Advertisement
Published in:
2023 | OriginalPaper | Chapter
A State Tracing Method for the System Data Obeying Poisson Distribution
Authors : Shuto Tanabashi, Yuto Torisaka, Yasuhiko Takemoto, Ikuo Arizono
Published in: Intelligent and Transformative Production in Pandemic Times
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
In the case that abnormality in a state of systems is found, identifying when the state in the system changed, that is, identifying the change-point is helpful to investigating the cause of the system abnormality and dealing with it. In our research, a method of identifying change-points and tracing the system state has been discussed based on the data from the system, when the characteristic values representing the system state obey the Poisson distribution. Specifically, based on the likelihood theory and information statistics, a method of selecting the best statistical model for explaining the state changes of the system has been proposed as the state transition tracing method. Then, the effectiveness of the proposed state tracing method has been verified through numerical simulation. In addition, an application example of inferring the cause of state changes from the outcome of our proposed method has been shown.