Fabric defect detection is very important in the textile quality process. Current deep learning algorithms are not effective in detecting tiny and extreme aspect ratio fabric defects. In this paper, we proposed a strong detection method, Priori Anchor Convolutional Neural Network (PRAN-Net), for fabric defect detection to improve the detection and location accuracy of fabric defects and decrease the inspection time. First, we used Feature Pyramid Network (FPN) by selected multi-scale feature maps to reserve more detailed information of tiny defects. Secondly, we proposed a trick to generate sparse priori anchors based on fabric defects ground truth boxes instead of fixed anchors to locate extreme defects more accurately and efficiently. Finally, a classification network is used to classify and refine the position of the fabric defects. The method was validated on two self-made fabric datasets. Experimental results indicate that our method significantly improved the accuracy and efficiency of detecting fabric defects and is more suitable to the automatic fabric defect detection.

Film cooling technology is of great significance to enhance the performance of aero-engines and extend service life. With the increasing requirements for film cooling efficiency, researchers and engineers have carried out a lot of work on the precision and digital measurement of cooling holes. Based on the above, this paper outlines the importance and principles of film cooling technology and reviews the evolution of cooling holes. Also, this paper details the traditional measurement methods of the cooling hole used in current engineering scenarios with their limitations and categorizes digital measurement methods into five main types, including probing measurement technology, optical measurement technology, infrared imaging technology, computer tomography (CT) scanning technology, and composite measurement technology. The five types of methods and integrated automated measurement platforms are also analyzed. Finally, through a generalize and analysis of cooling hole measurement methods, this paper points out technical challenges and future trends, providing a reference and guidance for forward researches.

Film cooling technology is of great significance to enhance the performance of aero-engines and extend service life. With the increasing requirements for film cooling efficiency, researchers and engineers have carried out a lot of work on the precision and digital measurement of cooling holes. Based on the above, this paper outlines the importance and principles of film cooling technology, reviews the evolution of cooling holes. Also, this paper details the traditional measurement methods of the cooling hole used in current engineering scenarios with their limitations and categorizes digital measurement methods into five main types, including probing measurement technology, optical measurement technology, infrared imaging technology, computer tomography(CT) scanning technology, and composite measurement technology. The five types of methods and integrated automated measurement platforms are also analyzed. Finally, through a generalize and analysis of cooling hole measurement methods, this paper points out technical challenges and future trends, providing a reference and guidance for forward researches.

As a key part of the fabric quality control for the textile industry, it is important to detect fabric defects quickly, accurately, and efficiently. To address the missed detection of the defects with tiny, extreme aspect ratios, and low contrast in fabric images, an improved YOLOv8s-HCG algorithm is proposed in this paper. First, the histogram specification algorithm is used to enhance the defect feature expression of low-contrast fabric images at the input side. Second, the content-aware reassembly of features (CARAFE) operator is used instead of the nearest-neighbor interpolation operator for up-sampling in the YOLOv8s. The CARAFE operator aggregates contextual information in a large receptive field to reassemble abundant detailed features, and reassembles features by using targets in the feature map with the adaptive reassembled kernel. Finally, the global attention mechanism module is added into the YOLOv8s neck network to construct the interdependence relationship between fabric defect image channels and spatial dimensions to capture important features. The algorithm was validated on a self-made fabric dataset and two public fabric datasets. The comparison experimental results show that the detection performance of the proposed algorithm in this paper is better than the other algorithms for defects with extreme aspect ratios, tiny, and low contrast. This research is of great significance to the fabric defect detection industry.

Excitation-emission fluorescence spectra is very effective to predict the concentration of organics in samples. However, redundant information and noises in the excitation-emission matrix (EEM) decrease the accuracy of the prediction concentration. Here we proposed a method to select more useful excitation and emission spectra from the EEM to increase the accuracy of prediction concentration and reduce the processing time. First, the excitation wavelengths were selected based on the clustering method to limit the redundant information in the EEM. Then the emission wavelengths were selected based on the Monte-Carlo method. To validate this method, we established the concentration prediction model with the spectra corresponding to the selected wavelengths by partial least square regression and predicted the multi component concentrations in the test samples. Our studies indicate that incorporation of this method increases the accuracy of the prediction concentration of organics and reduces the processing time.