摘要
电子电器在使用过程中,因元器件失效等导致的触电伤害在总伤害类型中占比高达59.6%。为了分析其触电伤害模式,评估风险程度,将熵权法和反向传播(back propagation,BP)神经网络法相结合,从电能意外释放角度分析触电风险的传递路径,构建了电子电器触电风险评估模型。通过对168组电子电器触电风险样本数据的训练及仿真模拟,结果表明:本文模型在低、中、高风险水平评估过程中的相对误差百分比分别为2.80%、4.97%、3.06%,准确率较高,评估结果与产品的实际风险程度具有良好的符合性。通过随机取样评估结果的对比分析,该模型评估的精准度比传统熵权法提高了。
The proportion of electric shocks is as high as 59.6%because of component failure during use.In order to analyze the electric shock injury mode and assess the risk degree,the transmission path of shock risk was analyzed from the perspective of accidental release of electric energy.Combined with entropy weight method and back propagation(BP)neural network method,an electric appliances electric shock risk assessment model was built.168 groups of sample data was used for training and simulation.The results prove that the model has a relative error percent of 2.80%,4.97%,and 3.06% for low-risk,medium-risk,and high-risk evaluations,respectively.The assessment accuracy is high,and the evaluation results are close to the actual risk of the product.Through the comparative analysis of random sampling evaluation results,the accuracy of this model evaluation is improved compared with the traditional entropy weight method.
作者
黄国忠
谢佳颖
谢志利
王长林
HUANG Guo-zhong;XIE Jia-ying;XIE Zhi-li;WANG Chang-lin(College of Civil and Resource Engineering,University of Science and Technology Beijing,Beijing 100083,China;Defective Product Administration Center of State Market Administration Regulation,Beijing 100101,China)
出处
《科学技术与工程》
北大核心
2021年第8期3414-3419,共6页
Science Technology and Engineering
关键词
BP神经网络
电子电器
触电风险
熵权法
BP neural network
electric appliances
electric shock risk
entropy weight method