Reliability simulation method and system for ship transmission shaft based on deep reinforcement learning

The invention discloses a reliability simulation method and system for a ship transmission shaft based on deep reinforcement learning, and belongs to the field of ship transmission shaft design. According to the method, a deep reinforcement learning algorithm is organically combined with fault features and reliability feature quantities, the reliability feature quantities of transmission shaft parts are substituted into a fault tree for quantitative analysis, and the state transition probability of each node is calculated; a Markov chain model is used to conclude the fault mode state transition rule of each node to establish a system fault state transition probability formula; fault mode analysis establishes a fault state space; qualitatively analyzing the probability correlation degree of the bottom event and the top event by using the fault tree to form an action space; a reward function weight factor of the Markov decision model is generated through the mathematical relationship of the reliability characte