Dust concentration prediction model in thermal power plant using improved genetic algorithm

Thermal power plants are very important to a country's energy, and dust is a major threat to the safety of thermal power plants. Over the past decade, dust explosion events of various degrees have emerged one after another, leading to serious respiratory disease, lung disease and even death. Therefore, the prediction of dust situation in coal mining face is helpful to take preventive measures in advance to ensure safety and has great significance for reducing dust hazards and avoiding coal dust accidents. The establishment of BP neural network model for the prediction of dust concentration of thermal power plant is practiced. The existing models lack the fitting ability of the algorithm and the inaccuracy of prediction. To address the challenges in the existing models, an improved genetic algorithm is proposed to improve the objective function. The proposed model is based on the optimal weight and threshold value. The threshold value is obtained by the improved genetic algorithm. The neural network prediction model is used to calculate the dust concentration of fully mechanized mining face. The new prediction model is compared with the common model and the standard BP neural network algorithm. The results show that the fitting ability and prediction accuracy of the neural network algorithm of the improved genetic algorithm are significantly improved.

Automated summary

The prediction of dust concentration in coal mining face is crucial for taking preventive measures and ensuring safety. The establishment of a BP neural network model has been proven to significantly improve the fitting ability and prediction accuracy.