Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Object-oriented analysis and design with applications (2nd ed.)
Object-oriented analysis and design with applications (2nd ed.)
| Hi-index | 0.00 |
This paper describes an intelligent system which detects the location of troubles in a local telephone cable network. Such a task is very challenging, tedious, and requires human experts with years of experience and high analytical skills. Our system captures the expertise and knowledge required for this task, along with automated access to database systems, so that the system can help a human analyst to pin-point network trouble location more efficiently and accurately, ultimately reducing the cost of maintenance and repair. The system utilizes probabilistic reasoning techniques and logical operators to determine which plant component has the highest failure probability. This is achieved by building a topology of the local cable network, constructing a causal net which contains belief of failure for each plant component, given their current status, history data, cable pair distribution, and connectivity to other components. The Trouble Localization (TL) Module described in this paper is a crucial part of a larger system: Outside Plant Analysis System (OPAS) which has been deployed Statewide for over nine months at Pacific Bell PMAC centers. The TL system module utilizes AI and Object-Oriented technology. It is implemented in C++ on Unix workstations, and its graphical user interface is in an X Window environment.