Modern radars face the problems of dense technology， complex structure， difficult performance and quality evaluation， and lack of quantitative evaluation methods. Considering this， a radar condition monitoring and comprehensive performance evaluation system is designed by technologies such as intelligent monitoring and automatic testing， as well as fuzzy comprehensive evaluation. In this way， the comprehensive evaluation of the quality condition is achieved for the radar system， which is mainly on monitoring data and fused with historical data and environmental data. Upon the introduction to the overall structure of the system， the design principles of the condition monitoring system and the comprehensive evaluation system are expounded in detail， and the application of the systems in a typical radar is given. It has been verified that the system design is reasonable and feasible and can comprehensively and excellently evaluate the performance of the radar system.

Multi-agent cooperation and competition has the characteristics of real-time and action continuity， incomplete information， huge search space， multi-complex tasks and time-space inference， etc. It is one of the most challenging problems in the current artificial intelligence field. Aiming at the problem of long training time for large-scale multi-agent reinforcement learning， this paper proposes an Actor-Critic-based cooperative confrontation framework， which uses meta curriculum reinforcement learning method to extract meta-models of basic tasks for small-scale scenarios. We carry out model migration to large-scale scenarios based on the curriculum learning， which continues training based on the meta-models and finally obtains a better collaboration strategy. This paper conducts simulation experiments on the "Star-Craft II" platform. The results show that the multi-agent cooperative confrontation technology based on the meta curriculum reinforcement learning can effectively accelerate the training process， and can achieve a higher win rate within a shorter time compared with the traditional training methods. The training speed is increased by about 40%. This method can effectively support the efficient generation of multi-agent cooperative confrontation strategies.