Demonstrating semantic interoperability of diagnostic reasoners via AI-ESTATE

Abstract

The Institute for Electrical and Electronics Engineers (IEEE), through its Standards Coordinating Committee 20 (SCC20), is developing interface standards focusing on Automatic Test System-related elements in cooperation with a Department of Defense (DoD) initiative to define, demonstrate, and mandate such standards. One of these standards-IEEE Std 1232-2002 Artificial Intelligence Exchange and Service Tie to All Test Environments (AI-ESTATE)-has been chosen for demonstration prior to mandate. In this paper, we discuss the results of the first phase of the AI-ESTATE demonstration, focusing on semantic interoperability of diagnostic models. The results of this demonstration successfully showed the effectiveness of semantic modeling in information exchange. In addition, the engineering burden was demonstrated to be manageable: all applications were constructed in less than four months by three graduate students working part time. 1,2 TABLE OF CONTENTS 1. INTRODUCTION.

Implementing AI-ESTATE with prognostic extensions in Java

“…Furthermore, services have been defined for standardized interactions between a test application and a diagnostic reasoner. We demonstrated AI-ESTATE's model exchange and reasoner interoperability in 2008 [6] and 2009 [7], respectively. In our previous work investigating extensions to AI-ESTATE to address requirements for prognostics and health management, we showed how AI-ESTATE can incorporate gray-scale health information.…”

“…The intent of the project was to demonstrate the feasibility of implementing AI-ESTATE in a component-based Automatic Test System (ATS), with the results summarized in [15]. Subsequently, under contract to the US Navy, preliminary versions of the recent standard were implement to demonstrate the validity of both model exchange and service interoperability, with results reported in [6] and [7] respectively. Here, we discuss implementation of the most current version of the standard along with extensions to the BNM and services for prognostics, in order to motivate prognostic extensions such as these to be eventually incorporated into the standard.…”

An AI-ESTATE conformant interface for net-centric diagnostic and prognostic reasoning

“…An early version of AI-ESTATE was evaluated over several phases of a U.S. Air Force funded SBIR to demonstrate the feasibility of implementing the standard in a component-based Automatic Test System (ATS) [4]. Under support from the U.S. Navy, prototype tools were developed and a controlled experiment run to demonstrate the model exchange [5] and service interoperability [6] of the standard across reasoners. A previous iteration of our current project introduced an extension to the Bayesian Network Model (BNM) and services API [7].…”

Distributed embedded condition monitoring systems based on OSA-CBM standard

“…IEEE 1232 standard for Artificial Intelligence Exchange and Service Tie to All Test Environments (AI-ESTATE) is a standard providing a set of formation data specifications to be exchanged between diagnostic reasoners [12]. [13]- [14] However, in CM applications, there are many more data processing steps apart from measurement and reasoning addressed by the IEEE 1451 and AI-ESTATE standards.…”