Fault diagnosis expert system based on decision tree for industrial Ethernet network

A network failure and expert system technology, applied in transmission systems, digital transmission systems, data exchange networks, etc., can solve the problems that the complexity and accuracy of mathematical models cannot meet the real-time requirements of high-speed networks, and the actual control effect is not satisfactory.

CN104506338AInactive Publication Date: 2015-04-08CHINA TOBACCO HENAN IND
2 Cites 44 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2015-04-08
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a fault diagnosis expert system based on a decision tree for an industrial Ethernet network. Firstly, an expert system comprising a knowledge base, an inference engine, a knowledge base management module, a knowledge acquisition module, an explanation facility and a control center is established; secondly, the knowledge base is utilized to contact the inference engine and the control center to obtain data required by the modules for storing a diagnosis rule, various pieces of data of the system and an intermediate result generated during the system diagnosis period; thirdly, comparison, commonly called as matching, is carried out between a condition part of a rule base and a content of a global data base through the inference engine, if matching is successful, a conclusion part is displayed, the global data base is modified according to an action part of an enable rule, the changed global data base can trigger a new rule, so that problem solving proceeds to the next state, and so forth, one problem is finally solved; and lastly, post processing is carried out through the inference engine, a new knowledge base is updated by the control center, so that the expert system is gradually improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of industrial Ethernet control systems, in particular to a decision tree-based industrial Ethernet network fault diagnosis expert system. Background technique

[0002] PROFINET, launched by PROFIBUS International (PI), is a new generation of automation bus standard based on industrial Ethernet technology. As a strategic technological innovation, PROFINET provides a complete network solution for the field of automation communication, covering hot topics in the field of automation such as real-time Ethernet, motion control, distributed automation, fail-safe and network security, etc. And, as a cross-supplier technology, it can be fully compatible with industrial Ethernet and existing fieldbus (such as PROFIBUS) technology to protect existing investment.

[0003] Over the past few years, industrial machine networks have experienced explosive growth in size. The application of the network has penetrated into e...

Examples

Embodiment Construction

[0038] Such as figure 1 As shown, the present invention includes a knowledge base, an inference engine, a knowledge base management module, a knowledge acquisition module, an explanation machine and a control center;

[0039] The knowledge base includes a global database and a rule base, the global database is a set of symbols describing process objects, and is used for problem description and environment description; the rule base is composed of a set of diagnostic rules, and the set of diagnostic rules A rule includes a conditional part and a conclusion part. The conditional part is a premise assertion about some data in the global database, and the conclusion part is the cause of this premise assertion or a similar premise that this premise assertion will occur in the future;

[0040] The inference engine is based on the design of decision tree reasoning. The decision tree includes decision attribute nodes, attribute value branches and leaf nodes. The decision attribute nod...