Research on deep learning and shearer drum elevation control is a hot topic in recent years. The shearer drum elevation control based on deep learning has been paid attention to by the majority of researchers and a series of studies have been carried out. In order to solve the problem that the traditional memory cutting method of shearer is not accurate, the research on intelligent elevation control method of shearer drum based on deep learning is proposed. In this essay, the intelligent control system of drum elevation of shearer is modelled mathematically, and the improved deep-learning firefly algorithm is used to optimise the PID parameters of the drum control system, and the Simulink simulation model of the intelligent control system of drum elevation is built. The response of the system using the improved and basic firefly algorithm is analysed. The experimental results show that the overshoot of the optimised system decreases by 21.6% under the step signal. Under the ramp signal, the overshoot of the optimised system decreased by 38.4%. Under the pulse interference signal, the overshoot of the optimised system is reduced by 21.9%. Under the step interference signal, the overshoot of the optimised system is reduced by 33.2%. Under the random interference signal, the wave range of the optimised response curve is reduced by 40.1%. Conclusion: After adding the PID controller optimised by the improved deep learning firefly algorithm to the drum elevation control system, the response performance and anti-interference performance of the system are greatly improved and enhanced. The research of this article provides important guidance for deep learning and shearer drum elevation control. K E Y W O R D S biomedical electronics, combinatorial mathematics | INTRODUCTIONThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.