Acoustic emission sources localization of laser cladding metallic panels using improved fruit fly optimization algorithm-based independent variational mode decomposition

Laser cladding technology has recently become an essential issue in engineering research and application. Specifically, acoustic emission (AE)-based structural health monitoring (SHM) of metallic panel laser cladding process is a hot research direction in the field of mechanical intelligent fault diagnosis. However, owing to the strong non-stationary characteristics of laser cladding AE signal, it is generally composed of multiple components (e.g. environmental noise, aperiodic pulses and other external signal), traditional AE source localization methods are generally difficult to localize and characterize AE sources in plate-like structure that has complex geometric features, such as laser cladding operations. To address this issue, a new method for the localization of laser cladding AE sources known as improved fruit fly optimization algorithm-based independent variational mode decomposition (IFOA-IVMD) is proposed in this paper, which can optimize effectively the inside parameters (i.e. mode number K and penalty parameter α) of IVMD and decompose adaptively the original AE signal into a number of intrinsic mode function (IMF) components. To validate the performance of the proposed approach, a 316L stainless steel is utilized to collect AE signals during the laser cladding experiments. Moreover, comparisons with three conventional AE source location methods (i.e. PAC AE acquisition system, Newton's method and multiple cross-correlation based on Geiger algorithm) and two representative approaches (i.e. deep learning and Bayesian methodology) for localizing AE sources generated by complex metallic structures are conducted, and the comparison results verify the effectiveness and advantage of the proposed approach in the localization of laser cladding AE sources. Finally, the generalization of the proposed approach is evaluated for typical scenarios in which laser cladding AE sources are generated by different processing parameters. The results demonstrate the effectiveness of the proposed approach for AE-based SHM of plate-like structures.