Research On Reconfigurable Intelligent Fault Diagnosis System Based On Immune Mechanism

As a kind of applied systems of AI in fault diagnosis, the intelligence fault diagnosis system gets very good effect in practice, with the gradual complication of the equipment and function of system, which leads to more complicated and exceptional faults, but, it can no longer meet all demand to diagnose fault of complex systems by existing static means. In the dynamic and changeable environment, it can no longer meet demand to diagnose fault used by the existing normal and fix reasoning model, fully utilizing existing or new diagnosis subsystems and other groups obtained, reconfigurable intelligent fault diagnostic system (RIFDS) can fast self-adaptation adjust diagnosis courses, diagnosis functions and diagnosis abilities, which is a research trends on fault diagnosis with a dynamic adaptation ability of fault diagnosis. Taking the national natural science program" Reconfigurable Fault Diagnosis System based on Immune Response Theory ", national defense program" Fault Diagnostic System Research on Launching Rocket Electricity Leakage" and enterprises program" Fault Diagnostic and Prediction System On-line Research on a Excitation Device" as background, On the key problem of diagnostic system reconfiguration, some important topics are lucubrated systematically and deeply in this dissertation including modeling methods for diagnosing system and its course, reasoning model and reconfigurable technology etc., the main contents of the dissertation is as follows: 1. On the basis of analyzing diagnoses basic theories and relevant immunology, the immunology theoretical foundation of reconfigurable fault diagnostic systems are explained, the method of using the immune mechanism of living beings is put forward to reconfigure fault diagnostic systems, by analogy, the shine relation between biological immune systems and RIFDS is established, RIFDS's goals based on immune mechanism are pointed out. 2. From the point of view of system engineering, a complex device system can be decomposed into layers according to its structure and function, and builds analytic model for device systems to describe systems'behavior structure and fault state space, On the base of the shine relation between biological immune systems and RIFDS, inspired by the immune response mechanism, system structure and relevant abstract algorithm, the immune frame of RIFDS is constructed, the software implementation methods based on the component and agent technology are analyzed, a diagnosis business course model is provided easy to reconstructed. 3. As the fundamental unit of reconfigurable diagnostic system, its design means is a base of reconfigurable fault diagnostic, on the basis of analyzing immune information procedure, with the consideration of agent technologies and diagnosis fault in complicated systems, the theory and methods of diagnosis reasoning models are presented, diagnosis reasoning models easy to reconstructed is set up, the technology of this system is described emphatically, the structure models of agents and functions of models are analyzed on detail and the general method is explained to reconstruct diagnosis models based on knowledge. 4. On the idea of learning from exiting diagnosis instances, it is a key factor of weighing the knowledge quality with similarity of experience examples, a new model of knowledge acquisition is designed by concept in immune theory, in which information entropy is adopted as the index of similarity measurement of experience examples, and a immune algorithms is provided to acquire best diagnosis knowledge by optimizing aim function, which validity is shown in knowledge acquisition of some fault instance. 5. On the basis of analyzing main cooperation models among agents and co-evolution with living beings, the mutually promotion and suppression among immune cells can be described as a peculiar immune co-evolution, combined with the diagnosis characteristic of RIFDS, a kind of new evolving diagnosis tactics and system model have been put forward to realize a evolution of multi-agents, self-organization and abruption in the diagnostic system. 6. Taking the consideration of the program" Fault Diagnostic and Prediction System On-line Research on a Excitation Device", applied technology of RIFDS in power systems are studied based on a integration of COM and KQML, a hardware and software structure of the diagnosis system are presented, main components and a work flow in the diagnosis system are analyzed. Summarily, the dissertation does a great deal of work in the aspect of exploiting the RIFDS model based on the immune mechanism and studying their theory and applications, while having acquired some achievements, RIFDS based on immune mechanism in the dissertation is an independent system, with a ability of reconfiguration, the whole integrated system shows its flexibility, quickness and convenience in a fault diagnosis practice, from now on, our research will be focused on studying the process of reconfiguring intelligent fault diagnostic systems.