Application Research of PNN Algorithm in Coalfield Lithology Identification
DOI:
https://doi.org/10.63313/SD.9016Keywords:
Coalfield, Lithology Identification, PNNAbstract
This paper introduces the principle of the Probabilistic Neural Network (PNN) method and its algorithm training and learning process, and elaborates on the selection of lithology parameters for network identification and the establishment process of the lithology identification model. The study shows that the PNN method achieves good performance in practical application with short training and recognition time. Using artificial neural network to automatically interpret and analyze logging data can meet the timeliness of logging while drilling (LWD) and the geosteering requirements of rapid interpretation and processing.
References
[1] Chen Chao, Wei Mao’an. Lithology identification from logging data based on radial basis function neural network[J]. Journal of Chongqing University of Science and Technology (Natural Science Edition), 2008(03):8–9+12.
[2] Long Xihua, Zhang Bing, Gao Kai. Application of hypersphere support vector machine in logging lithology identification[J]. Mathematics in Practice and Theory, 2013, 43(18):110–115.
[3] Shi Zhijun, Yao Ningping, Ye Genfei. Construction technology and equipment for underground gas drainage boreholes in coal mines[J]. Coal Science and Technology, 2009, 37(07):1–4.
[4] Chen Gang, Yang Xue, Pan Baozhi, et al. Research status of borehole trajectory calculation and visualization[J]. World Geology, 2015, 34(03):830–841.
[5] Sun Xiaogang, Zhang Jianhua, Hou Guolian, et al. Research on condenser fault diagnosis based on probabilistic neural network[J]. Modern Electric Power, 2005(03):58–61.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 by author(s) and Erytis Publishing Limited
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
