基于GA-BP神经网络薄煤层采煤机装煤性能预测

RESEARCH ON PERFORMANCE PREDICTION OF THIN SEAM SHEARER BY COMBINING GENETIC ALGORITHM WITH BP NEURAL NETWORK

提高装煤量是薄煤层采煤机设计中的重要内容。针对传统方法难以解决多因素影响采煤机装煤量的问题,提出了基于遗传算法(GA)与BP神经网络相结合的薄煤层采煤机装煤率预测方法。建立了薄煤层采煤机装煤量的数学模型,利用遗传算法对神经网络的权值和阀值进行优化,以仿真数据为训练和检测样本,用GA-BP算法训练网络,避免了单独使用BP神经网络训练容易陷入局部极小值以及单独利用仿真的办法工作量大,仿真时间长的问题。结果表明:利用提出的方法即加快了收敛速度也提高了训练精度,对薄煤层采煤机装煤性能的预测具有重要意义。

Increase the loading capacity of coal is an important part in the development of thin seam shearer. Optimization method based on the combination of genetic algorithm（ GA） and BP neural network was proposed for the problems that traditional method cant solve about the multi Factor impact shearer coal capacity. Established mathematical model of thin seam shearer,we use genetic algorithm to optimize the weighted values and threshold values of the BP neural network,using the simulation data for training and testing samples,and then use the BP algorithm to train the neural network,thus avoiding the local minimum values when the training is done with the BP neural network alone. The result shows that method not only speeding up the convergence speed but also improve the training accuracy,also obviously valuable for the performance prediction of thin seam shearer.