CertificateCohort 3 student Gergely Hantos took part in the Cambridge Spark Applied Data Science Bootcamp.

Gergely, who is based at Heriot-Watt and supervised by Prof. Marc Desmulliez, took part in the 6-months Cambridge Spark Applied Data Science Bootcamp. The course gave an excellent knowledge of the most relevant Data Science skills matching industry needs.

Each student had to carry out a one-month real-life project backed by industry partners that covered problem understanding, data cleaning and feature engineering, visualisation, model selection, training, evaluation and optimisation.

Gergely worked on a project for Entomics, a biological waste valorisation company that transforms organic waste into high value agricultural products using insect larvae as a unique bioconversion engine. The objective was to create a predictive machine learning model that optimizes the bioconversion by predicting the daily waste intake of the larvae.

Gergely delivered a solution that worked with so little prediction error that Entomics was able to use the output immediately. The outcome of this project has opened up a specialised software engineer position at Entomics.Presentation

A conference paper based on the work achieved was delivered for the First Symposium on Smart Systems Integration (SS1S) by Gergely on the 31st of August 2018 in Balatonvilágos, Hungary and is currently under review for publication in Periodica Polytechnica Electrical Engineering and Computer Science.

Cambridge Spark, the company delivering the course was also impressed by the work, thus they wrote a blog article about the project available here: Project Partner Case Study: Entomics that includes a video interview with Fotis Fotiadis, Co-Founder and CTO of Entomics.

Marcus Pollard, Robin Hamer, Gajarajan Sivayogan and Wen Gu have developed a proposal that aims to save money and time by ensuring predictive maintenance of tablet-making machinery.

The UK subsidiary of global Connectivity and Networks component manufacturing specialist HARTING challenged the students to suggest potential applications for their new product MICA.

MICA (Modular Industry Computing Architecture) is an edge computing device that can be digitally retrofitted into existing production facilities as a direct interface to machines.

It provides a bridge between machines and cloud-computing and can be immediately and securely integrated into a production environment for minimal cost, providing continuous data processing and condition monitoring analysis of key operating processes.

The students decided to focus on a pharmaceutical application after being inspired by Marcus’ placement year at a British multinational consumer goods company.

They decided to focus on tablet presses as they are one of the most common pieces of equipment in a pharmaceutical manufacturing environment.

They work by filling a hole – known as a ‘die’ – with a powder and this powder is compressed by two metal punches to form a tablet.

Tablet presses used in manufacturing continuously use multiple dies and punches – collectively known as ‘toolings’ – to achieve high output.

Some tablet presses can produce 229,500 tablets per hour with 32 sets of toolings and, as a result, these punches are under continuous wear and are prone to breakages.

Breakages mean that the tablet press needs to be stopped for maintenance, which costs money. Breakages of the punches could also lead to metal fragments being deposited in the tablet batch, which means the whole batch would need to be disposed of as it would be unsafe.

The Loughborough students’ came up with the idea of tracking the use of these punches and dies via RFID (radio-frequency identification) tags on the tooling that would be scanned by MICA and recorded in a database.

By tagging the tooling and tracking the number of tablets a machine has produced, the wear on the tooling could be continuously monitored so that when this hits a critical point it can alert a staff member via email.

It would let them know that a particular piece of tooling has reached its pre-defined end of operational life and needs replacing, giving its location to allow for minimum downtime.

The proposal also suggests that the tags on the tooling could store information on which machines had used the tooling, which operators had used the tooling, the length of its current life and how many of a particular tooling is in stock.  

Marcus commented: “We hoped this idea would help reduce breakages which in turn would reduce the production downtime meaning lower costs and reduce losses suffered from damaged batches, but also give a full history of the tooling which could provide useful accountability information for the manufacturer and regulatory bodies such as the MHRA [Medicines and Healthcare products Regulatory Agency]or FDA [Food and Drug Administration Agency].”  

Howard Forryan, Product Market Specialist at HARTING, said: “HARTING were very impressed by how quickly the students were able to understand the main operating concepts of the MICA edge computing device. 

“For example how best to programme it and download the most appropriate software from HARTING’s online stored range of “Open software” development containers, in accordance with the application requirements. 

“As a result of this specific well-developed and fully-engineered application case solution, HARTING have been able to market this concept to the wider pharmaceutical manufacturing industry.”

This work was conducted as part of our industrial group project scheme, which runs twice a year. If you want to know more about the scheme or our industry-relevant PhD programme and the options available to collaborate contact us.

1.0.0.19

Innovation Is Here

16 April 2018

Cohort 4 researcher Jake Rankin describes the event;

The Construction Equipment Association (CEA) held an Innovation Is Here event at One Great George Street, Westminster. Several companies had displays at a mini exhibition such as Nylacast, KHL and Perkins. There was also a huge library owned by the Institute of Civil Engineers even containing a Lego tower bridge (to engage younger, and also older, audiences with civil engineering). The event was sponsored by JCB and Perkins. The reason for visiting was to develop an understanding of the industry position with regards to AI.

The conference was moderated by Nick Higham (BBC broadcaster and journalist) who spoke about the need for the civil industry to move with the times with technology such as Industry 4.0, Internet of things and automation.

CEA Honorary President David Bell (JCB) gave a rundown of the program before introducing the first speaker, Duncan Riding (Senior Technical Steward of Perkins) who gave a talk titled Future Fuels - Diesel, Hybrid Electric...? His talk was broken up into three sections:
- The Important Issue
- Air Quality
- Future Fuels
The issue that Duncan discussed was the need for energy, and focused particularly on how dependent we were on it. This then led to why we still needed Diesel engines and suggested that electric was not yet ready for the demand (this would create an interesting discussion between themselves and Volvo, who were looking at electric technology). Duncan also spoke passionately about climate change and energy, with some good examples on Diesel vs electric cars. The key lesson from that using a basic energy equation could still highlight fundamental issues (such as the required overloading needed to supply a motor power, the amount of battery needed etc).
Air quality was then discussed, focused on particulates. 25-100 micrometers was the harmful range that Perkins needed to address and they presented their latest technology using Diesel Particulate Filters and a a Diesel Exhaust Fluid which reduced particulate emissions by 98%.
Finally, Duncan spoke about the Future of Fuels. He mentioned that in a review paper that 76% of industry leaders believed that hydrogen was the Future, however this was contradicted when further discussions with these leaders yielded concerns for packaging hydrogen and creating an infrastructure, similar issues to electric. This was also supported by a conversation he had with Prof Garner at Loughborough University.

Professor Rob Scott (Advanced Manufacturing Research at University of Sheffield, AMRC with Boeing) gave a talk on the Factory of the Future. He discussed the state of British manufacture when compared to other countries like France and Germany and highlighted that Britain urgently needed to modernise. The key point that he raised was of Horizontal Learning. This is where one industry learns about a technology from another industry, the example he suggested was civil engineering and manufacture. He then went on to discuss the changing customer demands of wanting everything customisable and delivered yesterday and talked about applicable technology that could be used to tackle this such as Cyber-Physical Systems and the Internet of Things. Rob then discussed the five key technologies available to civil engineering:
- AI and machine learning
- VR and AR
- Additive manufacture
- Robotics and automation
- Big data and connectivity
In particular, Rob focused on the importance of data, using famous case studies such as Uber and Airbnb to highlight how industries make money by selling a service, not a product.

The next talk was from Dale Hawkins and Mark Kennedy (UK Plant Operators) titled A View from the Cab - Augmented Reality training. This talk was particularly well received as it addressed a key issue in the industry; young people not going into civil engineering, particularly machine operating. The average age of a plant operator is 54 in the UK and companies were struggling to train up enough young drivers to meet demand. Mark then presented one solution; an AR cab setup to help train drivers in a safe environment whilst also engaging a younger “gaming” generation. This was a popular talk and several people were keen to try out the simulator.

After lunch, Inma Martinez (Deep Science Ventures, Innovator and Data Scientist) gave an insightful talk titled The Future is Now. She spoke about technology trends within information management and gave an overview on the various types on machine learning. It was encouraging to see that Inma spoke highly of Reinforcement Learning. Inma also discussed on of their projects; Blockchain. Inma also discussed about various data-mining methods and spoke about HPC methods and Exascaling (the reduction of data for useable scales) .This is a continually growing list of data that is secured by cryptography. What was also amazing to learn was that she was one of the pioneers of the internet, developing her work at CERN and has been involved with several projects, including helping to develop the first AI for mobile personalisation.

The final talk was from Jenny Elfsberg (Volvo CE, Director of Emerging Technologies) one Does the Construction Industry Need Innovation? The Journey from Manual to Autonomous Equipment. Jenny demonstrated Volvo’s current autonomous technology; an electric dump-truck and a hybrid loader. Jenny then went on to discuss the reasoning behind choosing electric, stating that one of the advantages was the simplicity. In a quarry environment, it could be relatively easy to establish a charging infrastructure because it is a smaller, contained environment. Electrification was also shown to be valuable from a Value Stream Mapping perspective, which aims to highlight waste within a system. The two biggest causes of waste energy were within the hydraulics (12%) and energy losses from the Diesel engine (63%). Because of this, electric energy was investigated where Volvo stated that this loss could be removed with electric hence their switch. Jenny then started explaining the journey needed to go towards full autonomy, comparing it to what Volvo had already developed.

Overall, this was an exciting and thought-provoking conference and gave me an opportunity to talk to leading figures in industry. For more information, please visit https://www.thecea.org.uk

Industry Open Day

15 April 2018

On 13 April Loughborough University hosted an Industry Open Day to promote the work of our researchers and opportunities for collaboration. Representatives from a range of companies attended the event from SMEs and large organisations with interests spanning smart manufacturing, AI, sensing and data analytics to name but a few.

During the afternoon attendees were given tours of research facilities on campus covering Loughborough University Centre for Autonomous Systems (LUCAS), Sports Technology Institute, Vision, Autonomous and Human-Computer Systems Research, Building Performance Laboratories and Embedded Integrated Intelligent Systems research.

 

Industry Day

Cohort 2 researcher Jamal Umer tells us abou the event;

I attended the conference on 14th and 15th March-2018 at the IET Austin Court Birmingham. This 2-days conference was an excellent opportunity to learn about recent progresses in the field of tribology. The keynote speakers were well-famous tribologist from universities and industries. In addition to those there were quite interesting poster talks from PhD students from various universities. This conference had various talks ranging from lubricant additives, friction, wear and coating technologies. In-situ measuring techniques to measure wear in tribometers by gathering online topographical data was interesting experimental procedure.  and topography was quite interesting. Conversations with several speakers also directed me to further literature review that will make me think of new aspect of current research. It was also good opportunity to get in touch with my industrial sponsor.

Cohort 4 researcher, Steve Ward explains;

On Tuesday 5th and Wednesday 6th March I attended the Ambition UK Emergency Preparedness, Resilience and Response Expo. This ran alongside the Security and Counter Terror Expo, and Forensics Europe Expo as part of UK Security Week, hosted at the Olympia, London.

During the expo I represented my co-sponsor company INMM (In Manibus Meis), demonstrating the research currently being undertaken at Loughborough University as part of the CDT-EI, and its link with their commercial offerings. Whilst at the event, I spent time on the companies exhibition stand meeting key stake holders and gaining a deeper insight into the operation of the business. There was a few prominent interested parties the company will be exploring further. Additionally, over the course of the two days there were opportunities to expand my own personal network, and attend a variety of talks by a wide range of interesting speakers as part of the conference programme. The insights gained from this will be extremely beneficial in applying my research outputs, taking into account the current relevant problems within the wider industry.

Picture1

Cohort 4 researcher, Matt Smith, tells us about attending his first research conference;

Matt OsEach year the Ordnance Survey (OS) invites the PhD students it sponsors to its HQ in Southampton for a workshop involving presentations of each student’s current status and work, panel discussion on topics and general networking. There were 22 PhD students present at the workshop, all from different backgrounds and Universities spanning the UK and even including one person who travelled from New Zealand.

Each student had the opportunity to prepare a poster and presentation. My poster focused on the opportunities of my research question and how I was planning to tackle the area, as I don’t have any data yet. My 10-minute presentation echoed this in more detail, giving examples of some of the design methods I want to use and what I have read so far. There was an hour-long poster session on both days which allowed the staff members to come and ask us about our projects. Feedback on my poster was positive. In particular, they found it visually appealing and engaging, however, it perplexed a few as it isn’t what you would expect for a typical PhD poster!

I felt quite unique as I am the only researcher with a ‘pure’ design background and the only one focussing on wearables and actual physical prototyping. From the conversations I had the majority of other researchers were focused on data, ontologies and especially deep/machine learning and forms of automation. As well as meeting other researchers sponsored by OS I was able to speak with a number of staff members, one person in particular, Tim Newman, expressed an interest in the project as he could see possible applications within the walkers’ community.

Picture1

Wen Gu & Shaun Smith, of Cohort 3 & 4 respectively, recently attended the 2-day Future Powertrain Conference (FPC2018). The FPC2018 invites over 500 delegates from both academia and industry to present innovative research ideas and discuss the future of the industry.

This was the first conference for the students since joining the CDT-EI and the main reasons for attending was to first potentially discover new research topics and secondly anchor their own research by considering where they could add their knowledge to the problems in the industry. In addition, the FPC2018 offered networking sessions throughout both days allowing the valuable opportunity for the students to fully immerse themselves in the sector by speaking to experts in the industry and open the door for possible collaboration.

The students highlighted several presentations that were very useful for a variety of reasons. These included, but were not limited to, talks by Prof Colin Garner of Loughborough University who challenged us to consider the most efficient sources of energy and to revisit the debate of “Battery vs Internal Combustion Engine”, Richard Burke of the University of Bath who presented a catalogue of research opportunities and Doug Cross of Leadfoot who provided a talk on the future of autonomous vehicle and if they can keep up with the expectations of the consumer. Furthermore, talks by Dr Yan Wang of Ford and Dr Mark Peckham of Cambustion provided a greater insight of the challenges that face the sector from an industry perspective

Wen Gu presented a poster at the conference to demonstrate his current research. By implementing the machine learning algorithm, he developed a model learning approach to reflect the engine behavior faster and more accurate. The adaptive model predictive control method is employed to dynamically optimise the engine fuel economy based on the developed time-varying model. This approach is promising in improving fuel economy of powertrain systems and leading the way to next generation low carbon engines. At the end of the conference, he won the third prize of poster competition section.

The future powertrain conference returns in 2019 at the National Motorcycle Museum, Solihull, where students will again be attending representing the CDT-EI.

For further information visit futurepowertrains.co.uk/

 

1.0.0.17

follow us
@cdt_ei

2 hours ago RT @WeKnowRobots: 📣Call for Papers and Registration 📣 2nd Robotics and Autonomous Systems Conference for PhD students & early-career resear…
2 weeks ago Supporting the Charnwood Orchestra and second violin Mary from @WolfsonSchool tonight for their winter concert… https://t.co/Zj9Y8AY5H9
1 month And @CDT_EI is one of them too! https://t.co/GJkTzCBlr0

General Enquiries Contacts:

Loughborough University

Loughborough, Leicestershire
LE11 3TU
United Kingdom
Tel: +44 (0)1509 263171
Dr Donna Palmer
cdt-ei@lboro.ac.uk

Heriot-Watt University

Edinburgh, Scotland
EH14 4AS
United Kingdom
Tel: +44 (0)131 449 5111
Dr Keith Brown
k.e.brown@hw.ac.uk