Ant colony optimization and stochastic gradient descent
Artificial Life
Ant colony system: a cooperative learning approach to the traveling salesman problem
IEEE Transactions on Evolutionary Computation
Application of Ant Colony System to an Experimental Propeller Setup
ICIC '08 Proceedings of the 4th international conference on Intelligent Computing: Advanced Intelligent Computing Theories and Applications - with Aspects of Theoretical and Methodological Issues
Hi-index | 0.00 |
Based on the modified ant colony system (ACS) algorithm, a novel design method for nonlinear PID controller with on-line optimal self-tuning gains is proposed. In this method, first the regulative laws of the three PID controller gains are designed respectively, which are three nonlinear functions of system error and its variation rate, and then the proposed modified ACS algorithm is used to optimize the nine parameters in the three nonlinear functions. The designed controller is called the ACS-NPID controller and was used to control the CIP-I intelligent leg prosthesis. The simulation experiments demonstrated that the ACS-NPID controller has better control performance compared with other three linear PID controllers designed respectively by the differential evolution algorithm, the real-coded genetic algorithm, and the simulated annealing. The simulation results also verified that the modified ACS algorithm has good performance in convergence speed and solution variation characteristic.