Condition monitoring (CM) of rotating machinery is critical for maintaining operational efficiency, reducing maintenance costs, and preventing unexpected failures. Traditionally, CM has relied primarily on vibration-based analysis using contact sensors. While effective, such approaches require physical installation and may interfere with system operation. Recent advances in vision-based techniques offer significant advantages, including non-contact measurement, full-field analysis, and high spatial resolution. This study presents a novel stroboscopic imaging-based method for monitoring the condition of rotating blades. Unlike conventional stroboscopic approaches that depend on costly lighting systems and high-speed cameras, the proposed technique operates with low-cost imaging hardware by combining phase-synchronized acquisition with vision-based measurement. The system employs a vision sensor triggered by phase-locked signals synchronized with the rotational speed to produce stroboscopic video sequences. These sequences are analyzed using a phase-based optical flow algorithm to estimate micro-displacements of rotating structures marked with designed markers. The resulting displacement fields are processed to extract diagnostic features, which are then used to classify structural conditions as normal or damaged. Experimental validation demonstrates that the method can reliably detect critical fault modes, including bolt loosening, mass imbalance, and shaft misalignment. The results highlight the potential of this vision-based approach to deliver robust, accurate, and efficient CM of rotating machinery, offering clear advantages over traditional contact-sensor methods. The proposed technique advances the development of non-invasive CM solutions and can be extended to a broad range of rotating mechanical systems.

• Robust vibration measurement under large motion and pose variations. • Crossline provides perspective-invariant features for robust center detection. • Crossline center accurately located using intersection of phase zero-crossing lines. • Enhanced pixel-wise camera imaging simulation improves sub-pixel motion validation. • Validated technique achieves image-plane tracking accuracy under 0.003 pixels. Monitoring of a vibrating target undergoing large motion has been an interest in the field of industrial informatics, aerospace testing, etc. However, the large translation and the possible pose variation of target impose difficulties to a stable and accurate vibration monitoring using vision tracking techniques. Herein, this study proposes a phase-based crossline center detection technique capable of accurate and robust absolute image-plane displacement tracking (mean absolute error under 0.003 pxl) even under large motion and severe pose changes. The two orthogonal lines of crossline pattern remain as line patterns even after perspective transformation, providing a stable feature for lateral phase extraction and center detection. Each line position is determined by searching for the phase zero-crossings after phase extraction along two directions, without the requirement of constant phase assumption and phase pyramid as the conventional phase-based optical flow. The center is accurately detected by intersecting the two lines. This study provides a derivation of the phase-based crossline center detection process, demonstrating that the marker center can be precisely located using phase zero-crossing. An improved pixel-wise camera imaging simulation method is also proposed to validate the accuracy and robustness of the proposed technique with different filter parameters and crossline poses and sizes. Laboratory experiments are conducted on a movable shaker with constant-amplitude vibration output testing the accuracy and robustness of the proposed technique. Field experiment is performed by monitoring the vibration of a moving spindle on a hybrid machine tool with comparison with accelerometers. The results confirm the effectiveness of the proposed phase-based crossline center detection and its potential for vibration monitoring tasks even with large motion and pose changes. In this context, accuracy refers to image-plane displacement, which corresponds to physical motion under planar conditions, while under significant pose changes and large motion it primarily indicates the motion’s order of magnitude, trends, and frequency content.

Recently, laser scanning-based full-field ultrasonic imaging techniques have emerged and gained tremendous interest from the structural health monitoring and non-destructive evaluation community. They offer several advantages, including noncontact structural measurement of structural response with high spatial resolution. This work presents an improved damage detection technique for non-isotropic composite structures using a steady-state response based on the use of a laser Doppler vibrometer (LDV). The basic principle behind this technique is to apply high-frequency steady-state excitations through a surface-bonded piezoelectric transducer and measure the subsequent steady-state wavefield using an LDV with a mirror-titling device. A wavenumber filtering process is then applied to determine the variations of the wavenumber components of each measured point. This technique performs directional correction of the wavenumber to minimize the anisotropic characteristic of composite plates for damage detection using local wavenumber variations. To validate this proposed technique, several experiments were performed on composite structures with introduced delamination damage. The results showed that the proposed technique is efficient in detecting and quantifying delamination and debonding damage on anisotropic composite structures.