http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Wenjing Zhang,Li Gao,Xun Jiao,Jun Yu,Xiaosi Su,Shanghai Du 한국지질과학협의회 2014 Geosciences Journal Vol.18 No.4
Earth fissures in Su-Xi-Chang land subsidence areahave induced massive damages to the area. The non-linear characteristicassociated with the process of earth fissure formation requiresnon-linear method for evaluating the occurrence of the hazard. Based on quantification of influence factors on breeding the hazard,GA-ANN method, which integrates artificial neural networks(ANN) with genetic algorithms (GA), is developed for evaluating theoccurrence of earth fissure hazard. Six indicators, that include thedepth of bedrock burial (DBB), the degree of bedrock relief (DBR),water level (WL) (the II confined aquifer), the gradient of landsubsidence (GLS), transmissivity (T) (the II confined aquifer) andthe thickness of clay soil (TCS), are selected as the input patternsof the integrated approach, and danger index (DI) as the outputpattern. A multilayer back-propagation neural network is trainedwith 30 sets of data samples including 15 sets of earth fissure samplesand 15 sets of safety samples for defining the architecture ofANN. Subsequently, GA is employed by optimizing the initial weightsof trained ANN by minimizing the deviation of output. The efficacy ofthe integrated approach is demonstrated by comparing the deviationof output from ANN and GA-ANN for 5 testing samples andthe result shows that the GA-ANN method is more accurate thanANN in identifying the occurrence of earth fissure. The integratedmethod is applied to the assessment of earth fissure hazard in typicalregions of earth fissure. According to the classification of DI, theregions are divided into four zones ‒ danger zone, sub-danger zone,sub-safe zone and safe zone.