文章摘要
姜兰兰,鲁海峰.基于PCA-WOA-ELM的矿井突水水源识别模型研究[J].唐山学院学报,2025,38(6):44-52
基于PCA-WOA-ELM的矿井突水水源识别模型研究
Research on a Mine Water Inrush Source Identification Model Based on PCA-WOA-ELM
投稿时间:2024-10-14  
DOI:10.16160/j.cnki.tsxyxb.2025.06.008
中文关键词: 矿井突水水源  主成分分析  鲸鱼优化算法  极限学习机
英文关键词: mine water inrush source  principal component analysis  whale optimization algorithm  extreme learning machine
基金项目:国家重点研发计划项目(2022YFF1303302)
作者单位
姜兰兰 安徽理工大学 地球与环境学院, 安徽 淮南 232000 
鲁海峰 安徽理工大学 地球与环境学院, 安徽 淮南 232000 
摘要点击次数: 452
全文下载次数: 231
中文摘要:
      准确快速识别突水水源对于煤矿水害防治尤为重要,极限学习机(ELM)被广泛应用于突水水源识别领域。为了弥补ELM的不足、提高识别精度与效率,文章提出了一种主成分分析(PCA)、鲸鱼优化算法(WOA)与ELM相融合的突水水源识别模型(PCA-WOA-ELM模型)。以新集二矿为例,选择影响安全回采的推覆体寒灰水、太灰水以及奥灰水作为突水水源,以水样中六大常规离子作为识别指标,首先采用PCA降低数据维度,其次基于Matlab运用WOA寻优ELM参数对测试样本进行识别,最后将PCA-WOA-ELM模型识别结果与其他识别模型进行对比。结果表明,该模型能够提取数据的主要特征,弥补了ELM初始参数随机选择的不足,识别效率与精度优于PCA-ELM,WOA-ELM,PCA-PSO-ELM以及PCA-GA-ELM这4种模型。
英文摘要:
      Accurate and rapid identification of water inrush sources is critical for the prevention and control of water inrush in coal mines, and extreme learning machine (ELM) is widely used in this field. In order to make up for the shortcomings of ELM and improve the accuracy and efficiency of recognition, a water source identification model (PCA-WOA-ELM model) is proposed, which combines principal component analysis(PCA), whale optimization algorithm (WOA) and ELM. With Xinji No. 2 Mine as an example, three types of water inrush sources of nappe Cambrian Limestone Water, Taiyuan Limestone Water, and Ordovician Limestone Water that affect the safe mining are selected, and the six conventional ions in the water sample are used as identification indicators. PCA is first used to reduce dimensionality; Then WOA is employed via Matlab to optimize ELM parameters for testing sample recognition. Finally, results from the PCA-WOA-ELM model are compared with other models. The results show that the model can extract the main features of the data,make up for the shortcomings of random selection of initial parameters of ELM, and the recognition efficiency and accuracy are better than those of PCA-ELM, WOA-ELM, PCA-PSO-ELM and PCA-GA-ELM.
查看全文   查看/发表评论  下载PDF阅读器
关闭
分享按钮

漂浮通知

关闭