Stability Evaluation and Reinforcement Methods of Bored Pile Wall - Taking the Southeast Coastal Area as an Example
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The current methods for evaluating the stability of cast-in-place pile hole walls are inefficient and have poor accuracy, leadingto incorrect selection of steel reinforcement methods and affecting the quality of construction projects. To address the aboveissues, a smart evaluation method for the stability of cast-in-place pile hole walls is proposed, taking the southeastern coastalregion as an example. Firstly, a wall stability evaluation index system was constructed based on typical local geologicalconditions, covering dimensions such as geological factors, groundwater levels, and construction parameters. PrincipalComponent Analysis (PCA) and Factor Analysis (FA) were applied to extract key feature variables. Secondly, historical datafrom 90 CIPP engineering projects were preprocessed through cleaning and normalization, and then divided into training andtesting sets in a 7:3 ratio. A multi-strategy Harris Hawks Optimization (MHHO) algorithm was used to optimize the initialweights of the Backpropagation Neural Network (BPNN), thereby building a stability prediction model. Finally, the modelperformance was evaluated using multiple metrics including F1-score, AUC, recall, and fitting degree. The results show thatMHHO-BPNN achieved an accuracy of 0.967 and an F1-score of 0.975 on the test set, significantly outperforming mainstreambenchmark models such as the Genetic Algorithm-optimized BPNN (RGA-BPNN) and the Particle Swarm OptimizationbasedSVM (IPSO-SVM). This method provides data support for rapid evaluation of wall stability and reinforcement schemeformulation, and demonstrates strong potential for practical engineering applications.
Abstract
The current methods for evaluating the stability of cast-in-place pile hole walls are inefficient and have poor accuracy, leadingto incorrect selection of steel reinforcement methods and affecting the quality of construction projects. To address the aboveissues, a smart evaluation method for the stability of cast-in-place pile hole walls is proposed, taking the southeastern coastalregion as an example. Firstly, a wall stability evaluation index system was constructed based on typical local geologicalconditions, covering dimensions such as geological factors, groundwater levels, and construction parameters. PrincipalComponent Analysis (PCA) and Factor Analysis (FA) were applied to extract key feature variables. Secondly, historical datafrom 90 CIPP engineering projects were preprocessed through cleaning and normalization, and then divided into training andtesting sets in a 7:3 ratio. A multi-strategy Harris Hawks Optimization (MHHO) algorithm was used to optimize the initialweights of the Backpropagation Neural Network (BPNN), thereby building a stability prediction model. Finally, the modelperformance was evaluated using multiple metrics including F1-score, AUC, recall, and fitting degree. The results show thatMHHO-BPNN achieved an accuracy of 0.967 and an F1-score of 0.975 on the test set, significantly outperforming mainstreambenchmark models such as the Genetic Algorithm-optimized BPNN (RGA-BPNN) and the Particle Swarm OptimizationbasedSVM (IPSO-SVM). This method provides data support for rapid evaluation of wall stability and reinforcement schemeformulation, and demonstrates strong potential for practical engineering applications.