Earticle

This paper addresses the problem of the autonomous vehicle storage and retrieval system (AVS/RS) scheduling optimization. AVS/RS relies on rail guide vehicle (RGV) to provide horizontal movement within a tier and uses lifts to provide vertical movement between tiers. Firstly, the process of RGVs’ compound operation is analyzed, and the corresponding mathematical model is established. Then, an improved artificial fish swarm algorithm (IAFSA) is proposed to solve the model. According to the characteristics of the storage and retrieval operation in the system, an encoding and decoding method is designed, which contains RGV task allocation and elevator selection information. The tabu list and the optimal strategy are introduced into this algorithm, coupled with memory action and communication action to avoid the algorithm to trap in local optimal solution. Meanwhile, the adaptive step and visual are used to increase the late convergence of this algorithm. Finally, simulations based on the concrete living example of AVS/RS in a provincial verification center are given.The results obtained by the proposed algorithm are compared with another two optimization algorithm. Analysis shows that the proposed algorithm has the characteristics of fast convergence and the best solution, so as to improve the practicality and robustness of the algorithm.

For the problem with imprecise optimal solution and reduced convergence efficiency of basic artificial fish swarm algorithm (BAFSA) in the late, the adaptive enhanced prey behavior of artificial fish and the segmented adaptive strategy of artificial fish’s view and step were designed. The hybrid adaptive artificial fish swarm algorithm (HAAFSA) was structured by the adaptive enhanced prey behavior and the segmented adaptive strategy of artificial fish’s view and step, which have been verified on research. According to the characteristics of the coalmine rescue environment, the path planning environment model was established in two-dimensional plane and the optimization constraints conditions were disposed by detecting the distance between path sections and barriers. The HAAFSA was applied to coalmine rescue robot path planning. Simulation results showed that the HAAFSA could improve the performance of the optimal path.

Artificial fish-swarm algorithm is a realization model of the swarm intelligence optimization algorithm. It uses the optimization model of imitated nature fish for feeding from top to bottom, clusters and rear, local optimization by individual fish, achieve the purpose of global optimal values highlighted in the groups. RBFNN based on the AFSA can accurately find the optimal solution quickly and ensure the diversity of artificial fish. It is easier to find the global optimal point of optimal fish. This design uses second-order pendulum as a controlled object, using artificial fish swarm algorithm applied to the neural network training algorithms, building design of RBF Neural networks control module , verifing by Matlab simulation of actual control controller performance.