Low-stress high-precision electric arc additive process control method based on computational intelligence

The invention provides a low-stress high-precision electric arc additive process control method based on computational intelligence. Based on an improved wavelet neural network algorithm, the residual stress, the surface flatness, the weld bead fusion width and the weld bead surplus height of an electric arc additive manufacturing workpiece under the laser-electromagnetic-ultrasonic synergistic effect are quantitatively predicted, and the closeness degree of each index predicted value and a target value and the uniformity weighted combination of the predicted values serve as a unified control optimization target. And finally, an optimal process parameter combination is searched scientifically, efficiently and accurately by utilizing an improved grey wolf optimization algorithm, and a key process collaborative optimization method is provided for accurate, stable and rapid automatic control of a low-stress and high-precision metal arc additive manufacturing process. And the method has important enlightenment an