0.09 mm/rev and depth of cut 0.15 mm under MQL. The comparative investigation exposed that significant improvement in Ra (1.1-16.6 %) and ST (1.3-2.3 %) of the material using MQL has been witnessed and gives a strong indication that MQL is the best substitute than the flood lubrication. The scientific contribution of the approach is to develop mathematical models under MQL and flood lubrication that will aid practitioners to choose input parameters for desired responses without experimentations. The work would be beneficial in the field of aviation, defense, and aeronautical applications due to the excellent mechanical properties of 15CDV6 HSLA steel.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88005812","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}
Green production mode is an advanced manufacturing mode. However, due to the environmental externality of green production, it is different for a pure market mechanism to promote the evolution of green operation mode of manufacturing enterprises. Government regulation is very important. This paper establishes an evolutionary game model of whether manufacturing enterprises choose to implement green production mode when the government implements two different mechanisms of reward and punishment. Considering the complexity of strategy selection of enterprises' green production behaviour under market competition, the method constructs the simulation analysis model of enterprises' green product production behaviour with multi-subject participation. We can simulate the influence of these factors on the strategic choice of both parties (enterprises and governments) by changing the different influence factors, and studying the evolutionary law of different government guidance and regulation strategies on the production behaviour of green products. These factors include government incentives, penalties, reputations, costs, differences in the cost of implementing green production on the corporate side, corporate reputation, and false rewards or penalties. By the computer implementation of multi-subject modelling, the results show that enterprises' green product production behaviour needs the government's guidance and regulation. When formulating relevant policies, the government should combine various guidance and regulation strategies and fully consider the influence of market competition.
{"title":"Evolutionary game of green manufacturing mode of enterprises under the influence of government reward and punishment","authors":"A.L. Awaga, W. Xu, L. Liu, Y. Zhang","doi":"10.14743/apem2020.4.375","DOIUrl":"https://doi.org/10.14743/apem2020.4.375","url":null,"abstract":"Green production mode is an advanced manufacturing mode. However, due to the environmental externality of green production, it is different for a pure market mechanism to promote the evolution of green operation mode of manufacturing enterprises. Government regulation is very important. This paper establishes an evolutionary game model of whether manufacturing enterprises choose to implement green production mode when the government implements two different mechanisms of reward and punishment. Considering the complexity of strategy selection of enterprises' green production behaviour under market competition, the method constructs the simulation analysis model of enterprises' green product production behaviour with multi-subject participation. We can simulate the influence of these factors on the strategic choice of both parties (enterprises and governments) by changing the different influence factors, and studying the evolutionary law of different government guidance and regulation strategies on the production behaviour of green products. These factors include government incentives, penalties, reputations, costs, differences in the cost of implementing green production on the corporate side, corporate reputation, and false rewards or penalties. By the computer implementation of multi-subject modelling, the results show that enterprises' green product production behaviour needs the government's guidance and regulation. When formulating relevant policies, the government should combine various guidance and regulation strategies and fully consider the influence of market competition.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89505358","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}
M. K. Amjad, S. I. Butt, N. Anjum, I. Chaudhry, Z. Faping, M. Khan
Flexible job shop scheduling problem (FJSSP) is a further expansion of the classical job shop scheduling problem (JSSP). FJSSP is known to be NP-hard with regards to optimization and hence poses a challenge in finding acceptable solutions. Genetic algorithm (GA) has successfully been applied in this regard since last two decades. This paper provides an insight into the actual complexity of selected benchmark problems through quantitative evaluation of the search space owing to their NP-hard nature. A four-layered genetic algorithm is then proposed and implemented with adaptive parameters of population initialization and operator probabilities to manage intensification and diversification intelligently. The concept of reinitialization is introduced whenever the algorithm is trapped in local minima till predefined number of generations. Results are then compared with various other standalone evolutionary algorithms for selected benchmark problems. It is found that the proposed GA finds better solutions with this technique as compared to solutions produced without this technique. Moreover, the technique helps to overcome the local minima trap. Further comparison and analysis indicate that the proposed algorithm produces comparative and improved solutions with respect to other analogous methodologies owing to the diversification technique.
{"title":"A layered genetic algorithm with iterative diversification for optimization of flexible job shop scheduling problems","authors":"M. K. Amjad, S. I. Butt, N. Anjum, I. Chaudhry, Z. Faping, M. Khan","doi":"10.14743/apem2020.4.372","DOIUrl":"https://doi.org/10.14743/apem2020.4.372","url":null,"abstract":"Flexible job shop scheduling problem (FJSSP) is a further expansion of the classical job shop scheduling problem (JSSP). FJSSP is known to be NP-hard with regards to optimization and hence poses a challenge in finding acceptable solutions. Genetic algorithm (GA) has successfully been applied in this regard since last two decades. This paper provides an insight into the actual complexity of selected benchmark problems through quantitative evaluation of the search space owing to their NP-hard nature. A four-layered genetic algorithm is then proposed and implemented with adaptive parameters of population initialization and operator probabilities to manage intensification and diversification intelligently. The concept of reinitialization is introduced whenever the algorithm is trapped in local minima till predefined number of generations. Results are then compared with various other standalone evolutionary algorithms for selected benchmark problems. It is found that the proposed GA finds better solutions with this technique as compared to solutions produced without this technique. Moreover, the technique helps to overcome the local minima trap. Further comparison and analysis indicate that the proposed algorithm produces comparative and improved solutions with respect to other analogous methodologies owing to the diversification technique.","PeriodicalId":48763,"journal":{"name":"Advances in Production Engineering & Management","volume":null,"pages":null},"PeriodicalIF":3.6,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85645734","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：