Abstract:Aiming at the demand of UAV for high-altitude weather detection, in this paper, an armoured platinum resistance temperature sensor with radiation shield is designed. Firstly, a computational fluid dynamics (CFD) approach was employed to work out the solar radiation error of armoured platinum resistance temperature sensors with or without radiation shield under multi-physical fields, and the comparative analysis was carried out. Then, Support Vector Machine (SVM) and Particle Swarm Optimization Support Vector Machine (PSO-SVM) algorithms were used for training data to compare the the forecast models. Finally, a low-pressure wind tunnel experimental setup was constructed for simulating the upper atmosphere environment, and the experimental data and the algorithm prediction results were compared. The experimental findings indicate that the mean measurement discrepancy of the proposed platinum resistance temperature sensor with radiation shield is 0.014 1 K, and the root mean square error is 0.015 0 K.

Abstract:This paper addresses the challenges of poor accuracy and reliability in fault diagnosis for hydraulic mechanical drive gear sets by proposing a research approach based on Support Vector Machines (SVM). The study begins by collecting vibration signals from the hydraulic mechanical drive gear group and constructing a fault signal separation model. Utilizing a low-rank algorithm, the research separates the vibration source signals of the hydraulic mechanical drive gearbox. Constraint conditions are designed for gear group fault signals to facilitate their classification. Based on these classification results, the SDAE model is employed to extract fault features from the hydraulic mechanical drive gear group. The extracted features are then input into the SVM for training, with the final output being the optimal diagnostic result. This approach achieves fault diagnosis of the hydraulic mechanical drive gear group based on SVM. Experimental results demonstrate that the classification error rate of this method does not exceed 3.5%, confirming its high feasibility.

Abstract:In unexpected emergency response scenarios, it is necessary to quickly obtain global situational images of the scene for subsequent assessment and decision-making. Swarm UAVs have the advantages of large number, low cost and fast imaging, and are widely used in military fields. This paper explores the application of swarm UAV cooperative reconnaissance to the field of emergency remote sensing, and constructs a swarm UAV remote sensing digital simulation and verification system, which researches and simulates and verifies the swarm UAV′s formation coordination, airway planning, and cooperative splicing of multi-channel video. Aiming at the problem of unstable overlap rate between multiple video frames, an adaptive dynamic sampling algorithm is proposed to maintain the idempotence of the overall efficiency of the splicing algorithm under different overlap rates. Subsequently, for the unstable characteristics of video streams in response scenes, a breakpoint re-splicing algorithm is proposed to ensure that the availability of the algorithm can be maintained at the expense of splicing accuracy in poor shooting environments. The results show that: swarm UAVs can construct a global situational image of the scene in quasi real-time, and this paper can provide technical support for the application of swarm UAVs in the field of remote sensing in emergency response.

Abstract:Aiming at the airway fault problems occurring during the operation of aero-engine, an aero-engine airway fault diagnosis model based on Convolutional Neural Network (CNN) combined with Bald Eagle Search Algorithm (BES) Optimized Extreme Learning Machine (ELM) is proposed. The aero-engine airway data are learned by CNN and the fault features hidden in the data are extracted, the BES algorithm is introduced to optimize the weights and biases of the ELM, and the optimized ELM is used to classify the abstract features extracted by the CNN, so as to achieve the purpose of fault diagnosis. The experimental results show that the CNN-BES-ELM-based model achieves an average accuracy of 97.80%, which is 2.7%, 5.4%and 7.35% higher than that of CNN-ELM, CNN and ELM, respectively, and compared with commonly used deep learning models such as Deep Belief Network (DBN) and Stacked Auto Encoder (SAE), the accuracy is improved by 5.4% and 3.4%; and still retains more than 90% accuracy in noise environments such as random noise, Gaussian noise and pretzel noise, which overall shows good diagnostic performance, generalization ability and noise immunity, and provides a theoretical basis for its practical application in aero-engine airway fault diagnosis.

Abstract:A double-closed-loop linear self-resistant control strategy is designed to solve the problem of the three-phase staggered-parallel bi-directional DC-DC converter affected by uncertainty perturbations in the DC microgrid systems. Firstly, a bidirectional DC-DC mathematical model is established, and the transfer function of the converter is derived by small-signal analysis. Secondly, a double closed-loop system with second-order LADRC in the current loop and first-order LADRC in the voltage loop is designed to estimate and compensate for the external disturbances and the internal uncertainties of the system in real time by designing its corresponding linear extended state observers and linear state error feedback. Finally, the stability of the control system is proved according to the Lienard-Chipard stability criterion, and the three control strategies are simulated in MATLAB/Simulink for comparison and verification under different operating conditions. The simulation results show that, compared with the traditional proportional-integral controller, the control strategy proposed optimizes the maximum dynamic deviation ratio of the bus voltage by 0.5% and 0.97% and shortens the regulation time by 78.3% and 76.9% under the disturbances of 20% voltage increase and decrease on the energy storage side, and optimizes the maximum dynamic deviation ratio of bus voltage by 0.79% and 1.5% and shortens the regulation time by 72% under the disturbances of 20% load increase and decrease, which effectively improves the dynamic performance and anti-disturbance capability of the system under the premise of ensuring the equal flow of each phase.

Abstract:To study fault prediction methods for wind turbines based on SCADA data, the SCADA data of a 2 000 kW doubly-fed wind turbine over 14 months is used as the research subject. First, the data is preprocessed to ensure its usability. Considering the issues with the traditional Transformer model, such as complex structure and numerous parameter settings, a Transformer model is constructed by introducing a linear decoder structure. This model is then used for fault prediction research on wind turbines. The study shows that the constructed algorithm model has long-term stability, can eliminate false predictions, and can predict faults 6 days in advance, providing a safeguard to prevent sudden shutdowns due to fault deterioration.

Abstract:On the basis of existing ways of realizing remote calibration and traceability of measuring instruments, a remote calibration method of electrical parameters based on modern communication technology is proposed. The calibration method combines the remote calibration method with non-physical standards as the transmission object and the standard source method of DC voltage source calibration, which places the standards in the laboratory rather than transmitting them to the field, solving the problems of long calibration period and difficult to measure additional errors of the traditional electrical parameter calibration method. Based on the principle of time-frequency calibration by the satellite co-vision method, the standard voltage source and the calibrated electrical parameters are converted into reliable digital quantities for the remote transmission of the electrical parameters, and the transmission and traceability chain of the electrical parameters is established; the reference voltage remote calibration module of the AD conversion module is designed, and a model of the remote self-calibration of the AD conversion module is established, and the remote calibration algorithm of the electrical parameters based on the satellite co-vision is investigated, and the remote self-calibration algorithm of the A/D conversion is also investigated. The remote self-calibration algorithm of analog-to-digital conversion is studied, and the conversion results of high-precision electric parameter acquisition module are corrected. After data analysis, its accuracy is 0.1 level.

Abstract:In the satellite navigation and positioning system, due to the low power of the navigation signal, it is easy to be interfered when it reaches the ground, resulting in positioning failure. Adaptive null steering technology can effectively improve the anti-jamming ability of satellite navigation receiver. However, due to the common space-time combined minimum power response, null steering jitter often occurs, so the anti-jamming performance of the receiver can not be effectively aligned. In this case, the paper proposes a method of smoothing and filtering the weights in the anti-interference algorithm, and verifies the feasibility of the algorithm by means of simulation, FPGA implementation and field measurement. This method can effectively suppress the jitter of the system weight and the zero trap position, so as to improve the stability and reliability of the anti-interference algorithm, and has certain reference value for related engineering fields.

Abstract:As research and development in the field of machine vision continue to advance, the requirements for image processing have become more complex and diverse. Edge information detection is particularly important when processing real-time images. This paper designs an FPGA image edge detection system based on the Sobel algorithm, capable of real-time video image acquisition, processing, and display. Adaptive threshold and non-maximum suppression algorithms are used, combined with an 8-direction Sobel edge detection algorithm to improve detection accuracy. The Sobel edge detection algorithm is validated and implemented in hardware before and after improvement. A pipeline design is adopted to generate a sliding window to accelerate image processing and enhance the real-time performance of image processing. Hardware synthesis experiments show that the FPGA image edge detection system based on the Sobel algorithm can efficiently achieve image edge detection of video streams, improving image processing speed by 57%, providing comprehensive edge detail detection, enhancing video image processing efficiency, and can be used for target recognition and tracking research.

Abstract:This paper proposes an information complementation algorithm of K nearest neighbor-random forest with an improved distance formula, aiming at the problem of indoor fingerprint localization fingerprint database data in the real environment with missing data leading to large positioning errors.First, the gathered fingerprint data is preprocessed using Gaussian filtering to eliminate interfering data points and enhance data dependability.Second, the nearest-neighbor set is sampled using the KNN algorithm, which combines Manhattan distance and Euclidean distance.The RF algorithm is then used to optimize the training of the nearest-neighbor set, and the prediction results of each individual decision tree are averaged to determine the predicted values of the missing data.This process is based on the division of the fingerprint data into training and testing sets.Finally, the improved complementary algorithm is compared with KNN, improved KNN,RF and KNN-RF complementary algorithms.The experimental results demonstrate that the modified complementary method in this study has superior prediction accuracy and precision than other algorithms, with a prediction accuracy of 91.3%.In the meantime, the fingerprint library of this paper′s complimentary algorithm has an average positioning error of 1.82 m, which is 1.6%~7.2% less than that of other complementary algorithms, and the positioning performance is improved.

Abstract:In order to solve the problem of high computational cost of model predictive control when solving nonlinear optimization problems in large nonlinear systems such as wastewater treatment, this paper proposes a reduced-order neural network model predictive control algorithm applied to wastewater treatment benchmark. First, for large-scale nonlinear and strongly coupled systems in wastewater treatment, the intrinsic orthogonal decomposition method is used to construct a reduced-order process model to reduce the complexity of the nonlinear system. Then, the long short-term memory network is used to approximate the reduced-order system, thereby solving the problem that the reduced-order system is difficult to express explicitly. Finally, a model predictive controller is designed based on this reduced-order system to achieve efficient control of wastewater treatment. Experimental results show that while ensuring good control effect, the proposed reduced-order neural network model predictive control strategy significantly reduces the computational time compared with the model predictive control strategy of the first principle model of wastewater treatment.

Abstract:As an important component of wind turbines, blades are easily affected by the natural environment, leading to damage such as erosion, cracks, and detachment of rubber coats, thereby affecting the efficiency of wind power generation and the safe operation of the unit. A modified YOLOv8 fan blade defect detection algorithm is proposed to address the issue of low accuracy in detecting blade defects in complex environments. The single module SPPF in the backbone feature extraction network is integrated into the LSKA attention mechanism to enhance the network′s attention to important features and improve the performance of the model; Secondly, the Neck section adopts a weighted bidirectional feature pyramid Bi-FPN structure and use FasterBlock to improve the C2f module. The Bi-YOLOv8-faster lightweight network structure is proposed to enhance the multi-scale feature fusion ability of the model and improve the accuracy of small target detection; Finally, the Inner-IoU method, which assists in calculating the loss of bounding boxes, is used to optimize the loss function and improve the accuracy and generalization ability of the model′s defect detection. Through the experiment of defect detection on the image of fan blades, the results show that the proposed method improves the accuracy rate of defect detection by 7.3%, mAP50 by 3.3%, and reduces the number of parameters by 27%.

Abstract:Construction sites such as construction, mining, and exploration are very complex and diverse areas. When conducting helmet wearing detection in such scenarios, there are problems such as severe image occlusion and easy loss of small target information. This article proposes a helmet wearing detection algorithm based on improved YOLOv8n. Firstly, the C2f module of the YOLOv8n model is improved by incorporating an improved inverted residual block attention mechanism, enabling the model to efficiently capture global features and fully utilize the key information of safety helmet features; secondly, by combining the SPPF module and LSKA attention mechanism, the SPPFLSKA module is proposed to enhance the network′s attention to key information of safety helmets and avoid the influence of background information on the detection of safety helmet wearing status in practical complex scenarios; finally, the Inner-SIoU loss function is used to optimize the network model and improve the stability of the model in detecting the wearing status of safety helmets. The experimental results show that the algorithm proposed in this paper can effectively detect the wearing status of helmets in complex environments mAP@0.5 has reached 93.7%, compared to the original YOLOv8 algorithm′s P, R, mAP@0.5 and mAP@0.5:0.95 has increased by 2.4%, 4.0%, 3.4%, and 5.3% respectively, the number of parameters has decreased by 6.7%, and the computational workload has decreased by 4.8%, improving the detection of false and missed safety helmet wearing status, facilitating the deployment of practical detection applications.

Abstract:In recent years, there has been an increasing demand for higher quality cigarette pack packaging. While modern production has significantly increased the speed of cigarette box production and made production equipment more intelligent, surface quality inspection of cigarette boxes still relies on manual methods. Addressing the issues of human error such as missed or incorrect detections in surface defect inspection, a cigarette box defect detection algorithm based on improved YOLOv8 is proposed. Firstly, a Gather-and-Distribute mechanism is introduced into the neck network of YOLOv8 to enhance the model′s fusion capability for information across different hierarchies. Secondly, a scale sequence feature fusion module is incorporated to strengthen the network′s ability to extract information from different scales. Finally, the head network of YOLOv8 is replaced with the Decoder of RT-DETR, eliminating the need for complex post-processing steps such as Non-Maximum Suppression, thereby simplifying the detection process and improving efficiency. Experimental results show that the improved algorithm model achieves a detection accuracy of 94.6% and a detection speed of 121.4 FPS on a self-made cigarette box defect dataset compared to YOLOv8. Moreover, compared with other object detection algorithms, the improved algorithm has certain advantages in terms of detection accuracy and speed, making it more suitable for application in cigarette factories for surface quality inspection of cigarette boxes.

Abstract:A hybrid optimization algorithm based on Levy-flight improved tuna swarm optimization and variable step size perturbation observation method is proposed to solve the problem that the traditional maximum power point tracking algorithm is prone to local optimality due to the multi-peak power of photovoltaic arrays under local shade conditions. The real-time position update law of Levy-flight improved tuna swarm optimization algorithm is introduced to reduce the possibility of falling into local optimal. A new step change law which changes with the slope of power characteristic is designed to improve the conventional perturbation observation method and increase the maximum power tracking speed. Combining Levy-flight improved tuna swarm optimization and variable step size perturbation observation method, a hybrid optimization algorithm is constructed to further improve tracking accuracy and speed, and suppress the influence of disturbance signals. Simulation results show that the optimization time and tracking error of the proposed algorithm are 0.036 s and 0%, 0.04 s and 1.06%, and 0.05 s and 1.06%, respectively, under the three lighting conditions of uniform full illumination, static local shading and dynamic local shading, which are superior to other comparison algorithms. And more accurate and fast to achieve the maximum power tracking of photovoltaic systems.

Abstract:The three-dimensional path planning problem of unmanned aerial vehicle (UAV) is a very complex global optimization problem. However, UAV path planning based on heuristic optimization algorithms has the problems of slow speed and insufficient accuracy. To solve this problem, a UAV path planning method that improves the dung beetle optimization algorithm is proposed. First, an improved dung beetle optimization algorithm (BCLDBO) is proposed by introducing Bernoulli chaos map, variable spiral search strategy, new inertia weight and Levy flight strategy. Through experimental comparison with other algorithms on six benchmark test functions, it is proved that the BCLDBO algorithm has higher optimization accuracy and faster convergence speed. Secondly, the path planning objective function is established through the track length cost, height cost, smoothing cost and threat cost, and three-dimensional mission spaces with different complexities are constructed. Finally, the BCLDBO algorithm is applied to the UAV threedimensional path planning problem, which proves that this algorithm has lower path cost and better path planning effect than other algorithms.

Abstract:Existing staining normalization methods are unable to accurately extract the complex structural features of colorectal pathological images, resulting in the loss of partial structural information and the inability to generate high-quality staining-normalized colorectal pathological images. To address this issue, a staining normalization method for colorectal pathological images based on a conditional diffusion model is proposed. The proposed method includes conditional diffusion model and image feature reconstruction. In conditional diffusion model，firstly, the Markov chain forward process is employed to add noise to the original colorectal pathological images. Then, the noisy images and conditional images are input into an enhanced denoising network for denoising. During this process, an enhanced activation module is utilized to learn the deep features of the colorectal pathological images and capture more contextual information. A skip-connection spatial attention module is introduced between the encoder and decoder to accurately extract the positional spatial information of the colorectal pathological images. Finally, a pyramid feature extraction module is designed to extract the features of the multi-scale conditional images and generated images, and a reconstruction loss function is constructed to optimize the performance of the entire network. Experimental results demonstrate that compared with existing methods, the proposed staining normalization method can generate higher-quality staining-normalized colorectal pathological images on public datasets GlaS and CRAG.

Abstract:This paper proposes an improved TAS-YOLO network model method based on YOLOv5s to address the issues of low accuracy, high missed and false detection rates, and difficulty in collecting uniformly distributed defect types datasets for detecting small road surface defects. Firstly, in the prediction result stage, a context decoupling head for a specific task is used to enhance the accuracy of the localization detection box by separating classification and localization tasks; secondly, by using the FPN structure to input feature maps of 5 scales into the decoupling head for prediction, the multi-scale feature information of small targets is enhanced; finally, use the silde loss function to optimize YOLOv5 and improve the detection accuracy of difficult to classify samples. The experimental results showed that TAS-YOLO algorithm improved the average detection accuracy of various defects, with mAP50 reaching 91.4% and FPS reaching 126, which improved the detection accuracy and efficiency compared with mainstream detection algorithms such as YOLOv7l, YOLOv8s, YOLOv9c-gelan and Efficientdet.

Abstract:To address the issue of missed and false detections for distant small objects and occluded objects in current road target detection algorithms in autonomous driving scenarios, a road target detection algorithm based on an improved YOLOv8n is proposed. In terms of feature extraction, the Receptive-Field Attention Convolution is lightweightly improved, and the C2f module is reconstructed to solve the problem of non-shared parameters in convolution calculations, enabling the network to effectively capture critical information. Then, a lightweight point sampling operator is introduced to reduce the loss of feature details during the upsampling process, better preserving image detail information. In terms of feature fusion, a multi-scale feature fusion network is designed to enhance small target feature information and enrich the bidirectional fusion of features at different scales. Simultaneously, a normalization attention mechanism is used to suppress irrelevant background information interference, improving the model′s anti-interference capability. Experimental results show that the proposed improved algorithm achieves detection accuracies of 92.6% and 78.7% on the KITTI dataset and the Udacity dataset, respectively, representing improvements of 2.1% and 1.6% compared to the original algorithm. The model still meets lightweight requirements and enhances adaptability to complex road scenes to a certain extent.

Abstract:Low illumination environments can lead to situations such as inconspicuous image target features and severe noise interference, which affect the detection performance of the object detector.To address the above problems, a multi-scale image feature enhancement module FEM is constructed, and in conjunction with YOLOv8s object detection network, an end-to-end low-light image object detection method FE-YOLO is constructed.Firstly, FEM is employed to extract feature information from the input image at three different scales and efficiently fuse them to obtain an enhanced image with rich feature representation.Then, in the neck network of YOLOv8s, a target feature enhancement module TFE is incorporated. TFE works by suppressing background noise information in higher-level features, thereby accentuating the representation capacity of target features.The experimental results show that the mean average precision mean (mAP) on the low-light image object detection dataset ExDark reaches 75.63%, which is 3.03% higher than the original YOLOv8s algorithm, and this paper′s algorithm achieves a better detection result in the low-light object detection task.

Abstract:Aiming at the defects of existing algorithms such as structural confusion and texture blurring when repairing murals with complex patterns, a dual-generation adversarial network model incorporating structural and textural feature guidance is proposed. Firstly, U-Net is introduced into the dual-generation network, and the texture and structure information extracted by using the direction and channel dual-attention mechanism guides the structure and texture decoders to complete the feature reconstruction of the structure and texture, respectively, and combines with the null residual block and the jump connection to achieve the extraction of multi-scale feature fusion. Secondly, the feature maps output from the two branches are deeply fused by the dual gated feature fusion module to complete the feature information interaction. Finally, the defect repair is completed through the joint dual-discriminator confrontation, enhancing the detail richness and global consistency of the mural restoration effect.The experiments use self-made dataset of non-national treasure real murals somewhere in Wutai Mountain for training and testing, and verified by comparison experiments and ablation experiments, this paper achieves an average improvement of 4.24 dB in the peak signal-to-noise ratio metric, and improves an average of 3.6% in structural similarity index. The experiments show that the method can effectively repair the damaged murals, so that they present better structural and textural information, and the visual effect is clearer and more natural.

Abstract:Due to complex image backgrounds, multiscale coexistence and wide distribution of targets in underwater optical image target detection, an underwater target detection algorithm named MEAS-YOLO is proposed here. Firstly, this algorithm augments training samples to achieve data enhancement by utilizing the Mosaic and Mixup algorithms. Secondly, the efficient multi-scale attention module is integrated with the YOLOv5 backbone section to enhance the model′s feature extraction capabilities. Simultaneously, the adaptively spatial feature fusion structure is introduced to enable the model to fully integrate features of different scales. Finally, the SIoU is used in the network model to improve detection accuracy. Experimental results demonstrate that our model has a mAP of 86.4% on the URPC 2020 dataset, improving the mAP by 2.1% than that of original model. This model exhibits high detection accuracy and lower model params, which provides a new support for precise underwater target detection.

Abstract:To address the challenges posed by the diverse types of defects, significant size variations, and high complexity of existing models with insufficient detection accuracy in steel surface defect detection, this paper proposes a detection algorithm named YOLOv8-ODAW based on an improved YOLOv8n. Firstly, Omni-dimensional Dynamic Convolution (ODConv) was introduced to enhance the capability of capturing multi-dimensional features and reduce information loss. Secondly, an Asymptotic Feature Pyramid Network (AFPN) was embedded to improve the feature fusion process, enabling direct interaction between non-adjacent level features and effectively alleviating semantic disconnection. Finally, the Wise-IoUv3 loss function with a dynamic non-monotonic focusing mechanism was adopted to optimize bounding box regression, accelerating network convergence while improving detection accuracy. A series of experiments were conducted on the NEU-DET dataset, and the results demonstrated that the modified YOLOv8-ODAW network model outperformed the original network model with a 7.3% increase in mAP at 50% and a 21.95% decrease in computational complexity (GFLOPs). This showcases superior localization and recognition capabilities for steel surface defects while meeting the speed requirements for industrial applications.