Papers by Keyword: Knowledge Reasoning

Abstract: A knowledge reasoning based on-line infrared image monitoring system of the power equipments in substation is designed. The function, feature and structure of the system are introduced. Compare with the usual on-line infrared imaging monitoring system, a knowledge base is added and a knowledge reasoning method is used to diagnose the fault mode of operating equipments. The representation method of knowledge and processing of knowledge reasoning engine are introduced. Our research demonstrates that fault can be diagnosed correctly.

Abstract: For the low efficiency and poor accuracy of turbo-generator Unit s fault diagnosis, this paper divided the common 18 kinds of vibration fault into four categories, and took advantage of support vector machine to distinguish the fault cluster for early fault diagnosis according to the characteristics of vibration signal spectrum. For different fault cluster, different fault pattern recognition model was established. With the use of certain symptom group and weighted fuzzy logic, this article engaged in knowledge reasoning to obtain the specific fault recognition mode. Besides, the searching methods of fault cause, fault influence and troubleshooting measures in the knowledge base were proposed, which made the diagnosis process more meticulous and comprehensive. Case analysis shows that it is feasible to use this method to develop a system for intelligent fault diagnosis of turbo-generator unit, which is valuable for further study in more depth.

Abstract: The power source subsystem of satellite is the basic guarantee of the normal orbit for the satellite that provides to energy for the entire satellite. The fault knowledge modeling method for power source subsystem of satellite based on ontology was proposed. Firstly, the failure modes and effects analysis (FMEA) of the power source subsystem of satellite was analyzed, and the fault knowledge was got by extracting key words. Secondly, the ontology of fault knowledge was established. Thirdly, the inference engine based on ontology was realized by analyzing the hierarchical structure of the reasoning system. Only the ontology needs to be created for the fault diagnosis system, which greatly reduces the knowledge creation time.

Abstract: This paper researches cloud knowledge service of supply chain. First the cloud computing technology is introduced. Then the reasons of the cloud computing suitable for knowledge service demand is analyzed. Finally, a knowledge service mode based on cloud knowledge is described.

Abstract: The knowledge reasoning can be used by the inference engine to acquire the implicit knowledge in supply chain,. The reasoning based on the ontology semantic can be directly used the rules and axiom. Four kinds of semantic relations are studied in this paper. Then the Tool of establish reasoning rules is introduced.

Abstract: Intelligent information processing is one of important research parts of knowledge reasoning as well as methods in artificial intelligence. In this paper, the application of classical logic in artificial intelligence for intelligent information processing is mainly studied, and also accurate definitions of mathematical statements are given with logic rules, thus laying a good foundation for the research field of computer intelligent information processing.

Abstract: Because of the universality, complexity and uncertainty of mechanical design knowledge, knowledge reasoning and integration of intelligent design system was one of the difficult problems. The valuation of weight by human was used in many methods for knowledge reasoning at present. In order to make the intelligent product design become more scientific and rational, and eliminate the subjective human factors, a method for reasoning using information entropy was proposed. First, by means of the advantage of the relational database include the redundancy, consistency and integrity, the mechanical product design knowledge base was established. Second, based on the information entropy theory, the weight of each attribute was calculated directly through the objective information. Third, based on the objective data in the original sample, the method for calculating the similarity between accurate attributes and uncertainty attributes and design schemes was given. Finally, this method was verified by fruit picking robot intelligent design system, and the result showed that it is objective and effective.

Abstract: The historical records of mechanical fault contain great amount of important information which is useful to identify the similar fault, but the structural representation and the knowledge reasoning problem are troubled that we use the historical records effectively. Aiming at the problem, the fault knowledge representation based on ontology is put forward out. Firstly, the knowledge characteristics, the ontology building significance and principle of fault are analyzed. Secondly, the fault ontology is defined and described. Finally, the applications of fault diagnosis ontology are studied in protégé. The case study shows that the fault knowledge representation based on ontology is very intuitive and efficient; it can provide us a novel way to deal with the fault diagnosis problem.

Abstract: According to the characters of mechanical product design, product design knowledge is classified into explicit knowledge and indefinite knowledge. A knowledge-driven product design system model was proposed based on the knowledge management. To meet the normal product design process, the design system structure was built on four layers. A mixed knowledge reasoning strategy was proposed, which is combined by design cases, models, and rules. The system provides a public integration interface, so different design tools such as UG NX, Catia and Pro-E can be applied. To resolve the design conflict in product design process, a collaborative design technique was put forward that the CAD, CAPP, CAM engineers worked togeth

Abstract: A remote fault diagnosis method for ultrahigh speeding grinding based on multi-agent is presented. The general faults of ultrahigh speed grinding are analyzed and diagnosis model based on multi-agent is established, the dialogue layer, problem decomposition layer, control layer and problem solving layer in the process of diagnosis are studied and the knowledge reasoning model of fault diagnosis is set up based case-based reasoning (CBR) combining rule-based reasoning (RBR). Based on theoretical research, a remote fault diagnosis system of ultrahigh speed grinding is developed. Results of the system running prove the theory is correctness and the technology is feasibility.