Optimization of Process Control Parameters for Fully Mechanized Mining Face Based on ANN and GA

• Published in: Computational intelligence and neuroscience 2021, Vol.2021 (1), p.5557831-5557831
• Main Authors: Zhao, Hongze, Xu, Zhihai, Li, Qi, Pan, Tao
• Format: Article
• Language: English
• Subjects: Algorithms; Analysis; Artificial neural networks; Automation; Chain conveyors; Chains; Coal mines; Coal mining; Conveying machinery; Cooperation; Cost function; Efficiency; Entropy (Information theory); Expected values; Friction stir welding; Genetic algorithms; Hydraulics; Industrial production; Learning theory; Mean square errors; Mineral industry; Mining industry; Neural networks; Optimization; Process controls; Process parameters; Production capacity
• ISSN: 1687-5265; 1687-5273
• DOI: 10.1155/2021/5557831

In the traditional optimization mathod, the process control parameters for fully mechanized mining face are determined by experts or technicians based on their own experience, which is lack of scientific basis, and need long production adjustment cycle. It is cause large loss, and not conducive to improving mine production efficiency. In order to solve this problem, the study proposes a process control parameter optimization method based on a mixed strategy of artificial neural network and genetic algorithm and uses a cross-entropy cost function to optimize an artificial neural network, which improves the learning speed and fitting accuracy of the neural network. Using the historical production data of a fully mechanized coal mining face, taking the pulling speed of the shearer, hydraulic support moving speed, chain speed of scraper conveyor, chain speed of stage loader, emulsion pump outlet pressure, and spray pump outlet pressure as the optimization objects and taking the value range of each process control parameter as a constraint condition to establish a mixed strategy optimization model of process control parameters for a fully mechanized mining face, each process control parameter is optimized with the output of coal per minute as the optimization goal. The results show that the method has high accuracy and short optimization process time and can effectively improve the production efficiency of the working face.