[1]刘小明①,唐北昌②,李荣华①,等.基于粒子群优化相关向量机的爆破飞石距离预测模型[J].爆破器材,2024,53(06):58-64.[doi:10.3969/j.issn.1001-8352.2024.06.009]
　LIU Xiaoming,TANG Beichang,LI Ronghua,et al.Prediction Model of Blasting Flying Rock Distances Based on Particle Swarm Optimization Relevance Vector Machine[J].EXPLOSIVE MATERIALS,2024,53(06):58-64.[doi:10.3969/j.issn.1001-8352.2024.06.009]
点击复制

基于粒子群优化相关向量机的爆破飞石距离预测模型()
分享到：

《爆破器材》[ISSN:1001-8352/CN:32-1163/TJ]

卷:
53
期数:
2024年06
页码:
58-64
栏目:
爆破技术
出版日期:
2024-12-06

文章信息/Info

Title:
Prediction Model of Blasting Flying Rock Distances Based on Particle Swarm Optimization Relevance Vector Machine
文章编号:
5910
作者:
刘小明①; 唐北昌②; 李荣华①; 陈德斌①; 梁培钊①
①广西壮族自治区地质环境监测站(广西梧州,543000)
②桂林理工大学土木与建筑工程学院(广西桂林,541004)
Author(s):
LIU Xiaoming①;  TANG Beichang②;  LI Ronghua①;  CHEN Debin①;  LIANG Peizhao①
① Geological Environment Monitoring Station of Guangxi Zhuang Autonomous Region (Guangxi Wuzhou, 543000)
②School of Civil and Architectural Engineering, Guilin University of Technology (Guangxi Guilin, 541004)
关键词:
粒子群优化算法; 相关向量机; 爆破; 飞石距离; 预测模型
Keywords:
particle swarm optimization algorithm;  relevance vector machine;  blasting;  distance of flying rock;  prediction model
分类号:
TD235.4
DOI:
10.3969/j.issn.1001-8352.2024.06.009
文献标志码:
A
摘要:
为了快速、准确地获取爆破飞石距离，及时控制爆破危害，提出了一种基于粒子群优化（particle swarm optimization, PSO）相关向量机（relevance vector machine, RVM）的爆破飞石距离预测模型。该模型用PSO对RVM模型核宽度参数进行优化，自适应获取最优参数，利用优化后的RVM建立炮孔孔径、炮孔长度、最小抵抗线与孔距之比、炮孔填塞长度、最大一段装药量和炸药单耗6个主要影响因素与爆破飞石距离的非线性映射关系。采用绝对值相对误差δ、均方根误差ERMS、均方误差EMS、平均绝对误差EMA、相关系数R2等多项指标对模型性能进行评价。将该模型应用于马来西亚柔佛州某矿山的爆破飞石距离预测，并与相同样本下的二次有理高斯过程回归模型、中等高斯核支持向量回归模型和双层神经网络模型3个模型中的最优结果对比：PSO-RVM模型的R2提高了7.1%,ERMS降低了14.56%,EMS和EMA分别降低了26.99%和15.96%。PSO-RVM模型的预测结果可信度和拟合度更好、精度更高。
Abstract:
In order to quickly and accurately obtain the distance of blasting flying rocks and timely control blasting hazards, a prediction model of blasting flying rock distance based on particle swarm optimization (PSO) and relevance vector machine (RVM) was proposed. PSO was used to optimize the core width parameter of RVM model, the optimal parameters could be adaptively obtained. The optimized RVM was used to establish the nonlinear mapping relationship between distances of blasting fly rock and six main influencing factors including borehole aperture, borehole length, ratio of minimum resistance line to borehole distance, borehole filling length, maximum section charge, and explosive consumption. Multiple indicators such as absolute relative error δ, root mean square error ERMS, mean square error EMS, mean absolute error EMA, and correlation coefficient R2?were used to evaluate the performance of the model. The model was applied to predict the distances of blasting flying rock in a mine in Johor, Malaysia, and compared with the optimal results of three models: quadratic rational Gaussian process regression model, medium Gaussian kernel support vector regression model, and double-layer neural network model using the same samples. R2?of PSO-RVM model increases by 7.1%, and ERMS?decreases by 14.56%. EMS?and EMA decrease by 26.99% and 15.96%, respectively. PSO-RVM model has better reliability and fit of prediction results, and higher accuracy.

参考文献/References:

［1］陈资, 李昌. 基于KPCA-WOA-ELM的爆破飞石距离预测［J］. 爆破器材, 2022, 51(2): 47-51.
CHEN Z, LI C. Prediction of blasting flyrock distance based on KPCA-WOA-ELM ［J］. Explosive Materials, 2022, 51(2): 47-51.
［2］刘文广. 中心城区超高层楼群多切口折叠爆破拆除［J］. 爆破器材, 2021, 50(5): 58-64.
LIU W G. Folding blasting demolition with multiple cuts of super high-rise buildings in central urban area ［J］. Explosive Materials, 2021, 50(5): 58-64.
［3］王振毅, 李静, 钱至桥, 等. 岩溶地质下露天深孔爆破飞石飞散距离的预测［J］. 爆破, 2022, 39(3): 199-203.
WANG Z Y, LI J, QIAN Z Q, et al. Prediction of flyrock distance in open-pit deep hole blasting under karst geology ［J］. Blasting, 2022, 39(3): 199-203.
［4］国家安全生产监督管理总局. 爆破安全规程: GB 6722—2014 ［S］. 北京: 中国标准出版社, 2014.
State Administration of Work Safety. Safety regulations for blasting: GB 6722—2014 ［S］. Beijing: Standards Press of China, 2014.
［5］孙远征, 龙源, 范磊, 等. 在复杂环境中的砖混烟囱定向爆破拆除［J］. 爆破, 2007, 24(2): 54-57．
SUN Y Z, LONG Y, FAN L, et al. Demolition of brick-concrete chimney by directional blasting in complex environment ［J］. Blasting, 2007, 24(2): 54-57.
［6］程康, 章昌顺. 深孔梯段爆破飞石距离计算方法初步探讨［J］. 岩石力学与工程学报, 2000, 19(4): 531-533.
CHENG K, ZHANG C S. Inquiry into flyrock distance for deep-hole blasting ［J］. Chinese Journal of Rock Mechanics and Engineering, 2000, 19(4): 531-533.
［7］MURLIDHAR B R, KUMAR D, ARMAGHANI D J, et al. A novel intelligent ELMBBO technique for predicting distance of mine blasting-induced flyrock ［J］. Natural Resources Research, 2020, 29(6): 4103-4120.
［8］刘庆, 张光权, 吴春平, 等. 基于BP神经网络模型的爆破飞石最大飞散距离预测研究［J］. 爆破, 2013, 30(1): 114-118.
LIU Q, ZHANG G Q, WU C P, et al. Research on maximum distance prediction of blast flyrock based on BP neural network ［J］. Blasting, 2013, 30(1): 114-118.
［9］FARADONBEH R S, ARMAGHANI D J, MONJEZI M, et al. Genetic programming and gene expression programming for flyrock assessment due to mine blasting ［J］. International Journal of Rock Mechanics and Mining Sciences, 2016, 88: 254-264.
［10］陈建宏, 彭耀, 邬书良. 基于灰色Elman神经网络的爆破飞石距离预测研究［J］. 爆破, 2015, 32(1): 151-156.
CHEN J H, PENG Y, WU S L. Prediction of blasting flyrock distance based on Elman neural network ［J］. Blasting, 2015, 32(1): 151-156.
［11］张西良. 岩体爆破环境效应预测的集成学习模型及工程应用［D］. 合肥: 中国科学技术大学, 2020: 65-90.
ZHANG X L. Ensemble learning model and engineering application of environmental effect prediction of rock mass blasting ［D］. Hefei: University of Science and Technology of China, 2020: 65-90.
［12］ARMAGHANI D J, KOOPIALIPOOR M, BAHRI M, et al. A SVR-GWO technique to minimize flyrock distance resulting from blasting ［J］. Bulletin of Engineering Geology and the Environment, 2020, 79: 4369-4385.
［13］张研, 吴哲康, 王鹏鹏, 等. 基于PCA-RVM的露天矿边坡稳定性预测模型［J］. 矿业研究与开发, 2021, 41 (3): 13-18.
ZHANG Y, WU Z K, WANG P P, et al. Prediction model of slope stability of open pit mine based on PCA-RVM ［J］. Mining Research and Development, 2021, 41(3): 13-18.
［14］赵春晖, 张燚. 相关向量机分类方法的研究进展与分析［J］. 智能系统学报, 2012, 7(4): 294-301.
ZHAO C H, ZHANG Y. Research progress and analysis on methods for classification of RVM ［J］. CAAI Transactions on Intelligent Systems, 2012, 7(4): 294-301.
［15］楼俊钢, 江建慧, 沈张果, 等. 软件可靠性预测的相关向量机模型［J］. 计算机研究与发展, 2013, 50(7): 1542-1550.
LOU J G, JIANG J H, SHEN Z G, et al. Software reliability prediction modeling with relevance vector machine ［J］. Journal of Computer Research and Development, 2013, 50(7): 1542-1550.
［16］TIPPING M E. Sparse bayesian learning and the relevance vector machine ［J］. Journal of Machine Learning Research, 2001, 1: 211-244.
［17］张研, 王鹏鹏. 基于RVM的爆破振动速度预测模型［J］. 爆破, 2022, 39(1): 168-174.
ZHANG Y, WANG P P. Blasting vibration velocity prediction model based on RVM ［J］. Blasting, 2022, 39(1): 168-174.
［18］张研, 王伟, 邓雪沁. 基于相关向量机的TBM掘进速度预测模型［J］. 现代隧道技术, 2020, 57(3): 108-114.
ZHANG Y, WANG W, DENG X Q. Prediction model of TBM advance rate based on relevance vector machine ［J］. Modern Tunneling Technology, 2020, 57(3): 108-114.
［19］陈财森, 胡海荣, 程志炜, 等. 基于BA-RVM算法的发动机故障诊断技术研究［J］. 计算机工程与科学, 2023, 45(2): 332-337.
CHEN C S, HU H R, CHENG Z W, et al. Engine fault diagnosis technology based on BA-RVM algorithm ［J］. Computer Engineering & Science, 2023, 45(2): 332-337.
［20］ESFANDYARI M, DELOUEI A A, JALAI A. Optimization of ultrasonic-excited double-pipe heat exchanger with machine learning and PSO ［J］. International Communications in Heat and Mass Transfer, 2023, 147: 106985.
［21］余修武, 谢晓永, 梁北孔, 等. 基于粒子群优化和巷道分区的深井WSN定位算法［J］. 中国安全科学学报, 2019, 29(2): 166-171.
YU X W, XIE X Y, LIANG B K, et al. A deep mine WSN localization algorithm based on both particle swarm optimization and tunnel partition ［J］. China Safety Science Journal, 2019, 29(2): 166-171.
［22］杨维, 李歧强. 粒子群优化算法综述［J］. 中国工程科学, 2004, 6(5): 87-94.
YANG W, LI Q Q. Survey on particle swarm optimization algorithm ［J］. Engineering Science, 2004, 6(5): 87-94.
［23］OKOJI A I, OKOJI C N, AWARUN O S. Performance evaluation of artificial intelligence with particle swarm optimization (PSO) to predict treatment water plant DBPs (haloacetic acids) ［J］. Chemosphere, 2023, 344: 140238.
［24］黄晶柱, 钟依禄, 黄裘俊, 等. 基于高斯过程回归矿山爆破飞石距离预测模型［J］. 工程爆破, 2023, 29(2): 73-79, 108.
HUANG J Z, ZHONG Y L, HUANG Q J, et al. Prediction model of blasting flyingrock distance in mine based on Gaussian process regression ［J］. Engineering Blasting, 2023, 29(2): 73-79, 108.

备注/Memo

备注/Memo:
收稿日期：2023-12-19
基金项目：国家自然科学基金(52068016)；广西重点研发计划（桂科AB21196041）
第一作者：刘小明（1981—），男，硕士，高级工程师，研究方向为地质灾害防治研究。E-mail: 352025898@qq.com
通信作者：李荣华（1972—），男，高级工程师，研究方向为地质灾害防治研究。E-mail: 360278465@qq.com
更新日期/Last Update: 2024-12-05