Tarek Maamari

Logic based row and column generation approach for solving integrated airline recovery problem

Airlines face a multitude of disruptions within their day of operations. The options available to them are to prepare for potential disruptions in advance by building in flexibility to their operations, and to respond to disruptions by rapidly finding solutions to bring three key resources together: aircraft, crew, and passengers. This project will investigate the possibility of preparing for potential disruptions in advance, and building integrated methods to search for optimal solutions.  The project is sponsored by Boeing.

 

Supervisor: Alena Puchkova

 

 

Adrien Ruche

Predicting supply chain disruptions in Aerospace

Disruptions in supply chains cost the aerospace industry millions of pounds annually. If potential disruptions could be estimated in advance;  appropriate mitigation mechanisms could be put in place to reduce their impact. In this project the student will work with the DIAL team and the Boeing Company, to apply a set of machine learning algorithms to goods delivery data for predicting supply chain disruptions.

 

Supervisors: Philip Woodall, Alexandra Brintrup, Pascal Wichmann

 

 

Designing resilient supply chains for disaster relief operations                                                   

 

Supervisor: Tariq Masood

 

 

Automated fault classification using machine learning for gas turbine failures

 

Supervisor: Zhenglin Liang

 

 

Anika Mistry

Optimisation of Resource Allocation and Production Sequencing in Off-site Construction

 

Supervisor: Raj Srinivasan

 

 

Barnaby Lloyd

Developing a Model for Automation Maturity: A Universal Method of Assessing the Maturity of Automated Systems

 

Supervisor: Alan Thorne

 

 

Svenja Fischer

Factors influencing the acceptance of self-service data preparation and analytics tools

 

Supervisors: Mohamed Zaki & Philip Woodall

 

 

Vivien Aufort

Optimisation of the production sequence for an off-site construction factory

 

Supervisor: Raj Srinivasan

 

 

Gregory Heidenreich

Optimisation in Farming

The production of agricultural products often involve intervention decisions on the quantity and frequency of watering, use of fertilisers, pesticides and herbicides, which are often determined by weather and disease events. These decisions in turn determine crop yield and have an impact on possible crop rotation. Although traditionally matching demand from wholesalers and these parameters involved tacit knowledge, modelling tools such as optimisation are increasingly considered for structured decision support. This project will consider the feasibility and benefits of optimisation using existing tools on a given range of farming scenarios. The project is sponsored by Gs Growers.

 

Supervisor: Alexandra Brintrup

 

Bas aan de Stegge

Quality analytics

Working with a powder metallurgy producer, this project will explore the use of online data from metrology equipment on the factory floor for to detect early warning signs of quality issues so that appropriate action can be taken during production. To achieve this, we will explore data analytics methods that can capture, filter, and analyse metrology data and convert it into adjustments of a quality inspection plan.

 

Supervisor: Alexandra Brintrup

 

 

Paul Jaccarini

A survey of supply network analytics: Opportunities and Challenges

One of the unifying concepts in Industry 4.0 technologies and capabilities, is the explosion of data in manufacturing.  Supply network data analytics is the science of studying data to discover hidden patterns that yield useful insights for improving supply chain operations. For example, these insights can be used to forecast deliveries, predict quality of goods, estimate the best price for procurement negotiations etc. In this project the student will survey a variety of manufacturing companies to understand what data is being generated and shared with their supply chain, to what extent it is being used and what potential opportunities and challenges exit within the emerging field of supply network data analytics.

 

Supervisor: Alexandra Brintrup