Project Overview
The ChainAI project aims to explore the feasibility of leveraging AI solutions to create custom workflows for SCM that optimise each stage of the process, improving efficiency, effectiveness, and performance in SCM and ultimately enhancing supply chain operations and outcomes.
The project will require a deeper insight into supply chain data to identify key patterns, trends, and opportunities for improvement. By gaining a thorough understanding of the supply chain process at a granular level, the project will pave the way towards producing AI-generated workflows that are tailored to the specific needs at each stage of the process, from planning and sourcing to production.
The project will bridge the gap between traditional SCM and AI-based optimisation. Developing custom workflows with the help of AI-powered data analysis and machine learning algorithms, businesses will gain real-time visibility into their operations, enabling them to identify and address issues before they become problems. The use of AI in SCM will help reduce delivery times and costs, giving them a competitive edge in their industry.
For example, with AI-powered sensors and tracking devices, the project will explore real-time tracking of shipments, to provide businesses with accurate information on the status and location of their goods. This allows businesses to optimise delivery routes and schedules, and ensure timely delivery. Additionally, AI-powered inventory management systems will be investigated to analyse demand patterns, seasonal trends, and other factors to optimise inventory levels thereby minimising stockouts and overstocking, improving overall efficiency in supply chains.
Furthermore, the benefits of ChainAI can be applied across sectors, and look at the feasibility of how this could be implemented within our existing platform to create a digital twin framework for looking at operational insights and multi-party data distribution. This will be based on strict data governance and provenance models, utilising a Public Distributed Ledger technology such as Hedera Hashgraph, coupled with our own data platform called Buttress, which has received Innovate UK funding in the past.
Project Aims
The aim of this project is to explore the feasibility of leveraging AI solutions to create customised workflows for Supply
Chain Management (SCM) that optimise each stage of the supply chain process, improving efficiency, effectiveness, and performance in SCM and ultimately enhancing supply chain operations and outcomes.
To achieve the aim, the following objectives will be addressed during this feasibility study:
- To gain a deeper understanding of the complexities of Supply Chain Management (SCM) and identify patterns, trends, and improvement opportunities in SCM.
- To identify key SCM-related challenges that can be addressed by AI-enabled customised workflows.
- To investigate the role of digital twins and language models in supporting this process.
- To explore the feasibility and develop prototypes (where possible) for workflows that are tailored to the specific needs of each stage of the supply chain process.
- To explore the feasibility and develop prototypes (where possible) and integrate AI algorithms into customised workflows that improve SCM.
- To explore the key factors that influence the adoption and success of AI-enabled customised workflows in supply chain management, and to develop strategies for effectively managing and optimising these factors.
- To evaluate the impact of AI-enabled customised workflows on supply chain performance metrics such as lead time, inventory levels, and order fulfilment, and to investigate how digital twins and language models can be leveraged to improve these metrics.
- To compare the efficiency, effectiveness, and cost of AI-enabled customised workflows to traditional supply chain management approaches, and to investigate the role of digital twins and language models in this comparison.
- To identify and mitigate potential risks and challenges associated with the implementation of AI-enabled customised workflows in supply chain management, and to develop strategies for effectively managing and mitigating these risks, with the support of digital twins and language models where appropriate.
Project Team
Principal Investigator: Dr Vahid Javidroozi, Associate Professor in Smart City Systems
Co-Investigator: Dr Abdel-Rahman Tawil: Professor in Software Engineering
Co-Investigator: Dr Raja Muhammad Atif Azad: Professor of AI
Co-Investigator: Dr Nouh Sabri Elmitwally: Lecturer in data science