Efficient Detection of Defective Parts with Acoustic Resonance Testing Using Synthetic Training Data

Abstract

Analyzing eigenfrequencies by acoustic resonance testing enables a fast screening of components regarding structural defects. The eigenfrequencies of each specific part depend on the general geometric and material properties, including tolerable part-to-part variations, as well as on possible structural flaws. Separating good parts from defective ones is not straightforward and each application-specific sorting algorithm is usually found from experimental training data. However, there are limitations and training data collection may be intricate. We worked on this challenge focusing on machine-made model parts varying slightly in geometry. The application objective was the eigenfrequency-based detection of parts featuring a through-hole test defect drilled into some of the parts and enlarged stepwise. The eigenfrequencies were measured concomitantly. Unlike the industry standard, our approach is based on synthetic training data created mainly by simulation techniques, which resulted in a principally satisfactory classification of the good and defective parts. However, the parts with small defects were not identified from the eigenfrequencies alone, due to overlaying geometric variations. In order to counteract such noise and to improve defect detection based on synthetic training data, the specific actual part geometry was used, in the sense of additional a priori information. A multimodal data evaluation model showed a clearly enhanced sorting power.

A Smart, Data-Driven Approach to Qualify Additively Manufactured Steel Samples for Print-Parameter-Based Imperfections

“…To further reinforce the accuracy of the frequencies elaborated in Table 6 , simulated frequencies of Mode-1 from Table 5 were inserted as column 5 for reference. The difference between the two hovered at 0.2%; such a difference was seen by other authors [ 10 ] when comparing the FEA data with experimental values. After finding a congruence between the experimental and FEM results, the sample quality was classified into three categories.…”

“…The in-plane or extensional modes (one longitudinal displacement prevails) is also seen along with bi-in-plane modes (two longitudinal displacement acts simultaneously) [ 29 ]. The modes are a combination of Mode-1, Mode-2, Mode-3, etc., according to an ascending order usually seen in a geometrically mean part [ 10 ]. The modal frequencies vary in a mode-specific way as a function of the mechanical part structures.…”

“…After the signals are obtained, a variety of filtering and transformation techniques are applied to extract different sound properties, including damping characteristics, amplitudes, and eigenfrequencies. By using an appropriate algorithm, which may separate good and bad samples based on sound characteristics, in addition to carrying out the filtering and transformation, operations can also be realized [ 10 ].…”

“…We next use the dataset to train a regression modelling algorithm. Subsequently, the algorithm might be incorporated into a tool designed especially for 3D-printed sample quality checking [ 10 ].…”

Examining the Feasibility of Acoustic Resonance Testing (ART) for Quality Control in Manufacturing

“…Furthermore, by comparing simulation data and experimental data, it is possible to determine which measurement methods are suitable for determining which eigenfrequencies and which correction factors must be applied [5,6].…”