Research On Intelligent Design System Method Of Precision Seed Metering Device Based On Knowledge

In order to save seeds and increase crop yield,people’s demand for precision seed metering device is increasingly personalized and diversified,forming the characteristics of many styles and weak adaptability of precision seed metering device.In order to solve the problems of low design efficiency,large workload,long development cycle and high cost caused by a large number of complex formula calculation,empirical knowledge and design steps in the design process of precision metering device,this paper is based on the general project of National Natural Science Foundation of China “Research on Intelligent Design method of precision metering device based on knowledge”(51975265).The intelligent design system method of precision seed metering device was studied.The specific research contents and conclusions are as follows:(1)This paper analyzes the design characteristics of precision seed metering device,summarizes the overall design steps,and puts forward the overall framework of intelligent design system of precision seed metering device,which provides a clear idea for the construction of intelligent design system.(2)Collect and sort out the relevant seed metering device design knowledge,and divide the knowledge into rule knowledge,empirical knowledge,case knowledge and descriptive knowledge.In order to transform the acquired knowledge into computer understandable form and study the representation methods of different knowledge types,the hybrid representation method combining production representation and frame representation is used to represent the design knowledge of precision seed metering device.The knowledge base and management system of intelligent design system of precision seed metering device are constructed based on My SQL database.(3)The reasoning algorithm of the intelligent design system of precision seed metering device is studied,and the reasoning module in the intelligent design system is determined to adopt the hybrid algorithm of deductive reasoning and case-based reasoning.The empirical knowledge is regularized by deductive reasoning,and the key parameters of seed metering device are extracted by case-based reasoning as case retrieval parameters.The nearest neighbor algorithm is used to calculate the similarity between the retrieval parameters and the instance parameters,the analytic hierarchy process and the deviation maximization method are used to determine the subjective and objective weight of the retrieval parameters,and the weighted similarity calculation is used to determine the availability of the corresponding instance.(4)According to the design knowledge in the knowledge base,the program driven case model is used to modify and design the retrieved precision metering device.Based on the previous theoretical research,My SQL database is used to store the data sorted out in the early stage and the data generated by the system,determine the user input parameters and formulate the principle that the user independently selects the system to give priority to the selection of seed metering device.The human-computer interaction interface is designed by using visual studio platform,and the intelligent design system of precision seed metering device is developed to make the system link with the database The second development of Solid Works,the operation of inference engine,the parameter design of parts and components and the automatic assembly of parts and components.(5)In order to verify the feasibility and reliability of the intelligent design system of precision seed metering device,three seeds with large shape differences,namely Panax notoginseng,rape and wheat,are selected,and the principle of different systems giving priority to seed metering device is selected,so that the system generates three different precision seed metering devices,which are simulated and verified based on discrete element numerical simulation method.The simulation results show that the single seed filling rate of the three seed metering devices is greater than 90%,and the missing filling rate and recharging rate are less than 5%,which proves that the seed metering device designed by the system fully meets the sowing requirements.