Papers by Keyword: Expert System

Abstract: The tools developed in the design of retaining structures focus mainly on aspects of design and stability analysis of the structural components. We propose in this paper the construction of an information base that serves not only to calculate conventional retaining structures, but can also help in the selection of the optimal type of structure, best suited to the economic and environmental situation of a project. For this purpose, we begin firstly by a general patterning of retaining structures, and then, we conduct a systematic analysis of the retaining structures built in its environment, to detect any kind of existing interaction and interrelation. Structuring and formalizing the derived information is the last step of this work. We present in this paper only an information base that eliminates the bad retaining structures related to the project context.

Abstract: This paper applies the theory of expert system to analysis for relay protection action based on PAS. And it also summarizes various rules according to the experience of operating personals and relay protection personals for several years. All these rules are suitable for 110kV and 66kV regional networks. This paper not only analyzes three-phase current protection, zero-sequence current protection, distance protection etc, but also discusses some special situations such as under voltage lockout over-current protection for transformer, remote backup protection etc.

Abstract: Credit risk is the main risk that Chinese commercial banks are facing. Taking into account three categories of risk factors, namely risk factors of enterprise, risk factors of commercial bank and risk factors of macroscopic economy, an index system was set up. Then, according to the index system and the characteristics of fuzzy neural network and expert system, a credit risk rating system based on fuzzy neural network and expert system was proposed.

Abstract: Information technology includes neural networks, ontology technology, expert system, and so on, and the growth model can predict and manage growth conditions of fruit trees. The traditional expert system has shortcomings of poor self-learning ability, so the improved expert system is used to perform diagnosis of diseases and insects of fruit tree. Firstly the ontology is used to collect related symptoms of diseases and insects of fruit trees, the expert system and neural network are combined to build the prediction model of diseases and insects of fruit tree, then the conclusions of the diagnostic process are regarded as the input neurons and output neurons of neural networks, and are diagnosed by expert, so the prediction models of disease diagnosis of fruit trees are made. The models can implement the function of expert diagnosis and prediction, and provide technical support and management decision for the growth management of fruit tree, greatly improving the diagnosis efficiency of diseases and insects of fruit tree.

Abstract: The objective of this study is to examine the possibility of using DSS in the engineering design of a special group of building constructions: 'cladded roofs'. These are roofs whose cladding is the same as the façade’s, giving buildings a homogeneous appearance. For architectural impression the roof is made of unusual materials and complex structures thus cannot be designed with traditional guidelines. The goal of using DSS is to facilitate and simplify the range of possible materials and structures, to assist and expedite finding the optimal version and to reduce the likelihood of design flaws. In addition to eco-efficiency in production, transportation, and energy consumption of buildings, we hold it to be important to reduce the amount of materials used to a necessary minimum. [1] To achieve this all materials should be used at places where their specific characteristics prevail most effectively. The criteria for applying DSS for ‘cladded roofs’ is the successful structuring of the necessary constructional data and variations. We propose a method to generate numerous proposed solutions and rank them based on their technical performance and value. The result is a kind of 'guided decision-making' which may be an important aid in the design of nonstandard structures.

Abstract: The frame structure of monitoring system is introduced and the network structure of monitoring system is analyzed in this paper. Fault diagnosis expert system is put forward and the fault inference rules are elaborated according to the fault of natural gas compressor of a company. The significance of the system is summarized in the end.

Abstract: The current proposed technologies for fault diagnosis of power system were investigated, including expert system, artificial neural network, optimization methods, and rough set theory. The applicability and characteristics of these technologies for power system fault diagnosis were briefly analyzed and also. The existing flaws and improvements are given. Finally, the recently research status were reviewed and discussed, the key technology issues on and main development trends of the issues are pointed out to motivate the developments.

Abstract: Automobile fault diagnosis is one of the hot issues in detection and diagnosis technology of automobile. The automobile fault has the characteristics of uncertainty and complexity problems. To solve the problems of qualitative description from drivers into quantitative, fuzzy mathematics is introduced. In addition, the fuzzy relationship of automobile fault and fault causes is expressed by setting the membership functions and fuzzy relation matrix. Finally, the qualitative analysis of real cases is present. The fuzzy theory and expert system for automobile fault diagnosis method is proved accurately through the algorithm analysis and real cases.

Abstract: The aim of this work is to build software which enables us to set up an active smart materials data base especially the piezoelectric ones. This is done using two approaches: firstly, by mean of literature, allow the different characteristics we select piezoelectric materials. The second approach consists of selecting the appropriate material according to its usage either as a sensor or as an actuator. The purpose is to provide users an easier way to combine use versus characteristics in an automatic manner. Therefore according to a given application we can overcome the selection difficulties by knowing much more about the materials through their integrated functions when actuating as sensors or actuators. This tool remains also based on an open chart that will permit to the user or developer to update it in concordance with future knowledge of material developments. This work presents the developed software (called ExTooPIEZ’s), its main features and first feed backs gained after first usage.

Abstract: In order to simulate growth and development process of tree, then provide services for production management and scientific research, all kinds of tree growth models are constructed. The paper firstly considers a variety of factors affecting the growth and development of tree, then studies artificial intelligence knowledge such as neural network and expert system, uses the neural expert system to solve the acquisition and management of tree growth parameters, and design and develop tree growth management and expert system based on growth models, the models combine morphogenesis model of tree and knowledge model to provide comprehensive environmental control and management decision-making. Practice has indicated that the growth models of tree can reflect the growth of trees under different physiological and ecological conditions, and visual effect is very good.