Expansive soil freezing process deformation decoupling method based on machine learning factor analysis

• Main Authors: CONG SHENGYI, ZHANG XIYANG, MAO XIAOGANG, BAE YUN-SANG, CHEN HONGWEI, ZHANG ZHONGYUAN, LING XIANCHANG, LI XINYU, CHENG ZHIHE, TANG LIANG
• Format: Patent
• Language: Chinese; English
• Published: 12.05.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses an expansive soil freezing process deformation decoupling method based on machine learning factor analysis, and the method comprises the steps: putting a manufactured soil sample into a frost heaving testing machine, and measuring various parameter changes in a temperature reduction soil sample freezing process; and importing the obtained data into MATLAB, and obtaining volume increment or volume decrement caused by volume ice content change and unfrozen water volume water content change by utilizing ICA and a regression fitting algorithm program in the MATLAB. According to the method, on the premise that volume increase caused by freezing of water into ice and volume reduction caused by water loss and shrinkage of soil particles of the expansive soil exist in the freezing process of the expansive soil, volume changes caused by water freezing and water loss of the soil particles are obtained respectively. According to the method, machine learning factor analysis and regression fitting