WINS CLIENT SPACE
RVI underground storage tank (UST) inspection (VIDEO)
President Tom Hay presents at Acoustic Emission Working Group (AEWG-54) meeting in Baltimore, MD, May 2012
President Tom Hay delivers talk on NDT Applied to Bridge Inspection at Association for Bridge Construction & Design (ABCD) in Batavia, NY, April 2012
New remote visual inspection (RVI) capability - Video
DOT special permit approval for Acoustic Emission Retesting of 107A tubes
New pipeline inspection technology for Splashtron coated pipes
2013 NDT Training Course Calendar
Pattern Recognition in Non Destructive Testing
This course introduces the practical aspects of pattern recognition. Using WINS NDT's Super ICEPak as a framework, the course covers the theory and applications of statistical pattern recognition and neural networks. This course is suitable for:
- Scientists and Engineers involved in the design and application of signal and image interpretation systems and control systems
- Basic Researchers in the engineering, physical, medical, education, environmental and military sciences who wish to apply advanced signal and image analysis and interpretation methods
- Test Engineers and Technicians looking for faster and more effective ways to develop automated testing and control systems.
Course material covers sufficient theoretical background and necessary terminlogy for trainees with no background in pattern recognition as well.
Course DatesMarch 22-23, 2010
September 9-10, 2010
December 20-21, 2010
This course is also offered by appointment. Please contact us about your dates of convenience.Course LocationThis course is offered at our facility as well as client sites.
Course DurationTwo days (16 hours)Course Price$800 per trainee for group sessions of five or more trainees and $3,000 for individualized company training for up to three persons.Course Outline 1. Overview of Artificial Intelligence 2. Terminology 3. Knowledge-Based Systems 4. When and When Not to use AI 5. Supervised Learning 6. Unsupervised Learning 7. Pattern Recognition Methods 8. Statistical Pattern Classifiers 9. Neural Networks 10. Waveform Representation 11. Waveform Transformations 12. Feature Extraction 13. Feature Set Optimization 14. Image Representation 15. Classifier Design 16. On-line Classification 17. Multi-Channel Data Acquisition 18. System Hardware and Software Design 19. Studies Case