PCB (Printed Circuit Board) splicing and blanking method based on deep intelligent genetic optimization algorithm

The embodiment of the invention provides a PCB (Printed Circuit Board) splicing and blanking method based on a deep intelligent genetic optimization algorithm. The method comprises the following steps: step 1, generating an initial population; 2, calculating the fitness of the initial population, and obtaining the state of the initial population; step 3, when the fitness value does not reach a preset value, inputting the current state st of the population into a deep intelligent genetic optimization algorithm for optimization; and 4, repeating the step 3 until the maximum specified operation round number is reached, and outputting the layout drawing and the utilization rate of the optimal individual. According to the method, a deep reinforcement learning model SAC is used for optimizing the genetic algorithm, crossover and mutation operations are separated from a traditional genetic algorithm and serve as action spaces of agents, the agents are trained through the SAC model, the crossover and mutation operati