Application of improved grey system in tunnel monitoring

Chen Zhuo; He Jun

doi:10.1117/12.2613945

10 November 2021 Application of improved grey system in tunnel monitoring

Chen Zhuo, He Jun

Proceedings Volume 12050, International Conference on Smart Transportation and City Engineering 2021; 120505J (2021) https://doi.org/10.1117/12.2613945
Event: 2021 International Conference on Smart Transportation and City Engineering, 2021, Chongqing, China

Abstract

The prediction of deformation law of tunnel surrounding rock is an important measure to ensure construction safety. Affected by engineering geology and construction factors, tunnel deformation prediction has volatility and randomness. Based on the grey theory, the background value of GM(1,1) prediction model was optimized by using the cotes integral formula, and the grey model (ncbc-gm (1,1)) was established according to the minimum rule of the sum of squares of relative error. The ncbc-gm (1,1) grey prediction model is used to predict the deformation trend of tunnel surrounding rock, and the prediction results are compared with the traditional GM(1,1) prediction model and the GM(1,1) prediction model based on background value construction optimization. The results show that the root mean square error of the ncbc-gm (1,1) grey model is 2.66mm and 0.10mm lower than that of the traditional GM(1,1) prediction model and the optimized GM(1,1) prediction model based on the construction of background value, respectively, and the average relative error is 6.76% and 0.23% lower, respectively. The prediction accuracy is obviously improved, which provides an important basis for tunnel deformation prediction.

Citation Download Citation

Chen Zhuo and He Jun "Application of improved grey system in tunnel monitoring", Proc. SPIE 12050, International Conference on Smart Transportation and City Engineering 2021, 120505J (10 November 2021); https://doi.org/10.1117/12.2613945

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available