Helping to Rebuild Houston's Inner-city Communities, One Step at a Time.

Menu:

Research and Development at GCS

IDS - Intelligent Diagnostic System

IDS (Intelligent Diagnostic System) was developed under a NASA SBIR Phase II grant for next generation spacecraft system health monitoring and control. The system is also called FLIDS. Designed as a general-purpose system, it can be used for many monitoring/diagnosis applications. Initiatied with human expert knowledge about a specific application system and connected to that system's measurement data, IDS draws optimal diagnostic conclusions based on the information available. It is designed for large, complex application systems, and can be used for both real-time and non-real time situations.

IDS consists of inference engines and a knowledge base. Three types of inference paradigms are used: a fuzzy logic engine using fuzzified maximum flow algorithm, a rule conversion engine, and a modular neural network engine. The user can enter knowledge in the form of connection relationships, data fuzzy membership functions, and linguistic rules. Also the system can take historical data for neural network training. The outputs of inference engines are optimized. Online learning can be performed using neural networks and reinforcement learning.

Simulation and Test Systems for Testing Avionics Software

Over the preceding seven years, GCS has provided computer and software integration skills on a variety of projects to produce embedded, real-time software validation systems. This work began with a system for verifying space station software and has been delivered for use in Independent Verification and Validation (IV&V) of all space station flight software components.