Health Status Recognition of Coal Shearer Based on Artificial Bee Colony Algorithm Optimized Deep Belief Network

In order to solve the problems that the current shearer health status recognition method requires repeated collection of expert comments and the low recognition rate of the shallow neural network, a shearer health status recognition algorithm based on the Artificial Bee Colony algorithm(ABC) to optimize the Deep Belief Network(DBN) is proposed. First, the state index parameters that affect the health status of the shearer are selected according to the evaluation index selection principle, and the parameters are used for the input of the status recognition model; second, the health status of the shearer is identified based on DBN recognition model, at the same time, in order to optimize the DBN network structure and improve the model recognition rate, Artificial Bee Colony algorithm is introduced to optimize the key parameters of the DBN model. Finally, the feasibility of the optimized identification method is demonstrated through comparative experiments.