Spectroscopy and Spectral Analysis, Volume. 41, Issue 7, 2288(2021)
Classification of Coal Mine Water Sources by Improved BP Neural Network Algorithm
Figures & Tables(10)
Fig. 1. Flow chart of mine water source prediction and classification model
Fig. 3. Original spectrogram and preprocessed image
(a): SG; (b): MSC; (c): Original preprocessed
Fig. 6. Comparison between the real value and the predicted value of each prediction model under nine different pretreatment methods
Fig. 7. Absolute error diagram of predicted value and true value of each model
Table 1. Training error of neuron number in different hidden layers
View tableView in ArticleTable 1. Training error of neuron number in different hidden layers
隐节点数 5 6 7 8 9 10 11 12 13 14 15 训练误差 1.914 1.338 4.066 5.230 1.036 0.039 0.038 0.039 0.037 0.039 0.039
Table 2. Comparison of evaluation indexes of each prediction model under different pretreatment methods
View tableView in ArticleTable 2. Comparison of evaluation indexes of each prediction model under different pretreatment methods
预处理方式 评价指标 BP
模型PSO-BP
模型IPSO-BP
模型R2 0.984 5 0.999 8 0.999 9 SG预处理 MRE 0.073 9 0.001 7 0.000 1 RMSE 0.072 5 0.000 8 0.000 1 R2 0.996 2 0.983 5 0.999 0 MSC预处理 MRE 0.028 8 0.019 7 0.002 3 RMSE 0.023 5 0.066 9 0.003 9 R2 0.995 5 0.998 8 0.998 8 Original MRE 0.044 1 0.009 1 0.004 2 RMSE 0.024 9 0.005 4 0.004 9
Tools
Get Citation
Copy Citation Text
Peng-cheng YAN, Song-hang SHANG, Chao-yin ZHANG, Xiao-fei ZHANG. Classification of Coal Mine Water Sources by Improved BP Neural Network Algorithm[J]. Spectroscopy and Spectral Analysis, 2021, 41(7): 2288
Paper Information
Category: Research Articles
Received: Dec. 30, 2020
Accepted: --
Published Online: Sep. 8, 2021
The Author Email: YAN Peng-cheng (pcyan1988@126.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20