An Algorithm for Solving the Pose of Bio 3D Printing based on Neural Network

Obtaining the pose state information of the printing nozzle in real time and performing error compensation is an important means to improve the accuracy of biological 3D printing. Traditional pose solving methods such as Newton iteration method and Analysis method have problems such as difficulty in selecting the initial value and slow calculation speed. To solve the above problems, a biological 3D printing pose solution algorithm based on the Elman neural network optimized by genetic algorithm is proposed. Firstly, the kinematics model of the biological 3D printing platform is established, then the GA-Elman neural network is established and the inverse solution of the platform is used as a training sample, and the pose information is solved by the method of network learning, and finally the accuracy of the algorithm is verified by simulation. The simulation results show that the algorithm has high calculation accuracy and fast solution speed, and can quickly and accurately solve the pose of biological 3D printing.