Soil compactness detection method based on multiple sensors and neural network

The invention discloses a soil compactness detection method based on multiple sensors and a neural network, which can be suitable for various terrains and comprises the following steps: collecting detection data of various texture soil samples; unscented Kalman filtering and data cleaning are carried out, and force-time-to-ground distance three-dimensional information and soil multi-parameter information data after noise removal are output; training a physical information neural network model based on force-time-to-ground distance three-dimensional information and soil multi-parameter information data; calculating force distribution, power distribution, dynamic distribution, frequency domain characteristics and time-frequency characteristics in each soil insertion process, and combining with three-dimensional information of time-to-ground distance to train a deep neural network model; fusing the trained models, and introducing a harmonic parameter alpha to train a hybrid model; and taking the force-time-to-gr