Foundation pit deformation prediction method based on improved artificial bee colony algorithm and BP neural network

• Main Authors: ZHONG XIAOCHUN, ZHANG JIAN, WANG CHAORAN, FENG TUGEN, HANG ZHIBIN, ZHOU KUN, XIE KANG, ZHANG KUNYONG, ZHANG FUHAI
• Format: Patent
• Language: Chinese; English
• Published: 20.11.2020
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention provides a foundation pit deformation prediction method based on an improved artificial bee colony algorithm and a BP neural network. The problem that the type and the risk part which possibly have the risk are difficult to pre-judge in advance is solved; an input variable consistent with the change trend of the prediction target can be found out by utilizing a grey relational analysis method; searching an optimal initial value of the BP neural network globally by using an artificial bee colony algorithm improved by adding an adaptive coefficient; the method is advantaged in thatnetwork training speed is accelerated, prediction precision is improved, possible deformation after foundation pit excavation is predicted before construction, reasonability of the employed construction parameters is estimated in advance, and the method has reference meaning for ensuring construction safety, controlling foundation pit deformation and scientifically planning the construction progress. 本发明提供了一种基于改进的人工蜂群算法与