Application of GA-ACO Algorithm in Thin Slab Continuous Casting Breakout Prediction

To address the problems of slow convergence and low recognition accuracy of back propagation neural network (BPNN), genetic algorithm (GA) and ant colony optimization (ACO) were used to optimize BPNN, and the optimized model was applied for the breakout prediction, and GA-ACO-BP breakout prediction model was established. The three models of BP, ACO-BP and GA-ACO-BP were tested offline using the data collected from the production site. The tests show that the GA-ACO-BP breakout prediction model combines the advantages of GA and ACO, has faster convergence speed and higher prediction accuracy, and can achieve 100% reporting rate and 98.36% prediction rate, which has good prediction effect and good application prospect.