基于IWOA-LSSVM的礦用差壓式流量計(jì)誤差補(bǔ)償方法

打開文本圖片集

中圖分類號(hào)：TD712 文獻(xiàn)標(biāo)志碼：A 文章編號(hào)：1672-9315（2025）04-0726-09DOI：10. 13800/j. cnki. xakjdxxb. 2025.0409

Error compensation method of mine differential pressure flowmeterbasedonIWOA-LSSVM

WANG Weifeng1，2， LI Yu3 ， TIAN Feng3，LI Zhuoyang1，BAI Yu3，LI Hanbing4

（1.CollegeofSafetyScienceand Engineering，Xi’an UniversityofScienceand Technology，Xi’an71Oo54，China; 2.Key Laboratory of Intelligent Safety Technology and Equipment for Coal Mines， Ministry of Emergency Management， Xi′ anUniversity of Science and Technology，Xi'an71oo54， China; 3.CollegeofommunicationandInfomationTehnologyXi’anUniesityofienceandTechnlogyXi'anhina; 4.College ofElectrical andControlEngineering，Xi'an UniversityofScienceand Technology，Xi’an710o54，China）

Abstract： Aiming at the problem that the diferential pressure flowmeter for mining was easily interfered by factors such as temperature，humidity and pressure in the underground gas drainage pipeline， resulting in relatively large measurement errors，an error compensation method based on the improved whale optimization algorithm（IWOA）optimizing the least squares support vector machine（LSSVM） was proposed.The whale optimization algorithm（ WOA） was used to optimize the kernel function parameters and penalty factor of the LSSVM model， tent chaotic mapping，random learning method and adaptive weight were introduced and the IWOA-LSSVM error compensation model was constructed; A simulated experimental platform was built to simulate the environment of the drainage pipeline，Matlab was used to simulate the test data， the error compensation result of BP neural network，PSO-LSSVM algorithm and GWO-LSSVM algorithm were compared. The results show that： Compared with the original measurement value，the BP Neural Network reduces the mean percentage error of the diferential pressure flowmeter from 7.40% to 1.13% ，the PSO-LSSVM algorithm further reduces this error to 1.05% ，the GWO-LSSVM algorithm reduces the mean percentage error to 0.47% ， while the IWOA-LSSVM algorithm further reduces the mean percentage error to 0.23% . The IWOA-LSSVM algorithm effectively eliminates the influence of environmental factors on the output results of the flowmeter and improves the reliability and detection accuracy of the differential pressure flowmeter for mining.

Key words： diferential pressure flowmeter; error compensation; whale optimization algorithm; least squares support vector machine; gas extraction

0 引言

為防止瓦斯超限以及瓦斯爆炸事故，保障井下人員生命安全和煤礦生產(chǎn)安全，礦井瓦斯高效抽采是一種經(jīng)濟(jì)有效的方法[1-4]。（剩余14288字）