UAV Interview with Ian Risk, CFMS
AVIPEO.COM had the chance to chat with Ian Risk, CTO at CFMS about artificial intelligence, computer vision and automated aircraft inspection.
About the interview partner
The Centre for Modelling & Simulation (CFMS) is a growing, not-for-profit specialist in digital engineering capability. Based in Bristol, UK, it's vision is to be the recognised, independent and trusted, digital test bed for the design of high value engineering products and processes.
Ian Risk is Chief Technology Officer (CTO) at CFMS, and is responsible for evolving the company's technical vision and leading all aspects of technology development according to its strategic direction and growth objectives. With 40 years experience in the aerospace sector, Ian has held a number of senior positions throughout his career at Airbus and British Aerospace with a demonstrable track record in technology innovation and research and development.
AVIPEO.COM had the chance to chat with Ian Risk about CFMS and its innovative services:
Your company has developed a concept for autonomous inspection for aircraft. Could you explain us the idea in three or four sentences?
Artificial Intelligence (AI) provides an opportunity to introduce innovation and new technology to all aspects of visual inspection whether in manufacturing or maintenance operations offering a more cost effective solution in often challenging environments. CFMS has produced a demonstrator that uses a combination of computer vision and AI technologies to show how the manual inspection process can be automated using images captured by a camera mounted on a drone or crawling robot.
Do you develop the entire product including the drone and the camera or do you provide only the software?
CFMS has developed the AI technology used, which can analyse video footage regardless of how it is collected. In the use case demonstrator being showcased, a drone with a mounted camera has been used to film video footage of an aircraft wing, to identify faults and non-conformant quality and performance.
What kind of technology do you use for your product?
The AI modules are fed with a series of images as an input, and processed with Convolutional Neural Networks (CNN) which are trained to learn the “rules for feature identification automatically” (rather than explicitly programmed rules) and identify objects (e.g. bolts, brackets etc.) and/or defects (e.g. corrosion, damage etc.) irrespective of their position or orientation in a real world inspection scenario.
What were the main challenges in the development of your technology?
The main challenge is the same for any data science project, capturing as sufficiently large data source to ensure reliability of any classifications made by the AI module. This means capturing and processing large numbers of images in order to train the algorithms. It is a lengthy process but the results demonstrate that even with a relatively small data set viable results can be achieved.
Airlines like Easyjet already tested drones for their maintenance procedures. How can your product help airlines or MRO companies in their work? What kind of use cases do you have for your products?
Visual Inspection is routinely carried out across aerospace to determine whether a structure, product, component or process meets the specified requirements. Typical examples include the detection of product defects in-service or during maintenance and as point of manufacturing in-process monitoring. There are a number of challenges associated with visual inspection such as accessibility constraints (height, confined space, hazardous environment etc.), increased susceptibility to human error (in the case of repetitive high frequency visual inspections) and recurring labour costs. Moreover, in industry the visual inspection activity is classified as essential but a non-value add step in the process. You can view the use case demonstrator of an aircraft wing, which is being filmed to identify faults and non-conformant quality and performance.
Does your product aim at an automated maintenance procedure? From your point of view: Which impact on maintenance procedures will Artificial Intelligence have in the next years?
Moreover, in industry the visual inspection activity is classified as essential but a non-value add step in the process of maintenance. Automated Inspection technology offers a range of benefits, and provides a more efficient and streamlined solution for inspecting difficult to access or hazardous environment and areas. It reduces both the inspection time, and the cost of inspection while increasing output and productivity, enabling the standardisation and automation of documenting assets, e.g. for condition of supply documentation. Over the coming years, automated inspection technology will significantly benefit high value manufacturing, maintenance, repair and operations, in aerospace, automotive, construction and energy sectors, where visual inspection is highly utilised.
What is your business model with this technology?
Access to the AI technology modules developed is available to UK industry organisations on a commercial basis. CFMS digital test bed provides a trusted, secure environment for the development and testing of new technologies such as AI ensuring the protection of sensitive data. CFMS is able to offer a range of skills, expertise and access to technologies that help enterprises go through the current journey of technological transformation in a seamless way; to first help them identify opportunities for AI-related topologies within their own businesses, and to do so with minimum impact and maximum benefit.
What are your plans for the next three years? Where do you see your company in three years from now?
With industry sectors being pressed to produce more complex products in ever reducing timescales, all stand to benefit from digitalisation. While this puts pressure on reducing the use of physical prototypes, it does motivate companies to investigate how they can transform products and processes. They not only stand to benefit from accelerated turnaround times, but will have a wider range of options available for consideration early in the design cycle that can visualise potential outcomes and return on investment.
For CFMS, the opportunity for growth is extremely positive. The company is part way through an expansion plan that will see the business grow significantly, focusing on the wider high value design engineering market. It’s a very exciting time to be in this sector.
Thank you very much for this interesting interview, Mr. Risk.
Source © AVIPEO.COM