基于改进迁移学习算法的岩体质量评价模型

doi:10.11872/j.issn.1005-2518.2021.06.089

Abstract

Abstract:

Rock mass quality classification is an important foundation for engineering design and construction， and it is also an important research topic at present. Taking into account the complexity and uncertainty of rock masses and the differences of rock masses in different regions， machine learning methods are widely used in rock mass quality evaluation. A case database was established by collecting 55 sets of measured samples and 17 sets of interpolated samples from different regions. RQD， uniaxial saturated compressive strength （Rw）， rock mass integrity coefficient （Kv）， structural plane strength coefficient （Kf）， groundwater seepage volume （ω） are determined as the input conditions of the model， and the rock mass quality grade is the output condition. Based on the case library， an improved two-stage regression migration learning （Two-stage TrAdaBoost.R2）-Isolated Forest multi-factor rock mass quality grade prediction model is proposed. The advantages of this model are of follows：（1） The idea of migration learning is introduced into the rock mass quality classification. Taking into account the differences of rock masses in different regions， using the idea of weight adjustment， a sample similar to the target rock mass is selected from the known samples to assist in the training of the model. Solved the problem of insufficient training samples， and achieve high-precision prediction of the model when there are fewer learning samples in the target field. （2） When using the migration algorithm to classify the quality of the rock mass， the classification problem is transformed into a regression problem. The regression algorithm is used to predict the quality of the rock mass. Only one model can be used to judge the multiple levels of the sample， which overcomes the limitation of the classification algorithm in solving the multi-classification problem. （3） The sample weight is adjusted in two stages， which solves the problem of the source domain weight falling too fast in the TrAdaBoost algorithm. （4） Combined the Two-stage TrAdaBoost.R2 algorithm with the Isolated Forest anomaly detection algorithm，the influence of abnormal data on the model is eliminated， and the stability of the model is increased. The trained model was used to make multiple judgments on 12 samples of the first phase underground project of Guangzhou Pumped Storage Power Station， and the prediction accuracy of the model was evaluated by the mean square error. The average mean square error of the test sample is 0.067， and the prediction accuracy is high. It proves that the model has good performance in the application of rock mass quality grade prediction.

Key words: rock mechanics, rock mass quality evaluation, machine learning, transfer learning, Isolated Forest, TrAdaBoost algorithm

CLC Number:

TU457

Jianhua HU,Mengmeng GUO,Tan ZHOU,Tao ZHANG. Rock Mass Quality Evaluation Model Based on Improved Transfer Learning Algorithm[J].Gold Science and Technology, 2021, 29(6): 826-833.

Figures/Tables 8

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Table 2

Table 3

Table 4

References

null	Barton N，2002.Some new Q-value correlations to assist in site characterization and tunnel design［J］.International Journal of Rock Mechanics and Mining Sciences，39（2）：185-216.
null	Barton N， L?set F， Lien R， al et，1981.Application of Q-System in design decisions concerning dimensions and appropriate support for underground installations［J］.Subsurface Space，（12）：553-561.
null	Bieniawski ZT，1978.Determining rock mass deformability：Experience from case histories［J］.International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts，15（5）：237-347.
null	Cai Guangkui，2001.Research on BP Network Model of Surrounding Rock Stability Classification［D］.Nanjing：Hohai University.
null	Chen Xing，2018. Application of fuzzy pattern recognition and LVQ neural network in the rock mass classification［J］.Pearl River，39（10）：1-6.
null	Dai W Y， Yang Q， Xue G R， al et，2007.Boosting for transfer learning［C］//Proceedings of the 24th International Conference on Machine Learning.Corvalis：Oregon State University： 193-200.DOI：https：//doi.org/10.1145/1273496.1273521
null	Gong Fengqiang， Li Xibing，2007.Application of distance discriminant analysis method to classification of engineering quality of rock masses［J］.Chinese Journal of Rock Mechanics and Engineering，26（1）：190-194.
null	He Yunsong， Xue Qiuchi， Zhao Qihua，2017.Improved support vector machine-based study on rock mass quality classification［J］.Water Resources and Hydropower Engineering，48（1）：133-138.
null	Hu Jianhua， Shang Junlong， Lei Tao，2012.Rock mass quality evaluation of underground engineering based on RS-TOPSIS method［J］.Journal of Central South University（Science and Technology），43（11）：4412-4419.
null	Liu F T， Ting K M， Zhou Z H，2012.Isolation-based anomaly detection［J］.ACM Transactions on Knowledge Discovery from Data，6（1）：1-39.
null	Liu Wanjun， Li Tianhui， Qu Haicheng，2018.Hyperspectral similar sample classification algorithm based on Fisher criterion and TrAadboost［J］.Remote Sensing for Land and Resources，30（4）：41-48.
null	Pardoe D， Stone P，2010. Boosting for regression transfer［C］//Proceedings of the 27th International Conference on Machine Learning.Haifa：International Machine Learning Society： 863-870.
null	Qin Y G， Luo Z Q， Wang J， al et，2019.Evaluation of goaf stability based on transfer learning theory of artificial intelligence［J］.IEEE Access，7：18862440.DOI：10.1109/ACCESS.2019.2929533
null	Tu W F， Li L P， Li S C， al et，2019.Research on the application of dynamic weighting on the rock mass quality rating［J］.Arabian Journal of Geosciences，12.DOI：https：//doi.org/10.1007/s12517-019-4264-9
null	Water Resources of the People’s Republic of China，2014. Standard for engineering classification of rock masses：［S］.Beijing：China Planning Press.
null	Wen Changping，2008.Classification of rock-mass stability based on attributive mathematical theory［J］.Journal of Hydroelectric Engineering，27（3）：75-80.
null	Xu Guizhi， Lin Fang， Gong Minghong， al et，2019.A TrAdaBoost-based method for detecting multiple subjects’ P300 potentials［J］.Journal of Biomedical Engineering，36（4）：531-540.
null	Yang Zhaohui， Liu Haowu，1999.Artificial neural network model for the stability classification of adjoining rock of underground construction［J］.Journal of Sichuan Union University（Engineering Science Edition），（4）：66-72.
null	Yao Yinpei， Li Xibing， Gong Fengqiang， al et，2010.Application of weighted Mahalanobis distance discriminant analysis method to classification of rock mass quality［J］.Chinese Journal of Rock Mechanics and Engineering，29（Supp.2）：4119-4123.
null	Yuan Guohong， Chen Jianping， Ma Lin，2005.Application of extenics in evaluating of engineering quality of rock masses［J］. Chinese Journal of Rock Mechanics and Engineering，（9）：1539-1544.
null	Zhang Biao， Dai Xingguo，2017.A classification model of rock mass based on finite interval cloud model and distance discrimination weighting［J］.Hydrogeology & Engineering Geology，44（5）：150-157.
null	Zheng S， Jiang A N， Yang X R， al et，2020.A new reliability rock mass classification method based on least squares support vector machine pptimized by bacterial foraging optimization algorithm［J］.Advances in Civil Engineering，（1）：1-13.
null	Zhou Shuda， Pei Qitao， Ding Xiuli，2016.Application of grey evaluation model based on classification degree and weight of classification of index to rock mass quality evaluation of underground engineering［J］.Chinese Journal of Rock Mechanics and Engineering，35（Supp.2）：3671-3679.
null	Zhou Tan， Hu Jianhua， Kuang Ye，2019.Rock mass quality evaluation method and application based on fuzzy RES-multidimensional cloud model［J］.The Chinese Journal of Nonferrous Metals，29（8）：1771-1780.
null	蔡广奎，2001.围岩稳定性分类的BP网络模型研究［D］.南京：河海大学.
null	陈星，2018.模糊模式识别法及LVQ神经网络在岩体质量分级中的应用研究［J］.人民珠江，39（10）：1-6.
null	宫凤强，李夕兵，2007.距离判别分析法在岩体质量等级分类中的应用［J］.岩石力学与工程学报，26（1）：190-194.
null	何云松，薛秋池，赵其华，2017.基于改进向量机的岩体质量分级研究［J］.水利水电技术，48（1）：133-138.
null	胡建华，尚俊龙，雷涛，2012.基于RS-TOPSIS法的地下工程岩体质量评价［J］.中南大学学报（自然科学版），43（11）：4412-4419.
null	刘万军，李天慧，曲海成，2018.基于Fisher准则和TrAdaboost的高光谱相似样本分类算法［J］.国土资源遥感，30（4）：41-48.
null	文畅平，2008.基于属性数学理论的岩体质量分级方法［J］.水力发电学报，27（3）：75-80.
null	徐桂芝，林放，宫铭鸿，等，2019.基于TrAdaBoost的跨脑辨识P300电位研究［J］.生物医学工程学杂志，36（4）：531-540.
null	杨朝晖，刘浩吾，1999.地下工程围岩稳定性分类的人工神经网络模型［J］.四川联合大学学报（工程科学版），（4）：66-72.
null	姚银佩，李夕兵，宫凤强，等，2010.加权距离判别分析法在岩体质量等级分类中的应用［J］.岩石力学与工程学报，29（增2）：4119-4123.
null	原国红，陈剑平，马琳，2005.可拓评判方法在岩体质量分类中的应用［J］.岩石力学与工程学报，（9）：1539-1544.
null	张彪，戴兴国，2017.基于有限区间云模型和距离判别赋权的岩体质量分类模型［J］.水文地质工程地质，44（5）：150-157.
null	中华人民共和国水利部，2014. 工程岩体分级标准：［S］.北京：中国计划出版社．
null	周述达，裴启涛，丁秀丽，2016.改进分类区分度及权重的岩体质量评价灰评估模型及应用［J］.岩石力学与工程学报，35（增2）：3671-3679.
null	周坦，胡建华，匡也，2019.基于模糊RES-多维云模型的岩体质量评判方法与应用［J］.中国有色金属学报，29（8）：1771-1780.

Related Articles 15

[1]	Qiang ZENG,Xiaorong HUANG,Xiaojun WANG,Qinglin CHEN,Jian LIU,Cong GONG. Experimental Study on Rock Burst Tendency and Acoustic Emission Characteristics of Limestone at Different Buried Depths [J]. Gold Science and Technology, 2021, 29(6): 863-873.
[2]	Guoyan ZHAO,Chengkai DANG,Huanxin LIU,Yang LIU,Quri XIAO,Yang LI,Liqiang CHEN,Wenjie MAO. Evaluation of Mine Rockburst Tendency Based on the Distance Discrimination Analysis [J]. Gold Science and Technology, 2021, 29(5): 690-697.
[3]	Jingkai JIA,Gun HUANG,Long WANG,Qiang CHENG,Libing ZHEN. Study on a New Method of Weakening End Effect in Uniaxial Compression Test [J]. Gold Science and Technology, 2021, 29(3): 382-391.
[4]	Jianhua HU,Zhezhe DONG,Shaowei MA,Yaguang QIN,Xiao XU,Zhuan Dai. Seepage Characteristics of Damaged Rock Under Stress-Seepage Coupling [J]. Gold Science and Technology, 2021, 29(3): 355-363.
[5]	Jin HUANG,Kewei LIU,Shaohu JIN. Numerical Simulation Study of High-strength Projectile Penetrating White Granite Target [J]. Gold Science and Technology, 2021, 29(3): 411-420.
[6]	Rui TIAN,Haidong MENG,Shijiang CHEN,Chuangye WANG,Dening SUN,Lei SHI. Comparative Study on Three Rockburst Prediction Models of Intensity Classi-fication Based on Machine Learning [J]. Gold Science and Technology, 2020, 28(6): 920-929.
[7]	Mufan WANG,Zhouquan LUO,Qi YU. Stability Prediction of Goaf Based on Stacking Model [J]. Gold Science and Technology, 2020, 28(6): 894-901.
[8]	Zhiqin LIAO, Liguan WANG, Zhengxiang HE. Feature Extraction and Classification of Mine Microseismic Signals Based on EEMD and Correlation Dimension [J]. Gold Science and Technology, 2020, 28(4): 585-594.
[9]	Wei QI,Wei LI,Zhenyang LI,Guoyan ZHAO. Rock Mass Quality Evaluation of Underground Mine Based on CRITIC-CW Method [J]. Gold Science and Technology, 2020, 28(2): 264-270.
[10]	Renhao LI,Helong GU,Xibing LI,Kuikui HOU,Deming ZHU,Xi WANG. A PSO-RBF Neural Network Model for Rockburst Tendency Prediction [J]. Gold Science and Technology, 2020, 28(1): 134-141.
[11]	Bing SUN,Yu LUO,Jiehui XIE,Sheng ZENG. Failure Test of N-type Combination Jointed Rock Mass Under Uniaxial Compression [J]. Gold Science and Technology, 2019, 27(4): 548-556.
[12]	Shijiao YANG,Zhihui WANG. Numerical Simulation on Stability of Shallow-buried Goaf Group with Overlying Highway [J]. Gold Science and Technology, 2019, 27(4): 505-512.
[13]	Chundi FENG,Rendong HUANG. Plastic Strain Analysis of Mineral Particles in Red Sandstone [J]. Gold Science and Technology, 2019, 27(4): 557-564.
[14]	XIAO Weijing，CHEN Chen，LI Yongxin，WANG Xiaojun，CAO Shirong，HAN Jianwen. Creep Experiment and Model of Deep Limestone Under Step Loading [J]. Gold Science and Technology, 2017, 25(2): 76-82.
[15]	GUO Guangjun，LIU Mingjun，XU Yongbin，CHENG Wei，YE Yanling，ZHENG Xiaoli，GAO Haifen. Stability Classification of Engineering Rock Body in Jiaojia Gold Mine，Shandong Province [J]. J4, 2012, 20(4): 71-75.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 10

[1]	JIANG Qi, WANG Rong-Chao. [J]. J4, 2010, 18(4): 37 -40 .
[2]	LI Hong-Jie, CU Jing-Ji, MA Shu-Jiang. [J]. J4, 2010, 18(4): 41 -46 .
[3]	YUAN Dong-Cheng, XU Xiao-Feng. [J]. J4, 2010, 18(4): 47 -49 .
[4]	CHEN Hua-Dun. [J]. J4, 2010, 18(4): 50 -53 .
[5]	YANG Meng-Rong, MAO Chang-Xian. Uncertainty Evaluation of Arsenic and Antimony in Chemical Prospecting Sa-mple by Atomic Fluorescence Spectrometry[J]. J4, 2010, 18(3): 68 -71 .
[6]	LIN An-Zhi, DIAO Yu-Suo, XIAO Zhen, QING Min, WEI Feng, JIU Zhen-Beng. [J]. J4, 2010, 18(4): 27 -32 .
[7]	CHI Ji-Song, PAI Hong-Kun, QI Chuan-Duo, WANG Hu, QIN Xiang-Wei, LI Wen-Yu. [J]. J4, 2010, 18(4): 68 -70 .
[8]	HU Qin-Xia, LI Jian-Zhong, YU Guang-Meng, XIE Yan-Fang, ZHANG Ku-Xiao. Discussion on Gold Ore Point of Bailongjiang Metallogenic Belt[J]. J4, 2010, 18(3): 51 -53 .
[9]	SU Jian-Hua, LIU Shu-Lin. Study of Gold Extraction from Tail Solution with High Acid Content and Low Concentration[J]. J4, 2010, 18(3): 72 -75 .
[10]	HUANG Jun, WU Jiafu, LU RuKuai , XIA Liyuan. [J]. J4, 2010, 18(4): 1 -5 .

类别	RQD/%	Rw/MPa	Kv	Kf	ω/［L·（min·10m）^-1］
Ⅰ	90~100	200~120	1.00~0.75	1.0~0.8	0~5
Ⅱ	75~90	120~60	0.75~0.45	0.8~0.6	5~10
Ⅲ	50~75	60~30	0.45~0.30	0.6~0.4	10~25
Ⅳ	25~50	30~15	0.30~0.20	0.4~0.2	25~125
Ⅴ	0~25	15~0	0.20~0.00	0.2~0.0	125~300

序号	RQD/%	Rw/MPa	Kv	Kf	ω/［L·（min·10m）^-1］	类别
1*	100.0	200.0	1.00	1.00	0.0	Ⅰ
2*	97.5	180.0	0.94	0.95	1.3	Ⅰ
3*	95.0	160.0	0.88	0.90	2.5	Ⅰ
4	92.5	140.0	0.81	0.85	3.8	Ⅰ
5	86.3	105.0	0.68	0.75	6.3	Ⅱ
6	82.5	90.0	0.60	0.70	7.5	Ⅱ
7	78.8	75.0	0.53	0.65	8.8	Ⅱ
8	68.8	52.5	0.41	0.55	13.8	Ⅲ
9	62.5	45.0	0.38	0.50	17.5	Ⅲ
10	56.3	37.5	0.34	0.45	21.3	Ⅲ
11	43.8	26.3	0.28	0.35	50.0	Ⅳ
12	37.5	22.5	0.25	0.30	75.0	Ⅳ
13	31.3	18.8	0.23	0.25	100.0	Ⅳ
14*	18.8	11.3	0.15	0.15	168.8	Ⅴ
15*	12.5	7.5	0.10	0.10	212.5	Ⅴ
16*	6.3	3.8	0.05	0.05	256.3	Ⅴ
17*	0.0	0.0	0.00	0.00	300.0	Ⅴ
18	82.0	95.0	0.70	0.35	20.0	Ⅱ
19	68.0	90.0	0.57	0.35	20.0	Ⅱ
20	40.0	25.0	0.22	0.35	20.0	Ⅳ
21	87.0	95.0	0.70	0.50	10.0	Ⅱ
22	76.0	90.0	0.57	0.50	10.0	Ⅱ
23	76.0	95.0	0.70	0.50	10.0	Ⅱ
24	72.0	90.0	0.57	0.50	10.0	Ⅱ
25	51.0	40.0	0.38	0.50	10.0	Ⅲ
26	52.0	25.0	0.22	0.50	10.0	Ⅲ
27	68.0	90.0	0.38	0.30	20.0	Ⅲ
28	28.0	40.0	0.32	0.30	20.0	Ⅳ
29	51.0	25.0	0.15	0.30	20.0	Ⅳ
30	75.0	95.0	0.70	0.50	0.0	Ⅱ
31	77.5	90.0	0.57	0.45	10.0	Ⅱ
32	75.5	90.0	0.45	0.52	8.0	Ⅱ
33	85.5	94.0	0.65	0.55	0.0	Ⅱ
34	85.0	93.0	0.60	0.50	0.0	Ⅱ
35	78.5	92.0	0.55	0.50	6.0	Ⅱ
36	80.0	95.0	0.50	0.45	0.0	Ⅱ
37	85.0	92.0	0.70	0.50	10.0	Ⅱ
38	78.0	80.0	0.75	0.50	0.0	Ⅱ
39	76.5	90.0	0.55	0.50	10.0	Ⅱ
40	85.0	95.0	0.65	0.50	0.0	Ⅱ
41	75.0	90.0	0.55	0.50	7.0	Ⅱ
42	75.0	90.0	0.55	0.50	10.0	Ⅱ
43	87.0	95.0	0.50	0.45	0.0	Ⅱ
44	82.0	96.0	0.75	0.35	0.0	Ⅱ
45	50.0	70.0	0.50	0.35	5.0	Ⅲ
46	50.6	26.0	0.26	0.35	20.0	Ⅲ
47	50.0	40.2	0.50	0.50	10.0	Ⅲ
48	52.0	25.0	0.20	0.50	5.0	Ⅲ
49	71.0	90.0	0.35	0.30	5.0	Ⅲ
50	50.9	34.0	0.32	0.35	21.0	Ⅲ
51	50.0	90.0	0.50	0.25	5.0	Ⅲ
52	30.2	70.0	0.40	0.20	10.0	Ⅲ
53	50.0	45.0	0.12	0.30	5.0	Ⅲ
54	51.0	35.0	0.32	0.35	15.0	Ⅲ
55	50.9	34.0	0.32	0.35	20.0	Ⅲ
56	50.0	45.0	0.15	0.35	5.0	Ⅲ
57	26.0	36.0	0.22	0.35	5.0	Ⅳ
58	31.5	20.0	0.23	0.25	46.0	Ⅳ
59	35.0	70.5	0.35	0.30	10.0	Ⅳ
60	31.5	20.0	0.23	0.25	50.0	Ⅳ

序号	RQD/%	Rw/MPa	Kv	Kf	ω/［L·（min·10m）^-1］	实测等级
1	71.8	90.1	0.57	0.45	0	Ⅱ
2	76.0	95.0	0.70	0.55	12.0	Ⅱ
3	87.0	95.0	0.70	0.50	9.8	Ⅱ
4	82.0	95.0	0.70	0.35	0	Ⅱ
5	76.0	90.0	0.57	0.50	11.0	Ⅱ
6	68.0	90.0	0.57	0.35	18.5	Ⅱ
7	51.0	40.2	0.38	0.55	10.5	Ⅲ
8	50.0	35.0	0.32	0.35	20.0	Ⅲ
9	68.0	90.0	0.38	0.38	21.0	Ⅲ
10	51.0	45.0	0.15	0.30	5.0	Ⅲ
11	52.0	25.0	0.22	0.52	12.0	Ⅲ
12	28	40	0.32	0.30	18.5	Ⅳ

序号	期望输出	实际输出
序号	期望输出	1	2	3	4	5	6	7	8	9	10
均方误差		0.083	0.167	0.167	0	0	0.083	0	0	0.083	0.083
1	Ⅱ	2	3*	3*	2	2	2	2	2	2	2
2	Ⅱ	2	2	2	2	2	2	2	2	2	2
3	Ⅱ	2	2	2	2	2	2	2	2	2	2
4	Ⅱ	2	2	2	2	2	2	2	2	2	2
5	Ⅱ	2	2	2	2	2	2	2	2	2	2
6	Ⅱ	3*	3*	3*	2	2	3*	2	2	3*	3*
7	Ⅲ	3	3	3	3	3	3	3	3	3	3
8	Ⅲ	3	3	3	3	3	3	3	3	3	3
9	Ⅲ	3	3	3	3	3	3	3	3	3	3
10	Ⅲ	3	3	3	3	3	3	3	3	3	3
11	Ⅲ	3	3	3	3	3	3	3	3	3	3
12	Ⅳ	4	4	4	4	4	4	4	4	4	4

Rock Mass Quality Evaluation Model Based on Improved Transfer Learning Algorithm

RichHTML

PDF (PC)