Energy prediction and optimization for robotic stereoscopic statue processing

Energy consumption has become one of the primary costs in the stone processing industry. Stereoscopic statue production, characterized by extensive material removal and prolonged cycles, consumes the most energy among stone products. Due to their high degrees of freedom, operational agility, precision, and broad scope, industrial robots are widely applied in stereoscopic statue processing. However, robotic processing of stereoscopic statues represents a quintessential high-energy-consuming process, especially during the rough machining phase, where energy consumption is particularly significant. Therefore, this paper proposes a method for predicting energy consumption during the rough machining phase of robotic stereoscopic statue processing and implementing energy-saving optimization. Firstly, a prediction model for the robot's body power is established by analyzing the energy consumption characteristics of the robot system. Subsequently, the spindle power of the robot is predicted based on the relationship between force and power variations during the grinding process. Finally, energy consumption optimization is achieved using the proposed feed-speed dynamic programming method based on genetic algorithms. Experimental results show that using the feed-speed dynamic programming method reduces energy consumption during rough machining by 16.9%, and processing time is shortened by 19.5%.