当前位置: X-MOL 学术Front. Neurorobotics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A new hydrogen sensor fault diagnosis method based on transfer learning with LeNet-5
Frontiers in Neurorobotics ( IF 3.1 ) Pub Date : 2021-04-16 , DOI: 10.3389/fnbot.2021.664135
Yongyi Sun , Shuxia Liu , Tingting Zhao , Zhihui Zou , Bin Shen , Ying Yu , Shuang Zhang , Hongquan Zhang

The fault safety monitoring of hydrogen sensors is very important for their practical application. The precondition of traditional machine learning (ML) methods for sensor fault diagnosis is that enough fault data with the same distribution and feature space under the same working environment must exist. However, widely used fault diagnosis methods are not suitable for real working environments because they are easily interfered by environmental conditions such as temperature, humidity, shock, and vibration. Under the influence of such complex conditions, the acquisition of sensor fault data is limited. In order to improve fault diagnosis accuracy under complex environmental conditions, a novel method of transfer learning (TL) with LeNet-5 is proposed in this paper. Firstly, LeNet-5 is applied to learn the features of the data-rich datasets of gas sensor fault in a normal environment and to adjust the parameters accordingly. The parameters of the LeNet-5 are transferred from the task in the normal environment to a task in a complex environment by using the TL method. Then, the migrated LeNet-5 is used for the fault diagnosis of gas sensors with a small amount of fault data in a complex environment. Finally, a prototype hydrogen sensor array is designed and implemented for experimental verification. The experimental results show that the method adopted presents an excellent solution for the fault diagnosis of a hydrogen sensor using a small quantity of fault data obtained under complex environmental conditions.

中文翻译:

基于LeNet-5迁移学习的氢传感器故障诊断新方法

氢传感器的故障安全监控对于其实际应用非常重要。传统的机器学习(ML)方法用于传感器故障诊断的前提是,必须在相同的工作环境下存在足够的具有相同分布和特征空间的故障数据。但是,由于故障诊断方法容易受到温度,湿度,冲击和振动等环境条件的干扰,因此不适用于实际的工作环境。在这种复杂条件的影响下,传感器故障数据的采集受到限制。为了提高复杂环境下故障诊断的准确性,提出了一种新的基于LeNet-5的迁移学习方法。首先,LeNet-5用于了解正常环境中气体传感器故障的数据丰富的数据集的特征,并相应地调整参数。LeNet-5的参数通过使用TL方法从正常环境中的任务转移到复杂环境中的任务。然后,将迁移的LeNet-5用于在复杂环境中带有少量故障数据的气体传感器的故障诊断。最后,设计并实现了原型氢传感器阵列,用于实验验证。实验结果表明,所采用的方法是利用复杂环境条件下获得的少量故障数据为氢气传感器故障诊断提供了一个极好的解决方案。LeNet-5的参数通过使用TL方法从正常环境中的任务转移到复杂环境中的任务。然后,将迁移的LeNet-5用于在复杂环境中带有少量故障数据的气体传感器的故障诊断。最后,设计并实现了原型氢传感器阵列,用于实验验证。实验结果表明,所采用的方法是利用复杂环境条件下获得的少量故障数据为氢气传感器故障诊断提供了一个极好的解决方案。LeNet-5的参数通过使用TL方法从正常环境中的任务转移到复杂环境中的任务。然后,将迁移的LeNet-5用于在复杂环境中带有少量故障数据的气体传感器的故障诊断。最后,设计并实现了原型氢传感器阵列,用于实验验证。实验结果表明,所采用的方法是利用复杂环境条件下获得的少量故障数据为氢气传感器故障诊断提供了一个极好的解决方案。设计并实现了原型氢传感器阵列,用于实验验证。实验结果表明,所采用的方法是利用复杂环境条件下获得的少量故障数据为氢气传感器故障诊断提供了一个极好的解决方案。设计并实现了原型氢传感器阵列,用于实验验证。实验结果表明,所采用的方法是利用复杂环境条件下获得的少量故障数据为氢气传感器故障诊断提供了一个极好的解决方案。
更新日期:2021-04-16
down
wechat
bug