Crack Classification of a Pressure Vessel Using Feature Selection and Deep Learning Methods

Manjurul Islam, Muhammad Sohaib, Jaeyoung Kim, Jong-Myon Kim

Research output: Contribution to journalArticlepeer-review

25 Citations (Scopus)


Pressure vessels (PV) are designed to hold liquids, gases, or vapors at high pressures in various industries, but a ruptured pressure vessel can be incredibly dangerous if cracks are not detected in the early stage. This paper proposes a robust crack identification technique for pressure vessels using genetic algorithm (GA)-based feature selection and a deep neural network (DNN) in an acoustic emission (AE) examination. First, hybrid features are extracted from multiple AE sensors that represent diverse symptoms of pressure vessel faults. These features stem from various signal processing domains, such as the time domain, frequency domain, and time-frequency domain. Heterogenous features from various channels ensure a robust feature extraction process but are high-dimensional, so may contain irrelevant and redundant features. This can cause a degraded classification performance. Therefore, we use GA with a new objective function to select the most discriminant features that are highly effective for the DNN classifier when identifying crack types. The potency of the proposed method (GA + DNN) is demonstrated using AE data obtained from a self-designed pressure vessel. The experimental results indicate that the proposed method is highly effective at selecting discriminant features. These features are used as the input of the DNN classifier, achieving a 94.67% classification accuracy.
Original languageEnglish
Article number4379
Issue number12
Publication statusPublished (in print/issue) - 11 Dec 2018


  • fatique crack detection
  • feature extraction
  • genetic algorithm
  • deep learning
  • pressure vessel
  • petrochemical industries
  • acoustic emission examination
  • nondestructive testing


Dive into the research topics of 'Crack Classification of a Pressure Vessel Using Feature Selection and Deep Learning Methods'. Together they form a unique fingerprint.

Cite this