Artificial Intelligence is finding its way deeper into product testing and inspection. A new development that may draw metalcasters’ attention stems from a collaboration by GE Aerospace and Waygate Technologies and integrates AI-enhanced software with video borescope devices to improve inspection of turbofan engines. For GE it’s part of an initiative to improve reliability and turnaround time for its engine maintenance and repair network.
Waygate develops non-destructive testing technologies and services, and is well-known for its borescope, radiography, and CT technologies. Borescopes are optical inspection devices that allow an inspector to view conditions within enclosed or inaccessible structures – such as cast valves, pumps, or engine blocks. Of course, borescopes also aid inspection of gas and steam turbines, and the cast parts therein.
And the same technology can be used to inspect machinery and built structures of any type.
The AI-assisted commercial engine borescope solution will be available to Waygate Technologies customers and introduced to GE Aerospace’s MRO network later this year. According to GE, it is the initial result of a Joint Technology Development Agreement that began last year – which initially focused on enhancing machine vision-based, assisted defect recognition (ADR) systems using AI.
High Pressure Compressor (HPC) inspections were targeted specifically, one of the most critical and time-consuming tasks for aircraft engine MRO.
“At GE Aerospace, we increasingly are seeing the value AI technologies are bringing to help improve the speed, accuracy, and reliability of commercial jet engine inspections,” stated Nicole Jenkins, chief MRO engineer.
Jenkins added that GE and Waygate have combined their industry domain knowledge and digital expertise to integrate new AI techniques with data collected by borescopes during MRO, to improve the detection capabilities.
Once GE has adopted the new AI-assisted borescope technology at its MRO shops, it will be used to perform high-pressure compressor (HPC) inspections for GEnx and CFM LEAP engines. “We believe this AI-assisted borescope system will help significantly reduce the time it takes to perform HPC inspections, while delivering high accuracy at the same time,” she said.
Waygate’s general manager for visual products Michael Domke predicted that the combination of GE Aerospace's extensive customer data and its own advanced borescope technologies will be “an extremely valuable optimization for the entire MRO sector.”
GE Aerospace provided Waygate with a comprehensive dataset of engine inspection videos, which resulted in thousands of representative images used to train Waygate Technologies’ gas power-assist ADR model. GE subject-matter expertise was used to ensure accurate data labeling, and Waygate Technologies used that data together with emerging AI techniques (e.g., a “compute-optimized,” object-detection algorithm and a temporal smoothing algorithm) to finalize the new borescope inspection capabilities.
As for the results, compared to the program starting point, GE reported the Waygate devices realized a 33.6% increase in True Positive Rate detection for HPC inspection; along with a 13.5% reduced False Positive Rate. The latter improvement was achieved both by an increased training dataset and the temporal smoothing algorithm used for detection confirmation.
Along with improvements to the gas power-assist ADR model, an automated data anonymization tool was developed – to protect sensitive data, while allowing it to be added to the training dataset efficiently.
New AI-assisted features will be integrated and available for deployment through a software update to customers for Waygate Technologies’ Mentor Visual iQ+ borescope later this year. And GE Aerospace will be introducing the model to its MRO network for inspections of GEnx and CFM LEAP engines. They expect to see both significantly reduced learning curves for new inspectors and assistance in detection of previously difficult to detect defects. “All users of this technology should see an increased probability of detection and a reduction in mental fatigue from inspection,” GE stated.