Font Size: a A A

Study On Intelligent Design Of Engine Based On Case-based Reasoning

Posted on:2013-12-22Degree:MasterType:Thesis
Country:ChinaCandidate:K CuiFull Text:PDF
GTID:2248330374981573Subject:Mechanical design and theory
Abstract/Summary:PDF Full Text Request
Engine design is a working process that calculates and analyses the structure and performance parameters of engine according to the uses and requirements, and turns it into specific description as manufacturing basis. It is the key part of engine production, and it determines the quality, cost, and market position of engine products fundamentally. Case-based Reasoning is a kind of intelligent design methods which solves the current design problem based on past examples or experience. CBR includes case-representation, case-retrieval, case-adaptation and case-maintenance four parts. It has a lot of advantages such as simple knowledge-acquisition, convenient system-maintenance, reasonable solving-logic, high solving-efficiency, and self-learning ability, etc. Using CBR in engine design, it can manage the knowledge and experience of engine design more effectively; can use the enterprise production ability of existing equipments more fully; and can make the development cost much lower and the development cycle much shorter. In brief, using CBR in engine design has very important significance and application value for engine design.In CBR technology, case retrieval is the most key technology, and it also is the core to reflect the intellectualization of design. Case retrieval is a case search process whose purpose is to match case from case database, and find out the same or similar cases of solving problem. Case matching based on K-NN is the main means of case retrieval application, and case similarity is the main measure criteria of case retrieval. This article focuses on the retrieval technology of engine intelligent design system, confirms the K-NN technology as the intelligent design retrieval technology. It enumerates a lot of reasonable case similarity calculation method, and puts forward new similarity measurement for some case matching problems. In the article, it puts forward a kind of "preliminary retrieval-reasoning retrieval" retrieval method, which can increase the retrieval efficiency greatly. For the weight-determine problem of the case feature, this article puts forward AHP and GA two kinds of weight-determining technology, using feature numbers as classification principles, and it introduces the principles and realization process steps of this two methods detailed.Combining CBR based on K-NN with the engine design knowledge, this article constructs engine intelligent design system platform framework, and build up the engine of intelligent design system software platform based on Visual Studio2008and SQL Server2005. The engine intelligent design system platform calculation processing module can be divided into the weight-determine module, case-retrieval module, case-maintenance module and case-output module four parts. The platform database includes engine and each part system case database and the case feature weights database two parts. This system platform completes intelligent design work of the engine through the man-machine interactive interface, and the system platform interface contains weight-determine interface, case-reasoning interface, case-adaptation interface, case-maintenance interface and case-output interface five parts. Finally, based on the intelligent design realization process of entire engine and Cooling System as example, this article introduces the realization principle and operation process of engine intelligent design system based on CBR detailed.
Keywords/Search Tags:Engine Design, Intelligent Design, Case-based Reasoning, WeightDetermine, Genetic Algorithm
PDF Full Text Request
Related items