Scheduling Control of Coal Mining Equipment Based on Fuzzy PID and Multi-Sensor Fusion

Full abstract

Read the full abstract

Abstract To address the problems of insufficient collaborative control accuracy, delayed scheduling response, and low multi-equipment coordination efficiency in coal mine equipment, this study proposes an intelligent scheduling control model for coal mine equipment by integrating fuzzy proportional-integral-derivative control and multi-sensor information fusion. The model first constructs a three-level information fusion architecture consisting of data-level, feature-level, and decision-level fusion, through which the operating parameters of key equipment, such as shearers, hydraulic supports, and scraper conveyors, are collected, filtered, and characterized in real time. Subsequently, the Kalman filtering algorithm is introduced to suppress noise and estimate states from multi-source sensor data, while a fuzzy reasoning mechanism is used to adaptively adjust the proportional, integral, and derivative parameters, thereby enhancing the control stability of the system under load fluctuations and complex operating conditions. On this basis, a dynamic scheduling model considering production efficiency, energy consumption, equipment health status, and safety risk is further established, and multi-equipment collaborative decision-making is achieved through task priority calculation and feedback optimization. The experimental results show that the proposed model achieves good control stability and scheduling optimization performance. Specifically, the overshoot is reduced to 2.5%, the state recognition accuracy reaches 98.7%, the raw coal output per unit time increases to 448.6 t/h, the energy consumption per ton of coal decreases to 6.7 kW·h, and the safety early-warning response time is shortened to 2.1 s. Overall, the proposed model outperforms the comparison methods. The results indicate that this method can provide technical support for multi-equipment collaborative control and unmanned operation scheduling in intelligent coal mining.