S^3 Disease Surveillance for Structures and Systems
Lead Research Organisation:
University of Sheffield
Department Name: Mechanical Engineering
Abstract
One of the main contributors towards the cost of high-value engineering assets is the cost of maintenance. Taking an aircraft out of service for inspection means loss of revenue. However, the alternative - allowing damage to remove the aircraft from service - is much more undesirable with cost and safety being issues. In terms of an offshore wind farm, the cost of an unscheduled visit to a remote site to potentially replace a 75m blade hardly bears thinking about. If one can adopt a condition-based approach to maintenance where the structure of interest is monitored constantly by permanent sensors and data processing algorithms alert the owner or user when damage is developing, one can optimise the maintenance program for cost without sacrificing safety. If incipient damage is detected, repair rather than replacement can be a viable option.
Unfortunately, the complexity of modern structures together with the challenging environments in which they operate makes it very difficult to develop data-processing algorithms which can detect and identify incipient damage. The discipline concerned with these problems - structural health monitoring (SHM) - suffers from serious problems which have prevented uptake of the technology by industry. The structural complexity makes analysis difficult; however, one variant of SHM - the data-based approach - shows promise in this respect. In this case one learns directly from data from the structure using pattern recognition techniques to diagnose different levels of damage. Sadly, data-based SHM has its own problems; the first is that most pattern recognition approaches to SHM require one to measure data from the structure in all possible states of damage. In the case of a structure like an aircraft - consider the A380 - it is simply not conceivable that one should damage a single one for data collection purposes, let alone many. Fortunately, if one is only interested simply in whether damage is present or not, this can be accomplished using only data from the healthy condition. One builds a picture of the healthy state of the structure and then monitors for deviations from this state. This raises the second major issue with data-based SHM; if one is monitoring the structure for changes, one does not wish to raise an alarm because of a benign change in its environmental or operational conditions; these are termed 'confounding influences'.
The solution may lie within the healthcare informatics community. A field called 'syndromic surveillance' (SS) has arisen over the last 20 years concerned with fast detection of disease outbreaks by monitoring human populations. The data themselves can be very different, from over-the-counter medicine sales to numbers of hits on health advice websites. The data are fused together and analysed to give a spatio-temporal picture of public health and alerting algorithms similar to the ones used for SHM can be used to warn healthcare professionals that an epidemic may be on the way. The ideas have even been embedded in software, the prime example being the ESSENCE II system which keeps a watchful eye over three US states.
The current proposal aims to develop a SS system for engineering structures with the capability of fast detection and location for faults on high-value assets. The population-based approach to SHM proposed here has the potential to solve the two problems discussed above. If many structures are monitored, inferences between structures can potentially avoid the need for very detailed knowledge of individual structures. As structures fail with time, the knowledge of damage states will build. In terms of the second problem, SS systems have always dealt with confounding influences and can provide inspiration for new algorithms for data-based SHM. As in the case of ESSENCE II; the system will be embedded in software so that multiple operators of structures can derive maximum benefit from the diagnostic capability of the population-based system.
Unfortunately, the complexity of modern structures together with the challenging environments in which they operate makes it very difficult to develop data-processing algorithms which can detect and identify incipient damage. The discipline concerned with these problems - structural health monitoring (SHM) - suffers from serious problems which have prevented uptake of the technology by industry. The structural complexity makes analysis difficult; however, one variant of SHM - the data-based approach - shows promise in this respect. In this case one learns directly from data from the structure using pattern recognition techniques to diagnose different levels of damage. Sadly, data-based SHM has its own problems; the first is that most pattern recognition approaches to SHM require one to measure data from the structure in all possible states of damage. In the case of a structure like an aircraft - consider the A380 - it is simply not conceivable that one should damage a single one for data collection purposes, let alone many. Fortunately, if one is only interested simply in whether damage is present or not, this can be accomplished using only data from the healthy condition. One builds a picture of the healthy state of the structure and then monitors for deviations from this state. This raises the second major issue with data-based SHM; if one is monitoring the structure for changes, one does not wish to raise an alarm because of a benign change in its environmental or operational conditions; these are termed 'confounding influences'.
The solution may lie within the healthcare informatics community. A field called 'syndromic surveillance' (SS) has arisen over the last 20 years concerned with fast detection of disease outbreaks by monitoring human populations. The data themselves can be very different, from over-the-counter medicine sales to numbers of hits on health advice websites. The data are fused together and analysed to give a spatio-temporal picture of public health and alerting algorithms similar to the ones used for SHM can be used to warn healthcare professionals that an epidemic may be on the way. The ideas have even been embedded in software, the prime example being the ESSENCE II system which keeps a watchful eye over three US states.
The current proposal aims to develop a SS system for engineering structures with the capability of fast detection and location for faults on high-value assets. The population-based approach to SHM proposed here has the potential to solve the two problems discussed above. If many structures are monitored, inferences between structures can potentially avoid the need for very detailed knowledge of individual structures. As structures fail with time, the knowledge of damage states will build. In terms of the second problem, SS systems have always dealt with confounding influences and can provide inspiration for new algorithms for data-based SHM. As in the case of ESSENCE II; the system will be embedded in software so that multiple operators of structures can derive maximum benefit from the diagnostic capability of the population-based system.
Planned Impact
A major issue in industrial take-up of structural health monitoring (SHM) technology is the complexity of the problem for individual structures. The S^3 concept can provide a paradigm shift by moving to population-based SHM where inter-structure information and data are leveraged to massively augment the results of individual structure SHM. This allows a transition to damage-tolerant design, leading to lighter, greener, safer structures with substantially lower cost of ownership. Aerospace industry most directly benefits with potential savings of millions of pounds from more effective maintenance and asset management strategies. The wind energy sector is also targeted; a major reason for the shortfall in expectations for UK round 1 wind farms was low availability. Wind energy needs to play a vital role in meeting UK targets for 15% of energy to come from renewables by 2012.
The principal means of ensuring industrial impact is to ensure that the proposal is industry goal-driven. To facilitate this a Steering Group (SG) will be set up with membership from major companies. From aerospace industry: BAE Systems, Airbus, Rolls-Royce, Messier-Dowty (MD) and Dstl have already agreed to join. From the wind energy sector, tacit agreement has been secured from NaREC (National Renewable Energy Centre) and Risoe (National Centre for Renewable Energy, Denmark). Academic members of the SG will include Professor James Brownjohn who will advise on transitioning S^3 ideas into the civil infrastructure domain. S^3 ideas will prove powerful in many other contexts, discussion with the Advanced Manufacturing Research Centre in Sheffield will lead to manufacturing applications; discussions with the NetworkRail Innovation & Technology Centre at Sheffield will focus on railways. A User Group (UG) will be used to encourage industrial participants to contribute field data for a system demonstrator. Workshops will be used to solicit members for the UG and to disseminate S^3 ideas into the academic and industrial communities; attendance will be encouraged by provision of bursaries. MD will benefit directly from the proposed work as one of the specific tasks is to detect incipient cracks in aircraft landing gear in fatigue tests; this is expected to lead to a patent. Another task here will lead to enhanced diagnostic capability in neuroimaging and this will motivate further applications of S^3 concepts in future generation healthcare.
Research visitors from Los Alamos National Laboratories (LANL) will aid dissemination of S^3 concepts to US academia and industry. SHM software at LANL will be enhanced by embedding ideas of population-based SHM; as the LANL software is extensively downloaded, this is an effective dissemination channel. By the PI and PDRA lecturing at the LANL Summer School, the students will be exposed to S^3 concepts. As the students go on to employment with major US companies or PhD projects in the most prestigious universities, there is no better way to propagate the S^3 ideas. The PI and PDRA will also give focussed seminars to technical staff at LANL and faculty at the University of San Diego.
Outreach activities are vital; S^3 ideas and its applications to wind energy and healthcare are likely to generate public interest. Presentations at Cafe Scientifique and on regional radio have been successful in the past and will be used here. To maximise media potential the PI and PDRA will attend a Royal Society course on public communication and the media. Ideas for outreach will be explored via creativity$@$home and the SG. Outreach into professional engineering will be via seminars in the programmes of professional institutions. The research will be seen by schoolchildren via demonstrations and interactive activities for the University of Sheffield Engineering Summer School. A web site will be set up for the project with both public and private pages; some pages will be tailored to communication to the lay public and media.
The principal means of ensuring industrial impact is to ensure that the proposal is industry goal-driven. To facilitate this a Steering Group (SG) will be set up with membership from major companies. From aerospace industry: BAE Systems, Airbus, Rolls-Royce, Messier-Dowty (MD) and Dstl have already agreed to join. From the wind energy sector, tacit agreement has been secured from NaREC (National Renewable Energy Centre) and Risoe (National Centre for Renewable Energy, Denmark). Academic members of the SG will include Professor James Brownjohn who will advise on transitioning S^3 ideas into the civil infrastructure domain. S^3 ideas will prove powerful in many other contexts, discussion with the Advanced Manufacturing Research Centre in Sheffield will lead to manufacturing applications; discussions with the NetworkRail Innovation & Technology Centre at Sheffield will focus on railways. A User Group (UG) will be used to encourage industrial participants to contribute field data for a system demonstrator. Workshops will be used to solicit members for the UG and to disseminate S^3 ideas into the academic and industrial communities; attendance will be encouraged by provision of bursaries. MD will benefit directly from the proposed work as one of the specific tasks is to detect incipient cracks in aircraft landing gear in fatigue tests; this is expected to lead to a patent. Another task here will lead to enhanced diagnostic capability in neuroimaging and this will motivate further applications of S^3 concepts in future generation healthcare.
Research visitors from Los Alamos National Laboratories (LANL) will aid dissemination of S^3 concepts to US academia and industry. SHM software at LANL will be enhanced by embedding ideas of population-based SHM; as the LANL software is extensively downloaded, this is an effective dissemination channel. By the PI and PDRA lecturing at the LANL Summer School, the students will be exposed to S^3 concepts. As the students go on to employment with major US companies or PhD projects in the most prestigious universities, there is no better way to propagate the S^3 ideas. The PI and PDRA will also give focussed seminars to technical staff at LANL and faculty at the University of San Diego.
Outreach activities are vital; S^3 ideas and its applications to wind energy and healthcare are likely to generate public interest. Presentations at Cafe Scientifique and on regional radio have been successful in the past and will be used here. To maximise media potential the PI and PDRA will attend a Royal Society course on public communication and the media. Ideas for outreach will be explored via creativity$@$home and the SG. Outreach into professional engineering will be via seminars in the programmes of professional institutions. The research will be seen by schoolchildren via demonstrations and interactive activities for the University of Sheffield Engineering Summer School. A web site will be set up for the project with both public and private pages; some pages will be tailored to communication to the lay public and media.
People |
ORCID iD |
| Keith Worden (Principal Investigator / Fellow) |
Publications
Antoniadou (I.)
(2014)
Ontologies and Structural Health Monitoring.
Antoniadou I
(2015)
A time-frequency analysis approach for condition monitoring of a wind turbine gearbox under varying load conditions
in Mechanical Systems and Signal Processing
Antoniadou I
(2015)
Aspects of structural health and condition monitoring of offshore wind turbines.
in Philosophical transactions. Series A, Mathematical, physical, and engineering sciences
Antoniadou, I
(2013)
Cointegration for the removal of environmental and operational effects using a single sensor
in Proceedings of 9th International Workshop on Structural Health Monitoring
Antoniadou, I
(2014)
Towards an ontology for verification and validation in structural dynamics
in Proceedings of 26th International Conference on Noise & Vibration Engineering
Antoniadou, I
(2014)
Use of a spatially adaptive thresholding method for the condition monitoring of a wind turbine gearbox
in Proceedings of 7th European Workshop on Structural Health Monitoring
Baldacchino T
(2016)
Variational Bayesian mixture of experts models and sensitivity analysis for nonlinear dynamical systems
in Mechanical Systems and Signal Processing
| Description | The original vision of the Fellowship is best summarised in the opening overview of the original proposal: `In the Public Health Informatics community, the discipline of Disease Surveillance or Syndromic Surveillance (SS) has emerged as a powerful means of tracking the initiation and progression of disease epidemics in human populations. The discipline is based on the concept of fusing data from radically disparate sources from school attendance records, through public prescription records to the results of internet surveys. Alerting algorithms then establish if an anomalous pattern of spatio-temporal activity is emerging indicative of a possible epidemic. The project proposed here is to establish a parallel discipline of 'Structural Syndromic Surveillance' (S3) for mechanical structures and systems.' This vision was extended as the Fellowship progressed. The work provided new insights, bringing within reach radically new ideas beyond the original ones inspired by Syndromic Surveillance. The main vision, of establishing a population-based approach to SHM stood; however, new approaches could be proposed based on novel ideas, e.g. that population-based SHM can come from a general representation theory of structures, and this led to a proposal for an extension, which was succesful. The Fellowship made major progress in its original aims and proved extremely productive in terms of output; this is summarised here in terms of the original Work Packages (WPs) and tasks. Thread (WP) 1: S3 - A radically new paradigm for SHM}. The broad aim of this thread, from the original proposal, was `... to solve the problem of maintaining, searching and interpreting distributed databases of condition data for populations of structures or systems-of-systems.' The thread was divided into five tasks: T1.1 Preliminary cost-benefit analysis for transition to condition-based population-based maintenance and asset management. T1.2 Develop the conceptual basis for an S3 system appropriate to a fleet of aerospace structures. T1.3 Develop S3-based maintenance system demonstrator appropriate to a System-of-Systems (SoS). T1.4 Develop an S3-based maintenance system demonstrator appropriate to an offshore wind farm. T1.5 Feasibility study for a proof-of-concept demonstrator based on specifications from the industrial partners. It was anticipated that the task order might change as a result of dead ends and windfalls. In fact, the programme moved because of a windfall, resulting in greater and earlier emphasis on Tasks T1.4 and T1.5. Originally, data for the offshore wind context was to come from the EU SYSWIND project and from Los Alamos National Laboratory tests on a single wind turbine (WT) blade and on a population of telescopes. In fact, early in the project, a collaboration with Vattenfall was forged, and the company made available extensive data sets relating to two entire wind farms. As a result, the database development of T1.2 was switched to the offshore wind context, rather than aerospace. The Steering Group (SG) for the project was augmented by representatives of Vattenfall and Siemens Wind Power. Following SG consultation, the feasibility study of Task T1.5 was re-focussed on data from the Lillgrund wind farm; the study continuing throughout the Fellowship. This data motivated the original development of a database as part of Task T1.2; the data are Supervisory Control And Data Acquisition (SCADA) data for 48 WTs, with hundreds of channels spanning many sensor modalities, sampled at ten-minute intervals over an entire year. The initial database was written using a Matlab front end and adopted principles of SS systems, as discussed in the original proposal. Since the project began, a very powerful SHM database has been produced by LANL -- the ECHO system -- and its use was negotiated for the Fellowship and its extension. The work in T1.2, T1.4 and T1.5 on the wind farm data has resulted in many publications (over 5 journal papers and 7 conference papers) which include the first principled attempts to make SHM inferences across populations. Work is also ongoing on data acquired from a WT blade fatigue test, which are also available to the Extension. Creating the basis for population-based SHM has involved new approaches to learning from large SHM data sets for the offshore wind and aerospace contexts of Tasks T1.2 and T1.4. Techniques developed and explored include: active learning, manifold, robust statistical methods, and, autoregressive, treed and heteroscedastic Gaussian processes - all of these are state-of-the-art machine learning/artificial intelligence methods. Greater focus on WTs in T1.4 and T1.5 has also demanded more attention to WT drivetrain condition monitoring, resulting in new signal processing methods and real case studies. Altogether, these studies produced over 20 new publications. The original T1.3 required the development of a laboratory-based SoS demonstrator. Eight structures were acquired and initial tests were completed. Three sets of tailplanes from Piper aircraft yielded three pairs of nominally-identical structures by cutting each into a left and right tail; there are design variations between the pairs (dimensions, numbers of rivets etc.). To create a disparate population, the Tomahawk wing of the original proposal was joined by a composite version. Tests will continue throughout the current Fellowship; results were reported in two papers, which showed that features could be defined which allowed inferences between structures. The set of test structures has also been augmented by the purchase of nine nominally-identical 2m WT blades; initial experiments are reported in. The proposal expressed a wish to implement ideas of population-based SHM in manufacturing, and a collaboration began with Dr Elizabeth Cross (UoS), the Advanced Manufacturing Research Centre (AMRC), and Safran Landing Systems. The initial work was summarised in the four conference papers. Thread (WP) 2: Novel methods of spatio-temporal novelty detection. WP2 was designed to provide solutions to specific problems of spatio-temporal novelty detection - i.e. detecting anomalies across spatial and temporal data sets - to underpin the data analysis technologies for WP1; the specific tasks were: T2.1 Develop Bayesian scan statistics for Acoustic Emission-based crack detection. T2.2 Develop Extreme-Value-based spatial novelty detection. T2.3 Development of new algorithms to project out confounding influences (i.e. benign changes to systems that mask damage. T2.4 Develop Genetic Programming algorithm for 'self-assembly' and optimisation of damage identification strategies. Task T2.1 was based on extending previous work on acoustic emission-based crack detection in landing gear by adapting the idea of spatial scanning statistics from the field of Syndromic Surveillance. This work was carried out in the early stages of the Fellowship; preliminary work led to a new Bayesian form of the scanning statistic, and the fusion of the ideas within the general methodology appeared in two main papers. New work on spatial scanning, based on change detection in spatio-temporal point processes is planned. Task 2.2 experienced delays in securing the proposed neuroimaging data from the main collaborator at the University of York. Acquisition of the data is still being discussed positively, and the delay led to a windfall. While the most recent extreme value theory was being surveyed for the task, it became clear that a very recently-developed variant - extreme function theory -- might prove powerful for wind turbine SHM. An extended version of extreme function theory was developed as a means of novelty detection based on WT power curves and was applied to new Vattenfall data and published, where it was shown to outperform a number of competing approaches to novelty detection in terms of error rates. T2.3 went very well. Cointegration was a technique we previously proposed for removing operational and environmental effects from SHM data, based on a technique from econometrics; but the existing algorithms were largely restricted to linear behaviour. For general SHM data, it was necessary to develop nonlinear cointegration; this was accomplished and resulted in over 10 publications New methods have also been developed for analysing confounding influences, including a powerful means of visualising data based on robust regression, and Bayesian methods. Task 2.4 was based on a new genetic programming algorithm for 'self-assembly' of damage identification strategies, and was to be the basis of a PhD studentship. In fact, the task was accomplished via an external collaboration with LANL and the University of California, San Diego. The task was used as the basis of a PhD project in San Diego and resulted in a collaboration leading to a joint publication. |
| Exploitation Route | The techniques developed will all be of use in any industrial context where damage detection is an issue. The focus of the project was on populations, so any owners or operators of multiple structures (wind farms, aircraft fleets) can potentially extend their structural health monitoring capability using the new ideas. Important general techniques were developed for the specific purposes of anomaly detection, or the removal of confusing influences from data. The project also led to a direct extension from EPSRC which is very much focussed on renewable energy systems; it also provided a lot of the ideas that will be applied in the major collaboration which is the EPSRC Prosperity Partnership between Sheffield, Hull and Durham Universities and Siemens and Orsted (formerly DONG Energy). |
| Sectors | Aerospace, Defence and Marine,Construction,Education,Energy,Financial Services, and Management Consultancy,Healthcare,Manufacturing, including Industrial Biotechology,Transport |
| Description | The project proved to be a foundation for a new research subject of 'population-based structural health monitoring' (PBSHM). The original idea was that the subject could be based on the concept of syndromic surveillance (SS), which originated and developed within the healthcare informatics community. In fact, although a great deal of useful work was carried out and a great many publications resulted, one of the main conclusions of the project was that SS was not on its own sufficient to found a working PBSHM, largely because populations of structures are much more diverse than human populations. With the knowledge gained from the project, it was possible to propose a much more general basis than SS, which was explored in the extension to the project. This new framework led directly to the extension, but also via discussions with Siemens-Gamesa, was instrumental in involving the Inevstigator in the Prosperity Partnership (PP) - 'A New Partnership in Offshore Wind', in which ideas of PBSHM for offshore wind farms were explored across two work-packages. In parallel to the PP, the project led to a separate 'commercial-in-confidence' project with Siemens-Gamesa (SG), which has in turn led to a patent for a new wind turbine blade monitoring system which will potentially be used across the entire SG fleet. Siemens-Gamesa have also made it clear that any renewal of the PP should include research based on the original Fellowship, and on its extension. Furthermore, as a result of the relationship forged with the original project, Siemens-Gamesa initiated an internal experimental project on turbine blade monitoring at a cost of over one million euros, in which the Sheffield team played a critical role. |
| Sector | Aerospace, Defence and Marine,Energy |
| Impact Types | Economic |
| Description | Collaboration with Vattenfall |
| Organisation | Government of Sweden |
| Department | Vattenfall |
| Country | Sweden |
| Sector | Public |
| PI Contribution | New collaboration with Swedish power company Vattenfall. Access to data from an operational wind farm. This is exceptionally valuable and the degree of access is rare for an academic partner. |
| Start Year | 2013 |
| Description | 11th International Workshop on Structural Health Monitoring |
| 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 | Zhang (T.), Worden (K.) & Barthorpe (R.J.) 2017 In Proceedings of 11 th International Workshop on Structural Health Monitoring, Palo Alto, CA. A simplified treed Gaussian process approach to the modelling of bridge data for structural health monitoring. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 11th International Workshop on Structural Health Monitoring |
| 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 | Shi (H.), Worden (K.) & Cross (E.J.) 2017 In Proceedings of 11 th International Workshop on Structural Health Monitoring, Palo Alto, CA. A time series decomposition method for heteroskedastic data in structural health monitoring. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 11th International Workshop on Structural Health Monitoring |
| 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 | Chandrasekhar (K.), Stevanovic (N.), Corbetta (M.), Dervilis (N.) & Worden (K.) 2017 In Proceedings of 11 th International Workshop on Structural Health Monitoring, Palo Alto, CA. On the structural health monitoring of operational wind turbine blades. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 11th International Workshop on Structural Health Monitoring |
| 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 | Fuentes (R.), Ray (N.), Rogers (T.), Worden (K.) & Cross (E.J.) 2017 In Proceedings of 11 th International Workshop on Structural Health Monitoring, Palo Alto, CA. Clustering-based crack growth characterisation using synchronised vibration and Acoustic Emission measurements. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 11th International Workshop on Structural Health Monitoring |
| 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 | Rogers (T.J.), Manson (G.), Worden (K.) & Cross (E.J.) 2017 In Proceedings of 11 th International Workshop on Structural Health Monitoring, Palo Alto, CA. On the Choice of Optimisation Scheme for Gaussian Process Hyperparameters in SHM problems. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 11th International Workshop on Structural Health Monitoring |
| 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 | Fuentes (R.), Worden (K.), Antoniadou (I.), Mineo (C.), Pierce (S.G.) & Cross (E.J.) 2017 In Proceedings of 11 th International Workshop on Structural Health Monitoring, Palo Alto, CA. Compressive sensing for direct time of flight estimation in ultrasound- based NDT. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 12th International Conference on Advances in Experimental Mechanics |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Rooker (T.), Dervilis (N.), Worden (K.), Stammers (J.), Hammond (P.) & Potts (G.) 2017 In Proceedings of BSSM's 12 th International Conference on Advances in Experimental Mechanics, Sheffield, UK. Predicting machining centre geometric tolerance thresholds with support vector machines. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 12th International Conference on Advances in Experimental Mechanics |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Bull (L.), Worden (K.) & Dervilis (N.) 2017 In Proceedings of BSSM's 12 th International Conference on Advances in Experimental Mechanics, Sheffield, UK. Active learning applications to acoustic emission data. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 12th International conference on Damage assessment |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Antoniadou (I.), Worden (K.), Marchesiello (S.), Mba (C.) & Garibaldi (L.) 2017 In Proceedings of 12 th International Conference on Damage Assessment - DAMAS 2017, Kitakyushu, Japan. An illustration of new methods in machine condition monitoring, Part II: Adaptive outlier detection. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 12th International conference on Damage assessment |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Worden (K.), Antoniadou (I.), Marchesiello (S.), Mba (C.) & Garibaldi (L.) 2017 In Proceedings of 12 th International Conference on Damage Assessment - DAMAS 2017, Kitakyushu, Japan. An illustration of new methods in machine condition monitoring, Part I: stochastic resonance. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 12th International conference on Damage assessment |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Civera (M.), Filosi (C.M.), Pugno (N.M.), Silvestrini (M.), Surace (C.) & Worden (K.) 2017 In Proceedings of 12 th International Conference on Damage Assessment - DAMAS 2017, Kitakyushu, Japan. Assessment of vocal cord nodules: a case study in speech processing by using Hilbert-Huang Transform. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 12th International conference on Damage assessment |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Bull (L.A.), Dervilis (N.), Worden (K.) & Cross (E.J.) 2017 In Proceedings of 12 th International Conference on Damage Assessment - DAMAS 2017, Kitakyushu, Japan. Is it worth changing pattern recognition methods for structural health monitoring? |
| Year(s) Of Engagement Activity | 2017 |
| Description | 35th International Modal Analysis conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Fuentes (R.), Cross (E.J.), Ray (N.), Dervilis (N.), Guo (T.) & Worden (K.) 2017 In Proceedings of the 35 th International Modal Analysis Conference, Orange County, CA. In-process monitoring of automated carbon fibre tape layup using ultrasonic guided waves. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 35th International Modal Analysis conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Civera (M.), Surace (C.) & Worden (K.) 2017 In Proceedings of the 35th International Modal Analysis Conference, Orange County, CA. Detection of cracks in beams using treed Gaussian processes. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 35th International Modal Analysis conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Dervilis (N.), Maguire (A.E.), Papatheou (E.) & Worden (K.) 2017 In Proceedings of the 35 th International Modal Analysis Conference, Orange County, CA. Wind turbine health monitoring: current and future trends with an active learning twist. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 35th International Modal Analysis conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Shi (H.), Worden (K.) & Cross (E.J.) 2017 In Proceedings of the 35 th International Modal Analysis Conference, Orange County, CA. An exploratory study on removing environmental and operational effects using a regime-switching cointegration method. |
| Year(s) Of Engagement Activity | 2017 |
| Description | 36th International Modal Analysis Conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Worden (K.), Iakovidos (I.) & Cross (E.J.) 2018 In Proceedings of the 36 th International Modal Analysis Conference, Orlando, FL. On Stationarity and the Interpretation of the ADF Statistic. |
| Year(s) Of Engagement Activity | 2018 |
| Description | 36th International Modal Analysis Conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Rooker (T.), Dervilis (N.), Stammers (J.), Worden (K.), Hammond (P.), Potts (G.) & Brown (T.) 2018 In Proceedings of the 36 th International Modal Analysis Conference, Orlando, FL. Predicting geometric tolerance thresholds in a five-axis machining centre. |
| Year(s) Of Engagement Activity | 2018 |
| Description | 36th International Modal Analysis Conference |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Bull (L.), Manson (G.), Worden (K.) & Dervilis (N.),2018 In Proceedings of the 36 th International Modal Analysis Conference, Orlando, FL. Active learning approaches to structural health monitoring. |
| Year(s) Of Engagement Activity | 2018 |
| Description | 7th International Conference on Advances in Experimental Structural 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 | Worden (K.), Farrar (C.R.), Shi (H.) & Cross (E.J.) 2017 In Proceedings of 7 th International Conference on Advances in Experimental Structural Engineering, Pavia, Italy. Why the Z24 Bridge is so Important. |
| Year(s) Of Engagement Activity | 2017 |
| Description | Airbus Space and Defence |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Meeting with Andy Kiley, Airbus Space and Defence to discuss collaboration opportunities. Also attended by DRG members C. Lord, J. Rongong, D. Wagg & N. Ray |
| Year(s) Of Engagement Activity | 2017 |
| Description | IEEE Symposium Series on Computational Intelligence (SSCI), Hawaii. |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Industry/Business |
| Results and Impact | Dervilis (N.), Antoniadou (I.), Cross (E.J.), Farrar (C.R.) & Worden (K.) 2017 IEEE Symposium Series on Computational Intelligence (SSCI), Hawaii. Aspects of computational intelligence in structural health monitoring. |
| Year(s) Of Engagement Activity | 2017 |
| Description | In Proceedings of Surveillance |
| Form Of Engagement Activity | A talk or presentation |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Professional Practitioners |
| Results and Impact | Coletta (G.), Surace (C.), Worden (K.), Shi (H.) & Cross (E.J.) 2017 In Proceedings of Surveillance 9, Fez, Morocco. Nonlinear cointegration using statistical learning theory. |
| Year(s) Of Engagement Activity | 2017 |
| Description | RAL Space, Airbus Space & Defence, Servotest |
| Form Of Engagement Activity | A formal working group, expert panel or dialogue |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Meeting held between K. Worden, R. Barthorpe, N. Ray, C. Field and Mike Shepherd (NSTF Project Manager, RAL Space), Andy Kiley (Airbus Space & Defence) and Jean-Paul Power (UK Sales Manager, Servotest Testing Systems Ltd). Discussed scope of potential project utilising Chamber 2 & MAST system for approximately 4 weeks. |
| Year(s) Of Engagement Activity | 2018 |
| Description | Royal Aeronautical society RAers 150 event- AMRC |
| Form Of Engagement Activity | Participation in an activity, workshop or similar |
| Part Of Official Scheme? | No |
| Geographic Reach | National |
| Primary Audience | Industry/Business |
| Results and Impact | Sell out event, tour of AMRC facilities, networking opportunities with companies exhibiting. |
| Year(s) Of Engagement Activity | 2016 |