Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves wood utilization. Traditional neural network techniques have not yet been employed for wood defect detection due to long training time, low recognition accuracy, and nonautomatical extraction of defect image features. In this work, a model (so‐called ReSENet‐18) for wood knot defect detection that combined deep learning and transfer learning is proposed. The “squeeze‐and‐excitation” (SE) module is firstly embedded into the “residual basic block” structure for a “SE‐Basic‐Block” module construction. This model has the advantages of the features that are extracted in the channel dimension, and it is fused in multiscale with original features. Instantaneously, the fully connected layer is replaced with a global average pooling; consequently, the model parameters could be reduced effectively. The experimental results show that the accuracy has reached 99.02%, meanwhile the training time is also reduced. It shows that the proposed deep convolutional neural network based on ReSENet‐18 combined with transfer learning can improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects.

Rolling bearings are essential transmission and support components in aircraft engines, playing a critical role in ensuring their safe and stable operation. Rolling bearing faults have a significant impact and should not be ignored. The effective diagnosis of bearing faults has always been a critical requirement for ensuring reliable operation. With the increasing demands of modern manufacturing to reduce costs and improve quality, the development of advanced bearing fault detection methods has become indispensable. This paper presents the brief review of recent trends in research on bearing failure modes, bearing fault detection and diagnosis methods, and development trends and prospects. This article provides a comprehensive review of the existing fault diagnosis methods for rolling bearings in four aspects: the integration of advanced sensor technology and advanced data processing technology, multimodal fusion, intelligent detection, and real-time monitoring. It discusses methods based on vibration analysis, acoustic methods, current-based methods, electromagnetic methods, infrared methods, radiographic methods, visual methods, and intelligent detection methods. This study reveals that the application of intelligent detection technology, multimodal fusion detection technology, and real-time online monitoring technology has achieved favorable results. In the future, bearing fault detection will develop in a more intelligent, integrated, and real-time direction.

Wood defects are quickly identified from an optical image based on deep learning methodology, which effectively improves the wood utilization. The traditional neural network technique is unemployed for the wood defect detection of optical image used, which results from a long training time, low recognition accuracy, and nonautomatic extraction of defect image features. In this paper, a wood knot defect detection model (so‐called BLNN) combined deep learning is reported. Two subnetworks composed of convolutional neural networks are trained by Pytorch. By using the feature extraction capabilities of the two subnetworks and combining the bilinear join operation, the fine‐grained features of the image are obtained. The experimental results show that the accuracy has reached up 99.20%, and the training time is obviously reduced with the speed of defect detection about 0.0795 s/image. It indicates that BLNN has the ability to improve the accuracy of defect recognition and has a potential application in the detection of wood knot defects.

Defects, such as delamination and debonding, are critical to the performance of carbon fiber-reinforced polymer (CFRP) composites. In recent years, non-destructive testing techniques have been improved for the inspection of these defects among CFRPs. In this study, an all-optical and non-destructive laser ultrasonic technique with an optical microphone detection module has been presented to detect the artificial subsurface defects among the CFRP composites. A finite element simulation based on the thermo-mechanical coupling model was used to study the process of nanosecond pulsed laser excitation of the CFRP laminate to produce ultrasound and the propagation behavior of ultrasound among the CFRP laminate. A series of non-contact laser ultrasonic testing experiments were carried out to study the flat bottom holes of different sizes via a laser ultrasonic detection system. The artificial subsurface defects were reliably identified by the presented all-optical laser ultrasonic system imbedded in the optical microphone using four feature images.

For the first time, organic light-emitting diodes (OLEDs) based on bis(8-hydroxyquinoline) zinc with a styryl group (ZnStq) dispersed in poly(N-vinylcarbazole) matrix (ZnStq_R:PVK, where R = H, Cl, OCH₃) were fabricated. The ZnStq_R:PVK films made via the spin-coating method were used as the active layer in these devices. The produced OLEDs showed strong electroluminescence with yellow emissions at 590, 587 and 578 nm for the ZnStq_H:PVK, ZnStq_Cl:PVK and ZnStq_OCH₃:PVK, respectively. For all the studied thin films, the main photoluminescence emission bands were observed between 565 and 571 nm. The OLED with the ZnStq_OCH₃:PVK layer with a narrow electroluminescence spectrum was found to have sufficient color purity to produce ultra-high-resolution displays with reduced power consumption (full width at half maximum of 59 nm, maximum brightness of 2244 cd/m² and maximum current efficiency of 1.24 cd/A, with a turn-on voltage of 6.94 V and a threshold voltage of 7.35 V). To characterize the photophysical properties of the active layer, the ZnStq_R:PVK layers samples were additionally deposited on glass and silicon substrates. We found that the obtained results predestine ZnStq_R:PVK layers for use in the lighting industry in the future.