Fault detection, diagnostics, and prognostics: Software agent solutions

Fault diagnosis and prognosis are important tools for the reliability, availability, and survivability of navy all-electric ships (AES). Extending the fault detection and diagnosis into predictive maintenance increases the value of this technology. The traditional diagnosis can be viewed as a single diagnostic agent having a model of the component or the whole system to be diagnosed. This becomes inadequate when the components or system become large, complex, and even distributed as on navy electric ships. For such systems, the software multiagents may offer a solution. A key benefit of software agents is their ability to automatically perform complex tasks in place of human operators. After briefly reviewing traditional fault diagnosis and software agent technologies, this paper discusses how these technologies can be used to support the drastic manning reduction requirements for future navy ships. Examples are given on the existing naval applications and research on detection, diagnostic, and prognostic software agents. Current work on a multiagent system for shipboard power systems is presented as an example of system-level application.