The battery industry has been growing fast because of strong demand from electric vehicle and power storage applications.Laser welding is a key process in battery manufacturing. To control the production quality, the industry has a great desire for defect inspection of automated laser welding. Recently, Convolutional Neural Networks (CNNs) have been applied with great success for detection, recognition, and classification. In this paper, using transfer learning theory and pre-training approach in Visual Geometry Group (VGG) model, we proposed the optimized VGG model to improve the efficiency of defect classification. Our model was applied on an industrial computer with images taken from a battery manufacturing production line and achieved a testing accuracy of 99.87%. The main contributions of this study are as follows: (1) Proved that the optimized VGG model, which was trained on a large image database, can be used for the defect classification of laser welding. (2) Demonstrated that the pre-trained VGG model has small model size, lower fault positive rate, shorter training time, and prediction time; so, it is more suitable for quality inspection in an industrial environment. Additionally, we visualized the convolutional layer and max-pooling layer to make it easy to view and optimize the model.

Fiber Bragg gratings (FBGs) inscribed by using femtosecond laser point-by-point (PbP) technology typically have high birefringence due to the elliptical cross-sectional pattern of refractive index modulations (RIMs) created in the fiber core. Additionally, a highly reflective type II PbP FBG, which has a large coupling coefficient, also exhibits large insertion loss due to the limited RIM area induced by a single femtosecond laser pulse. Here we demonstrate a slit beam shaping method for femtosecond laser PbP inscription of high-quality FBGs, featuring by high reflectivity, low insertion loss, and low birefringence. The slit beam shaping method could reduce the ellipticity in the cross-sectional pattern of RIMs without reducing the cross-sectional area, leading to low birefringence and low insertion loss. The experimental results agree well with numerical calculations. Hence, a high-quality type II PbP FBG, which has high reflectivity of 99.12% (i.e., Bragg resonance attenuation of 20.52 dB), low insertion loss of 0.30 dB, and low birefringence of 1.86 × 10 ^-6 , was successfully created by use of a slit width of 0.8 mm. Moreover, an enlarged cross-sectional area was created by use of a slit width of 0.2 mm, resulting in a high ratio of 172.46 of the coupling strength coefficient to the scattering loss coefficient in the fabricated PbP FBG, which exhibits very high reflectivity of 99.99% (i.e., a strong Bragg resonance attenuation of 46.65 dB) and low insertion loss of 0.27 dB. Such high-quality FBGs will be promising in many applications, such as optical fiber communications, sensors, and lasers.

Reconfigurable intelligent surface (RIS) has recently been regarded as a potential technique to enhance the performance of wireless communication systems by creating additional communication links. However, it is almost impossible to get the perfect channel state information (CSI) from the base station (BS) to the Internet of Things Devices (IoTDs) and the RIS-related channels. Furthermore, residual transceiver hardware impairments inevitably affect the performance of wireless communication systems. Hence, we study the robust design for an RIS-aided wireless communication system based on the imperfect CSI and hardware impairments. Minimizing the power consumption of BS is formulated by ensuring the minimum signal-to-interference-plus-noise ratio (SINR) demands of the IoTDs and the unit-modulus constraints of the RIS. Specifically, after approximating the nonconvex constraints by using the S-procedure and the successive convex approximation (SCA) methods, we adopt the block coordinate descent (BCD) technique to iteratively optimize one set of variables while keeping the other variables fixed in various channel uncertainty scenarios. Simulation results demonstrate that the influence of transceiver hardware impairments can be effectively decreased by deploying RIS even with channel uncertainty, which is more advantageous than increasing the number of BS’s antennas.

Research on light modulation has typically examined the wavelength, intensity, and exposure time of light, and measured rhythm, sleep, and cognitive ability to evaluate the regulatory effects of light variables on physiological and cognitive functions. Although the frequency of light is one of the main dimensions of light, few studies have attempted to manipulate it to test the effect on brain activation and performance. Recently, 40-Hz light stimulation has been proven to significantly alleviate deficits in gamma oscillation of the hippocampus caused by Alzheimer’s disease. Although this oscillation is one of the key functional characteristics of performing memory tasks in healthy people, there is no evidence that 40-Hz blue light exposure can effectively regulate brain activities related to complex cognitive tasks. In the current study, we examined the difference in the effects of 40-Hz light or 0-Hz light exposure on brain activation and functional connectivity during a recognition memory task. Through joint augmentation of visual area activation, 40-Hz light enhanced brain areas mostly in the limbic system that are related to memory, such as the hippocampus and thalamus. Conversely, 0-Hz light enhanced brain areas mostly in the prefrontal cortex. Additionally, functional connection analysis, with the hippocampus as the seed point, showed that 40-Hz light enhanced connection with the superior parietal lobe and reduced the connection with the default network. These results indicate that light at a frequency of 40 Hz can change the activity and functional connection of memory-related core brain areas. They also indicate that in the use of light to regulate cognitive functions, its frequency characteristics merit attention.

Due to the tremendous expectations placed on batteries to produce a reliable and secure product, fault detection has become a critical part of the manufacturing process. Manually, it takes much labor and effort to test each battery individually for manufacturing faults including burning, welding that is too high, missing welds, shifting, welding holes, and so forth. Additionally, manual battery fault detection takes too much time and is extremely expensive. We solved this issue by using image processing and machine learning techniques to automatically detect faults in the battery manufacturing process. Our approach will reduce the need for human intervention, save time, and be easy to implement. A CMOS camera was used to collect a large number of images belonging to eight common battery manufacturing faults. The welding area of the batteries’ positive and negative terminals was captured from different distances, between 40 and 50 cm. Before deploying the learning models, first, we used the CNN for feature extraction from the image data. To over-sample the dataset, we used the Synthetic Minority Over-sampling Technique (SMOTE) since the dataset was highly imbalanced, resulting in over-fitting of the learning model. Several machine learning and deep learning models were deployed on the CNN-extracted features and over-sampled data. Random forest achieved a significant 84% accuracy with our proposed approach. Additionally, we applied K-fold cross-validation with the proposed approach to validate the significance of the approach, and the logistic regression achieved an 81.897% mean accuracy score and a +/− 0.0255 standard deviation.