Data61 provides decision support for owners and maintainers of civil and industrial assets. Sensing, continuous monitoring and advanced data analysis techniques enable asset managers to make more informed maintenance decisions.
Assets are typically maintained when something goes wrong or according to preventative maintenance schedules.
These approaches do not make the best use of limited maintenance resources.
Reacting to problems when they occur means assets operate at reduced service levels until resources are mobilised to repair the problem. Preventative (or time based) maintenance is an improvement though often inefficient as maintenance is often done too early or too late.
Data61 has developed technology to enable more informed maintenance decision making. There are three main technology components:
Sensing and Data acquisition – sensors and distributed processing capabilities developed by Data61’s Networks Research Group allow the scalable collection and the efficient analysis of high volumes of data, from small rural structures to large iconic ones.
Data Analytics – analytical techniques developed by Data61’s world-class Machine Learning Research Group and Networks Research Group provide information for specific situations such as damage detection, condition assessment, loading assessment and maintenance prioritisation. Data sources can be from Data61 or other sensing systems, and other sources of data such as environmental data, inspection and maintenance records.
A continuous monitoring service – the service applies data management and the analytical techniques to provide asset managers and engineers with situational awareness and the information they need to make decisions. The service is hosted from Data61 data centres and available to users via web and mobile applications and database services.
Roads and Maritime Services NSW (RMS) needs to maximise service life of the Sydney Harbour Bridge road deck without significant increase in expenditure. Data61 is implementing a bridge monitoring system using 2400 sensors. Machine learning and statistical based predictive analytics assess the data continuously and provide early warning of problems before bridge users are affected.
By continuously monitoring the structural health of each of 800 steel and concrete supports under the roadway, RMS can undertake condition based and predictive based maintenance.
Data61 Structural Health Monitoring enables maintenance to be scheduled based on actual asset condition. Predictive analytics enables maintenance and capital works decisions to be made that maximise return on resources allocated, while maintaining asset performance. The benefits are increased productivity and extended asset life.
- P. Runcie, A. Boulis, M. Ott, R. Berriman, Y. Tselishchev, T. Rakotoarivelo, “Integrity of a civil structure”, US Patent 20,150,142,337, 2013.
- B. Zhang, Z. Li, Y. Wang, and F. Chen, “Determining a health condition of a bridge,” application filed (N12 023-PCT), 2012.
- A.D. Oliván, N.L.D. Khoa, M. Makki Alamdari, Y. Wang, F. Chen, P. Runcie, “A Clustering Approach for Structural Health Monitoring on Bridges”, Journal of Civil Structural Health Monitoring, Springer, 2016.
- M. Makki Alamdari, B. Samali, J. Li, H. Kalhori, and S. Mustapha, “Spectral-Based Damage Identification in Structures under Ambient Vibration” Journal of Computing in Civil Engineering, 2015. (A)
- S. Mustapha, L. Ye, X.J. Dong and M. Makki Alamdari, “Evaluation of Barely Visible Indentation Damage (BVID) in CF/EP Sandwich Composites Using Guided Wave Signals”, Journal of Mechanical Systems and Signal Processing, 2016. (A*)
- Mustapha, S., Hu, Y., Khoa, N.L.D., Alamdari, M.M., Runcie, P., Dackermann, U., Nguyen, V.V., Li, J. and Ye, L., “Pattern Recognition Based on Time Series Analysis Using Vibration Data for Structural Health Monitoring in Civil Structures”, Electronic Journal Of Structural Engineering, Vol 14, Issue 1, 2015.
- Nguyen, V.V., Dackermann, U., Li, J., Alamdari, M.M., Mustapha, S., Runcie, P. and Ye, L., “Damage Identification of a Concrete Arch Beam Based on Frequency Response Functions and Artificial Neural Networks”, Electronic Journal Of Structural Engineering, Vol 14, Issue 1, 2015.
- C. P. Huynh, S. Mustapha, P. Runcie and F. Porikli, “Multi-class support vector machines for paint condition assessment on the Sydney Harbour Bridge using hyperspectral imaging”, Structural Monitoring and Maintenance, Volume 2 , Issue 3, pp. 181-197, 2015.
- S. Mustapha, C. P. Huynh, P. Runcie, F Porikli, “Paint condition assessment of civil structures using hyper-spectral imaging”, 7th International Conference on Structural Health Monitoring of Intelligent Infrastructure (SHMII 2015).
- M. Makki Alamdari, J. Li, B. Samali, P. Runcie, “Symbolic Time-series Analysis of Space Truss Structures”, the 2nd Australasian Conference on Computational Mechanics, Brisbane, Australia, 2015.
- M. Makki Alamdari, V.V. Nguyen, P. Runcie, S. Mustapha, “Damage Characterization in Concrete Jack Arch Bridges Using Symbolic Time Series Analysis”, International workshop on Structural Health Monitoring, Stanford University, California, USA, 2015.
- M. Makki Alamdari, N.L.D. Khoa, P. Runcie, S. Mustapha, U. Dackermann, J. Li, V.V. Nguyen, X. Gu, “Application of unsupervised Support Vector Machine for Condition Assessment of Concrete Structures”, A mini Symposium in PLSE, Brisbane, Australia, 2015.
- N.L.D. Khoa, B. Zhang, Y. Wang, W. Liu, F. Chen, S. Mustapha and P. Runcie, “On Damage Identification in Civil Structures Using Tensor Analysis”, in the 19th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2015), Ho Chi Minh, Vietnam, pp. 459-471, 2015. (A)
- P. Runcie, S. Mustapha & T. Rakotoarivelo, “Advances in structural health monitoring system architecture”, in the fourth International Symposium on Life-Cycle Civil Engineering (IALCCE 2014), Tokyo, Japan, 2014.
- S. Mustapha, Y. Hu, U. Dackermann, V.V. Nguyen, N.L.D. Khoa, P. Runcie, J. Li, L. Ye, “Structural health monitoring in civil structures based on the time series analysis”, in the 9th Austroads Bridge Conference, Sydney, Australia, 2014.
- N.L.D. Khoa, B. Zhang, Y. Wang, F. Chen and S. Mustapha, “Robust Dimensionality Reduction and Damage Detection Approaches in Structural Health Monitoring”, in International Journal of Structural Health Monitoring (SHMIJ), SAGE Publications, vol. 13, issue 4, pp. 406-417, 2014. (A)
- S. Tamura, B. Zhang, Y. Wang, F. Chen, N.L.D. Khoa, “Supervised and unsupervised machine learning approaches for bridge damage prediction”, in International Workshop in Structural Health Monitoring (IWSHM), Stanford, USA, pp. 182-189, 2013.
Download the Structural Health Monitoring brochure.