With environmental issues arising from the excessive use of fossil fuels, clean energy has gained widespread attention, particularly the application of lithium-ion batteries. Lithium-ion batteries are integrated into various industrial products, which necessitates higher safety requirements. Narrowband Internet of Things (NB-IoT) is an LPWA (Low Power Wide Area Network) technology that provides IoT devices with low-power, low-cost, long-endurance, and wide-coverage wireless connectivity. This study addresses the shortcomings of existing lithium-ion battery pack detection systems and proposes a lithium-ion battery monitoring system based on NB-IoT-ZigBee technology. The system operates in a master-slave mode, with the subordinate module collecting and fusing multi-source sensor data, while the master control module uploads the data to local monitoring centers and cloud platforms via TCP and NB-IoT. Experimental validation demonstrates that the design functions effectively, accomplishing the monitoring and protection of lithium-ion battery packs in energy storage power stations.

To prevent the frequent occurrence of transmission line galloping accidents, many scholars have carried out studies. However, there are still many difficulties that have not been solved. To address the issues that have arisen during the installation of the monitoring system, a new installation technique for the galloping monitoring terminal structure has been developed, and structural design and transmission line impact have been taken into account. A method combining Kalman and Mahony complementary filtering has been shown to solve the problem of wire twisting when galloping is taken into account. The displacement is derived by double-integrating the acceleration, although the trend term has a significant impact on the integration result. To handle the trend term issue and other error effects, a method combining the least-squares method, the adaptive smoothing method, and the time-frequency domain hybrid integration approach is used. Finally, the monitoring terminal’s structural design is simulated and evaluated, and the measured amplitude is assessed on a galloping standard test bench. The difference between the measured amplitude and the laboratory standard value is less than 10%, meeting the engineering design criteria. And the galloping trajectory is identical to the test bench trajectory, which is critical for user end monitoring.

Aiming at the real-time object detection requirements of the intelligent control system for laboratory item transportation in mobile embedded unmanned vehicles, this paper proposes a lightweight hybrid detection system based on the OpenMV vision module. The system adopts a two-stage detection mechanism: in long-distance scenarios (>32 cm), fast target positioning is achieved through red threshold segmentation based on the HSV(Hue, Saturation, Value) color space; when in close range (≤32 cm), it switches to a lightweight deep learning model for fine-grained recognition to reduce invalid computations. By integrating the MobileNetV2 backbone network with the FOMO (Fast Object Matching and Occlusion) object detection algorithm, the FOMO MobileNetV2 model is constructed, achieving an average classification accuracy of 94.1% on a self-built multi-dimensional dataset (including two variables of light intensity and object distance, with 820 samples), which is a 26.5% improvement over the baseline MobileNetV2. In terms of hardware, multiple functional components are integrated: OLED display, Bluetooth communication unit, ultrasonic sensor, OpenMV H7 Plus camera, and servo pan-tilt. Target tracking is realized through the PID control algorithm, and finally, the embedded terminal achieves a real-time processing performance of 55 fps. Experimental results show that the system can effectively and in real-time identify and track the detection targets set in the laboratory. The designed unmanned vehicle system provides a practical solution for the automated and low-power transportation of small items in the laboratory environment.

In recent years, multi-modal 3D object detection algorithms have experienced significant development. However, current algorithms primarily focus on designing overall fusion strategies for multi-modal features, neglecting finer-grained representations, which leads to a decline in the detection accuracy of small objects. To address this issue, this paper proposes the Instance-aware Fine-grained feature Enhancement Cross Modal Transformer (IFE-CMT) model. We designed an Instance feature Enhancement Module (IE-Module), which can accurately extract object features from multi-modal data and use them to enhance overall features while avoiding view transformations and maintaining low computational overhead. Additionally, we design a new point cloud branch network that effectively expands the network’s receptive field, enhancing the model’s semantic expression capabilities while preserving texture details of the objects. Experimental results on the nuScenes dataset demonstrate that compared to the CMT model, our proposed IFE-CMT model improves mAP and NDS by 2.1% and 0.8% on the validation set, respectively. On the test set, it improves mAP and NDS by 1.9% and a 0.7%. Notably, for small object categories such as bicycles and motorcycles, the mAP improved by 6.6% and 3.7%, respectively, significantly enhancing the detection accuracy of small objects.

With the rapid advancement of computer vision and deep learning technologies, the accuracy and efficiency of real-time gesture recognition have significantly improved. This paper introduces a gesture-controlled robot system based on thermal imaging sensors. By replacing traditional physical button controls, this design significantly enhances the interactivity and operational convenience of human–machine interaction. First, a thermal imaging gesture dataset is collected using Python3.9. Compared to traditional RGB images, thermal imaging can better capture gesture details, especially in low-light conditions, thereby improving the robustness of gesture recognition. Subsequently, a neural network model is constructed and trained using Keras, and the model is then deployed to a microcontroller. This lightweight model design enables the gesture recognition system to operate on resource-constrained embedded devices, achieving real-time performance and high efficiency. In addition, using a standalone thermal sensor for gesture recognition avoids the complexity of multi-sensor fusion schemes, simplifies the system structure, reduces costs, and ensures real-time performance and stability. The final results demonstrate that the proposed design achieves a model test accuracy of 99.05%. In summary, through its gesture recognition capabilities—featuring high accuracy, low latency, non-contact interaction, and low-light adaptability—this design precisely meets the core demands for “convenient, safe, and natural interaction” in rehabilitation, smart homes, and elderly assistive devices, showcasing clear potential for practical scenario implementation.