A novel ultrasonic inspection method of the heat exchangers based on circumferential waves and deep neural networks

Azamatjon Kakhramon Ugli Malikov; Younho Cho; Young H Kim; Jeongnam Kim; Hyung-Kyu Kim

doi:10.1177/00368504221146081

A novel ultrasonic inspection method of the heat exchangers based on circumferential waves and deep neural networks

Sci Prog. 2023 Jan-Mar;106(1):368504221146081. doi: 10.1177/00368504221146081.

Authors

Azamatjon Kakhramon Ugli Malikov¹, Younho Cho², Young H Kim³, Jeongnam Kim¹, Hyung-Kyu Kim⁴

Affiliations

¹ Graduate School of Mechanical Engineering, 34996Pusan National University, Busan, Korea.
² School of Mechanical Engineering, 34996Pusan National University, Busan, Korea.
³ Institute of Nuclear Safety and Management, 34996Pusan National University, Busan, Korea.
⁴ Nuclear Fuel Safety Research Division, 65405Korea Atomic Energy Research Institute, Daejeon, Korea.

Abstract

The heat exchanger (HE) is an important component of almost every energy generation system. Periodic inspection of the HEs is particularly important to keep high efficiency of the entire system. In this paper, a novel ultrasonic water immersion inspection method is presented based on circumferential wave (CW) propagation to detect defective HE. Thin patch-type piezoelectric elements with multiple resonance frequencies were adopted for the ultrasonic inspection of narrow-spaced HE in an immersion test. Water-filled HE was used to simulate defective HE because water is the most reliable indicator of the defect. The HE will leak water no matter what the defect pattern is. Furthermore, continuous wavelet transform (CWT) was used to investigate the received CW, and inverse CWT was applied to separate frequency bands corresponding to the thickness and lateral resonance modes of the piezoelectric element. Different arrangements of intact and leaky HE were tested with several pairs of thin piezoelectric patch probes in various instrumental setups. Also, direct waveforms in the water without HE were used as reference signals, to indicate instrumental gain and probe sensitivity. Moreover, all filtered CW corresponding to resonance modes together with the direct waveforms in the water were used to train the deep neural networks (DNNs). As a result, an automatic HE state classification method was obtained, and the accuracy of the applied DNN was estimated as 99.99%.

Keywords: circumferential wave; continuous wavelet transform (CWT); deep neural networks; heat exchangers; leaky guided waves; ultrasonic guided waves.