基于HS-BP算法的尾矿库安全评价

Safety evaluation of mine tailings facilities based on HS-BP algorithm

为有效预防尾矿库事故的发生,针对尾矿库事故率具有随机波动性和非线性的特点,采用和声搜索算法(HSA)和BP神经网络建立尾矿库安全评价模型.该方法利用HS算法对BP神经网络权值进行优化,进而对尾矿库进行安全评价.通过对辽宁本溪南芬尾矿库安全现状进行拟合预测,结果表明:将HS算法和BP神经网络有机结合,能够克服传统BP网络易陷入极小值、收敛速度慢得缺陷,有效的刻画了尾矿库事故的随机波动特性,并且预测能力均优于其他评价算法,具有重要意义.

For the purpose of preventing mine railings accident effectively, aimed at the characteristics of stochastic fluctuation and nonlinear, a prediction model for mine railings accident rate is established by adopting harmony search algorithm and BP neural network. The method introduced harmony search algorithm to optimize the weight of BP neural network, and evaluate the safety of mine tailings. The applied prediction on mine tailings accident of Liaoning province Benxi Nanfen mine tailing shows that combining HS and BP can overcome flaws of easily getting into minimum and slow convergence, effectively describe the stochastic fluctuation of mine tailings accident, and capability and robustness are better than the other algorithms.