Development of intelligent leak detection system based on artificial pressure transient signal using integrated Kurtosis-based Algorithm for Z-filter Technique (I-Kaz)

• Main Authors: Hanafi, M. Yusop, M. F., Ghazali, Mohd Fadhlan, Mohd Yusof, Wan Sofian, Wan Hamat
• Format: Article
• Language: English
• Published: UiTM Press 2017
• Subjects: TJ Mechanical engineering and machinery
• Online Access: http://umpir.ump.edu.my/id/eprint/21759/1/Development%20of%20intelligent%20leak%20detection%20system%20based%20on%20artificial%20pressure%20transient%20signal.pdf; http://umpir.ump.edu.my/id/eprint/21759/; http://jmeche.com/wp-content/uploads/bsk-pdf-manager/7_Vol_4_4_T6_09_223.pdf
• Institution: Universiti Malaysia Pahang

In recent studies, the analysis of pressure transient signal can be seen as an accurate and low-cost method for the leak and feature detection in water distribution system. This paper applied Hilbert-Huang Transform (HHT) as a method to analyse the pressure transient signal. HHT is a way to decompose a signal into intrinsic mode function (IMF). However, this method has the difficulty in selecting the suitable IMF for the next data post-processing method which is Hilbert Transform (HT). To develop intelligent leak detection system through Hilbert-Huang Transform (HHT) analysis, the selection for IMF must be automated and self-decision making process through the system. The current paper presented the implementation of Integrated Kurtosis-based Algorithm for z-filter Technique (I-Kaz) to kurtosis ratio (I-Kaz-Kurtosis) for the purpose of self-decision method in selecting IMF with the correct IMF selecting criterion. This work demonstrated artificial sine signal constructed using Matlab software in order to identify the effectiveness and accuracy of this method. Meanwhile, a random signal was also generated to test the efficiency of I-Kaz-kurtosis ratio. The analysis results using I-Kaz-kurtosis ratio revealed that the method was suggested to be used as self-decision method to select the right IMF. The performance of I-Kaz-kurtosis ratio was also tested using random signal and this method revealed positive results. Meanwhile, the efficiency of I-Kaz-kurtosis ratio was compared to kurtosis coefficient, and this method revealed better result from kurtosis coefficient. Therefore, I-Kaz-kurtosis ratio is recommended and advised to be implemented as self-decision method for selecting the IMF through HHT analysis and intelligent leak detection system can be developed.