AdhesiveGPT (AdGPT)

In this section

Back to Core Research Programme AMorph – 4D Printing for Field Morphing Structures Automation of Composite and Hybrid Joining Process Coaxial Wire Additive Manufacturing Processes and In-Line Monitoring Tools Development of Coded Excitation Technique for Non-Metallic Pipes Inspection Development of Digital Twin technology as a demonstrator for real-time integrity assessment of crack growth in tensile specimens Development of Friction Stir Welding (FSW) for Hydrogen Fuel Storage Tanks Development of Leak-Before-Break Hydrogen Storage Composite Pressure Vessels With Polymeric Liner Establishing Assessment Methods for Determining Safe Service Limits of High-Temperature Materials in Extreme Environments Fracture toughness in aggressive environments: effect of crack monitoring techniques on test results In-process detection and non-destructive testing of electron beam weld imperfections Internal Bore Coatings for Applications in Corrosion and Hydrogen Environment Joining of Additively Manufactured Materials Long term behaviour of polymeric liner materials/coatings in hydrogen service Techniques for High Temperature Ultrasonic Inspection of Arc Welding Ultimate Leverage Fund

Project Code: 35586

Start date and planned duration: August 2023, 5 months

Objective

Enhance decision-making through data analysis.
Improve efficiency and accuracy in adhesive selection.
Facilitate knowledge sharing and collaboration.
Advance adhesive selection practices for key industry sectors.

Project Outline

The main idea is to create an adhesive selection tool utilising the power of AI to interrogate a large body of disparate adhesives data and enable a database to be created far quicker and more efficiently than doing so manually. The tool, AdGPT, will enable TWI to directly support its members with adhesive selection requirements in a rapid and cost effective manner.

The tool will be developed using the following approach:

Gathering pertinent data and information on adhesives.
Training a domain-specific Generative Pre-trained Transformer (GPT) model using the resources obtained from step 1.
Generating a comprehensive database of listed adhesives, encompassing adhesive type, properties, application areas, compatibility, performance data, safety ratings, and other pertinent attributes.
Creating a user-friendly graphical user interface (GUI) to facilitate the input of necessary information by users.
Developing the ML program to down select the adhesive.
Validating the AdGPT.

Industry Sectors

- Power

- Aerospace

- Defence

- Transport

- Oil and Gas

- Medical

- Leisure

Benefits to Industry

The proposed knowledge for adhesive selection is not readily deducible due to several limitations. These include the absence of a single source for comprehensive adhesive information, the time-consuming process of manually searching and comparing adhesives, the potential for incomplete or outdated information, and the lack of systematic data analysis to identify trends and correlations.

A database to support adhesive selection is crucial for many industries including automotive, aerospace, and oil and gas. An artificial intelligence (AI)-powered adhesive selection tool is important because it has the potential to offer many benefits including saving time and costs, improving product performance, enhancing productivity, reducing risk and maintenance, fostering innovation, and promoting sustainable practices. TWI will be able to effectively exploit this capability, using it to support member companies with their adhesive bonding requirements.