Plant control systems are characterized by complexity and fuzziness. Genetic algorithm is one of the combinational optimization techniques for complex systems, which utilized genetic operations such as crossover and mutation.The present work is attempted to apply genetic algorithm and artificial neural network to the optimal control problem for intermittent solution supply in deep hydroponic system. The neural network is used for constructing dynamic model of net photosynthetic rate to drainage and supply in the intermittent solution supply, and the genetic algorithm is used for searching optimal value from numerous responses simulated by the model. The optimal control problem in the present study is to decide 4-step combinational times of the drainage and supply (t1, t2, t3 and t4), which maximize the net photosynthetic rate of the plant.By applying genetic operations, we could obtain optimal value easily. In this case, the degree of reaching optimal value (evolution speed) is closely related to crossover rate and mutation rate. Higher the both values increased the evolution speed. For example, when the crossover rate (Pc) and mutation rate (Pm) are respectively equal to 0.8 and 0.8, the optimal value can be obtained within 5-generation. However, lowered the both values caused significant delay of evolution speed. In this case, however, the optimal value can be successfully obtained.Thus, it was found that the genetic algorithm is very powerful tool for finding the optimal value of objective function contains numerous variables. It seemed that the combination of genetic algorithm and neural network allows available control for growth optimization.
[1]
Yasushi Hashimoto,et al.
Identification and Control of Hydroponic System in Greenhouses
,
1985
.
[2]
Yasushi Hashimoto.
Computer integrated plant growth factory for agriculture and horticulture
,
1991
.
[3]
Tetsuo Morimoto,et al.
Application of fuzzy logic and neural network to the process control of solution ph in deep hydroponic culture
,
1991
.
[4]
F.-C. Chen,et al.
Back-propagation neural networks for nonlinear self-tuning adaptive control
,
1990,
IEEE Control Systems Magazine.
[5]
John J. Grefenstette,et al.
Optimization of Control Parameters for Genetic Algorithms
,
1986,
IEEE Transactions on Systems, Man, and Cybernetics.
[6]
Tetsuo Morimoto,et al.
Identification of Hydroponics in an Advanced Control System of the Greenhouse
,
1992
.
[7]
Kumpati S. Narendra,et al.
Identification and control of dynamical systems using neural networks
,
1990,
IEEE Trans. Neural Networks.
[8]
橋本 康,et al.
Mathematical and control applications in agriculture and horticulture : proceedings of the IFAC/ISHS workshop, Matsuyama, Japan, 30 September-3 October 1991
,
1991
.
[9]
Yasushi Hashimoto,et al.
ENVIRONMENTAL CONTROL FOR PLANT GROWTH IN PLANT FACTORY OPERATION AND GREENHOUSE MANAGEMENT FROM PHYSIOLOGICAL VIEWPOINT
,
1991
.