Active Diagnosis by Self-Organization: An Approach by The Immune Network Metaphor

We propose a concept of active diagnosis that differs from the conventional passive (i.e. event-driven) diagnosis in temporal (diagnosis is carried out by always monitoring normal condition as opposed to identifying faulty only when abnormal condition is detected) sense as well as spatial (diagnosis is carried out by agents distributed in the sensor network) sense. As one way of realizing active diagnosis, we present immunity-based agents approach based on the self creating, monitoring, and maintaining feature of immune systems. We apply the approach to process diagnosis where the agents are defined on the sensor network. Each agent corresponding to sensor or process constraint evaluates a kind of reliability by communicating other agents. System level recognition of sensor/process fault can be attained by continuously and mutually monitoring and maintaining consistency among sensor values and process constraints. 1 Introduction Diagnosis based on qualitative constraints (expressed by graphically (e.g. [Iri et al. 80; Ishida 88]) or logically) have been studied extensively in several communities. One of the important aspect of diagnosis for dynamical systems (such as processing plants) would be that the abnormal state propagate rapidly through many parts, hence results in the pattern (normal/high/low; oscillation ; stick etc.) of a large number of sensors (syndrome). The first thing to do may be filtering out unimportant sensor pattern and focusing on the key sensor pattern. We used qualitative reasoning to explain one sensor pattern from the other sensor pattern. In the qualitative diagnosis, by checking the consistency among sensor patterns , the sensor pattern that cannot be explained by the other sensor pattern will be focused, as in [Ishida 88]. There already has been proposed using the consistency monitoring and maintenance in the qualitative constraints among sensor values and process knowledge based on the metaphor of immune system [Ishida 90]. The main point of using the immune system metaphor is using agents (corresponding to immune related cells) that interact mutually, continuously, and dynamically. The immunity-based approach, thereby makes the consistency monitoring and maintenance possible in the dynamic environment where on-line data from sensors arrives dynamically. Another important aspect of the immunity-based approach is that it agrees with the concept of active diagnosis presented in this paper and hence it would be one way of realizing the active diagnosis. The concept of active diagnosis may be briefly stated as: diagnosis that is attained by actively and continuously monitoring consistency among the current state and …