Research on factor analysis and method for evaluating grouting effects using machine learning

Abstract

Abstract The evaluation of grouting effects constitutes a critical aspect of grouting engineering. With the maturity of the grouting project, the workload and empirical characteristics of grouting effect evaluation are gradually revealed. In the context of the Qiuji coal mine’s directional drilling and grouting to limestone aquifer reformation, this study thoroughly analyzes the influencing factors of grouting effects from geological and engineering perspectives, comparing these with various engineering indices associated with drilling and grouting. This led to the establishment of a “dual-process, multi-parameter, and multi-factor” system, employing correlation analysis to validate the selected indices’ reasonableness and scientific merit. Utilizing the chosen indices, eight high-performing machine learning models and three parameter optimization algorithms were employed to develop a model for assessing the effectiveness of directional grouting in limestone aquifers. The model’s efficacy was evaluated based on accuracy, recall, precision, and F-score metrics, followed by practical engineering validation. Results indicate that the “dual-process, multi-parameter, multi-factor” system elucidates the relationship between influencing factors and engineering parameters, demonstrating the intricacy of evaluating grouting effects. Analysis revealed that the correlation among the eight selected indicators—including the proportion of boreholes in the target rock strata, drilling length, leakage, water level, pressure of grouting, mass of slurry injected, permeability properties of limestone aquifers before being grouted, permeability properties of limestone aquifers after being grouted—is not substantial, underscoring their viability as independent indicators for grouting effect evaluation. Comparative analysis showed that the Adaboost machine learning model, optimized via a genetic algorithm, demonstrated superior performance and more accurate evaluation results. Engineering validation confirmed that this model provides a more precise and realistic assessment of grouting effects compared to traditional methods.

Keywords

• Grouting effect evaluation
• Correlation analysis
• Optimization algorithm
• Machine learning