摘要
本文基于Jordan神经网络构造了多因素输入和精矿品位动态时间序列反馈的浮选生产指标预测模型,运用BP算法和TD法相结合的网络学习算法,应用结果表明,该模型预测命中率和预测精度较高、误差小,且具有较强的抗干扰能力和稳定性,具有一定的实用价值,应用是成功的。
This article establishes a prediction model of ore dressing date based on Jordan neural network including input of influence factors and dynamic time sequence feedback of concentrate grade,by combining BP algorithm with the temporal difference methods. The results demonstrate that predictive precision is high, error is little and the stability is high. It is of practical use and the application is satisfied.
出处
《科技广场》
2009年第11期36-38,共3页
Science Mosaic
关键词
神经网络
预测模型
选矿指标
BP算法
TD法
Neural Network
Prediction Model
Flotation Production Targets
BP Algorithm
TD Method
