A Novel Layer by Layer Progressive Recognition Algorithm for Wear Particle Sequence Images

To address the challenges of omission and misidentification caused by defocused particles in single-image analysis, a progressive layer-by-layer recognition algorithm for wear particles in ferrograph sequence images is proposed.

First, an instance segmentation model, termed WearIS, is developed for a single ferrograph image. This model incorporates the Convolutional Block Attention Module (CBAM), a variance-cascaded head network, and a segmentation branch fusing deep and shallow features to accurately identify clear wear particles in the images. Second, a progressive layer-by-layer recognition algorithm is designed to iteratively refine the recognition results across sequence images, which utilizes metrics such as the intersection-over-union (IoU) of overlapping particles between consecutive frames and confidence scores.