Prediction method for shearing parameters of Martian soil based on GA-BP neural network

Abstract

The invention discloses a prediction method for shearing parameters of Martian soil based on a GA-BP neural network, and the method comprises the steps: S1, determining a BP network weight and threshold, and using an improved genetic algorithm (GA) to optimize the BP neural network weight and thresholds: firstly coding the BP neural network weight and threshold, carrying out the selection, crossing and mutation operations of the weight and threshold according to a fitness function to obtain a new weight and a threshold until a training error reaches 0.001, otherwise continuing the optimizationto obtain the weight and threshold; S2, establishing a BP prediction model; S3, training the BP model to predict shearing parameters of Martian soil. The method improves a selection operator of the GA, maintains the diversity of populations while effectively selecting a better individual in the populations, thereby optimizing the weight and threshold of the BP neural network model and enabling the BP network to accurately estimate the shearing parameters of the Martian soil.

Description

technical field [0001] The invention relates to the technical field of Mars exploration, in particular to a method for predicting shear parameters of Martian soil based on a GA-BP neural network. Background technique [0002] Exploring the mechanical properties of Martian soil is crucial to the landing ability of the Mars rover and whether it can walk safely and effectively on the surface of Mars. But so far humans have not obtained Martian soil samples from Mars; although the Mars rover can measure the mechanical parameters on the surface of Mars, the delay in returning the data to Earth has affected the autonomous operation of the Mars rover; and due to the mass and size of the existing Mars rover And other limitations, making it impossible to carry special equipment for measuring the mechanical parameters of Martian soil. Therefore, it is particularly important to obtain the mechanical parameters of Martian soil in real time through in-situ analysis. At present, at home...

AI Technical Summary

Problems solved by technology

[0003] Neural network (ANN) is a mathematical model that uses a structure similar to that of brain synaptic connections for information processing. It has strong nonlinear fitting capabilities, simple learning rules, and is easy to implement, so it is widely used. Slow convergence speed, sensitive to initial weight, poor global search ability, easy to fall into local extremum and other problems, genetic algorithm belongs to evolutionary algorithm, it finds the optimal solution by imitating the mechanism of selection and inheritance in nature, it is a parallel global search algorithm , has strong robustness, but the search speed is slow, the local search ability is poor, and the problem of premature convergence is prone to occur

Images