Dr Peter Matthews, MA DipCS PhD MIET
(email at email@example.com)
Peter Matthews is an Associate Professor in Design Informatics at the Department of Engineering. His research in Design Informatics utilises data mining and machine learning tools to critically appraise technical data sets, such as operational sensor data from wind turbines (typically from SCADA systems). Gaining insights to the underlying processes governing these systems gives us a deeper understanding, which ultimately leads to improved design for the next generation of system.
The primary goal for machine learning with technical data is to be able to predict with sufficient warning when a machine is likely to fail. This prognostic ability has the potential of providing significant cost savings to industry: maintenance can be performed at the optimal time, allowing better planning, and the risk of incurring secondary damage is mitigated. Dr Matthews has led several successful projects which have accurately predicted failures for specific sub-systems (see results with Chen (2015), Godwin (2013), and Smith (2015)).
Another important component of Dr Matthews’ research is the production of tractable and humanly-understandable rules. Tractable rules require a much simpler validation process and are therefore more useable by system operators and designers when seeking to improve a system’s performance.
Dr Matthews' wind energy research is primarily in data mining SCADA and other wind turbine operational data. This research is primarily aimed at developing diagnostic and prognostic measures for individual wind turbine health. The approach taken is based around statistical modelling of healthy wind turbines, and then comparing live wind turbines against this healthy model. Other methods (eg physics based) are under development as well, again using ‘big data’ approaches to validate.
In addition to SCADA analysis, Dr Matthews has directed research in wake optimisation and maintenance strategy simulation. The wake optimisation research has delivered a workable dynamic wind farm controller that can minimise the effect of in-farm wakes on total production. The maintenance strategy simulation provided a Monte Carlo based approach for developing and testing alternative off-shore wind farm maintenance strategies.
Much of the Wind Energy research is undertaken with industrial partners Ørsted Energy and Maia Eolis (now Engie Green).
The energy distribution sector has a broad range of customers, from domestic through to large industrial customers. All these customers use electricity in different ways, and their consumption is recorded using SCADA systems. Dr Matthews’ research in the Energy Distribution sector centres around data mining these SCADA databases of thousands of customers, as well as hundreds of electrical substations, to gain better understanding of the overall picture of electricity use. Dr Matthews has also directed research to forecast the demand increases at substation level using substation demographic customer profiles.
Much of this research is undertaken with Northern Powergrid.
The Design Analysis research is based on data mining, but with considerably smaller datasets. Here, the aim is to extract the tacit rules the human designers have applied, and gain better understanding of the design domain through making these rules explicit. Design data often contains greater textual information, and so text mining approaches have also been applied with interesting results. Other techniques that have been used include Bayesian Belief Network and p-boxes. These techniques have been used to mitigate against the greater uncertainty levels that can be associated with early designs.
This research has been undertaken with Rolls-Royce (Aerospace) and BAE Systems.
- Artificial Intelligence and Machine Learning
- Data mining
- Wind Energy
- Monte Carlo methods
- Engineering Uncertainty modelling and management
- Knowledge Management
- Engineering Design
- Design process
- Game theory
- Ms Nor Zahari
- Miss Elvia Izquierdo-ruiz
- Mr Weiqi Hua
- Mr Roger Cox
- Mr Luke Payne
- Miss Karen Gonzalez-trapero
- Miss Nadia Khan
- Mr. Abdulkarim Athwer
- Mr Amin Elfasi
- Mr. Sermed Alsaadi
Chapter in book
- Godwin, J. & Matthews, P.C. (2014). Robust Statistical Methods for Rapid Data Labelling. In Data Mining and Analysis in the Engineering Field. Bhatnagar, V. IGI Global. 107-141.
- Ahmad, T., Girard, N., Kazemtabrizi, B. & Matthews, P.C. (2015), Analysis of Two Onshore Wind Farms with a Dynamic Farm Controller, European Wind Energy Association 2015. Paris, France, European Wind Energy Association, Paris.
- Smith, C.J., Wadge, G.N., Crabtree, C.J. & Matthews, P.C. (2015), Characterisation of Electrical Loading Experienced by a Nacelle Power Converter, European Wind Energy Association 2015. Paris, France, European Wind Energy Association, Paris.
- Smith, C.J., Crabtree, C.J. & Matthews, P.C. (2015), Evaluation of Synthetic Wind Speed Time Series for Reliability Analysis of Offshore Wind Farms, European Wind Energy Association 2015. Paris, France, European Wind Energy Association, Paris.
- Sidwell, N., Ahmad, T. & Matthews, P.C. (2015), Onshore Wind Farm Fast Wake Estimation Method: Critical Analysis of the Jensen Model, EWEA 2015. Paris, France, European Wind Energy Association, Paris.
- Akperi, B.T. & Matthews, P.C. (2014), Analysis of clustering techniques on load profiles for electrical distribution, Power System Technology (POWERCON), 2014 International Conference on 2014 International Conference on Power System Technology. Chengdu, China, IEEE, Chengdu, 1142-1149.
- Akperi, B.T. & Matthews, P.C. (2014), Analysis of customer profiles on an electrical distribution network, in Conlon, M., Micu, D.D., Al-Tai, M. & Ferreira, C. eds, Power Engineering Conference (UPEC) 2014 49th International Universities Power Engineering Conference (UPEC). Cluj-Napoca, Romania, IEEE, Cluj-Napoca, 1-6.
- Ahmad, Tanvir, Basit, Abdul, Anwar, Juveria, Coupiac, Olivier, Kazemtabrizi, Behzad & Matthews, Peter (2019). Fast Processing Intelligent Wind Farm Controller for Production Maximisation. Energies 12(3): 544.
- Ahmad, T., Coupliac, O., Petit, A., Guignard, S., Girard, N., Kazemtabrizi, B. & Matthews, P. (2018). Field Implementation and Trial of Coordinated Control of Wind Farms. IEEE Transactions on Sustainable Energy 9(3): 1169-1176.
- Trenkel-Lopez, M. & Matthews, P. C. (2018). Method for Designing a High Capacity Factor Wide Area Virtual Wind Farm. IET Renewable Power Generation 12(3): 351-358.
- Smith, C.J., Crabtree, C.J. & Matthews, P.C. (2017). Impact of wind conditions on thermal loading of PMSG wind turbine power converters. IET Power Electronics Special Issue: Power Electronics Converters for Marine Renewable Energy Applications 10(11): 1268-1278.
- Chen, B., Matthews, P.C. & Tavner, P.J. (2015). Automated on-line fault prognosis for wind turbine pitch systems using supervisory control and data acquisition. IET Renewable Power Generation 9(5): 503-513.
- Ullah, B., Trevelyan, J. & Matthews, P.C. (2014). Structural optimisation based on the boundary element and level set methods. Computers & Structures 137: 14-30.
- Godwin, J.L. & Matthews, P.C. (2013). Classification and Detection of Wind Turbine Pitch Faults Through SCADA Data Analysis. International Journal of Prognostics and Health Management 4: 016.
- Chandler, S.R. & Matthews, P.C. (2013). Through-Life Systems Engineering Design & Support with SysML. Procedia CIRP 11: 425-430.
- Chen, Bindi, Matthews, P.C. & Tavner, P.J. (2013). Wind turbine pitch faults prognosis using a-priori knowledge-based ANFIS. Expert Systems with Applications 40(17): 6863-6876.
- Matthews, P.C. & Philip, A.D.M. (2012). Bayesian project diagnosis for the construction design process. Artificial Intelligence for Engineering Design, Analysis and Manufacturing 26(4): 375-391.
- P.C. Matthews (2011). Challenges to Bayesian decision support using morphological matrices for design: empirical evidence. Research in Engineering Design 22(1): 29-42.
- Peter C. Matthews & Chris D. W. Lomas (2010). A methodology for quantitative estimates for the work and disturbance transformation matrices. Journal of Engineering Design 21(4): 413-425.
- Matthews, PC (2008). A Bayesian support tool for morphological design. Advanced Engineering Informatics 22(2): 236-253.
- Bulkeley, H.A., Matthews, P.C., Whitaker, G., Bell, S., Wardle, R., Lyon, S. & Powells, G. (2015). High Level Summary of Learning: Domestic Smart Meter Customers on Time of Use Tariffs. Northern Powergrid (Northeast) Limited.
- Bulkeley, H.A., Whitaker, G., Matthews, P.C., Bell, S., Lyon, S. & Powells, G. (2015). High Level Summary of Learning: Domestic Smart Meter Customers. Northern Powergrid (Northeast) Limited.
- Bulkeley, H.A., Whitaker, G., Matthews, P.C., Bell, S., Lyon, S. & Powells, G. (2015). High Level Summary of Learning: Domestic Solar PV Customers. Northern Powergrid (Northeast) Limited.
- Capova, K.A., Wardle, R., Bell, S., Lyon, S., Bulkeley, H.A., Matthews, P.C. & Powells, G. (2015). High Level Summary of Learning: Electrical Vehicle Users. Northern Powergrid (Northeast) Limited.
- Bell, S., Capova, K.A., Barteczko-Hibbert, C., Matthews, P.C., Wardle, R., Bulkeley, H.A., Lyon, S., Judson, E. & Powells, G. (2015). High Level Summary of Learning: Heat Pump Customers. Newcastle upon Tyne, Northern Powergrid (Northeast) Limited.
- Jones, O., Wardle, R. & Matthews, P.C. (2014). Micro-CHP Trial Report. Northern Powergrid (Northeast) Ltd.
- Whitaker, G., Wardle, R., Barteczko-Hibbert, C., Matthews, P.C., Bulkeley, H.A. & Powells, G. (2013). Insight Report: Domestic Time of Use Tariff: A comparison of the time of use tariff trial to the baseline domestic profiles. Northern Powergrid (Northeast) Limited.