A comparison of the corrosion inhibition performance in sulfamic acid medium between refluxed and ultrasonic extracts of rapeseed meal

Journal of Colloid and Interface Science, Год журнала: 2025, Номер 688, С. 714 - 735

Опубликована: Фев. 27, 2025

Язык: Английский

---

Fault diagnosis method of mining vibrating screen mesh based on an improved algorithm

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 147, С. 110343 - 110343

Опубликована: Фев. 26, 2025

Язык: Английский

---

Multi-scale defect detection on product surface in grayscale images using YOLOv8-Ms algorithm

Nondestructive Testing And Evaluation, Год журнала: 2025, Номер unknown, С. 1 - 25

Опубликована: Март 23, 2025

Surface defect detection is crucial in engineering quality control. While existing single-stage and two-stage models have advanced the field, conventional object algorithms still face challenges detecting multi-scale defects accurately representing features greyscale images due to their monotonicity. To address these issues, this paper proposes YOLOv8-MS, an enhanced YOLOv8 model for efficient accurate surface detection. We use convolutions design MSC2f module adapt at different scales. A novel GFPN introduced information fusion, a multi-information attention further boosts network's performance. handle single-channel nature of images, we develop input preprocessing method. Experiments on three open-source datasets show that our achieves mean average precision (mAP) 44.7% NEU-DET, 4.1% improvement over YOLOv8, outperforms YOLOv5 other datasets. Moreover, inference time not significantly increased, effectively balancing accuracy efficiency.

Язык: Английский

---

Lightweight defect detection network based on steel strip raw images

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 145, С. 110179 - 110179

Опубликована: Фев. 6, 2025

Язык: Английский

---

Multisource data-driven intelligent method for detecting surface defects in cold-rolled copper strips

Engineering Applications of Artificial Intelligence, Год журнала: 2025, Номер 152, С. 110730 - 110730

Опубликована: Апрель 11, 2025

Язык: Английский

---

AWBN-YOLO: A Surface Defect Detection Method for Aero-Engine Blades in Sample-Limited Scenarios

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Май 8, 2025

In the production process of aero-engine blades (AEBs), surface defect detection is essential. However, data scarcity and class imbalance in practical industrial scenarios make deep learning-based identification AEBs challenging. this article, we propose AWBN-YOLO, an enhanced YOLOv10n-based framework to address these challenges. Specifically, design Adaptive Sample Augmentation Method (ASAM) synthesize photorealistic samples by adaptively aligning geometries with blade contours optimizing background consistency. We also a Feature-driven Wavelet Downsampling (FWD) module preserve critical spatial-frequency details through adaptive wavelet basis selection, enhancing sensitivity fine-grained defects. Furthmore, introduce BiFPN-Concat Normalized Wasserstein Distance Loss (NWD-Loss) optimize multi-scale feature fusion small-defect localization. Experiments on AeBAD-SL dataset, sample-imbalanced benchmark for have proven that AWBN-YOLO can achieve state-of-the-art performance 82.2% precision, 71.9% recall, 71.7% mAP50, surpassing baseline YOLOv10n 2.8%, 1.2%, 2.6%, respectively. achieves superior accuracy while maintaining real-time (140 FPS), offering robust solution quality inspection under constraints.

Язык: Английский

---

A high-precision and real-time lightweight detection model for small defects in cold-rolled steel

Journal of Real-Time Image Processing, Год журнала: 2024, Номер 22(1)

Опубликована: Дек. 23, 2024

Язык: Английский

---