Wind-Induced Pressure Prediction on Tall Buildings Using Generative Adversarial Imputation Network

Abstract

Wind tunnel testing techniques are the main research tools for evaluating the wind loadings of buildings. They are significant in designing structurally safe and comfortable buildings. The wind tunnel pressure measurement technique using pressure sensors is significant for assessing the cladding pressures of buildings. However, some pressure sensors usually fail and cause loss of data, which are difficult to restore. In the literature, numerous techniques are implemented for imputing the single instance data values and data imputation for multiple instantaneous time intervals with accurate predictions needs to be addressed. Thus, the data imputation capacity of machine learning models is used to predict the missing wind pressure data for tall buildings in this study. A generative adversarial imputation network (GAIN) is proposed to predict the pressure coefficients at various instantaneous time intervals on tall buildings. The proposed model is validated by comparing the performance of GAIN with that of the K-nearest neighbor and multiple imputations by chained equation models. The experimental results show that the GAIN model provides the best fit, achieving more accurate predictions with the minimum average variance and minimum average standard deviation. The average mean-squared error for all four sides of the building was the minimum (0.016), and the average R-squared error was the maximum (0.961). The proposed model can ensure the health and prolonged existence of a structure based on wind environment.

Multiple regression method for working face mining pressure prediction based on hydraulic support monitoring dataset

“…As the pressure in the transition ladle during the manufacturing of amorphous alloys could be influenced by numerous factors, (Liu et al, 2022) employed a backpropagation (BP) neural network to ensure the prediction of the transition ladle pressure during the production of amorphous alloys. Kim et al (2021) team used the data attribution ability of a machine learning model to predict the missing wind pressure data of tall buildings and proposed a generative adversarial imputation network for predicting the pressure coefficients on tall buildings at various instantaneous time intervals.…”

“…The prediction technique employed in this study is based on machine learning. The existing popular research methods in machine learning include the GA-BP neural network model, Grey neural network model, BP neural network, extreme learning machine, support vector machine, artificial neural network, grid search algorithm, a gradient boosting decision tree, and generative time intervals imputation network (Huang et al, 2019;Tan et al, 2019;Arshad et al, 2021;Kim et al, 2021;Wang et al, 2022a;Liu et al, 2022;Weng and German Paal, 2022). However, the existing prediction methods are only applicable to data features with a single data quantity or evident data characteristic.…”

A Stacked Generalization Model to Enhance Prediction of Earthquake-Induced Soil Liquefaction

“…A model with sufficient and rich data performs efficiently with better predictive accuracy. Supplying a good quantity of data may reduce the training errors and improve the overall performance of the model [ 31 ]. It is important that the data are in an algorithm-recognizable tabular format as the performance of the stacked generalization approach depends on the quantity of the supplied data.…”

An HGA-LSTM-Based Intelligent Model for Ore Pulp Density in the Hydrometallurgical Process

“…To alleviate these problems, intelligent models have been used to predict wind flow around buildings by establishing inferential mathematical prediction models [ 6 ]. Owing to rapid response, accurate prediction results, and low maintenance costs, intelligent models have currently become one of the main methods for detecting quality variables in industrial processes, such as wind-induced pressure prediction [ 7 ], temperature prediction for roller kiln [ 8 ], and surface crack detection [ 9 ].…”