Intelligent manufacturing is a general concept that is under continuous development. It can be categorized into three basic paradigms： digital manufacturing, digital-networked manufacturing, and newgeneration intelli...Intelligent manufacturing is a general concept that is under continuous development. It can be categorized into three basic paradigms： digital manufacturing, digital-networked manufacturing, and newgeneration intelligent manufacturing. New-generation intelligent manufacturing represents an indepth integration of new-generation artificial intelligence （AI） technology and advanced manufacturing technology. It runs through every link in the full life-cycle of design, production, product, and service. The concept also relates to the optimization and integration of corresponding systems; the continuous improvement of enterprises＇ product quality, performance, and service levels; and reduction in resources consumption. New-generation intelligent manufacturing acts as the core driving force of the new indus- trial revolution and will continue to he the main pathway for the transformation and upgrading of the manufacturing industry in the decades to come. Human-cyher-physical systems （HCPSs） reveal the tech- nological mechanisms of new-generation intelligent manufacturing and can effectively guide related the- oretical research and engineering practice. Given the sequential development, cross interaction, and iterative upgrading characteristics of the three basic paradigms of intelligent manufacturing, a technol- ogy roadmap for ＂parallel promotion and integrated development＂ should he developed in order to drive forward the intelligent transformation of the manufacturing industry in China.展开更多
This paper deals with the problem of attribute discernibility reduction and proposes some new concepts to rough set theory （RST） based on the discernibility matrix of Skowron, such as secondary core, regeneration ma...This paper deals with the problem of attribute discernibility reduction and proposes some new concepts to rough set theory （RST） based on the discernibility matrix of Skowron, such as secondary core, regeneration matrix and the degree of attribute discernibility （DAD）. This paper puts forward an attribute reduction algorithm based on maximum discernibility degree, which opens up an effective way of gaining minimum attribute reduction of decision table. The efficacy of this algorithm has been verified by practical application in a diagnostic system of loader, which substantially decreases information gathering requirement and lowers the overall cost with no loss of accuracy.展开更多
The distributed flexible job shop scheduling problem(DFJSP),which is an extension of the flexible job shop scheduling problem,is a famous NP-complete combinatorial optimization problem.This problem is widespread in th...The distributed flexible job shop scheduling problem(DFJSP),which is an extension of the flexible job shop scheduling problem,is a famous NP-complete combinatorial optimization problem.This problem is widespread in the manufacturing industries and comprises the following three subproblems:the assignment of jobs to factories,the scheduling of operations to machines,and the sequence of operations on machines.However,studies on DFJSP are seldom because of its difficulty.This paper proposes an effective improved gray wolf optimizer(IGWO)to solve the aforementioned problem.In this algorithm,new encoding and decoding schemes are designed to represent the three subproblems and transform the encoding into a feasible schedule,respectively.Four crossover operators are developed to expand the search space.A local search strategy with the concept of a critical factory is also proposed to improve the exploitability of IGWO.Effective schedules can be obtained by changing factory assignments and operation sequences in the critical factory.The proposed IGWO algorithm is evaluated on 69 famous benchmark instances and compared with six state-of-the-art algorithms to demonstrate its efficacy considering solution quality and computational efficiency.Experimental results show that the proposed algorithm has achieved good improvement.Particularly,the proposed IGWO updates the new upper bounds of 13 difficult benchmark instances.展开更多
文摘Intelligent manufacturing is a general concept that is under continuous development. It can be categorized into three basic paradigms： digital manufacturing, digital-networked manufacturing, and newgeneration intelligent manufacturing. New-generation intelligent manufacturing represents an indepth integration of new-generation artificial intelligence （AI） technology and advanced manufacturing technology. It runs through every link in the full life-cycle of design, production, product, and service. The concept also relates to the optimization and integration of corresponding systems; the continuous improvement of enterprises＇ product quality, performance, and service levels; and reduction in resources consumption. New-generation intelligent manufacturing acts as the core driving force of the new indus- trial revolution and will continue to he the main pathway for the transformation and upgrading of the manufacturing industry in the decades to come. Human-cyher-physical systems （HCPSs） reveal the tech- nological mechanisms of new-generation intelligent manufacturing and can effectively guide related the- oretical research and engineering practice. Given the sequential development, cross interaction, and iterative upgrading characteristics of the three basic paradigms of intelligent manufacturing, a technol- ogy roadmap for ＂parallel promotion and integrated development＂ should he developed in order to drive forward the intelligent transformation of the manufacturing industry in China.
文摘This paper deals with the problem of attribute discernibility reduction and proposes some new concepts to rough set theory （RST） based on the discernibility matrix of Skowron, such as secondary core, regeneration matrix and the degree of attribute discernibility （DAD）. This paper puts forward an attribute reduction algorithm based on maximum discernibility degree, which opens up an effective way of gaining minimum attribute reduction of decision table. The efficacy of this algorithm has been verified by practical application in a diagnostic system of loader, which substantially decreases information gathering requirement and lowers the overall cost with no loss of accuracy.
基金supported by the National Natural Science Foundation of China(Grant Nos.51825502 and U21B2029)。
文摘The distributed flexible job shop scheduling problem(DFJSP),which is an extension of the flexible job shop scheduling problem,is a famous NP-complete combinatorial optimization problem.This problem is widespread in the manufacturing industries and comprises the following three subproblems:the assignment of jobs to factories,the scheduling of operations to machines,and the sequence of operations on machines.However,studies on DFJSP are seldom because of its difficulty.This paper proposes an effective improved gray wolf optimizer(IGWO)to solve the aforementioned problem.In this algorithm,new encoding and decoding schemes are designed to represent the three subproblems and transform the encoding into a feasible schedule,respectively.Four crossover operators are developed to expand the search space.A local search strategy with the concept of a critical factory is also proposed to improve the exploitability of IGWO.Effective schedules can be obtained by changing factory assignments and operation sequences in the critical factory.The proposed IGWO algorithm is evaluated on 69 famous benchmark instances and compared with six state-of-the-art algorithms to demonstrate its efficacy considering solution quality and computational efficiency.Experimental results show that the proposed algorithm has achieved good improvement.Particularly,the proposed IGWO updates the new upper bounds of 13 difficult benchmark instances.
