| An expert system (ES) is a computer program that is designed to emulate the logic and reasoning processes that an expert would use to solve a problem in his/her field of expertise, using artificial intelligence technology. The research and application of expert system have become the researching focus of the artificial intelligence of the world. Great benefits have been brought by its application in the fields of agriculture. The strategy of developing intelligent agriculture our government put forward gives intelligent agriculture development an unlimited opportunity.Based on practical need of our country's greenhouse horticulture, the expert system is development in order to solve the problem in practice, which integrates both domestic complexion and international. There are eight subsystems, which named cucumber breed choice, greenhouse choice and building, seeding technique, root management, vegetable adjustment, diagnosis of diseases and insect pests, system help. Specially, cucumber diseases and insect pests-diagnosis expert system (CD1P-ES) is the main content of this paper.(1) Aiming at the character of the cucumber diseases and insect pests diagnosis, database-based rules and other information-base arc designed in this paper. The rule-base with such structure is the result of simulating the information storage and activation of brain information. Operation simple and maintenance easy arc the advantage of the rule-base with such structure.(2) Knowledge representation is the "bottle neck" problem in the development of artificial intelligence. It is also a problem in developing diagnostic expert system for CD1P-ES. In this paper, according to the characters of diagnostic knowledge of diseases and insect pests of cucumber, a knowledge representation method is presented, which represented as IF THEN CF. Signs is a symptoms set of a diseases or a insect pest. Diseases or insect pests represent the name of a set of diseases or insect pests, while every disease or insect pest has its own number of symptoms. CF is the reliability of the diseases and insect pests to be the result of inference when the symptoms arc presented. The sum of CF to a kind of diseases or a kind of insect pest is 100.(3) Based on traditional accurate reasoning and fuzzy reasoning, a new way of inference with both forward and backward chain is presented in the paper. It is the result of simulating experts' thinking during the process of cucumber diseases and insect pests diagnosis. This inference contains two parts. On the first stage, forward chain will be used. A set of hypothesis will be gotten form the information provided by users through the forward chain of this stage. Then the inference mechanism will turn to the second stage to test the hypothesis. Otherwise, the inference will repeat this process.During the whole reasoning process, this research adopt the artifice of numeral between symptom and diseases and insect pests, which denote the intensity connection of them and realize digital diagnosis for this expert system. Thus the expert system realizes dynamic interactive between expert and user. The expert system has more human, efficient, veracious and applicative because it imitate the human's thinking process and the reasoning method partly.(4) Reusing is the base of all scientific research. Expert system of diagnosis for cucumberdiseases share common parts, therefore, if one of such system has been developed, its thought of construction, controls and components can be reused in other expert system's construction. In this paper, some reusing technologies have been discussed, which can be used in the development of diagnostic expert system for any diseases and insect pests of all vegetable.(5) The software of Authorwarc is used to establish the main flow in this expert system. In the CDIP-ES, the language of Visual Basic, Access database and Photoshop arc adopted lo built the subsystem. The running environment of the ES is win98/win2000/winXP. 800*60...
|
PDF Full Text Request