Research on a Method of Gross Error Elimination for Slope Monitoring Data Based on Machine Learning

Abstract

Many high and steep slopes are formed in the open pit mining process, whose stability will directly affect the construction and safety. Therefore, it is particularly important to detect and eliminate rough errors of slope monitoring data. This paper proposes an improved two-layer extreme learning machine (TELM) based on particle swarm optimization (PSO) to establish monitoring slope model. In particular, the parameters of the first layer of the whole algorithm are obtained by particle swarm optimization algorithm, and the parameters of the second layer are calculated through a new solution method. First, some basic principles and concepts of extreme learning machine are introduced, and the algorithm thought, basic principles and related derivation of the improved two-layer extreme learning machine in this paper are emphatically discussed. A better mapping relationship between the input space and the output space is found through the parameter solution method, which improves the precision of the algorithm. Then, the data collection and traditional gross error elimination methods are studied. Finally, in order to test the ability of the two hidden layer extreme learning machine to solve the slope monitoring problem, the algorithm is applied to the gross error elimination of the slope data. The experimental results show that compared with the traditional gross error elimination method and ELM algorithm, the proposed method has higher precision, stronger robustness, and more practicability.

Keywords

• Extreme learning machine (ELM)
• gross error elimination
• two-layer extreme learning machine
• particle swarm optimization