The Particle Swarm Optimization Algorithm Based On Intelligent Decision System Grain Situation Control

Food is not only the people’s livelihood and social development of important strategicmaterials, but also the people the most basic physical infrastructure. China, as a traditionalagricultural-based large population, food security and economic and social sustainable andhealthy development are closely related. The safe storage of food postpartum affect our foodsecurity is one important factor, of which grain situation detection is an important part of safegrain storage.In food during storage, due to their life activities and food grain bulk internal biologicalfactors, non-biological factors such as interaction and changes in the external environment,prone to mildew grain bulk, condensation and other phenomena, leading to food storageduring the Deterioration of the quality and quantity losses. The longer China’s grain reserves(foreign countries are generally less than1year, China is generally2to5years), so ifphysical examination and prediction of grain mass temperature and humidity changes, caneffectively improve the safety of food storage.Grain bulk can be regarded as the internal environment of a nonlinear dynamic system,and neural network model has strong nonlinear mapping ability and flexible network structure.On this basis, the further integration of fuzzy theory and particle swarm theory, put forwardfor the detection of Grain corresponding improvement algorithm.Fuzzy theory and neural networks is proposed based on the idea of Grain fuzzy neuralnetwork intelligent detection algorithm (Fuzzy Neural Networks based Grain EnvironmentsDetection Algorithm, FNNGD). Firstly, grain storage structures using fuzzy neural networkmodel, and according to the model temperature, humidity, tracking and forecasting. Thealgorithm is simple compared with the actual food situation analysis of data, the algorithmcan better detect the slow changes in food conditions, but there the error accumulationphenomenon, rapid changes in the grain situation detection ineffective.To further enhance the effectiveness of Grain detection algorithm and robustness of thispaper, particle swarm theory and neural networks was proposed based on adaptive chaoticparticle swarm Grain Detection (Improved chaotic particle swarm optimization algorithm ofadaptive system, ICPSAS). The chaotic particle swarm algorithm optimizing neural networkweights and thresholds of each layer, adaptive tracking changes in grain situation. Analysisfound that compared with the measured data detection algorithm error is small, fuzzy neural network based intelligent detection algorithm food situation has improved compared to theeffectiveness and robustness, rapid changes in the food situation to them when Make effectivedetection, to achieve real-time intelligent detection Grain.This situation causes for the grain complex, difficult problem detection, combined withneural networks and particle swarm algorithm, two kinds of Grain intelligent detectionalgorithms, to achieve the grain storage temperature, humidity information, adaptive tracking,prediction, provided for managers more scientific decision-making support.