论文部分内容阅读
苯是基本化工原料之一,大量用于各种有机合成和有机溶剂。本文利用神经网络具有自学习、自组织、自适应能力特性,运用BP神经网络的方法和生产车间的统计数据,对现场空气中的苯蒸汽浓度进行模拟预测,得到工人的苯暴露浓度,运用MATLAB来实现各种BP神经网络的设计和训练,结果显示模拟数据与实测数据吻合很好。文章通过实例阐述了BP神经网络进行苯职业暴露风险预测的可行性,对于降低职工苯中毒事故的发生概率,减少工人的职业伤害具有十分重要的意义。
Benzene is one of the basic chemical raw materials, a large number for a variety of organic synthesis and organic solvents. In this paper, the self-learning, self-organizing and self-adaptive capability of neural network is used to predict the concentration of benzene vapor in the air by BP neural network and statistical data of production workshop. The benzene exposure concentration of workers is obtained. To achieve a variety of BP neural network design and training, the results show that the simulated data and measured data are in good agreement. The article expounds the feasibility of using BP neural network to forecast the occupational exposure to benzene by examples. It is of great significance to reduce the probability of benzene poisoning accident and reduce the occupational injuries of workers.