Finite element simulation (fes) and transfer learning (tl)-based inversion method for firmness of on-tree peach fruit

A finite element simulation (FES) and transfer learning (TL)-based inversion method for firmness of an on-tree peach fruit, comprising following steps:

• step 1, collecting vibration signals of on-tree peach fruits at different growth stages by using a laser Doppler vibrometer, preprocessing the vibration signals to serve as a model input, measuring a reference firmness value of the peach fruit by using a texture analyzer, and constructing an experimental dataset;
• step 2, establishing finite element models with bionic fidelity for peach fruit vibration, and calculating a simulated vibration response;
• step 3, modifying material properties of the obtained finite element models with bionic fidelity for the peach fruit vibration in the step 2 to obtain vibration responses of peach fruits with different firmness levels, and constructing a simulated dataset;
• step 4, constructing a domain-adversarial neural network (DANN), performing training by using the simulated dataset obtained in the step 3 as a source domain and the experimental dataset obtained in the step 1 as a target domain, and obtaining a peach fruit firmness inversion model through adversarial training;
• and
• step 5, inputting a vibration response of the on-tree peach fruit into the peach fruit firmness inversion model, and obtaining a firmness value of the peach fruit, so as to guide fruit picking.