基于IPSO-BP神经网络的富氧底吹铜熔炼炉喷枪寿命预测模型

Life Prediction Modelof Spray Gun in Oxygen-Enriched Bottom Blown Copper Smelting Furnace Based on IPSO-BP Neural Network

富氧底吹铜熔炼炉喷枪是整个熔炼炉中最重要的部件,并且造价高,易损坏,工作环境恶劣复杂,对其进行准确的寿命预测比较困难。提出了一种基于IPSO-BP神经网络的寿命预测模型,粒子群优化算法解决了BP神经网络容易陷入局部极小值和训练速度慢的问题,优化的粒子群算法优化了惯性权重和学习因子,进一步加快了训练速度和搜索速度,提高了BP神经网络跳出局部极小值的能力。以工作环境中容易对喷枪寿命造成影响的因素作为输入,喷枪寿命作为输出,通过实际生产采集的数据做验证,并与BP神经网络和PSO-BP神经网络预测模型作对比。结果表明,本文构建的寿命预测模型预测效果比BP神经网络和PSO-BP神经网络的预测更加准确,精度更高,该预测模型为富氧底吹铜熔炼的喷枪寿命预测提供了一种方法借鉴。

The lance of oxygen-enriched bottom-blown copper smelting furnace is the most important part in the whole smelting furnace,and its cost is high,it is easy to be damaged,and its working environment is harsh and complicated,so it is difficult to predict its life accurately.A life prediction model based on IPSO-BP neural network was put forward,in which,the particle swarm optimization algorithm solves the problems that BP neural network is easy to fall into local minimum and the training speed is slow,the optimized particle swarm optimization algorithm optimizes the inertia weight and learning factor,and further accelerates the training speed and search speed.Taking the factors that easily affect the service life of the spray gun in the working environment as input and the service life of the spray gun as output,it is verified by the data collected in actual production,and compared with BP neural network and PSO-BP neural network prediction model.The results show that the prediction effect of the life prediction model constructed in this paper is more accurate and precise than that of BP neural network and PSO-BP neural network.This prediction model provides a method for the life prediction of lance in oxygen-enriched bottom blowing copper smelting.