中文摘要：

信息物理融合系统（CPS）应用日趋广泛,如何使系统自主捕捉到复杂状态变化并做出相应动作是CPS的核心问题之一，针对此关键问题,结合强化学习算法提出一种基于相似度计算的CPS自决策方法（SCBRLA），该方法首先提取系统特征和系统目标状态特征,然后通过计算系统当前状态与目标状态的相似度决定采取相应动作及其顺序，该方法可较好地用于分析CPS服务在受到攻击时,系统采取的自适应决策.仿真结果表明该方法能够帮助CPS系统实现自决策,且与传统算法相比能获得更快的响应速度。

英文摘要：

Cyber-Physical systems （CPS） are getting more and more popular How to make the system automatically capture the changes of complex statuses and take proper actions responding to the changes is one of the key problems of CPS. Combining with the reinforcement learning algorithm, a novel features of both system and system targets are firstly extracted, and then the similarities of current system state and target states are computed. Based on the computation result, system takes corresponding actions and decides the execution order of those actions. The p strategies of system self-decision when it receives attacks. algorithm can help systems realize self-decision, and traditional method. roposed algorithm can be well used to analyze The simulation results it has faster response show that the proposed speed compared with