Potential well type selection is critical for the convergence of the QPSO (Quantum-behaved Particle Swarm Optimization) algorithm. This paper analyzed the motion pattern of particles in square potential well, given the position equation of the particles by solving the Schrödinger equation and proposed the Ternary Correlation QPSO Algorithm Based on Square Potential Well (TC-QSPSO). In this novel algorithm, the internal relations during particles own experience information, group sharing information and the distance from the particles current location to the population mean best position was created by using Copula functions. The simulation results of the test functions show that the improved algorithms outperform the original QPSO algorithm and due to the error gradient information will not be over utilized in square potential well, the particles are easy to jump out of the local optimum, the TC-QSPSO is more suitable to solve the functions with correlative variables.
展开▼