- Our Company
- News & Events
FDH NDT Research Engineer III, Joshua Scott, will present No Reference Measurements? No Problem! A Machine Learning-Based Approach to Measuring Bolt Tension at the ASME Bolted Joint Reliability Symposium, at 3:45 pm on Thursday, October 27.
In his presentation, Scott examines the use of bi-wave Ultrasonic Testing (UT) to estimate bolt tension without the need for individual unknown bolt lengths or longitudinal time of flight measurements.
This bi-wave approach, combined with sophisticated signal processing and machine learning techniques, measures bolt lengths through a lightweight, easy-to-use tool any technician can use.
Signal processing techniques indicate whether collected data is of sufficient quality, eliminating the need for manual analysis by field technicians. The machine learning approach identifies the bolt coating, correcting any “outlier” data if necessary, and uses a regression model to predict the bolt tension. Finally, developing a longitudinal and shear wave transducer combined with a novel dry couplant further reduces user variation.
Learn more about the event here.
For more information on FDH’s innovative solutions for critical infrastructure or to inquire about participating in field testing, visit FDH’s products page.