Intelligent Adjustment of Temperature Control Parameters Based on Deep Reinforcement Learning for Stretch Blow Molding Machine

Stretch blow molding is the main technology used in the production of PET bottles. The stretch blow molding machine is usually composed of preform infeed system, transfer system, heating system, molding system, bottle discharge system, etc. Among them, the temperature control of the heating system is one of the key factors affecting the quality of PET bottle, especially in the face of the environmental temperature changes greatly between morning and evening in some seasons. The on-site operators of the stretch blow molding machine often need to adjust the infrared heating lamps in the heating system several times. The adjustment process is highly dependent on experience of the personnel. It has become a production challenge for the bottle manufacturers. Therefore, this paper takes the heating system of the stretch blow molding machine as the object and uses the deep reinforcement learning method to develop an intelligent adjustment technique of temperature control parameters. The proposed method can improve the problems such as the interference of environmental temperature changes and the aging variation of infrared heating lamps. The experimental results show that the proposed method can adjust the temperature control parameters automatically in the heating process to eliminate the effect of the environmental temperature change and to control the surface temperature of the preforms stably within ±3 °C of the target temperature (the requirement is within±5 °C).