An Out-of-order Execution-Based Method of Instruction Control for Production-Logistics in Smart Manufacturing

LI Mingxing; QU Ting; LI Ming; LI Congdong; HE Zhen; HUANG Guoquan

doi:10.3969/j.issn.1007-7375.240169

Abstract：Intelligent control and decision-making for production-logistics operations in complex and dynamic environments is one of the core technologies in discrete manufacturing systems.To cope with the complexity of system structures and multi-resource interdependencies,the complexity of production-logistics operations under various disturbances and multi-resource constraints,and the difficulty in bridging the gap between decision-making and execution under uncertainty,this paper propose a novel approach.It develops an instruction-driven operational architecture for intelligent production-logistics systems,inspired by"out-of-order execution"in high-performance central processing units(CPU).This architecture reconstruct the production-logistics operation mode from dynamic deconstruction of manufacturing systems,spatiotemporal inference of uncertainty,fundamental interaction logic between production and logistics,and core control mechanisms and decision-making methods.A case study is carried out to verify the effectiveness of out-of-order execution in stochastic environments with frequent disturbances.Results show that the proposed method performs well in terms of makespan,average job delay,average job flow time,and average operator utilization rate,exhibiting smaller fluctuations and greater stability in stochastic environments.Finally,future applications and research directions of out-of-order execution in intelligent manufacturing systems are discussed,providing new insights and methods for optimizing production-logistics operations in smart manufacturing factories.