Intelligent and Collaborative Assets for Industrial Manufacturing
Lead Research Organisation:
University of Cambridge
Department Name: Engineering
Abstract
Project Aim:
To propose a feasible (applicable to the real-world manufacturing) methodology for an autonomous factory which will solve the efficiency, information visibility and availability problems in manufacturing and asset management.
Project Objectives:
Explore and exploit current concepts used in Industry 4.0 (i.e. Industrial Internet of Things (IIoT), Digital Twins, Cyber-Physical Systems (CPS), Edge-Cloud Computing, etc.).
Identify the issues in applying current concepts in real-world and their effect on small and medium-sized enterprises (SMEs).
Identify whether the hierarchical model of computer-integrated manufacturing is still suitable to be used with IIoT. If not, propose a new/ updated model.
Design communication and system architectures which enable the assets to share their status with each other in order to achieve a given goal collaboratively.
Identify and propose how to utilise the machine learning algorithms to provide predictive maintenance and analytical decisions to the assets.
Identify and propose how to automatically compute the best strategy for the overall production line and the shop floor in unexpected situations (disruptions and failures), so the assets will autonomously handle the situation.
Develop and evaluate a prototype autonomous factory which incorporates intelligent assets and intelligent processes.
To propose a feasible (applicable to the real-world manufacturing) methodology for an autonomous factory which will solve the efficiency, information visibility and availability problems in manufacturing and asset management.
Project Objectives:
Explore and exploit current concepts used in Industry 4.0 (i.e. Industrial Internet of Things (IIoT), Digital Twins, Cyber-Physical Systems (CPS), Edge-Cloud Computing, etc.).
Identify the issues in applying current concepts in real-world and their effect on small and medium-sized enterprises (SMEs).
Identify whether the hierarchical model of computer-integrated manufacturing is still suitable to be used with IIoT. If not, propose a new/ updated model.
Design communication and system architectures which enable the assets to share their status with each other in order to achieve a given goal collaboratively.
Identify and propose how to utilise the machine learning algorithms to provide predictive maintenance and analytical decisions to the assets.
Identify and propose how to automatically compute the best strategy for the overall production line and the shop floor in unexpected situations (disruptions and failures), so the assets will autonomously handle the situation.
Develop and evaluate a prototype autonomous factory which incorporates intelligent assets and intelligent processes.
Publications
Don Ranasinghe G
(2021)
Prognostics Under the Conditions of Limited Failure Data Availability
Ranasinghe G
(2020)
Using Expert Knowledge to Generate Data for Broadband Line Prognostics Under Limited Failure Data Availability
in IFAC-PapersOnLine
Ranasinghe G
(2019)
A Methodology for Prognostics Under the Conditions of Limited Failure Data Availability
in IEEE Access
Salvador Palau A
(2019)
Collaborative prognostics in Social Asset Networks
in Future Generation Computer Systems
Salvador Palau A
(2019)
Collaborative prognostics in Social Asset Networks
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| EP/N509620/1 | 30/09/2016 | 29/09/2022 | |||
| 1949527 | Studentship | EP/N509620/1 | 30/09/2017 | 30/03/2021 | Gishan Don Ranasinghe |
| Description | The research produced a methodology for predicting equipment failures under the conditions of limited failure data availability. This methodology aims to enable the effective implementation of intelligent and collaborative assets for industrial manufacturing, and hence allows the effective implementation of predictive maintenance for industrial organisations. This enables preventing costs due to under maintenance (e.g. unexpected downtime) and over maintenance of equipment. The research is evaluated on two real-world industrial case studies: (i) BT residential broadband line prognostics under the conditions of limited failure data availability (ii) Scania heavy-truck component prognostics under the conditions of limited failure data availability. It is shown that the proposed methodology has outperformed existing techniques available in the literature by a large margin. |
| Exploitation Route | The academic community could use the methodology for researching and developing effective data-driven models for intelligent and collaborative assets for the prognostics and predictive maintenance application in industrial manufacturing. Industrial organisations could use the published theoretical foundation of the methodology to overcome the problem of limited failure data availability for industrial equipment prognostics. Hence, implement predictive maintenance within their organisations effectively. |
| Sectors | Manufacturing including Industrial Biotechology |
| Description | Collaboration with Scania |
| Organisation | Scania |
| Country | Sweden |
| Sector | Private |
| PI Contribution | This research showed the potential for improving equipment failure prognosis, and was demonstrated using a public dataset published by Scania. This has led to a collaboration agreement with Scania to test the methodology on more truck components. |
| Collaborator Contribution | Scania has shared datasets and access to engineering personnel. |
| Impact | Ongoing partnership. Further results will be published later this year. |
| Start Year | 2019 |