Harbin Gongcheng Daxue Xuebao/Journal of Harbin Engineering University,2006年27(SUPPL.):393-396 ISSN：1006-7043
[毕忠伟; 张志军; 饶龙; 丁德馨] School of Architectural Engineering Resources and Environment, Nanhua University, Hengyang 421001, China;[毕忠伟; 张志军; 饶龙] School of Resources and Safety Engineering, Central South University, Changsha 410083, China
The design work is important to normal use and safety and stabilization of a project of the geotechnical engineering. The system Geotechnical engineering researched is extremely complicated and indeterminate, therefore, it is difficult to design an actual project problem ideally with traditional design methods. Because of the indetermination of the geotechnical engineering, an ANN-based inverse design approach is established and applied to inverse design for the angle and height of a certain slope. The result shows that the new approach has ability of handling the nonlinear problem, and is suitable for dealing with the extremely complicated and indeterminate problem of the geotechnical engineering, besides, it is an excellent inverse design approach.
School of Resource and Safety Engineering, Central South University, Changsha;School of Nuclear Resources and Safety Engineering, University of South China, Hengyang , China;School of Urban Construction, University of South China, Hengyang , China;School of Nuclear Resources and Safety Engineering, University of South China,Hengyang , China
the 2nd International Conference GEDMAR08(第二届岩土工程减灾与修复国际会议)
the 2nd International Conference GEDMAR08(第二届岩土工程减灾与修复国际会议)论文集
Because of the uncertainty of the parameters and characteristics of rock joints, this paper performed research in three respects. (1)The contract model of structural planes established by using ABAQUS, and, based on the contract model, the non-linear finite element model for analyzing the stability of rock slope was established. (2) The model between the rock mass mechanics parameters and anti-slide and down-slide forces was built up by using the Adaptive Neuro-Fuzzy Inference System (ANFIS) consisting of artificial neural network and fuzzy logical inference. (3) The program of reliability analysis was compiled by using Monte-Carlo simulation (MCS) and MATLAB, a new reliability analysis method was proposed by coupling ABAQUS, ANFIS and MCS , and the method was used to analyze the reliability of a rock slope. The results show that the contact model of structural planes has great influence on the precise of numerical simulation, that the tangent spring element model could ensure the precision and enhance the convergent efficiency, and that the method could avoid compiling redundant finite element program, reduce the computing time, and improve calculation precision.
Current design method for circular sliding slopes is not so reasonable that it often results in slope sliding. As a result, artificial neural network (ANN) is used to establish an artificial neural network based inverse design method for circular sliding slopes. A sample set containing 21 successful circular sliding slopes excavated in the past is used to train the network. A test sample of 3 successful circular sliding slopes excavated in the past is used to test the trained network. The test results show that the ANN based inverse design method is valid and can be applied to the design of circular sliding slopes.
Journal of Coal Science & Engineering(China),2005年11(2):13-15 ISSN：1006-9097
[Bi, Zhong-Wei] School of Resources and Safety Engineering, Central South University, Changsha 410083, China;[Zhang, Xin-Hua; Bi, Zhong-Wei; Ding, De-Xin] School of Architecture and Resources Environment Engineering, Nanhua University, Hengyang 421001, China
The theory of Monte-Carlo simulation method is that the event happened probability was estimated by happened frequency in the experiments. So it is very im-portant to ascertain the times of simulation. The probability and statistic theory are used to determine the optimal simulation times through strict mathematic reasoning. The study of two cases is made to show the availability of the presented method, and some relative problems were discussed.
Journal of Central South University of Technology,2006年13(4):438-444 ISSN：1005-9784
[Bi, Zhong-Wei; Ding, De-Xin; Zhang, Zhi-Jun] School of Resources and Safety Engineering, Central South University, Changsha 410083, China;[Bi, Zhong-Wei; Ding, De-Xin; Zhang, Zhi-Jun] School of Architectural, Resources and Environment Engineering, Nanhua University, Hengyang 421001, China
[Ding De-xin] Cent S Univ, Sch Resources & Safety Engn, Changsha 410083, Peoples R China.
mining induced surface subsidence;fuzziness and interaction of parameters;artificial neural fuzzy inference system
There are many parameters influencing mining induced surface subsidence. These parameters usually interact with one another and some of them have the characteristic of fuzziness. Current approaches to predicting the subsidence cannot take into account of such interactions and fuzziness. In order to overcome this disadvantage, many mining induced surface subsidence cases were accumulated, and an artificial neuro fuzzy inference system(ANFIS) was used to set up 4 ANFIS models to predict the rise angle, dip angle, center angle and the maximum subsidence, respectively. The fitting and generalization prediction capabilities of the models were tested. The test results show that the models have very good fitting and generalization prediction capabilities and the approach can be applied to predict the mining induced surface subsidence.
建筑材料学报,2016年19(2):369-372 and 384 ISSN：1007-9629
[张志恒; 丁德馨; 栗建新; 石建军; 刘华良; 刘权] School of Urban Construction, University of South China, Hengyang, 421001, China;[丁德馨; 石建军] School of Resources and Safety Engineering, Central South University, Changsha, 410083, China