Abstract

Deformation of ground during tunnelling projects is one of the complex issues that is required to be monitored carefully to avoid the unexpected damages and human losses. Accurate prediction of ground settlement is a crucial concern for tunnelling problems, and the adequate predictive model can be a vital tool for tunnel designers to simulate the ground settlement accurately. This study proposes relatively new hybrid artificial intelligence models to predict the ground settlement of earth pressure balance shield tunnelling in the Bangkok MRTA project. The predictive models were various nature-inspired frameworks, such as differential evolution, particle swarm optimization, genetic algorithm, and ant colony optimizer to tune the adaptive neuro-fuzzy inference system. To obtain the accurate and reliable results, the modeling procedure is established based on four different dataset scenarios including preprocessed and normalized, preprocessed and nonnormalized, non-preprocessed and normalized, and non-preprocessed and nonnormalized datasets. Results indicated that PPN dataset scenario significantly affected the prediction models in terms of their perdition accuracy. Among all the developed hybrid models, ANOFS-PSO model achieved the best predictability performance. In quantitative terms, PPN-ANFIS-PSO model attained the least root mean square error value of 7.98 and a correlation coefficient value of 0.83. Overall, the attained results confirmed the superiority of the explored hybrid AI models as robust predictive model for ground settlement of earth pressure balance shield tunnelling.