基于神经网络的高寒地区CF4和SF6/CF4检测
Neural Network-based CF4 and SF6/CF4 Detection in High Altitude and Extreme Cold Regions
马汝括 1董杰 2王雅湉 2伊国鑫 2丁祥浩 2马乐2
作者信息
- 1. 国网青海省电力公司,青海西宁 810008
- 2. 国网青海省电力公司超高压公司,青海西宁 810000
- 折叠
摘要
高寒地区须携带多台仪器以满足3种不同量级SF6 气体中CF4 气体浓度的检测需求,现场运维效率低且仪器购置成本高.为此,首先设计了一种基于热释电检测技术的SF6 气体中CF4 气体浓度检测仪器,可自动选择不同的放大电阻以实现多量程切换.然后提出了BP和PSO-BP 2 种神经网络温度-压力协同补偿模型,并通过搭建高效模拟实验平台为模型预测提供数据支撑,预测结果表明,PSO-BP神经网络优于BP神经网络.最后将PSO-BP神经网络温度-压力协同补偿模型内置于多量程检测仪器CF4 气体浓度检测仪器.模拟实验结果表明,该检测仪器在不同温度和压力下,小量程和大量程检测误差和重复性分别不超过±2%和1.6%,混合比量程下误差和重复性分别不超过±0.5%和0.2%,对高寒地区电网运维检修具有重要作用.
Abstract
In extreme cold regions,the need to carry multiple instruments to meet the demands for detecting varying concentration levels of CF4 gas within SF6 gas leads to inefficient field operations and high costs for instrument acquisition.To overcome this,an SF6 gas CF4 concentration detector utilizing pyroelectric detection technology was initially developed,capable of automatically switching among different ranges by selecting appropriate amplification resistances.Subsequently,two neural network models for temperature-pressure collaborative compensation,BP and PSO-BP,were introduced.Data for model predictions were supported by an effective simulated experimental platform,with results indicating the PSO-BP neural network's superiority over the BP network.The PSO-BP neural network's temperature-pressure collaborative compensation model was then embedded within the multi-range detection instrument for CF4 gas concentration.Simulation experiments demonstrated that the instrument maintains a detection error and repeatability within±2%and 1.6%across small and large ranges,and within±0.5%and 0.2%for mixed ratio ranges,respectively,under varying temperatures and pressures.This technological advancement significantly enhances maintenance operations within the power grids of cold regions.
关键词
CF4/气体浓度检测/热释电检测技术/高寒地区/三量程/PSO-BP神经网络模型/温度-压力协同补偿Key words
CF4 gas concentration detection/pyroelectric detection technology/high altitude and extreme cold regions/three-range/PSO-BP neural network model/collaborative temperature-pressure compensation引用本文复制引用
基金项目
国家电网青海省电力公司科技项目(52282121N004)
出版年
2024
国家科技期刊平台
NSTL
万方数据