Prediction of occupational health damage caused by coal mine noise based on t-SSA-BP
In order to accurately predict the occupational health damage of workers exposed to noise in coal mines,the influencing factors were selected based on the quantile plot method.According to the noise occupational health damage assessment method,the adaptive t distribution variation operator and SSA were used as parameter optimization algorithms to establish the t-SSA-BP coal mine noise occupational health damage prediction model,and the benchmark function was used to test the optimization performance of the algorithm.10 coal mines in northern Shaanxi were taken as the research objects,and the prediction model was verified by field investigation,theoretical analysis and Matlab simulation.The results show that the noise exposure intensity,individual age,length of service and noise exposure post are the influencing factors of noise health damage in coal mines.The overall accuracy of t-SSA is 66.0％,which is higher than that of SSA in four benchmark functions.The order of accuracy of the five prediction models is:t-SSA-BP＞SSA-BP＞PSO-BP＞CFA-PSO-RBF＞PSO-GRNN.Compared with SSA-BP,the MAE and MAPE of t-SSA-BP prediction model decreases by 68.1％and 66.7％respectively,and the R2 reaches 0.999.The prediction accuracy and convergence rate are significantly improved.
adaptive t distribution mutation operatorsparrow search algorithm(SSA)coal mine noiseprediction of health damageBP neural network
万方数据
维普
