This exciting PhD focuses on cutting-edge maintenance management technology.
Recent Artificial Intelligent (AI) advancements have led to a proliferation in the number of sensing, processing and communications tasks. These developments warrant increasingly large amounts of big data. Although this can be readily available via various Industrial Internet of Things (IIoT) sources, it application is not straightforward. This research will first study the evolution of reliability modelling technology and then develop the next generation maintenance technology. The PhD candidate will focus on AI and IIoT based intelligent maintenance to investigate (1) recent machine learning algorithms including probabilistic reliability modelling with deep learning, (2) real-time data collection, transfer, and storage through wireless smart sensors, (3) human-machine interface technologies with visual, audio and olfactory capabilities (4) integration, validation and deployment of machine learning models, (5) field testing with better decision-making.
This project will keep the focus on real-time processing. It will focus on criteria such as learning speed, stability as well as storage and computation requirements of a peripheral device and a processing system. Due to their different operating behaviours and performance considerations, these two types of devices require different designs of learning. Emphasis will be placed on optimisation techniques to speed up the convergence, to better maintain the required maintenance performance in a dynamic system with large variations and to test the algorithm in real-world conditions to validate the simulation results.
The aim of the PhD is to develop the next generation of maintenance technology. It focuses on the following research questions:
In particular, the research questions include:
(1) How to implement the AI algorithms developed in other fields to real-time series data for industrial maintenance?
(2) How to record data from wireless/remote sources that are not continuously connected to the network?
(3) How to store and process data seamlessly?
(4) How to validate models for on-field deployment?
(5) How to optimise decision-making?
Business & Management, Engineering Management
3 years | Full time
Not defined yet
1. Determine AI algorithm implementation complexity requirements;
2. Develop a robustness evaluation strategy;
3. Addressing the technological barriers, i.e., lack of computation, knowledge representation, network performance, interfacing and communication;
4. Validation of the concept in a real-world setting.
At Cranfield, the candidate will be based at the Centre for Digital Engineering and Manufacturing, which hosts cutting-edge simulation and visualisation facilities. The student will have access to high-end computers for simulating the complex nature of maintenance. There will be relevant visits to various organisations throughout the PhD to develop and demonstrate the research.
Candidates should have a minimum of an upper second (2.1) honours degree (or equivalent) preferably in Computer Science/ Mechanical Engineering / Industrial Engineering / Mathematics / Operations Research but candidates in other degrees related to Engineering or related quantitative fields would be considered. Candidates with an MSc degree in these disciplines will be desirable.