Abstract: Addressing the search matching and service composition issues between manufacturing capabilities and task requirements in the context of intelligent manufacturing resource service sharing in cloud computing environments,this study presents a cloud manufacturing capability demand model and matching strategy based on semantic similarity and an improved Particle Swarm Optimization (PSO) algorithm is presented. First,building upon the proposed cloud manufacturing capability demand model,the concept of domain ontology tree is introduced to calculate concept similarity,sentence similarity,and numerical similarity,thereby achieving intelligent service search for cloud manufacturing capability demands based on semantic similarity. Subsequently,addressing the issue of service composition for cloud manufacturing capabilities,based on analyzing the Quality of Service (QoS) attributes of manufacturing capabilities, a service composition method based on an improved PSO algorithm is proposed using the Analytic Hierarchy Process (AHP) to normalize and sum various attributes. Finally,experimental comparisons demonstrate the superiority of the proposed approach over existing methods,leading to the realization of an intelligent matching prototype system for cloud manufacturing capability demands.

Key words: cloud manufacturing capabilities, task demands, search matching, service composition, semantic similarity, improved Particle Swarm Optimization (PSO) algorithm