Postgraduate research opportunities Environmental Digital Twin for Enabling a Circular Economy

Bridging the digital world and physical environment is essential for Industry 4.0, which is a top strategic priority for most technical and manufacturing organisations. The shift towards smart, autonomous systems, fuelled by data and machine learning has many advantages in terms of predictive maintenance, streamlining manufacturing processes and supply chain optimization. These are great for business efficiencies and cost savings, but can it support a greener future?

Conventionally once a product or complex electro-mechanical device has left the manufacturing facility it is no longer the concern of the producer. This is in line with the traditional take-make-dispose economy. As consumers, governments, and legislators are slowly realising, this is an unsustainable consumption model. While models for a circular economy have been around for a while, the understanding within industry of how they are implemented or how advanced digital technology can support the enablement is still not fully understood.

Increasingly manufacturers of complex digital devices are using internal sensors to get a deeper understanding of their products to allow them to understand failures and predict maintenance cycles. For many products it is external factors that influence and impact the reliability of the device, such as intensity of UV light - degrading plastics, dust, and particulates – wearing down or clogging mechanisms, extreme heat or cold – putting severe stress on internal components or increasing power consumption. Having a better understanding of these external environmental factors help to build a much richer picture of the products context.

The project aims to demonstrate through case studies and close collaboration with industry how external digital sensors, collecting contextual data and allowing for inter-product communication can allow manufacturers to gain greater contextual awareness which help increase the remaining useful life (RUL) of a product, predict maintenance cycles, and reduce waste. This effectively repositions a ‘dumb’ product into a data point within a global network.

The principal objectives of the project are:

• Develop a new machine learning approach to establish the first principles around the use of environmental sensing technology and how it can be used to support the circular economy.
• To develop a scalable kit that can be adopted by industry to be integrated into their solutions.
• To gain an in-depth knowledge of the practicalities of implementing a circular business model.
• To implement and evaluate physical and data prototypes in real-world scenarios. These may include basic algorithmic tools that can interface between background data and physical parts/modules.

Further information

Interviews with qualified and promising candidates will be conducted on a rolling basis until the position is filled.