Reducing Risk and Increasing Reliability and Safety of Compressed Air Systems by Detecting Patterns in Pressure Signals

Document Type : Original Research Article


1 School of Mechanical & Design Engineering, University of Portsmouth, Portsmouth, PO1 2UP, UK.

2 School of Energy & Electronic Engineering, University of Portsmouth, Portsmouth, PO1 2UP, UK.


This paper investigates the design of a classifier that effectively identifies undesired events by detecting patterns in the pressure signal of a compressed air system using a continuous wavelet transform. The pressure signal of a compressed air system carries useful information about operational events. These events form patterns that can be used as ‘signatures’ for event detection. Such patterns are not always apparent in the time domain and hence the signal was transformed to the time-frequency domain. Data was collected using an industrial compressed air system with load/unload control.  Three different operating modes were considered: idle, tool activation , and faulty. The wavelet transforms of the pressure signal revealed unique features to identify events within each mode. A neural network classifier was created to detect faulty compressed air system behaviourbehaviour. Future work will investigate the detection of more faults and using other classification algorithms.


Main Subjects

[1] H. Fridén, L. Bergfors, A. Björk, and E. Mazharsolook, “Energy and LCC optimised design of compressed air systems: A mixed integer optimisation approach with general applicability,” Proc. - 2012 14th Int. Conf. Model. Simulation, UKSim 2012, no. Lcc, pp. 491–496, 2012, doi: 10.1109/UKSim.2012.74.
[2] S. Murphy and K. Kissock, “Simulating Energy Efficient Control of Multiple-Compressor Compressed Air Systems.,” Proc. Ind. Energy Technol. Conf., 2015.
[3] T. Nehler, R. Parra, and P. Thollander, “Implementation of energy efficiency measures in compressed air systems: barriers, drivers and non-energy benefits,” Energy Effic., vol. 11, no. 5, pp. 1281–1302, 2018, doi: 10.1007/s12053-018-9647-3.
[4] M. Benedetti, V. Cesarotti, V. Introna, and J. Serranti, “Energy consumption control automation using Artificial Neural Networks and adaptive algorithms: Proposal of a new methodology and case study,” Appl. Energy, vol. 165, pp. 60–71, 2016, doi: 10.1016/j.apenergy.2015.12.066.
[5] M. Thabet, D. Sanders, V. Beccera, G. Tewkesbury, M. Haddad, and T. Barker, “Intelligent Energy Management of Compressed Air Systems,” in 10th IEEE International Conference on Intelli­gent Systems IS’20, 2020.
[6] D. A. Sanders, D. C. Robinson, M. Hassan, M. Haddad, A. Gegov, and N. Ahmed, “Making decisions about saving energy in compressed air systems using ambient intelligence and artificial intelligence,” Adv. Intell. Syst. Comput., vol. 869, no. September, pp. 1229–1236, 2018, doi: 10.1007/978-3-030-01057-7_92.
[7] A. Santolamazza, V. Cesarotti, and V. Introna, “Evaluation of Machine Learning techniques to enact energy consumption control of Compressed Air Generation in production plants,” Proc. Summer Sch. Fr. Turco, no. 2004, pp. 79–86, 2018.
[8] A. Santolamazza, V. Cesarotti, and V. Introna, “Anomaly detection in energy consumption for Condition-Based maintenance of Compressed Air Generation systems: an approach based on artificial neural networks,” IFAC-PapersOnLine, vol. 51, no. 11, pp. 1131–1136, 2018, doi: 10.1016/j.ifacol.2018.08.439.
[9] A. Desmet and M. Delore, “Leak detection in compressed air systems using unsupervised anomaly detection techniques,” Proc. Annu. Conf. Progn. Heal. Manag. Soc. PHM, pp. 211–220, 2017.
[10] R. X. Gao and R. Yan, Wavelets: Theory and Applications for Manufacturing. Springer, 2011.
[11] P. S. Addison, The illustrated wavelet transform handbook. 2017.
[13] Y. Lei, Intelligent fault diagnosis and remaining useful life prediction of rotating machinery. 2016.
[14] R. Polikar, “Pattern Recognition,” Pattern Recognit., pp. 1–22, 2006, doi: 10.1016/B978-0-12-369531-4.X5000-8.
[15] N. Mohd-Safar, D. Ndzi, D. Sanders, H. Noor and L. Kamarudin, Integration of fuzzy c-means and artificial neural network for short-term localized rainfall forecast in tropical climate. Lecture Notes in Networks and Systems, vol. 16, Springer, pp. 499-516,2017.
[16] Lawrence Berkeley, “Compressed Air: a sourcebook for industry,” pp. 1–128, 2003.
[17] M. Thabet, D. Sanders, M. Haddad, N. Bausch, NG. Tewkesbury, V. Becerra, T. Barker, and J. Piner, Management of compressed air to reduce energy consumption using intelligent systems. Advances in Intelligent Systems and Computing, vol. 1252, Springer, pp. 206-217, 2020. doi10.1007/978-3-030-55190-2_16.
[18] D. Robinson, D. Sanders, and E. Mazharsolook, 'Ambient intelligence for optimal manufacturing and energy efficiency', Assembly Automation, vol. 35, no. 3, pp. 234-248. 2018, doi10.1108/AA-11-2014-087.
[19] D. Robinson, D. Sanders, and E. Mazharsolook, 'Sensor-based ambient intelligence for optimal energy efficiency', Sensor Review, vol. 34, no. 2, pp. 170 - 181. 2014, doi10.1108/SR-10-2012-667.
[20] D. Sanders, 'Artificial intelligence tools can aid sensor systems: original paper based journal publication in Control Engineering', Control Engineering, pp. 44-48, 2013.
[21] P. Omoarebun, D. Sanders, F. Ikwan, M. Hassan Sayed, M. Haddad, M. Thabet, J. Piner, and A. Shah, Intelligent monitoring using hazard identification technique and multi-sensor data fusion for crude distillation column. Intelligent Systems and Applications: Volume 3. Advances in Intelligent Systems and Computing, vol. 1252, Springer, pp. 730-741, 2020, doi10.1007/978-3-030-55190-2_61.
[22] M. Haddad, D. Sanders, G. Tewkesbury, and N. Bausch, 'Analysing the Behaviour of Three Discrete Multi-Criteria Decision Making Methods in the Presence of Uncertainty', Operational Research Perspectives.
[23] Haddad, MJM & Sanders, D 2018, 'Selection of discrete multiple criteria decision making methods in the presence of risk and uncertainty', Operational Research Perspectives, vol. 5, pp. 357-370, 2019, doi10.1016/j.orp.2018.10.003.