Research On Collaborative Optimization Of Service Scheduling For Industrial Cloud Robotics Based On Knowledge Sharing

With the rapid development of sensor technology,control technology and artificial intelligence,Industrial Robots(IRs)have been widely used in various manufacturing industries.Industrial Cloud Robotics(ICR),is the combination of Cloud Computing and Industrial Robots,and has the characteristics of resource sharing,convenient access,lower costs and high efficiency,which can make up for the lack of information sharing of traditional industrial robots,and can interact and share knowledge sharing in a wide area.Towards service-oriented manufacturing model,the collaborative optimization of service scheduling for industrial robots towards workshop manufacturing tasks in a wide-area has become a focus of many scholars and enterprises.However,the lack of effective information interaction and knowledge sharing among industrial robots seriously restricts the further improvement of the collaborative optimization performance of service scheduling.Therefore,it is of great practical significance to study the collaborative optimization of service scheduling for industrial cloud robotics based on knowledge sharing.In view of the above problems,this paper takes industrial cloud robotics as the research object,and focuses on the collaborative optimization of service scheduling for industrial cloud robotics based on knowledge sharing.The main research work is as follows:(1)A cloud-based knowledge sharing mechanism of industrial robots is studied.Towards the workshop production environment,the architecture of industrial robotic manufacturing system in the cloud environment is constructed,and a knowledge sharing mechanism based on the approach of knowledge coding-knowledge exchange-knowledge reuse is proposed.The production process information of the manufacturing tasks is analyzed,and Web Ontology Language(OWL)is used to encode the knowledge related to the production process of industrial cloud robotics.After the uplink and downlink knowledge exchange,Dynamic Description Logic(DDL)is used for capability matching based on knowledge and semantic information,and knowledge reuse is completed,so as to realize the cloud-based knowledge sharing mechanism of industrial robots.(2)A collaborative optimization method of service scheduling for industrial cloud robotics based on Deep Q-Network(DQN)is studied.On the basis of knowledge sharing mechanism,aiming at the collaborative optimization scenario of service scheduling towards production process,the Markov Decision Process(MDP)model for collaborative optimization of service scheduling for industrial cloud robotics is constructed.Combining the service evaluation model of industrial robot based on QoS and energy consumption,the collaborative optimization method of service scheduling for industrial cloud robotics based on DQN is proposed.Finally,the effectiveness of the proposed method is verified by the assembly case of industrial cloud robotic production line.(3)A service platform prototype system of industrial cloud robotic based on knowledge sharing is designed and developed,which can support the unified management and scheduling of resources releated to industrial cloud robotics and information related to production tasks.The system mainly includes manufacturing resource management module,knowledge service management module,production task management module and production scheduling management module.Through the unified management and scheduling of resources releated to industrial cloud robotics and information related to production tasks,the operation of actual workshop can be guided and the production efficiency and economic benefits of the enterprise can be improved.