论文部分内容阅读
[目的]建立一种基于反向传播(back propagation,BP)神经网络的化工行业职业病危害综合定量评价方法。[方法]在全面分析化工项目职业卫生状况影响因素的基础上,建立包含11项指标的综合评价指标体系,并实现了指标的量化。收集本市23家石油化工类建设项目的相关资料,其中18组作为训练样本对神经网络进行训练,建立BP神经网络模型。[结果]5组作为测试样本,输入训练好的神经网络模型中进行测试,结果与专家评估结果相符,正确率100%。[结论]本研究所建立的多指标综合定量评价的神经网络模型可用于定量评价化工项目的职业病危害风险,为职业病危害风险评估法的研究提供了一种新的思路,为化工项目的分级管理和风险控制提供了有效的途径。
[Objective] The research aimed to establish a comprehensive quantitative evaluation method of occupational hazards in chemical industry based on back propagation (BP) neural network. [Method] Based on a comprehensive analysis of the influencing factors of occupational health status in chemical projects, a comprehensive evaluation index system containing 11 indicators was established and the indicators were quantified. Collecting relevant information of 23 petrochemical construction projects in this Municipality, 18 of them are used as training samples to train neural networks, and a BP neural network model is established. [Results] The 5 groups were used as the test samples and tested in the trained neural network model. The results were in good agreement with those of the experts, and the correct rate was 100%. [Conclusion] The neural network model of multi-index comprehensive quantitative evaluation established in this study can be used to quantitatively evaluate the risk of occupational hazards in chemical projects, providing a new idea for the study of risk assessment of occupational hazards, And risk control provides an effective way.