Evaluation of Tunnel Boring Machine (TBM) Based on Different Cutting Tool Layouts in the Cutter-Head

Abstract

The arrangement and layout of cutting tools in the cutter head are among the most critical factors affecting the performance of the Tunnel Boring Machine (TBM). These factors directly impact the drilling operation efficiency, the TBM's useful lifespan, and the cutting tool's overall performance. In general, designing the cutting tool layout poses a multi-objective optimization challenge with non-linear constraints, resulting in computational complexity during the design process. Researchers have faced significant challenges in developing efficient computational models for designing cutting tool layouts in TBMs due to the complexities arising from the technical requirements of TBM structures and drilling engineering constraints. In this study, the primary aim is to assess the influence of different cutting tool layouts on TBM performance. To achieve this, a numerical model has been created, employing the Grey Wolf Optimization (GWO) metaheuristic algorithm to design three types of layouts: stochastic, spiral, and star. To evaluate the performance of the developed design model, a practical TBM for rock excavation was selected, and the process of designing the cutting tool layout in its cutter head was analyzed. According to the research findings, it is evident that the TBM's performance has shown remarkable improvement with all three types of cutting tool layouts: stochastic, spiral, and star, compared to the original setup. The results indicate that the TBM with a stochastic cutting tool layout outperformed the spiral and star layouts, achieving an approximately 8% reduction in the overall lateral force compared to the star layout, and a 10% reduction compared to the spiral layout. Furthermore, the stochastic layouts led to an 11% decrease in eccentric torque compared to the star layout, and a 14% decrease compared to the spiral layout. After analyzing the results and assessing the TBM's performance under the spiral and star layouts, it was evident that the TBM with the star cutting tool layout outperformed the spiral layouts. The star layout resulted in a more significant reduction, approximately 4%, in the overall lateral force of the TBM and a 2.5% decrease in the eccentric torque compared to the spiral layouts. The most crucial outcome of this research was the successful development of an efficient numerical model for designing optimal cutting tool layouts, including stochastic, spiral, and star layouts in the TBM cutter head, utilizing the GWO algorithm. The proposed model exhibited versatility, making it applicable to different operational conditions and various types of TBMs.

Keywords

• tunnel boring machine (tbm)
• machine learning modeling
• stochastic layout
• star layout
• spiral layout
• gwo algorithm