A semantic infrastructure for advanced manufacturing

Lead Research Organisation: University of Huddersfield
Department Name: Sch of Computing and Engineering

Abstract

We are stepping into a new era of digitalisation. In this new era machines will communicate and exchange large amounts of data to ensure they can work harmoniously and collaboratively with little human intervention. Current machines use symbolic language to represent the data, but they cannot directly interpret its meaning. As a result, information loss and incorrect interpretation can often happen during communication. To improve manufacturing intelligence, we need the manufacturing system to "understand" the data, which we refer to as "semantics" of the data. If the manufacturing system can be represented at a semantic level, the data will become knowledge to the machine and enable it to be ready for exchange, interrogation and reuse. There is current work taking place to upgrade manufacturing systems to a semantic level but this is still at an early and enabling stage. This fellowship aims to effect a step change in manufacturing intelligence, to support rigorous semantic exchanges between different manufacturing phases, and to allow formalisation and reuse of new/existing knowledge from advanced manufacturing.

The proposed research will build a novel semantic infrastructure for advanced manufacturing by supporting knowledge representation, interrogation, reasoning and exchange for smart design, manufacturing and measurement of advanced products. The focus will be on the development of a toolbox to formalise knowledge in/between design, manufacturing and measurement, especially for additive manufacturing (AM). The resulting semantic infrastructure will allow the machine to "interpret" the meaning of the data/information. To be more specific: how the design parameters (geometries, tolerances and materials) are related to each other; how the design parameters relate with the AM process/post process parameters (layer thickness, build orientation); and how the design and process parameters contribute to the measurement details (methods, calibration, etc.). The work will provide a new universal language for any data/information involved in a manufacturing value chain, and will permit a comprehensive infrastructure to digitalise the fast growing AM industry.

Planned Impact

It is expected that the proposed work will have economic impact as well as benefiting industrial and academic communities. The novel semantic infrastructure will provide a smart language to formalise AM knowledge at different stages, providing a well-suited knowledge management tool to enable right-first-time AM production. The proposed technology may open an untraveled path in providing a smart toolbox to enable designers, AM engineers and inspectors to truly communicate with each other in an intelligent, robust and productive way.

Working closely with industry partners (Reliance Precision, Renishaw and NPL) the proposed programme will develop customised knowledge blocks to support decision-making and semantic exchange. Using the industry partner's expertise in AM design, process/post process control and measurement solutions as an input, customised knowledge blocks can then be developed using the semantic toolbox. The developed semantic exchange protocol will ensure that the knowledge blocks can be exchanged between different production stages. Equipped with the developed reasoning mechanism, AM designers and engineers can interrogate the knowledge blocks to retrieve answers such as how each design parameter is related with specific process parameters, and how to choose the series of measurement parameters from the specification. It will also enable an accurate interpretation from the design semantics to the process control semantics, and from the design semantics to the measurement semantics. Right-first-time of designing and process parameters can then be ensured, therefore greatly reducing power usage and failure rate, lowering the cost of production and making a more environmentally-friendly manufacturing technology. It is also expected that the developed semantic infrastructure will facilitate a quicker adoption for SME's in manufacturing, as the development of customised knowledge blocks will reduce the cost of employing skilled and experienced AM designers, engineers and inspectors of which there is a national and shortage.

Advanced manufacturing and industrial digital technologies will directly benefit from the novel semantic infrastructure. The proposed work will also be beneficial to those in the interdisciplinary areas where advanced informatics is applied in different disciplines such as biological informatics, chemical informatics, healthcare informatics and smart cities. To demonstrate the great potential of the semantic infrastructure to a wider academic community, visits to academic partners (University of Sheffield, Huazhong University of Science and Technology, China) are planned to exchange expertise and share knowledge. Throughout the duration of the fellowship, academic engagement and dissemination activities such as publications in multidisciplinary journals, presentations at conferences, seminars and workshops are scheduled.

To promote the general public's understanding of our research and how the research will impact the economy, the PI and team will engage with the general public via hosting workshops, presenting our research outputs at public research activities at UoH, seeking media opportunities through UoH's Press Office, and sharing our research highlights and vision through the Women in Science and Engineering (WISE) network, LinkedIn and other engineering and science news bulletins.

Publications

10 25 50
publication icon
Pagani L (2020) Characterisation of diamond abrasive grains of grinding tools using industrial X-ray computed tomography in The International Journal of Advanced Manufacturing Technology

publication icon
Shi P (2020) Intersecting machining feature localisation and recognition via single shot multibox detector in IEEE Transactions on Industrial Informatics

 
Description A prototype of smart semantic toolbox, named CatLab has been developed. During the last one and half years, particular focus was directed to the development of two semantic libraries for object level and category level (Task 1); basic categorical laws have been applied to develop semantics for objects, morphisms, morphism structures and categories; a set of reasoning rules and algorithms of how and when to apply the rules (Task 3) for object level and category level. The focus was later directed to the development of an initial user-interface (UI) for semantic libraries and the knowledge reasoning rules. The current version of CatLab v0.0, is under continues development, including the before mentioned UI for reasoning, and a graphic UI for objects, morphisms and morphism structures.
New research methods were also applied. For example, a deep neural network framework based on multiple sectional view representation name MsvNet has been proposed to automatically recognise both single and multi-features of a 3D model, and multiple criteria decision-making technologies based on fuzzy set have been used to determine the optimal build orientation for additive manufacturing.
We have recently developed a new collaboration with NIST (National Institute of Science and Technology of USA). Together we are developing a new version of smart information system for profile surface texture. We are having regular meetings with the NIST group since November.
Exploitation Route Working closely with industry partners (Renishaw, Reliance Precision and NPL) the programme will develop customised knowledge blocks to support decision-making and semantic exchange. Using the industry partner's expertise in AM design, process/post process control and measurement solutions as an input, customised knowledge blocks can then be developed using the semantic toolbox.
Part of the Pathways to Impact activities will focus on academic engagement and dissemination within the digital manufacturing communities, and various visit to academic partners are planned. The research team will attend national and international advanced manufacturing related conferences to disseminate research findings through oral presentations and posters. The group will also participate in seminars and workshops led by AM companies and academics. Further research results will be presented to manufacturing/metrology networks, engineering and science society news bulletins.
Sectors Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Healthcare,Manufacturing, including Industrial Biotechology,Pharmaceuticals and Medical Biotechnology

 
Description Huazhong University of Science and Technology 
Organisation Huazhong University of Science and Technology
Country China 
Sector Academic/University 
PI Contribution Technical expertise
Collaborator Contribution Case studies, knowledge and data
Impact N/A
Start Year 2019
 
Description National Institute of Standards & Technology (NIST) 
Organisation National Institute of Standards & Technology (NIST)
Country United States 
Sector Public 
PI Contribution Our expertise on implementing category theory into a semantic language, and applying it on real cases in engineering, especially on surface texture design and measurement.
Collaborator Contribution Their expertise of category theory (mathematician), and application experience on system modelling.
Impact Expected outcome: 1. A new version of a smart surface texture information system to be developed jointly with NIST. 2. A joint research paper entitle "category theory for metrology". The goal of this paper was to combine the work of Huddersfield work on CSL with the CQL. The idea is to show use of CT at different levels of the problem of verifying the geometric specification for the manufactured part. 3. Joint research project to be proposed. This is indeed a multi-disciplinary collaboration, which brings researchers from manufacturing, mathematics, computer science and system engineering.
Start Year 2019
 
Description National Physical Laboratory NPL 
Organisation National Physical Laboratory
Country United Kingdom 
Sector Academic/University 
PI Contribution Technical expertise
Collaborator Contribution Input into the research direction for the PDRA and PhD students; Hosing one or more researchers at NPL for up to one month; Case studies and data; Testing of toolbox components; Aligned and complementary research and development.
Impact Data science, manufacturing
Start Year 2019
 
Description Reliance 
Organisation Reliance Precision Limited
Country United Kingdom 
Sector Private 
PI Contribution Technical expertise
Collaborator Contribution Case studies, provide advice and knowledge.
Impact N/A
Start Year 2019
 
Description Renishaw 
Organisation Renishaw PLC
Country United Kingdom 
Sector Private 
PI Contribution Technical expertise
Collaborator Contribution Cade studies on Additive manufacturing, training of AM machines.
Impact Additive manufacturing
Start Year 2019
 
Description The Polytechnic University of Milan 
Organisation Polytechnic University of Milan
Country Italy 
Sector Academic/University 
PI Contribution Our expertise on a smart semantic language, and the development of smart databases on manufacturing.
Collaborator Contribution Their expertise of onotology-based factory data model, and rich experience on factory case studies.
Impact We are currently working on a joint paper on "A coherent synchronisation of data model in manufacturing using delta lenses".
Start Year 2019
 
Description University of Sheffield 
Organisation University of Sheffield
Country United Kingdom 
Sector Academic/University 
PI Contribution Technical expertise
Collaborator Contribution Technical expertise, case studies.
Impact Manufacturing
Start Year 2019
 
Description Applied Category Theory Conference 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact This was our first academic conference on applied category theory, in which the majority participants were mathematicians and computer scientists. We discovered how category theory was applied in mathematics and computer science, mostly in programming and artificial intelligence. We have also demonstrated our application case in engineering, which of interest to many mathematicians who is seeking a real world application of category theory.
Year(s) Of Engagement Activity 2019
URL http://www.cs.ox.ac.uk/ACT2019/
 
Description Collaboration meeting with NPL 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Group of two (Dr Qunfen Qi and Mr Yuchu Qin) have had a two days intensive meeting with Data Science Group at NPL (including seven member), to discuss collaborative research related to smart database, ontology and category semantic language. Prof Alistair Forbes has NPL's current vision of "Data Science for Metrology", and Dr Qunfen Qi has presented on "COL and its Applications". Both parties shared a common interest in the strong expressiveness of COL and its great potential in representing data/information/knowledge in metrology. Further actions were then planed, including organising a joint workshop by NPL, UoH, University of Strathclyde and the Alan Turing Institute; further engagement between NPL and UoH; introduction to the British Computer Society, etc.
Year(s) Of Engagement Activity 2019
 
Description Collaboration meeting with Renishaw 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact A group of six met at Renishaw's headquarter (Wotton-under-Edge). Both parties have demonstrated and introduced related work. An in-depth discussion was carried out to explore possible use of the categorical semantics in Design for Manufacture (DfM) group of Renishaw.
Year(s) Of Engagement Activity 2018
 
Description Collaboration visit from Northwestern University, USA 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact A group of three academics (Prof Jian Cao, Prof Kornel Ehmann and Dr Ping Guo) from Northwestern University have had a formal academic visit for three days to our research group. Prof Cao has introduced their work on flexible MFG systems; Prof Kornel has introduced their work on surface engineering; Dr Guo has introduced their work on structural coloration and levitation. From the Huddersfield side, Prof Jiang has introduced our Hub and research theme; Dr Qunfen Qi has introduced her work on Category Semantics and its applications; Dr Tong has introduced their group work on nano manufacturing. We then subsequently discussed on collaborations and exchange.
Year(s) Of Engagement Activity 2019
 
Description EPSRC Women in Engineering Society member's Inaugural Workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact This was the first EPSRC WES member's meeting, also the first similar type of meeting EPSRC has ever held. During the meeting, Katherine from the WES given a brief introduction of WES and its different types of events. Then the new head of ED&I from RAEng Poly given a brief report of ED&I (many statistics are enclosed), and introduction of a set of toolkit that RAEng has developed regarding ED&I issues. After that Laura from EPSRC given a brief report of ED&I policy and stat in the EPSRC.
After that, each member given a mini presentation (15 mins) to introduce themselves; what have you done so far in the EDI field, including any activity since/resulting from having been awarded the membership? Why did you get involved with the EPSRC WES call? What are you planning to achieve with your membership? There were in total nine members from University of Bristol, Coventry University, University of Leeds, University of Nottingham, University of Surrey and University of Huddersfield.
Year(s) Of Engagement Activity 2019
 
Description ISO TC/213 Chairman Iain Macleod visit Huddersfield 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Industry/Business
Results and Impact Iain Macleod, the chairman of ISO Technical Committee 213, which is responsible for international standards for Geometrical Tolerancing and Geometrical Product Specification, visited our research group. We have represented our work, and discussed possibilities of introduce of our work to ISO committee.
Year(s) Of Engagement Activity 2019
 
Description Interview for a online research story 
Form Of Engagement Activity A magazine, newsletter or online publication
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Media (as a channel to the public)
Results and Impact Me and Dr Luca Pagani were interviewed by John Ramsdin, our public relations manager from the University. John will write a story about our conference paper at the 15th CIRP Conference on Computer Aided Tolerancing - CIRP CAT 2018, which was taken place at Milan, Italy. The story has sparked many interest from industry and media.
Year(s) Of Engagement Activity 2018
URL https://www.hud.ac.uk/news/2018/july/additive-manufacturing-smart-language/
 
Description Invited talk at CIRP GA STC Dn Technical session 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Policymakers/politicians
Results and Impact Dr Qunfen Qi has given a talk entitled "A smart semantic language for Digital Manufacturing" during the STC Dn meeting at the 69th CIRP General Assembly in Birmingham, UK, 22 August 2019. In the talk, category semantic language was introduced for any data/information involved in a manufacturing value chain and it will permit a comprehensive foundation to digitalise advanced manufacturing. Various test cases were demonstrated to show how the smart language can be used, and benefits for such applications were discussed. Based on the test cases, particularly focus was on the discussion of applying the language towards the digital twin approach, and exploration of any possible test cases via potential collaborations. The talk has received a very positive feedback and attracted many interests from both academic and industry. This has initiated a collaboration with the Polytechnic University of Milan.
Year(s) Of Engagement Activity 2019
URL https://www.cirp.net/meetings-conferences/about-cirp-events/general-assembly.html
 
Description Invited talk at Huaqiao University 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Me and Professor Dame Xiangqian Jiang visited Huaqiao University from 14th -15th December 2019. We visited the Institute of Manufacturing Engineering, had a lab tour and I have given a talk entitled "A smart Semantic Language for Digital Manufacturing" for the researchers, postgraduate students and undergraduate students. We then carried out a short research meeting with researchers at the Institute of Manufacturing Engineering. Possible collaborative research directions were discussed, and further visits from both parties were then arranged.
Year(s) Of Engagement Activity 2019
 
Description NIST (National Institute of Standards and Technology) academic visit 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Three researchers from the Information Technology Lab of NIST (National Institute of Standards and Technology, USA) reached us as we share a common interest in applications of category theory. While they study potential applications for category theory to address problems in data management, interoperability and systems modelling, they are quite interested in the work that Dr Qunfen Qi and her group have done, and the fact that Dr Qi have implemented some of the ideas in practice is especially exciting. Subsequently they travelled to Huddersfield to have a whole day academic meeting with us on 12th July, 2019. During the day, Dr Qunfen Qi has introduced how category theory was used in a real engineering case, i.e. providing the foundation for a smart database of surface texture. Dr Spencer Breiner then briefly introduced their work at NIST in data management, interoperability and systems modelling. We were then established a very detailed collaboration work plan, starting with writing a joint paper on category theory for metrology, then follow on trip to NIST for further engagement.
Year(s) Of Engagement Activity 2019
 
Description RAEng international women in engineering 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Royal Academy of Engineering celebrates International Women in Engineering Day, which takes place on 23 June 2018 at London. The event celebrates the achievements of women in engineering from all backgrounds on an international scale, and encourages more girls to consider a career in the field.
Year(s) Of Engagement Activity 2018
 
Description Research collaboration with the Polytechnic University of Milan 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Follow on with the interest from Professor Marcello Urgo from the Polytechnic University of Milan, we have arranged a video meeting with Professor Urgo and Dr Walter Terkaj on 15th Oct. 2019 to discuss a collaborative work on ontology for manufacturing. During the meeting, we have decided to define a collaboration area in the field of the use of tracking/versioning approaches for the modelling of elements in a factory and the use of multi-level/multi-scale approaches in the modelling of manufacturing systems. We then shared our data and later further extended our current focus to "a coherent synchronisation of data model in manufacturing using delta lenses".
Year(s) Of Engagement Activity 2019
 
Description Research visit to NIST 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Me and Professor Dame Xiangqian Jiang visited NIST at Gaithersburg, MD, USA, from 30th October to 3rd November 2019. This is an official academic visit which was planned during the last visit of NIST members to the University of Huddersfield. Apart from the Information Technology Lab, we have visited Additive manufacturing Metrology testbed at the Intelligent Systems division, AM data science group at the System integration division, and the surface metrology lab at the Sensor science division. During each visit, we have carried out very detailed discussion about our common research interest and questions. One meeting was arranged with the AM data science group to discuss how category theory can be used for AM data/information representation and integration. Most importantly, we have carried out a sequence of meetings with Professor Eswaran Subrahmanian, Dr Spencer Breiner and Dr Blake Pollard. The focus include: 1. Discussion of the collaborative paper on "category theory for metrology"; 2. An industrial meeting with CEO and Dr Ryan Wisnesky from Conexus to discuss potential collaboration with Conexus and possible industrial cases; 3. A detailed collaboration plan was finalised. We then arranged regular video meeting via BlueJean every fortnight.
Year(s) Of Engagement Activity 2019
 
Description Research visits to Shanghai Jiaotong University and Fudan University 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact We have had a visit to Shanghai Jiaotong University, Institute of Intelligent Manufacturing and Information Engineering on 13th December 2019. We have had a meeting with researchers at the Institute of Intelligent Manufacturing and Information Engineering to discuss collaborative research plans. I later visited department of Optical Science and Engineering, Fudan University, and had a lab tour of the optical science lab.
Year(s) Of Engagement Activity 2019
 
Description UK Manufacturing Forum: Driving forward the priorities 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact The second UK Manufacturing Forum event in December 2018 at Warwick set a clear agenda for Government, academia and research technology organisations. The event reported the progress made since the last UK Manufacturing Forum and how we can work together to pull through four of the technologies that will underpin a sustainable high value manufacturing future for the UK: Digital, Composites Manufacturing, Metrology and Additive Manufacturing.
Year(s) Of Engagement Activity 2018
URL https://hvm.catapult.org.uk/news-events-gallery/news/uk-manufacturing-forum-driving-forward-the-prio...
 
Description Visit Leeds University 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Professional Practitioners
Results and Impact We have had a visit to Leeds University, Schools of Mechanical Engineering and School of Electronic and Electrical Engineering on 18th October 2018. We have had a meeting with Professor Shane Xie to explore potential collaboration opportunity, and had a lab tour of Robotics and Autonomous System lab.
Year(s) Of Engagement Activity 2018