The idea of particle swarm optimization algorithm PSO (particle swarm optimization) comes from the research on the predation behavior of birds. It is a method to find the optimal solution by simulating the flight foraging behavior of birds, the cooperation and information sharing among individuals in the cluster. Each particle can be regarded as a search individual in the n-dimensional search space, the current position of the particle corresponds to a candidate solution of the optimization problem, and the flight process of the particle represents the search process of the individual. The flight speed of particles can be dynamically adjusted according to the historical optimal position of particles and the historical optimal position of population. The optimal solution satisfying the termination condition is finally obtained by continuously iterating the update speed and position.
The speed and position update formula is as follows:
Among them, the value range of particle population is [30,50]; Vid represents the flight speed of the ith particle in the D dimension; ω Is inertia weight, which can be calculated according to ω The global optimization and local optimization performance are adjusted according to the size of the value, and the value range is [0.6,1.2]; C1 and C2 are individual learning factors and social learning factors of particles, usually C1 + C2 ∈ [0,4]; Rand (0,1) is a random number on interval [0,1]; PID represents the individual extremum of the ith particle in the D dimension; XID represents the position of the ith particle in the D dimension; PGD is the d-dimensional global optimal solution.
In this paper, the low-carbon model of the process of Moldless sand casting is established, and the parameter optimization model is established combined with the process parameter types of Moldless composite mold. On the basis of meeting the conditions of casting forming quality and mold mechanical properties, a multi-objective optimization model based on particle swarm optimization algorithm is proposed, focusing on the optimization of the coupling process parameters of composite mold. The technical route of composite mold process parameter optimization based on particle swarm optimization algorithm is as follows:
(1) The fitness function and constraint function are established;
(2) Set PSO parameters, including population size, learning factors C1, C2 and inertia weight ω And the number of iterations;
(3) The particle swarm is generated randomly, and the fitness f (XI) of the initialization particle is calculated, where I = 1, 2, 3,…, N;
(4) Calculation by τ Fitness f (XI) of particles after the second iteration τ)， The particle fitness is compared with the extreme value f (GD), when f (XI) τ) When it is better than f (GD), the alternative GD is Xi τ， Otherwise, it remains unchanged;
(5) Update the global optimal velocity and position of particles;
(6) When the iteration termination condition is satisfied, the optimal mold process parameters are output.