论文信息 - GCHP system optimal predictive control based on RBFNN and APSO algorithm

GCHP system optimal predictive control based on RBFNN and APSO algorithm

Aiming at energy consumption saving problem of ground-coupled heat pump (GCHP) system, a nonlinear optimal control strategy based on adaptive particle swarm optimization (APSO) algorithm and radial basis function neural network (RBFNN) predictive control algorithm is proposed in this paper. This paper firstly utilizes RBFNN for estimating the GCHP system model and forecast the output values, then calculated the optimal control inputs of the GCHP system via the rolling optimization of APSO algorithm. Finally, the simulation results show that this control strategy can efficiently reduce the total energy consumption of the GCHP system.

Zhang Yating | Wang Guiyang | Han Guang

[1] Sen Qun-tai. Multi-steps predictive control of neural networks based on AEPSO optimization , 2007 .

[2] Wei Wu,et al. Convergence analysis of online gradient method for BP neural networks , 2011, Neural Networks.

[3] Alireza Alfi,et al. PSO with Adaptive Mutation and Inertia Weight and Its Application in Parameter Estimation of Dynamic Systems , 2011 .

[4] Mustafa Inalli,et al. Modelling of a vertical ground coupled heat pump system by using artificial neural networks , 2009, Expert Syst. Appl..

[5] Jinhai Yu,et al. A Newly Self-Adaptive Strategy for the PSO , 2008, 2008 Fourth International Conference on Natural Computation.

[6] Xiao Yu,et al. Synthesis of Unequally Spaced Antenna Arrays by Using Inheritance Learning Particle Swarm Optimization , 2011 .

[7] John Moody,et al. Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[8] Kurt Hornik,et al. Convergence of learning algorithms with constant learning rates , 1991, IEEE Trans. Neural Networks.

[9] S. Kalogirou,et al. A new approach using artificial neural networks for determination of the thermodynamic properties of fluid couples , 2005 .

[10] Guang-Bin Huang,et al. Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions , 1998, IEEE Trans. Neural Networks.