[1]宋家威①,郇宝乾①,秦涛①,等.基于IGWO-CatBoost模型的岩石爆破块度预测[J].爆破器材,2024,53(02):56-64.[doi:10.3969/j.issn.1001-8352.2024.02.009]
　SONG Jiawei,HUAN Baoqian,QIN Tao,et al.Prediction of Rock Blasting Fragmentation Based on IGWO-CatBoost Model[J].EXPLOSIVE MATERIALS,2024,53(02):56-64.[doi:10.3969/j.issn.1001-8352.2024.02.009]
点击复制

基于IGWO-CatBoost模型的岩石爆破块度预测()
分享到：

《爆破器材》[ISSN:1001-8352/CN:32-1163/TJ]

卷:
53
期数:
2024年02
页码:
56-64
栏目:
爆破技术
出版日期:
2024-04-03

文章信息/Info

Title:
Prediction of Rock Blasting Fragmentation Based on IGWO-CatBoost Model
文章编号:
5862
作者:
宋家威①; 郇宝乾①; 秦涛①; 张宇庭①; 王雪松②; 徐振洋①
①辽宁科技大学矿业工程学院（辽宁鞍山，114051）
②沈阳工业大学建筑与土木学院（辽宁沈阳，110870）
Author(s):
SONG Jiawei①;  HUAN Baoqian①;  QIN Tao①;  ZHANG Yuting①;  WANG Xuesong②;  XU Zhenyang①
①School of Mining Engineering, University of Science and Technology Liaoning (Liaoning Anshan, 114051)
②School of Architecture and Civil Engineering, Shenyang University of Technology (Liaoning Shenyang, 110870)
关键词:
改进灰狼算法; IGWO-CatBoost模型; 随机森林; 块度预测
Keywords:
improved grey wolf algorithm;  IGWO-CatBoost model;  random forest;  block prediction
分类号:
TD235；TU751.9
DOI:
10.3969/j.issn.1001-8352.2024.02.009
文献标志码:
A
摘要:
针对无法准确预测矿山岩石爆破后块度大小的问题，提出一种基于改进灰狼算法（IGWO）优化的CatBoost块度预测模型。采用一种新的非线性收敛因子，引入动态权重策略，改进已有的灰狼算法（GWO），通过4个测试函数和5种优化算法验证了IGWO的寻优能力。对公开数据库和现场采集的32组数据进行预测分析。首先，采用随机森林算法进行特征重要性筛选，利用IGWO对CatBoost进行参数寻优，建立IGWOCatBoost爆破块度预测模型；然后，将预测结果与在相同条件下建立的CatBoost、XGBoost、LightGBM模型进行对比分析。经过IGWO调参，CatBoost模型的预测准确度得到有效提高，IGWO-CatBoost模型的预测准确度均优于其他3种预测模型。对比结果表明，IGWO-CatBoost模型具有很好的预测能力和适应性。
Abstract:
Aiming at the problem of inaccurate prediction of block size after rock blasting in mines, a CatBoost block size prediction model based on improved grey wolf algorithm (IGWO) optimization was proposed. A new nonlinear convergence factor and a dynamic weight strategy were introduced to improve the existing grey wolf algorithm (GWO). The optimization ability of IGWO was verified by four test functions and five optimization algorithms. Thirty-two sets of data collected from the public database and the field were predicted and analyzed. Firstly, the random forest algorithm was used to screen the feature importance, and IGWO was used to optimize the parameters of CatBoost to establish the IGWO-CatBoost prediction model for blasting fragmentation. Then, the prediction results were compared and analyzed with the CatBoost, XGBoost and LightGBM models established under the same conditions. The prediction accuracy of the CatBoost model is effectively improved by IGWO, and the prediction accuracy of IGWO-CatBoost model is better than the other three prediction models. The comparison results show that IGWO-CatBoost model has good prediction ability and adaptability.

参考文献/References:

［1］FARAMARZI F, MANSOURI H, EBRAHIMI FARSANGI M A.A rock engineering systems based model to predict rock fragmentation by blasting ［J］. International Journal of Rock Mechanics and Mining Sciences, 2013, 60(8): 82-94.
［2］HASANIPANAH M, ARMAGHANI D J, MONJEZI M, et al. Risk assessment and prediction of rock fragmentation produced by blasting operation: a rock engineering system ［J］. Environmental Earth Sciences, 2016, 75(9): 808.
［3］SANCHIDRIAN J A, SEGARRA P, LOPEZ L M. Energy components in rock blasting ［J］. International Journal of Rock Mechanics and Mining Sciences, 2007, 44(1): 130-147.
［4］周先平, 李彦坡, 吴新霞, 等. 岩体爆破块度控制技术新进展［J］. 水利水电技术, 2018, 49(增刊1): 7-13.
ZHOU X P, LI Y P, WU X X, et al. New advance of control technique for blasting fragment-size of rock mass ［J］. Water Resources and Hydropower Engineering, 2018, 49(Suppl.1): 7-13.
［5］王仁超, 朱品光. 基于随机森林回归方法的爆破块度预测模型研究［J］. 水力发电学报, 2020, 39(1): 89-101.
WANG R C, ZHU P G. Study on blasting fragmentation prediction model based on random forest regression method ［J］. Journal of Hydroelectric Engineering, 2020, 39(1): 89-101.
［6］顾清华, 江松, 李学现, 等. 人工智能背景下采矿系统工程发展现状与展望［J］. 金属矿山, 2022(5): 10-25.
GU Q H, JIANG S, LI X X, et al. Development status and prospect of mining system engineering under the background of artificial intelligence ［J］. Metal Mine, 2022(5): 10-25.
［7］史秀志, 郭霆, 尚雪义, 等. 基于PCA-BP神经网络的岩石爆破平均粒径预测［J］. 爆破, 2016, 33(2): 55-61.
SHI X Z, GUO T, SHANG X Y, et al. Prediction of mean particle size of rock blast based on combination of PCA and BP neural networks ［J］. Blasting, 2016, 33(2): 55-61.
［8］KULATILAKE P H S W, QIONG W, HUDAVERDI T, et al. Mean particle size prediction in rock blast fragmentation using neural networks ［J］. Engineering Geology, 2010, 114(3/4): 298-311.
［9］唐跃, 徐曲, 柯波, 等. 基于交叉验证的矿岩爆破块度SVM模型优选研究［J］. 爆破, 2018, 35(3): 74-79.
TANG Y, XU Q, KE B, et al. Study on optimization of SVM model of rock blasting fragmentation based on cross-validation ［J］. Blasting, 2018, 35(3):74-79.
［10］史秀志, 王洋, 黄丹, 等. 基于LS-SVR岩石爆破块度预测［J］. 爆破, 2016, 33(3): 36-40.
SHI X Z, WANG Y, HUANG D, et al. Prediction of rock blasting fragmentation based on LS-SVR ［J］. Blasting, 2016, 33(3): 36-40.
［11］刘阳, 谭凯旋, 郭钦鹏, 等. 运用随机森林和GA-BP神经网络预测岩石爆破块度［J］. 矿业研究与开发, 2021, 41(1): 135-140.
LIU Y, TAN K X, GUO Q P, et al. Prediction for blasting fragmentation of rocks using random forest and GA-BP neural network ［J］.Mining Research and Development, 2021, 41(1): 135-140.
［12］柳小波, 袁鹏喆, 张兴帆. 基于RBF神经网络的露天矿爆破效果预测研究［J］. 中国矿业, 2020, 29(1): 81-84.
LIU X B, YUAN P Z, ZHANG X F. Study on blasting effect prediction of open-pit mine based on RBF neural network ［J］.China Mining Magazine, 2020, 29(1): 81-84.
［13］叶海旺, 胡俊杰, 雷涛, 等. LOO-XGboost模型预测岩石爆破块度［J］. 爆破, 2022, 39(1): 16-21.
YE H W, HU J J, LEI T, et al. Fragmentation prediction of rock blasting by LOO-XGboost model ［J］. Blasting, 2022, 39(1): 16-21.
［14］关富僳, 吴发名, 罗志, 等. 基于灰色关联分析及GA-BP模型的岩体爆破块度预测［J］. 爆破器材, 2021, 50(4): 40-47, 53.
GUAN F S, WU F M, LUO Z, et al. Prediction of rock blasting fragmentation based on grey correlation analysis and GABP model ［J］. Explosive Materials, 2021, 50(4): 40-47, 53.
［15］刘翔, 谢涛, 王训洪, 等. 基于改进随机森林算法的岩石爆破块度预测［J］. 矿业研究与开发, 2022, 42(7): 25-29.
LIU X, XIE T, WANG X H, et al. Prediction for blasting fragmentation of rocks based on improved random forest regression method ［J］. Mining Research and Development, 2022, 42(7): 25-29.
［16］PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: unbiased boosting with categorical features ［C］//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montreal, Canada, 2018.
［17］MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer ［J］. Advances in Engineering Software, 2014, 69: 46-61.
［18］赵超, 王延峰, 林立. 基于改进灰狼算法优化核极限学习机的锂电池动力电池荷电状态估计［J］. 信息与控制, 2021, 50(6): 731-739.
ZHAO C, WANG Y F, LIN L. State of charge estimation for lithium battery based on kernel extreme learning machine optimized by improved grey wolf algorithm ［J］. Information and Control, 2021, 50(6): 731-739.
［19］RODR-GUEZ L, CASTILLO O, SORIA J, et al. A fuzzy hierarchical operator in the grey wolf optimizer algorithm［J］. Applied Soft Computing, 2017, 57: 315-328.
［20］郭振洲, 刘然, 拱长青, 等. 基于灰狼算法的改进研究［J］. 计算机应用研究, 2017, 34(12): 3603-3606, 3610.
GUO Z Z, LIU R, GONG C Q, et al. Study on improvement of gray wolf algorithm ［J］. Application Research of Computers, 2017, 34(12): 3603-3606, 3610.
［21］张阳, 周溪召. 求解全局优化问题的改进灰狼算法［J］. 上海理工大学学报, 2021, 43(1): 73-82.
ZHANG Y, ZHOU X Z. Modified grey wolf optimization algorithm for global optimization problems ［J］. Journal of University of Shanghai for Science and Technology, 2021, 43(1): 73-82.
［22］HUDAVERDI T, KULATILAKE P H S W, KUZU C. Prediction of blast fragmentation using multivariate analysis procedures ［J］. International Journal for Numerical and Analytical Methods in Geomechanics, 2011, 35(12): 1318-1333.
［23］赵蒙生, 周敏, 代永新, 等. 灰色关联度对边坡稳定性的预测分析［J］. 金属矿山, 2012(10): 130-133.
ZHAO M S, ZHOU M, DAI Y X, et al. Prediction and analysis of slope stability by grey correlation ［J］. Metal Mine, 2012(10): 130-133.

备注/Memo

备注/Memo:
收稿日期：2023-07-13
基金项目：辽宁兴辽英才项目（XLYC2203173）
第一作者：宋家威（1998—），男，硕士研究生，主要从事工程爆破方面的研究。E-mail：1079031610@qq.com
通信作者：徐振洋（1982—），男，教授，主要从事工程爆破理论与技术的研究。E-mail：xuzhenyang@ustl.edu.cn
更新日期/Last Update: 2024-04-02