An Intelligent Advanced Classification Method for Tunnel-Surrounding Rock Mass Based on the Particle Swarm Optimization Least Squares Support Vector Machine

The fast and accurate classification of surrounding rock mass is the basis for tunnel design construction has significant value in engineering applications. Therefore, this paper proposes a method classifying predicting based on particle swarm optimization (PSO)–least squares support vector machine (LSSVM). premise research that data acquired from digital drilling technology are divided into training group test group; continuously optimizes algorithm least machine, then used verification. Moreover, searching abilities significantly accelerate computational power accuracy making it high-speed analog search tool. Taking Jiaozhou Bay undersea China as an example, comparison evaluation results PSO-LSSVM QGA-RBF (quantum genetic algorithm-radical function neural network) undertaken. show matches well with field-measured grade. Applying context proves good self-learning abilities, even when sample size small prediction high; such, meets requirements. technique advantages prediction, pattern recognition, nonlinear prediction.