White Papers

Machine Learning Techniques for Extending BIT Coverage to Sensor Faults

April 07, 2017 | BY: Alan Cooke

Download PDF

In this paper, we describe the problem of developing sensor fault detection within airborne instrumentation systems, and solutions based upon machine-learning techniques. We conclude with a report on our proof-of-concept demonstrator, and outline next-steps towards implementation of an autonomous self-diagnostic sensor solution.

Introduction

Good data is key to the success of an instrumentation program, and modern data acquisition systems allow for reliable, high fidelity data capture. Unfortunately, instrumentation programs are often hindered by undetected sensor and wiring problems that can lead to invalid data and inconclusive analysis. Traditionally BIT (builtin test) coverage is limited to the electronic acquisition units and does not extend to sensors and associated wiring.

Many authors have identified sensors and wiring as the weakest link in an entire instrumentation system (e.g. [1], [2]), where the transducer and consistency of the transducer/structure interface can “make or break” a system. Choosing long-life sensors with lifetimes in excess of assets under test is one approach for addressing this problem; however, these high cost and high specification sensors are rarely economically viable. Traditionally for airborne measurement programs, there is a realistic expectation that sensors will be replaced over time, and that dedicated data analysts will be available to spot subtle signs within data, which indicates the onset of sensor/wiring faults. This approach does not scale well for large fleet deployments and does not allow for robust automation.

Figure 1: Confusion Matrix Results

Download our Machine Learning Techniques for Extending BIT Coverage to Sensor Faults White Paper to read more about:

  • Machine Learning
  • Sensor faults
  • Built-in Test

Author Biography for Siobhan Grayson, Insight Centre for Data Analytics

 

Author’s Biography

Alan Cooke

Principal Software Architect


Alan Cooke is Principal Software Architect within the Avionics & Electronics group of Curtiss-Wright. He received his Bachelor of Science in Applied Physics from Dublin City University. Joining Curtiss-Wright in 2000 as a software engineer, he is now closely involved in the design and maintenance of the XidML schema as Principal Software Architect.

Share This Article

  • Share on Linkedin
  • Share on Twitter
  • Share on Facebook
  • Share on Google+
Connect With Curtiss-Wright Connect With Curtiss-Wright Connect With Curtiss-Wright
Sales

CONTACT SALES

Contact our sales team today to learn more about our products and services.

YOUR LOCATION

PRODUCT INFORMATION

Support

GET SUPPORT

Our support team can help answer your questions - contact us today.

REQUEST TYPE

SELECT BY

SELECT Topic