基于微粒群算法的大豆生育期内有限水量的最优分配

Optimal distribution of the limited water in growth period of soybean based on particle swarm optimization

粒子群优化算法(PSO)是基于群体智能理论的优化算法。该算法利用生物群体内个体的合作与竞争等复杂性行为产生群体智能,对解空间进行智能搜索,从而发现最优解。通过水肥互作盆栽试验,应用Jensen模型对大豆水分生产函数进行拟合,计算出不同氮肥条件下的各生育阶段的水分敏感指数。利用PSO收敛速度快、预测精度高等优势,建立一种大豆灌水量优化分配模型,旨在准确预测大豆灌水量。结果表明,粒子群算法应用于灌溉制度优化中是可行的,既拓宽了PSO应用领域,又为制定合理的灌溉制度与提高水分利用效率提供新思路。

Particle Swarm Optimization （PSO） algorithm is based on swarm intelligence theory. The algorithm can search the solution space intelligently and find out the best solution, through intelligence generated from complex activities such as cooperation and competition among individuals in the biologic colony. Through the interaction between fertilizer and water means of the pot - grown experiment, using Jensen model to calculate the Soybean - water Production Functions, calculating the different N fertilizer of water sensitive index during soybean each growth period. In order to provide foundation for predicting the irrigation water of soybean, using the advantage of fast convergence speed and high forecasting precision of PSO to establish a model for optimum distributing irrigation water of soybean. Results showed that PSO model was feasible for irrigation schedule, expanding the application areas of PSO model and providing a new way for making scientific irrigation schedule and heighten the water use efficiency.