Digital Twin Enhanced Optimization of Manufacturing Service Scheduling for Industrial Cloud Robotics

Abstract

The industrial cloud robotics (ICR) has the characteristics of intelligence, reliability, and scalability. In the smart manufacturing environment, ICR can be encapsulated as services through virtualization and servilization technology, enabling the rapid matching of personalized manufacturing capabilities and services for end users. However, the manufacturing resources are physically isolated and the physical workshop environment is vulnerable to dynamic disturbances, which reduces manufacturing system performance. In this context, taking the cycle time into consideration, the manufacturing service scheduling model for ICR is established and the digital twin (DT) enhanced scheduling optimization mechanism is proposed. When disturbances occur, the digital twin platform interacts with the cloud layer and physical workshop to analyze multi-source data in order to monitor the manufacturing environment in real time and optimize the production efficiency. Meanwhile, the manufacturing service scheduling based on an improved discrete differential evolution (IDDE) algorithm is proposed, in which the adaptive mutation and crossover operator and double mutation strategies are applied to converge to the optimal scheduling sequence. Finally, the case study is implemented to verify the proposed mechanism shows better performance compared with the existing optimization algorithms.