欢迎访问现代地质!

现代地质 ›› 2023, Vol. 37 ›› Issue (04): 963-971.DOI: 10.19657/j.geoscience.1000-8527.2021.063

• 水资源与环境地质 • 上一篇    下一篇

基于自适应BPNN-GIS耦合的地下水源热泵适宜性分区研究

闫佰忠1,2(), 孙剑1,2,3, 陈佳琦1,2, 孙丰博1,2, 李晓萌1,2, 付庆杰4   

  1. 1.河北地质大学水资源与环境学院,河北省高校生态环境地质应用技术研发中心,河北 石家庄 050031
    2.河北省水资源可持续利用与开发重点实验室,河北 石家庄 050031
    3.中化地质矿山总局浙江地质勘查院,浙江 杭州 311201
    4.山东省鲁南地质工程勘察院(山东省地勘局第二地质大队),山东省地热清洁能源勘查开发工程研究中心,山东 济宁 272100
  • 收稿日期:2020-11-16 修回日期:2023-01-25 出版日期:2023-08-10 发布日期:2023-09-02
  • 作者简介:闫佰忠, 男, 博士, 副教授, 硕士生导师, 1988年出生, 地下水科学与工程专业,主要从事水文地质、地热资源等方面的研究。Email:jluybz@126.com
  • 基金资助:
    国家自然科学基金项目(42002251);河北省自然科学基金项目(D2020403022);河北省自然科学基金项目(D2018403040);河北省高等学校科学技术研究项目(ZD2019082);山东省鲁南地质工程勘察院开发基金课题(LNY2020-Y12);山东省自然科学青年基金项目(ZR2020QD122)

Suitability Zoning for Groundwater Source Heat Pump Based on Adaptive BPNN-GIS Method

YAN Baizhong1,2(), SUN Jian1,2,3, CHEN Jiaqi1,2, SUN Fengbo1,2, LI Xiaomeng1,2, FU Qingjie4   

  1. 1. School of Water Resources & Environment, Hebei Center for Ecological and Environmental Geology Research, Hebei GEO University, Shijiazhuang, Hebei 050031, China
    2. Hebei Key Laboratory of Geological Resources and Environment Monitoring and Protection, Shijiazhuang, Hebei 050031, China
    3. Zhejiang Geological Prospecting Institute of CCGMB, Hangzhou, Zhejiang 311201, China
    4. Shandong Provincial Lunan Geology and Exploration Institute (No.2 Geological Brigade of the Shandong BGMR), Shandong Provincial Engineering Research Center of Geothermal Energy Exploration and Development, Jining, Shandong 272100, China
  • Received:2020-11-16 Revised:2023-01-25 Online:2023-08-10 Published:2023-09-02

摘要:

基于石家庄市的地质条件构建了地下水源热泵适宜性评价指标体系。利用自适应Back Propagation (BP)神经网络与(GIS)耦合的方法进行地下水源热泵适宜性分区评价,同时与模糊层次分析法评价结果进行对比。结果表明,两者适宜性分区除了面积略有差异,适宜性分布情况基本相同,BP神经网络与模糊层次分析法适宜区评价结果面积占比仅相差3.80%,较适宜区面积占比相差8.06%,不适宜区面积占比相差11.86%。采用自适应BPNN-GIS的评价方法解决了传统人工手动调参以及主观赋权的弊端,同时评价效率更高、精度更高,更能反映研究区单点适宜性程度。

关键词: 地下水源热泵, BP神经网络, 适宜性分区, 石家庄

Abstract:

Based on the geological and hydrogeological conditions of Shijiazhuang City, the suitability evaluation index system of groundwater source heat pump is established. The adaptive BP neural network and GIS coupling method were used to evaluate the suitability of groundwater source heat pump, and the results were compared with the fuzzy analytic hierarchy process. The results show that in addition to the difference in the area, the suitability distribution of the two methods is basically the same. The proportion difference of the suitable area between the BP neural network and fuzzy analytic hierarchy process is only 3.80%, 8.06%, and 11.86%, respectively. The self-adaptive BPNN-GIS evaluation method could resolve the drawbacks of traditional manual adjustment and subjective weighting. Meanwhile, both the evaluation efficiency and accuracy are higher, which can reflect the degree of single point suitability in the study area.

Key words: groundwater source heat pump, BP neural network, suitability area, Shijiazhuang

中图分类号: