NASA SBIR 2002 Solicitation


PROPOSAL NUMBER:02-II H3.09-9224 (For NASA Use Only - Chron: 022775 )
SUBTOPIC TITLE: Spaceport Command, Control, and Monitor Technologies
PROPOSAL TITLE: New and Improved Classifiers for Fault Diagnosis

SMALL BUSINESS CONCERN: (Firm Name, Mail Address, City/State/ZIP, Phone)
Intelligent Automation, Inc.
7519 Standish Place, Suite 200
Rockville , MD   20855 - 2785
(301 ) 294 - 5200

PRINCIPAL INVESTIGATOR/PROJECT MANAGER: (Name, E-mail, Mail Address, City/State/ZIP, Phone)
Chiman Kwan
7519 Standish Place, Suite 200
Rockville , MD   20855 - 2785
(301 ) 222 - 0421

Pattern classifiers are useful for many commercial and military applications such as target recognition, fault diagnostics, pattern recognition, etc. The main goal of this research is to improve the classification performance of existing classifiers. Our proposed architecture consists of two major parts. One is to improve the individual classification performance of each classifier. We propose to apply the latest development in classification theory known as Support Vector Machines (SVM) to improve the accuracy of classifiers. SVM has many attractive advantages. Recent applications include automatic target recognition, breast cancer prognosis, particle identification in high energy physics, etc. Another is to use a robust fusion algorithm called Dempster-Shafer theory to fuse the decisions from different classifiers so that the overall classification performance can be further improved.

During Phase II we will further refine our techniques and take on more challenging problems in chemical vapor concentration estimation and mixture component estimation. We will build a real-time version of our classifier for the e-nose application. We will also work with Boeing engineers to prototype a solenoid valve health monitoring system. Besides, we will extend these applications to a number of additional shuttle components and subsystems, and/or other NASA systems of interest.

The proposed algorithm will be useful for equipment diagnostics. The market for military applications such as Future Combat Systems and Joint Strike Fighters is quite large. It is impossible to determine precisely a market price for the unit we envision, but we expect to market equipment and related services, as well as integration and follow-on consulting. This has been IAI?s preferred business model. In addition, out evolving expertise in this area will lead us to team with other companies eager to apply out skills and technology to their programs and systems.

We also believe that e-noses can be used for mine detection for Army and Marine because explosives are chemicals, too, and can be sniffed and identified by the e-noses.

Other potential applications include NASA systems such as e-nose application for NASA, Main Propulsion System, Thermal Control System, etc. It should be noted the classification and fusion algorithms can be used for target and pattern recognition for geology, law enforcement agency, agriculture, medical applications, fingerprint recognition, face recognition, border and coast patrol. The size of this market is not small and hard to estimate. We expect the aggregate market size will be similar to that of military applications.

In addition, we believe the e-noses can find wide applications such as drug detection and disease diagnosis. Drug detection using e-noses will be certainly beneficial to police while e-nose can provide good assistance to doctors in correctly diagnose some diseases.

As shown in the support letter, Mr. James Engle?s division at Boeing has many systems related NASA. We expect to commercialize directly many NASA systems through Boeing.

Form Printed on 10-03-03 11:34