In April 2018, our cohort 1 researcher Dimitrios Pantazis attended the 6th AnyLogic Conference in Baltimore, US.

The AnyLogic (https://www.anylogic.com/) is a multimethod simulation tool, which provides the opportunity to end-users to experiment with discrete event, agent-based and system dynamics modelling. The flexibility of combining these different simulation methods under the same environment and the ease of extending the embedded libraries via Java to fit the user needs have established AnyLogic as the go-to solution in many sectors, such as automotive, healthcare and oil and gas plant engineering.

The purpose of this 2-day annual conference was to demonstrate the new capabilities of the software and also give the opportunity to the audience to expand their horizons by real case studies from industry experts like Intel and researchers from world-leading universities such as the National University of Singapore.

The attendees had the chance to gain insight and engage into discussions about active research topics such as the smart factory and digital twin modelling for the Industry 4.0 (presentations by FairDynamics and decisionLab), simulations of autonomous vehicles impact on road networks (presented by the Boston Consulting group) and integration of AI into simulation modelling (presented by PwC), only to name a few. The conference was accompanied by three workshops, one of which was delivered by Dr. Andrei Borshchev, CEO of the AnyLogic Company.

As part of his trip, Dimitris also had the opportunity to visit the Johns Hopkins University and also experience the third annual Light City festival (https://lightcity.org/).

The event was a very pleasant experience both academically and as an opportunity for Dimitris to expand his network and enhance his transferable skills. If you are interested and would like to learn more, the presentation videos will soon be available on AnyLogic’s YouTube channel: https://www.youtube.com/user/anylogic/videos

 Baltimore Blog

In April 2018, Rhys Comissiong from Cohort 2 attended the Society of Automotive Engineers World Congress in Detroit, Michigan, US. The conference was held over 3 days from the 10th to the 12th at the Cobo Center. The conference consisted of technical sessions, keynote speeches and an exhibition; which included exhibits from the top automotive manufacturers including GM, Toyota and Ford. The technical sessions were divided into 6 key areas: Body and Pedestrian Safety, Advanced Powertrain, Materials, Emissions Management, Design and Automotive Electronics/IOT/Connectivity.

 

Wcx

Dr Thomas Steffen (Left) and Rhys Comissiong (Right) @ the COBO Center

On the Wednesday, Rhys presented a ‘Review of Selection Criteria for Sensor and Actuator Configurations Suitable for Internal Combustion Engines’ which was co-authored by his supervisor Dr Thomas Steffen. The paper assessed the different criteria that went into selecting the right sensor and actuator configurations for an engine. The key finding was that a tool was required to evaluate the control architecture, and this would be beneficial to the other industries in addition to the automotive sector. The presentation was well received with a good turnout in the Sensor and Actuator technical session.

Outside of the presentation Rhys attended a range of talks by expert panels including the future of prognostics and diagnostics and Blockchain and IOT. There were also several opportunities to network including a careers fair with a range of employers in the automotive sector such as Hitachi, Denso and Tesla. With recent developments in autonomous systems and electrified powertrains, the conference provided a great insight into the current and future state of the automotive sector globally.

 

2017 09 26 15 57 03

View of Detroit, Michigan, US from Windsor, Ontario, Canada.

During the conference Rhys stayed in Windsor, Ontario, Canada and spent time with other Loughborough Academics and PhD students whilst trying out the local restaurants. After a journey to find a hat as a souvenir he found himself in a college baseball game at the Detroit Tigers Stadium, which was more entertaining than Cricket!

Tigers

Baseball Match at Detroit Tigers Stadium – Toledo @ Madonna

For the second year running the CDT-EI has been represented at the annual Loughborough University Postgraduate Awards.

Cohort 1 researcher, Joe Holt, was nominated by his peers for the John Philips Contribution to Community Award, which recognises the impact and efforts of a volunteer(s) who has given much of their own time to improve the postgraduate experience at both campuses by creating a close-knit and supportive postgraduate community.

On collecting his award Joe said "I was both honoured and surprised to win the award knowing some of the other nominees I was up against. It was great to have my volunteering as part of the PhD Student Support Network recognised on a personal level but also for the Network as a whole. The award is a lovely addition to the rest of my experience here at Loughborough University."

Congratulations Joe!

Picture1

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

Jake Rankin from Cohort 4 gives us a description of the conference he recently attended which was hosted by ADAS dSPACE and Warwick Manufacturing Group (WMG) at Warwick University entitled 'The State of the Art for Developing and Testing Advanced Drive Assist Systems'.

 

After an introduction, Dr Phillip Clarke discussed autonomous vehicle testing methods, in particular Hardware in the Loop (HiL) testing. HiL is a key means of being able to increase both the volume and range of testing, working closely with ISO 26262, dSPACE use a combination of Automotive Simulation Models (ASM) and Virtual Validation (Left-Shifting) to help further train simulations. The purpose of the conference was to discuss how this method was implemented and why it was useful.

After discussing the various levels of autonomy, and recognising that several sensors would be needed, three challenges were highlighted:

  • Fusing data at different frequencies
  • A need for an increasing communication bandwidth
  • Validating simulated models

Typically, two methods of testing are used. Open-loop testing is used to check the performance of the algorithm and closed-loop testing is similar but with the addition of a simulation model that gives feedback. HiL is a type of closed loop testing which both records and analyses simulations and feeds real sensors data to see how the simulated models work. Some of the tools included a radar test chamber which contained a radar in a circular chamber with movable rings that emit acoustics to mimic distance. Testing can be done even before a CAN setup is used to just test the algorithms, which is called left-shifting. dSPACE use a system called VEOS to test the model behaviour.

Rapid control prototyping of machine algorithms was the next discussion and firstly focused on the basics of sensor/actuation interaction. In particular, it discussed the means of applying neural networks and deep-learning into an actual system by first developing and training the learner with Tensorflow, with the help of SLAM algorithms. Next, Nvidia hardware such as the Jetson X2 is used to optimise the learning algorithm and the algorithm is finally places into dSPACE’s MicroAutoBox II. The system was shown to be very flexible in terms of coding languages that it can accept as well as other off-shelf programs such as MATLab.

WMG’s Graham Lee then gave an overview of the facilities at Warwick University, part of the CATAPULT group and Innovate UK. Currently, Warwick are finalising their NAIC building which will also give MSc courses on autonomous vehicles; the first in the country. The main project that Graham was working on was a system called SAVVY. This is a project which hopes to develop scalable AI testing, using some of the aforementioned equipment from dSPACE.

Finally, Torten Kluge gave a talk on scenario-based testing and sensor simulation. One of the challenges was acquiring data and dSPACE were able to collect a lot of their data from GIDAS, which are accident studies in Germany. These scenarios would then be uploaded into the simulation, with additional input from services such as SUMO (a traffic-flow simulator). All of this was demonstrated with dSPACE’s simulation which included all of the sensor data, car behaviours and states. Because of the simulation design, even with critical components such as the ECU and sensors, the simulation could still be tested.

Overall, it was a very interesting insight into autonomous vehicles and certainly resulted in useful subjects to research for vehicle autonomy. https://www.dspace.com/en/inc/home/applicationfields/our_solutions_for/driver_assistance_systems.cfm for more information.

1.0.0.19

Cohort 3 researcher Orange Gao was invited to be a main stage presenter at Teesside Digital Forensics Conference (TDFCon 2018), a student-led international conference for computer and digital forensics students at Teesside University.

The theme for conference this year was ‘Resilient and Secure Societies’ and focussed on understanding and developing responses to the complex range of inter-related global processes that create risk and threaten the physical and emotional security of individuals, communities and societies.  Attendees included students, academics, practitioners, police officers from local forces, and some government agency/civil service employees. Orange spoke about artificial intelligence from the perspective of computer vision and related it to digital forensics. She described her recent work using recent advances in deep learning technology to generate images from verbal descriptions for accurate facial composites in criminal investigations. This novel approach reduces subjectivity in decision making and increase law enforcement response times.

1.0.0.19

Matt Smith from Cohort 4 describes his recent visit to the Ergonomics & Human Factors Conference.

 

The purpose of this event was to bring together PhD students with human factors and ergonomics projects and go through different part of a PhD including writing techniques, planning and procrastinations. Each of the 11 attendees had to give a ten-minute presentation on their research and progress and were asked engaging and relevant questions afterwards.

I created a presentation that covered my progress so far including a breakdown of the design methods I intended to use, visuals that I had generated from data gleaned from my semi-structured systematic literature review and the current work I am doing around the wearables which I am looking to design. My presentation won the prize for ‘most ascetical presentation’ earning me a signed copy of Introduction to Human Factors and Ergonomics, Fourth Edition by Robert Bridger and a cap. I received advice regarding previous works I should study and was asked questions about how I was planning to conduct my first study with critical design pieces.

The majority of the participants were human factors researchers with backgrounds in psychology. This included several participants from Nottingham University currently engaged in pursuing research relating to transport and one individual from Sweden who was studying wearables in personal lighting plans. I was the only attendee with a background in design.

 

 

 

The 3rd International Conference on Control and Robotics Engineering, ICCRE 2018, was held at the Nagoya Institute of Technology, Nagoya, Japan through April 20th-23rd, 2018. The aim as well as the objective of ICCRE 2018 is to present the latest research and results of scientists related to Control and Robotics Engineering topics. Christos Kouppas (cohort 3) attended to present his preliminary results on his PhD and his algorithms. The conference started with the enrolment day and the first meet up of the attendees. The main conference was held for two days (21st and 22nd). The conference finished with sightseeing day of Nagoya.

 

 Picture1

 

During the conference, Christos, presented his work on Machine Learning Comparison for Step Decision Making of Bipedal Robot. In his paper he compared different classical and neural classifiers. His results showed a clear advantage of neural networks with memory for continues systems like a robot. Those results will be used as his ground knowledge for his PhD. Additionally, Christos won the award of the best oral presentation in its session with title “Robot System Design and Path Planning”.

Picture2

follow us
@cdt_ei


General Enquiries Contacts:

Loughborough University

Loughborough, Leicestershire
LE11 3TU
United Kingdom
Tel: +44 (0)1509 227 518
CDT Office
cdt-ei@lboro.ac.uk