Laser marking method for nonferrous metal casting ingots based on improved RANSAC algorithm

Non ferrous metal casting ingots must carry relevant production information, usually using manual pasting of copper coated paper, manual lifting of spray code, and pneumatic marking methods. These methods have a low degree of automation and severe material waste. To this end, genetic algorithm (GA) is used to guide sampling of random sample consensus algorithm (RANSAC) based on probability, and the two are combined for simulation to optimize the shortcomings of RANSAC algorithm in random sampling. On the ground of the optimized RANSAC to fit the plane equation, the normal vector of the plane is calculated, and the angle between the coordinate axis and the normal vector in the pendulum coordinate system is determined through the normal vector, enabling automatic alignment and vertical focusing functions to be achieved. Finally, based on the actual situation, the marking position is determined using set relationships to achieve motion control of mechanical functions. A laser marking method for non-ferrous metal casting ingots based on the improved RANSAC algorithm was designed. Through experimental analysis, it was found that the average F1 value of the method is 96.42, the average accuracy is 98.24%, the RMSE is 0.236, and the running time is 18.40 seconds. The F1 value represents the combined performance of the model's accuracy and recall rate when dealing with the marking task. Combined with the above results, it can be seen that the research and design method can efficiently and accurately laser marking metal casting ingot, and improve production efficiency.