| 概率神经网络在汽轮发电机组故障诊断中的应用 |
| |
| 引用本文： | 刘斌,曹民.概率神经网络在汽轮发电机组故障诊断中的应用[J].教育技术导刊,2019,18(10):23-26. |
| |
| 作者姓名： | 刘斌 曹民 |
| |
| 作者单位： | 上海理工大学 光电信息与计算机工程学院，上海 200093 |
| |
| 摘 要： | 汽轮发电机组逐渐智能化，功能不断增强，但不确定性因素和不确定性信息仍然大量存在。针对该问题，用概率神经网络（PNN）诊断汽轮发电机组故障。PNN优点较多，机器学习算法简易、方便训练，相比于传统样本处理方法，PNN可训练样本并引入训练网络，更好地确保诊断结果正确率与可信度。MATLAB仿真结果表明，PNN在保证诊断结果准确的基础上，速度更快、分类性能大幅提高，诊断效率也提高至98%。
|
| 关 键 词： | 故障诊断 汽轮发电机组 神经网络 概率神经网络 |
| 收稿时间： | 2019-01-12 |
Application of Probabilistic Neural Network in Fault Diagnosis of Turbo-generator |
| |
| LIU Bin,CAO Min.Application of Probabilistic Neural Network in Fault Diagnosis of Turbo-generator[J].Introduction of Educational Technology,2019,18(10):23-26. |
| |
| Authors: | LIU Bin CAO Min |
| |
| Institution: | School of Optical and Computing Engineering， University of Shanghai for Science and Technology， Shanghai 200093， China |
| |
| Abstract: | Turbo-generator units are becoming increasingly intelligent and functional. But uncertainty and uncertain information exist. Focusing on these issues， the probabilistic neural network （PNN） is used to diagnose the faults of turbo-generator units. PNN has many benefits， and the machine learning algorithm is simple and convenient to train. Compared with the traditional sample processing method， PNN can train samples and introduce them to training network， so as to ensure the correct and reliable diagnostic results. The results of MATLAB simulation show that on the basis of ensuring the accuracy of diagnosis results， PNN can speed up the classification performance and improve the diagnosis efficiency to 98%. |
| |
| Keywords: | fault diagnosis turbo-generator sets neural network probabilistic neural network |
|
| 点击此处可从《教育技术导刊》浏览原始摘要信息 |
| 点击此处可从《教育技术导刊》下载免费的PDF全文 |
