Digital twin self-evolution means that digital twin can fuse online sensor data from physical entity to evolve itself, hence improve credibility of the model and represent the physical entity faithfully. There is an urgent need to address the fundamental theories and techniques on how to build such a self-evolving digital twin system for complex equipment optimization and control. Focused on this problem, integrating Bayesian optimization theory and deep reinforcement learning, this paper has proposed a method to build dynamic selfevolving equipment digital twin system for optimal control. First, considering the complexity of current equipment and real-time requirement of dynamic self-evolution scenario, we design digital twin dynamic selfevolution engine using Bayesian optimization theory, which can continuously integrate real-time sensing data, adapt to the dynamic uncertainty changes of physical equipment, so as to improve the credibility of digital twin. Then, a decision-making agent based on deep reinforcement learning algorithm SAC(Soft Actor-Critic) is designed, which can interact with equipment digital twin in virtual space. When the digital twin model evolves, the agent follows and continues to learn and update itself through online fine-tuning strategy, so as to continuously improve the equipment optimization control performance. Finally, the feasibility and effectiveness of the proposed method are verified by two simulation cases.

As an emerging technology, digital twin is expected to bring novel application modes to the whole life cycle process of unmanned ground equipment, including research and development, design, control optimization, operation and maintenance, etc. The highly dynamic, complex, and uncertain characteristics of unmanned ground equipment and the battlefield environment also pose new challenges for digital twin technology. Starting from the new challenges faced by the digital twin of unmanned ground equipment, this paper designs a service-oriented cloud-edge-end collaborative platform architecture of the digital twin system of unmanned ground equipment, and further analyzes several key technologies supporting the implementation of the platform architecture.