Project Code: 35586
Start date and planned duration: August 2023, 5 months
- 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.
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.
- Oil and Gas
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information, the time-consuming process of manually searching and comparing adhesives, the potential for incomplete or outdated information, and the lack of systematic data analysis to identify trends and correlations.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.