Search

The development of sensor technology provides multisource remote sensing images (RSIs) observed from different resolutions and angles for object recognition applications. To process multisource data presenting diverse feature distributions, it is proper to exploit domain adaptation methods to reduce the distribution differences across sources. However, most domain-adaptive methods can only deal with homogeneous RSIs and rely on standard discriminative criteria, making it challenging to ensure effective subsequent recognition results. To attack these obstacles, the Robust heterogeneous feature discriminant embedding (RHFDE) method is proposed to learn domain adaptation discriminant features using cross-resolution and cross-angle RSIs. To deal with heterogeneous input, the specific-size projection matrices are constructed to map multisource RSIs. Then, unlike the current methods relying on common discriminant criteria, the support vector machine discriminant term is established and forms the optimization model. To improve robustness and adapt to unlabeled samples, the adaptive weight factors and semi-supervised learning strategy are presented to further improve RHFDE’s performance. Results from experiments using datasets with multi-resolution and multi-angles show that RHFDE obtains better recognition accuracy than typical feature-level domain adaptation methods.

Stochastic Computing (SC) has recently gained attraction due to its inherent error tolerance and extremely simple arithmetic hardware, making it particularly effective for accelerating modern applications such as neural networks on resource-constrained devices. Traditional SC architectures often adopt binary computing principles, relying on dedicated hardware, i.e. AND gates for multiplication and multiplexers (MUX) for addition. However, SC’s mathematical foundation enables the fusion of complex operations into remarkably simple hardware. Several SC studies demonstrated the potential of MUX-based architectures to perform multiply-and-accumulate (MAC) operations, but existing designs face correlation complication, scaling problems, and limited application scope. This paper introduces an auxiliary logic block to address the complexity of MUX select inputs, significantly enhancing the scalability of MUX-based MAC operations. The proposed approach has been validated through SC image processing tasks, including grayscale conversion and Sobel edge detection, achieving up to 75% reduction in hardware resource utilization on field-programmable gate arrays (FPGAs) and up to 96% improvement in computational accuracy compared to traditional AND/XNOR-based SC multipliers.

This paper investigates the problem of dynamic event-triggered asynchronous guaranteed cost control for uncertain Markov jump systems with actuator saturation and nonideal transition probabilities. First, a hidden Markov model is employed to estimate system modes that cannot be accurately detected in practical scenarios. Second, a dynamic event-triggered mechanism is established based on the hidden Markov model to conserve limited network resources and an asynchronous event-triggered state feedback control law is designed. Third, a convex hull representation is adopted to deal with saturated inputs and parameter uncertainties are incorporated in the system model. Moreover, since it is complex to obtain accurate transition probabilities for the Markov chain of the original system and the hidden Markov model in the observation process, unknown and uncertain transition probabilities are simultaneously considered in both mode transitions and mode observation processes, and a separation strategy is implemented to handle the nonideal probabilities in each process independently. Through the application of Lyapunov equations and linear matrix inequality techniques, sufficient conditions are derived that ensure the resulting system is stochastically stable with/without nonideal transition probabilities and satisfies specific cost bounds under three different initial boundary conditions. Finally, a convex optimization algorithm is proposed to design the optimal asynchronous event-triggered guaranteed cost control law, and a DC motor model is provided to validate its effectiveness.

Rapidly detecting foreign objects in the railway’s natural environment is crucial for safe railway operation and passenger safety. Traditional detection methods are limited by technology and environment and are costly and inefficient for large-scale detection. To improve the efficiency of foreign object intrusion detection in railways, this study proposes a YOLO-UAT method to detect foreign objects in railways effectively. First, a railway foreign object intrusion image dataset is created. Then the EfficientNet network is employed to replace the backbone extraction network of YOLOv5s, achieving a lightweight model that enhances detection speed. Secondly, a C $3\_$ CBAM module is constructed to enhance feature extraction and enhance the model’s detection ability for small-scale targets. Concurrently, the K-means++ algorithm is introduced to cluster the a priori frames, which improves the accuracy and convergence speed of the a priori frame clustering. YOLO-UAT reduces the number of parameters by 36% compared to the original YOLOv5s and mAP increased by 6.1% to 91.5%. Implemented on a Jetson Nano, it achieves a detection rate of 26.4 FPS. The experimental results demonstrate that the enhanced YOLOv5s model effectively enhances the accuracy and speed of foreign object encroachment detection in railroads while ensuring lightweightness, facilitating deployment, and aligning with the operational needs of railroads.

Due to the inherent imaging characteristics of Optical Coherence Tomography (OCT), the contrast between the choroid and sclera is low, presenting significant challenges in choroidal segmentation, such as subchoroidal boundary blurring and difficulty in accurate boundary delineation. To address these issues, this paper proposes an automatic choroid segmentation network, termed Boundary Enhancement Net (BENet), which enhances boundary information to facilitate precise recognition and achieve end-to-end automatic segmentation. BENet is constructed on the TransUnet backbone and integrates a boundary enhancement module, leveraging a multi-branch architecture and dilated convolutions to capture features across multiple scales. The attention mechanism is incorporated to dynamically highlight critical features, thus improving the model’s capacity to represent boundary details. Furthermore, the channel enhancement mechanism further refines the expression of salient channel futures, while the adaptive activation function improves the sensitivity of the network to boundary futures. A custom loss function, specifically designed to replace the conventional Mean Squared Error (MSE) loss, is utilized to optimize network parameters, leading to further improvements in segmentation performance. The BENet architecture achieved a Dice coefficient of 95.24%, a Hausdorff distance of 2.68, and an accuracy of 99.12%. Compared to the original TransUnet, BENet demonstrated an increase of nearly 5% in the Dice coefficient and 0.85% in accuracy. Ablation studies and results from multiple medical image datasets validate that BENet consistently delivers precise segmentation outcomes. The boundary enhancement module effectively improves the accuracy of choroidal segmentation, while the custom loss function optimizes network performance, increasing both stability and generalization capabilities. Moreover, the modular design of the boundary enhancement module ensures its portability across different segmentation tasks, making it a versatile component for integration into existing frameworks.

This paper mainly investigates the asynchronous observer-based guaranteed cost control problem for two-dimensional Markov jump Roesser systems with nonideal transition probabilities. First, a hidden Markov model is developed to describe the asynchronous phenomenon caused by the mode mismatch between the controlled system and the controller. Second, an asynchronous observer-based feedback control law based on the hidden Markov model is designed against the inaccessibility of the system states. Third, since accurate transition probabilities of the Markov chain and the hidden Markov process are difficult to obtain, nonideal transition probabilities are simultaneously considered in both mode transition and mode observation processes. By using the quadratic Lyapunov function techniques and linear matrix inequality methods, some sufficient criteria are developed such that the resultant closed-loop system is asymptotically stable with/without nonideal transition probabilities and satisfies a guaranteed cost performance under three different boundary conditions. Finally, an asynchronous observer-based optimal guaranteed cost controller design algorithm is proposed and two numerical examples are considered to demonstrate its effectiveness.

The performance degradation is a crucial factor affecting the commercialization of proton exchange membrane electrolyzer. However, it is difficult to establish a mechanism model incorporating all degradation categories due to their different time and spatial scales. In this paper, the data-driven method is employed to predict the electrolyzer voltage variation over time based on a convolutional neural network-long short term memory (CNN-LSTM) model. First, two datasets including constant operation for 1140 h and start-stop load for 660 h are collected from the durability tests. Second, the data-driven models are trained through the experimental data and the model hyper-parameters are optimized. Finally, the electrolyzer degradation in the next few hundred hours is predicted, and the prediction accuracy is compared with other time-series algorithms. The results show that the model can predict the degradation precisely on both datasets, with the R2 higher than 0.98. Compared to conventional models, the algorithm shows better fitting characteristic to the experimental data, especially as the prediction time increases. For constant and start-stop operations, the electrolyzers degradate by 4.5 % and 2.5 % respectively after 1000 h. The proposed method shows great potential for real-time monitoring in the electrolyzer system.

In recent years, deep learning has been extensively applied to small object detection, achieving significant advancements. Nevertheless, there remains substantial potential to improve both the effectiveness and efficiency of small object detection in Uncrewed aerial vehicle (UAV) images. In this article, we propose a novel YOLO model with multi-scale, effective, and lightweight methods for traffic small object detection, termed MEL-YOLO. Initially, the improved model reconstructed the multi-scale network structure, the high-resolution feature enhancement network increases size from $40\times 40$ to $160\times 160$ . Secondly, the improved model incorporates a decoupled detection head, which separates the classification task from the localization task, thereby improving detection accuracy while increasing detection complexity. Furthermore, we explore the Soft-NMS algorithm to effectively mitigate small object occlusion and reduce missed detection. Finally, this study emphasizes the design of a lightweight model by introducing a model pruning strategy along with the Ghost module. We have selected four C3 modules, each with a substantial number of output channels, to integrate with the Ghost module. This method results in fewer parameters, lower GFLOPs, and higher FPS. Experiment on the VisDrone2019 public dataset, compared to the baseline YOLOv5s, our model demonstrates an improvement of 8.5% in mAP@0.5 and 6.2% increase in mAP@0.5:0.95. Furthermore, there is a 55.7% reduction in parameters, a decrease of 7.0% GFLOPs, and an increase of 11.3% in FPS. To demonstrates the versatility and robustness of MEL-YOLO model, we conducted validation experiments on the SODA10M and CCTSDB datasets, where the mAP@0.5 improved by 1.9% and 1.2%, the FPS increased by 18 frame/s and 6 frame/s, respectively. These results align with our expectations, indicating that our model is a more effective and lightweight algorithm for dense and small objects detection in aerial images.

Solar panels play a crucial role in converting solar energy into electricity, with PhotoVoltaic (PV) modules being their core components. To ensure solar panels function well, efficient and accurate defect detection of PV modules is essential. Visual-based deep learning detection methods, such as Transformer and Convolutional Neural Network (CNN) models, provide a cost-effective and adaptable solution. Although the Transformer-based detectors outperform CNN-based ones in detection tasks, their complicated model structures also lead to great computational cost and latency, limiting their application in resource-constrained environments or time-sensitive tasks. To improve the real-time performance of the DEtection TRansformer (DETR) model on these edge devices, a novel Lightweight Decoder-only DETR (LD-DETR) is proposed for defect detection of PV modules, which achieves high performance and low computational cost with an easy architecture. We remove the resource-intensive Transformer Encoder structure from the DETR baseline so that the Decoder can directly utilize the finely fused features produced by a specialized lightweight convolution module that includes an upsample operation to preprocess the features. Experiments demonstrate that the proposed LD-DETR achieves competitive performance on the PV cell dataset of ElectroLuminescence (EL) images with an accuracy of 87.4% and an inference time of 6.1ms on GPU as well as 1.1s on embedded CPU. Our source code is available at https://github.com/SeveralYang/LD-DETR.

Efficiently detecting intrusions on a railway perimeter is crucial for ensuring the safety of railway transportation. With the development of computer vision, researchers have been actively exploring methods for detecting foreign object intrusion via image recognition technology. This article reviews the background and importance of detecting railway perimeter intrusion, summarizes the limitations of traditional detection methods, and emphasizes the potential of improving detection accuracy and efficiency in image recognition with deep learning models. Further, it introduces the development of deep learning in image recognition, focusing on the principles and progress of key technologies such as convolutional neural networks (CNNs) and vision transformers (ViTs). In addition, the application status of semantic segmentation and object detection algorithms based on deep learning in detecting railway perimeter intrusion is explored, including the classification, principles, and performance of the algorithms in practical applications. Finally, it highlights the primary challenges faced in railway perimeter intrusion detection and projects future research directions to resolve these challenges, including multisource data fusion, large-scale dataset construction, model compression, and end-to-end multitask learning networks. These studies support the accuracy and real-time detection of railway perimeter intrusion, and provide technical guarantees for railway transportation monitoring tasks.

Sea ice plays a critical role in influencing various aspects of the atmosphere, ecology, oceans, and even human activities, making the task of sea ice retrieval (SIR) immensely important. Recent advancements have seen the application of machine learning methods based on Global Navigation Satellite System Reflectometry (GNSS-R) technology in the field of sea ice remote sensing. However, the existing algorithms are hindered by an over-reliance on labels, structural redundancies, and limited effectiveness in dealing with sample imbalances. To overcome these challenges, the Anomaly Detection Driven Semi-supervised Multi-task Retrieval Algorithm for Sea Ice based on GNSS-R is proposed in this paper. In the novel approach within the field of SIR, this study introduces the concept of semi-supervised anomaly detection. This method addresses the challenge posed by an over-reliance on labeled data and the issue of sample imbalance. The proposed algorithm is composed of two primary components: the data preprocessing module and the multi-task network structure Sea Ice Multi-Tasks Retrieval Network (SIMTRN) based on GNSS-R. The SIMTRN includes a sea ice detection (SID) module, which employs an implicit deep bootstrap mechanism for enhanced detection capabilities. Additionally, it encompasses a sea ice concentration retrieval (SICR) module that implements an innovative inter-module data feature sharing mechanism. This dual-module approach within a single network structure not only facilitates simultaneous execution of SID and SICR tasks but also effectively addresses and resolves the issue of structural redundancy. Experiments conducted on the datasets illustrate the superior SIR performance of the proposed method.

A method of automatic recognition of radar waves based on time-frequency analysis (TFA) and ConvNeXt model is proposed in the paper. The method aims to address the challenges of feature extraction difficulty and low recognition correctness in complex multi-class radar waveform recognition under the conditions of low signal-to-noise ratio (SNR) and sample imbalance. The first step is to convert the signal’s time domain waveform into a two-dimensional time-frequency image (TFI) using TFA. This allows for the essential characteristics of the signal to be reflected. Next, TFI preprocessing is carried out to retain complete information, which is then adapted to the input of the deep learning (DL) model. Finally, ConvNeXt model was constructed to automatically extract signal TFI features to realize radar waveform classification and recognition, and focal loss was embedded to increase the weight of classes with small sample numbers in training and solve the problem of sample imbalance. Therefore, ConvNeXt network has stronger feature learning and representation ability compared with other algorithms based on deep learning, and effectively improves the overall recognition rate of 16 classes signals. The recognition accuracy of 6 types of signals with similar time-frequency characteristics (Frank, LFM, P1, P2, P3, P4) is higher, and the recognition rate is close to normal samples under the condition of unbalanced samples. Experimental results verify the effectiveness of the proposed algorithm.

For multi-object tracking (MOT), jointly learning the detector and embedding model (JDE) is one of the mainstream solutions. However, an inherent problem in this architecture arises as the tasks of target detection and appearance feature extraction compete with each other. FairMOT, as a representative method, attempts to address this issue by employing two homogeneous branches, but it overlooks the essential difference between these two tasks. Upon the original network architecture, we propose an adaptive dual decoder structure. Our objective is to separately learn more focused features for the target detection and the appearance feature extraction. Furthermore, we introduce a noise-adaptive Kalman filter based on the width estimation. In the motion information matching stage, we enhance the affinity matrix of motion information by employing an expanded-width strategy, combined with a more accurate overlap measure. We verify the effectiveness of our proposed approach through extensive experiments using the MOT17 dataset.

Centralized deepfake service providers have large amounts of computing power and training data, giving them the ability to produce high-quality deepfake content. However, once these service providers are attacked or malfunction, it may lead to the collapse of the entire deepfake ecosystem, making deepfake a potential threat to data security. This monopoly development has led to the uneven distribution of deepfake resources, which in turn has brought about the risk of single points of failure. To deal with the problem, this paper proposes a decentralized deepfake task management algorithm (DD-TMA) based on blockchain and edge computing. The blockchain in this algorithm can provide a decentralized storage and management platform to ensure that the data and models of deepfake tasks will not be tampered with or lost. Edge computing can distribute tasks to edge devices close to the data source for processing, reducing data transmission delays and bandwidth consumption, and improving the efficiency and security of deepfake tasks. The paper innovatively integrates blockchain, federated computing, and edge computing. Firstly, the algorithm establishes a decentralized computing platform based on blockchain. Subsequently, it enhances computing power during the execution of decentralized deepfake tasks through the integration of federated computing and edge computing. Finally, the algorithm increases the active performers of decentralized deepfake tasks through gamification, thereby improving task execution efficiency. Experiments conducted in this study on public data sets demonstrate that the algorithm is efficient, robust, and reusable. Compared with other algorithms, the efficiency of DD-TMA is improved by more than 20% and the stability is improved by more than 13%. This algorithm proves effective in solving the problems encountered in the execution of centralized deepfake tasks. The research provides new ideas for future evaluations of decentralized deepfake effects based on different strategies.

Utilizing Unmanned Aerial Vehicles (UAVs) plays a pivotal role in the localization of ground construction personnel targets within the specialized operational environments of the energy industry. To ensure the safety of personnel in these areas effectively, this study introduces an innovative dual UAV cooperative positioning system designed to address the challenges of personnel localization in various complex settings. In the first place, the research establishes a dual UAV collaborative remote sensing platform, specifically tailored for executing dual UAV flight control and ground personnel identification and localization tasks. Subsequently, this study proposes a high-precision ground personnel localization solution. This solution integrates the flight data of two UAVs with the pixel coordinates of targets in natural remote sensing imagery, enabling the precise localization of moving targets within complex environments. Moreover, due to the irregularity of ground personnel shapes in imagery, this research introduces an improved rotating target detection network based on the YOLOv7 architecture. This network is specifically optimized for detecting ground targets in remote sensing imagery, significantly enhancing the accuracy of target localization. Extensive experimental validation has demonstrated that this localization system can maintain target localization errors within a 5-meter threshold, effectively enhancing the safety and efficiency of personnel in specific operational areas of the energy industry.

Migration-based Dynamic Platform (MdyPlat) is a type of Moving Target Defense (MTD) techniques to protect the task executed on the platform. MdyPlat actively hinders sophisticated attacks through randomly and dynamically setting up a platform for executing the task. This paper aims to investigate how MdyPlat-related factors make quantitative impact on the capability of MdyPlat technique. We develop a semi-Markov model for describing the system dynamics and then derive metric calculation formulas for investigation. Compared to the existing analytical-modeling-based evaluation methods, our modeling approach can work even the times of all MdyPlat-related events follow any type of distribution. The comparison between simulation and numerical results validates the approximate accuracy of the model and formulas. Numerical experiment results uncover that 1) MdyPlat technique can effectively enhance the task security, particularly under high attack intensity; 2) The security risk of the executed task varies in different task-execution scenarios, which are denoted by the number of platforms and the probability distribution of the times of MDP-related events; and 3) Different cumulative distribution function of event time under the same mean value leads to different analysis result of the task security.

Conformer has become one of the most popular models in the field of automatic speech recognition, achieving superior speech recognition performance by integrating a convolutional module into Transformer. However, existing Conformer models face challenges with high computational complexity in the attention mechanism when capturing global dependencies, and lack flexibility in dynamically adjusting local dependencies, which limits their efficiency in processing sequences. To address these challenges, we propose a new model called Ubranch Conformer, which combines Up-Down sampling and branch attention to enhance the ability to capture input information and reduce computational complexity. First, we designed a new architecture with an Up-Down sampling strategy that adjusts the sampling of embedded sequences between blocks in the model’s intermediate layers, reducing complexity without compromising efficiency. Second, we introduce a more efficient block structure that mainly contains branch attention and convolution gate modules, combining convolution with attention to improve the model’s ability and flexibility in capturing global and local dependencies. Experiments on multiple datasets show that our Ubranch Conformer achieves a more advanced level of performance compared to existing models, and achieves a good balance between performance and complexity.

The optimal selections of supplier portfolios and supplier substitutes are important research contents of the supplier selection problem. However, most of the existing supplier selection methods are based on the efficiency of indicator capability of supplier, the complementary capability (i.e., weak similarity) between suppliers for the supplier portfolio, and the substitution capabilities (i.e., strong similarity) of supplier substitutes for the best supplier may not be considered. Therefore, two new supplier selection models, namely TOPSIS-NS considering the negative influence of similarity for supplier portfolio selection and TOPSIS-PS considering the positive influence of similarity for supplier substitute selection, are proposed based on TOPSIS and intuitionistic fuzzy set (IFS). Firstly, the efficiency of indicator capability of supplier is expressed by the membership degree of IFS obtained by TOPSIS, while the similarity among suppliers is expressed by the nonmembership degree of IFS obtained by the concordance correlation coefficient. Then, the process of TOPSIS-NS for supplier portfolio selection is constructed based on the score function of IFS, and the supplier portfolio selected by TOPSIS-NS can have higher complementary capabilities. Furthermore, the process of TOPSIS-PS for supplier substitute selection is constructed based on the accuracy function of IFS, and the supplier substitute selected by TOPSIS-PS can have higher substitution capabilities. Finally, two illustrative examples for optimal selections of supplier portfolio and supplier substitute are given respectively, and the results show the superiority of TOPSIS-NS in supplier portfolio selection and TOPSIS-PS in supplier substitute selection.

The jet pump is one of the most popular types of fluid machinery in agriculture, industry and environmental engineering and many other fields. However, its internal flow structure is complex, showing obvious unsteady characteristics. The effect of throat diameter size on jet pump performance and energy property was investigated in this study based on numerical calculation and test verification, in order to improve the performance and internal flow field stability of jet pump. Five models with different throat diameters were obtained by adjusting the assembly structure and simulated by the computational fluid dynamics software to solve the Navier–Stokes equations for three-dimensional steady flow. The accuracy of numerical methods was verified by comparison with the experimental results. The compact jet pump performance under different throat diameters was then compared and analysed. The backflow at effuser outlet of different throat diameters causes the changes of vortex structure inside the injector rear chamber. The vortex diffuses downstream to the impeller inlet, making the flow structure of the impeller inlet show obvious circumferential inhomogeneity. This forms different vortex structures at different impeller flow channels, changing the distribution of entropy production within the impeller, ultimately leading to a decrease of pump efficiency. Therefore, this study found that selecting a reasonable throat diameter of the injector can improve the performance of the jet pump impeller, and thus improve the overall efficiency of the system. For the research object in this paper, the recommended range of throat diameter of injector is 16 mm–17 mm. This finding could provide useful insights for the improvement of the hydraulic performance and operational stability of compact jet pumps.

Electricity demand forecasting is of great significance to the electricity system and residents’ life, but it is difficult to forecast the electricity demand series because of the influence of cyclical factors. Electricity demand forecasting also faces the problem of small data amounts. Therefore, we need to design a model that is less affected by data volume and can cope with complex electricity demand series. Based on the Autoformer model, this paper establishes a novel forecasting framework with excellent performance. In the part of data preprocessing, multiple linear regression with 10 variables and Bootstrap processing are added. In the part of the model, the Auto-Correlation mechanism is modified to better extract the historical and nonlinear characteristics of electricity demand series from different time spans. Using this framework, we further analyze the impact of working days and seasonal changes on the electricity demand in Taixing City and New South Wales. In addition, we propose a new electricity demand forecasting method, which can adjust the original sequence according to the actual situation. The experimental results show that this method can achieve good precision in demand forecasting. Taking Taixing of China and New South Wales of Australia as examples, the forecasting performance with the proposed framework is better than that of Autoformer, Reformer, Informer, and other mainstream models. The forecasting indexes with our proposed framework of the test set are MAE: 35.05, RMSE: 47.28, MAPE: 1.63 in Taixing and MAE: 193.17, RMSE: 239.96, MAPE: 2.43 in NSW.

To separate electromagnetic interference sources with an unknown source number, a new separation method is proposed, which includes five key steps: spatial spectrum estimation, source number and direction-of-arrival estimation, mixed matrix estimation, separation matrix estimation, and source signal recovery. A pseudospatial spectrum estimation network based on a convolutional neural network is proposed to estimate the number of electromagnetic radiation sources, their direction of arrival, and the mixing matrix. A new loss function is designed as an optimization criterion for estimating the separation matrix. To ensure generalization, both simulated and measured datasets are used to train the proposed network. Experimental results demonstrate that the proposed separation method outperforms existing source separation techniques in terms of correlation coefficient, root mean square error, and running time. Importantly, it exhibits strong performance in underdetermined cases, as well as in overdetermined or determined cases.

Abstract The model‐based sensorless control of permanent magnet synchronous motor (PMSM) relies on the motor parameters. In practice, the considerable uncertainty of inductance and the difference between the apparent inductance and the incremental inductance exists. To overcome it, an online apparent inductance identification method for PMSM sensorless control is proposed. First, an initial incremental inductance table (IIT) is obtained offline. Then, an asymmetric high‐frequency square wave injection method is proposed to identify the incremental inductance at the operation point, and an adaptive minimum adjustment algorithm is proposed to adjust IIT automatically. Finally, the apparent inductance is calculated using the adjusted IIT. Based on it, the complete PMSM sensorless control is designed. The experimental results indicate this method is feasible and effective.

On the basis of summarizing the characteristics of tidal current power generation and power quality analysis methods at home and abroad, this paper comprehensively analyzes the power quality problems existing in tidal current power generation, and Hilbert–Huang transform (HHT) is finally applied to detect and analyze the issues. Using MATLAB to establish the simulation model, and the analysis algorithm of power quality in frequency domain and time domain is focused. The simulation results of single disturbances and some mixed disturbances show that this method has good adaptability to the non-stationary and multi-disturbance characteristics of tidal power generation.

Abstract Deep learning has demonstrated notable success in mechanical signal processing with a large amount labelled data. However, the systems of the Jiaolong deep‐sea submersible prone to malfunction are typically diverse, due to the high complexity of its structure and operational environment. Consequently, this diversity gives rise to variations in the types of sensor signals and their associated data distributions that require analysis. Unsupervised domain adaptation (UDA) uses transferable knowledge derived from the source domain and applies it to an unlabelled target domain in order to improve the reusability of pre‐existing models and data. Inspired by the diffusion models that have the robust capabilities to transform data distributions across a large gap, we propose a novel diffusion‐based unsupervised domain adaptation (diffusion‐UDA) model, which leverages contrastive learning to alleviate the challenges of cross‐domain analysis for fault diagnosis within different systems of the deep‐sea submersible. Experimental results show the proposed method achieves state‐of‐the‐art performance on various benchmarks.

Fluorescent probes play a crucial role in analytical chemistry and biological imaging, offering selective detection of metal ions. Herein, we present the synthesis and characterization of a novel rhodamine-based fluorescent probe, RbHC (Rhodamine B Helicin), which was obtained through the condensation of rhodamine B hydrazide and helicin in ethanol. The probe demonstrates remarkable selectivity and anti-interference capabilities towards Cu2+ and Fe3+ ions in 80% acetonitrile solution. Spectral titration analysis revealed a linear relationship between the intensity and the concentration of Cu2+/Fe3+. The formation of complex between Cu2+/Fe3+ and RbHC was confirmed to be 1:1, and it was further confirmed by ESI mass spectroscopy and DFT calculations. The coordination with Cu2+/Fe3+ caused the opening of RbHC's spirolactam ring, resulting in distinct color change and red fluorescence emissions. Moreover, RbHC exhibits high stability and water solubility under both acidic and neutral conditions, enabling its application in the imaging of plant tissues. Besides, the absorption intensity of RbHC–Cu2+ increased significantly when exposed to sunshine and 365 nm UV radiation, indicating that it might be used as a potential indicator for measuring outdoor UV intensity.

Abstract In this work, electrical tree inception and ageing experiments were conducted to investigate the initiation, growth characteristics and structural characteristics of electrical trees of nano‐SiO2 doped epoxy resin at different temperatures. Electrical tree inception and ageing experiments were conducted using power frequency voltage of 15 kV at 20, 40, 60, 80 and 100°C. Electrical breakdown properties of epoxy resin were investigated by applying AC and DC voltages at 20, 40, 80 and 120°C. There are two major observations based on the experimental results. With the increase of temperature, the morphological structure of the electrical trees changes from dendritic to plexiform, the tree inception voltage decreases and the growth rate of the electrical trees increases obviously. Either under DC or AC voltage, the breakdown strength of the nano‐SiO2 doped epoxy resin decreases as the temperature increases. Finally, based on the space charge and the trap level measurement, the mechanism of the electrical tree propagation and breakdown in nano‐SiO2 doped epoxy resin was analysed.

To balance the relationship between current THD and switching loss, an optimal predictive control method using single and double vector hybrid modulation of NPC-3L inverter is proposed. Firstly, the relationship of the THD of output current and the Aoc&rc(the Area enclosed by output current and reference current) is built. Secondly, the current threshold is defined to control the switching time of single/double vectors, which is used to balance the current THD and switching loss and determined by the target current THD value. Thirdly, the output of single vector or double vector is determined by comparing the output real-time current value with the set current threshold. That is, when the output current is greater than the current threshold, a single vector is used to reduce the switching loss. When the output current is less than the current threshold, the THD of the output current is raised by using output double vectors. At the same time, by using this control method, the disadvantages of single/dual vector independent operation are mutually offset. Finally, a simulation model is built to verify the proposed control method. Compared with traditional methods, the simulation results show that the proposed method is correct and effective.

With the advent of IoT technology, the dynamic nature of IoT devices has introduced new obstacles to access control. It is essential to consider the security requirements of the actual physical environment, rendering the traditional access control approach centered on the information space. In the IoT ecosystem, there are several issues such as the dynamics of devices frequently entering and leaving, the lack of computing and storage capacity, and distributed deployment. To address these challenges, this paper proposes the Domain Attribute Based Access Control(DABAC) that incorporates domain elements to implement the physical location limitation of dynamic devices. Moreover, an intelligent gateway is utilized to divide the physical area and act as a proxy to achieve regional device management, automatic networking of devices in the domain, and the dynamic expansion of the sensor network resulting from device entry or exit. Then, given the distributed deployment of devices, smart contracts are employed to deploy access control mechanisms and construct a trusted environment to mitigate threats such as single points of failure. Finally, the DABAC is implemented on the Ethereum platform, simulating a smart medical situation. The experimental results demonstrate that the proposed solution effectively addresses the problem of access control of device dynamics in an untrusted IoT environment while maintaining system security.

Imaging satellite mission planning has received more and more attention as one of the core problems in the field of imaging satellite applications. In this paper, a hybrid discrete artificial bee colony (HDABC) algorithm is proposed to address this problem. The HDABC algorithm improves the three search phases of the basic artificial bee colony (ABC) algorithm to make them applicable to the discrete satellite mission planning problem. In the employed bee search phase, the population is divided and a multi-strategy search equation mechanism is used to balance the exploration and development of the algorithm. In the following bee search phase, two kinds of neighborhood search operators are designed based on the problem characteristics to further improve the fitness values of the better solutions. In the scout bee search phase, a migration operator and an immigration operator are introduced to improve the fitness values of the worse solutions and promote the exchange of different subpopulations to achieve co-evolution. In the experimental part, orthogonal experimental design is used to determine the appropriate algorithm parameters. Simulation experiments are carried out to test problems of different sizes. The experimental results show that the proposed HDABC algorithm shows good performance.

Using deep learning and machine learning techniques for network intrusion detection is of great significance for enhancing the defense capability of network security systems. Given the characteristics of generative adversarial networks, such as the approximate consistency of generated samples with the input data distribution but with a random distribution within a certain bounded interval, and in response to the problem of insufficient classification performance and detection omission caused by the imbalance of different degrees of data categories and quantities in network intrusion traffic, and in light of the fact that the effectiveness of existing classification algorithms based on unbalanced traffic data still has some room for improvement, this paper proposes a network intrusion detection strategy based on auxiliary classifier generative adversarial networks. The data expansion experiments are conducted with the intrusion detection dataset NSL-KDD. The data are classified into twenty-three categories before and after the expansion by binary classification validation. The results show that the expansion of the generated samples for unbalanced network traffic data improve the subsequent recognition effect significantly. Finally, five classification performance index verification experiments are conducted. The results prove that the strategy of this paper performs better in accuracy, precision, recall rate and F-value indexes, and is capable of obtaining a large number of features from limited samples and inferring complete data distribution based on fewer features. The model as a whole has stronger generalization ability and defense effect.

As the core technology in the field of imaging satellite application, imaging satellite mission planning has received more and more attention. Aiming at this problem, this paper proposes a distributed imaging satellite mission planning method (DISMPA) based on multi-agent system. Firstly, a distributed imaging satellite mission planning model with variable collaborative division of labor is constructed based on multi-agent system theory. The model defines the intelligence level of satellites in the satellite cluster and the interaction mode between satellites. Secondly, the cooperation mechanism between satellite agents is established based on blackboard model. Two negotiation strategies of worker serial activation and worker parallel activation are proposed. In order to improve the efficiency of negotiation, the targets are preassigned before negotiation. Finally, a hybrid discrete multi-verse optimization algorithm is proposed to solve the mission planning problem of worker agents in the model. Simulation experiments show that the average fitness values obtained by DISMPM using serial activation strategy and DISMPM using parallel activation strategy are up to 20% higher than those obtained by the centralized algorithm with the best solution effect in this paper, and the average negotiation times of the two DISMPM methods are both reduced by more than 80% compared with the contract network algorithm, effectively reducing the system traffic and reducing the communication burden. It is proved that DISMPA is suitable for distributed imaging satellite mission planning.

Non-invasive voltage measurement of transmission lines plays an important role in the process of power system digitization. Aiming at the phase to phase coupling effect of the field source structure of the transmission line, the paper proposed a self-decoupling voltage measurement method based on the field source structure parameters of the measuring point, to achieve the accurate measurement of three-phase voltage by a single sensor. Voltage measurement is achieved at the measuring point of the sensor by utilizing a three-dimensional electric field induction probe. The principle of voltage self-decoupling measurement is introduced in this paper. The measurement model of voltage self-decoupling is analyzed. Simulation calculations are then performed to calculate and adjust the coefficient of the self-decoupling matrix. Finally, the voltage measurement and decoupling effect of this method are verified using a three-phase horizontal distribution transmission line as an example. The results show that the voltage measurement error under steady-state and transient conditions is less than 2.8% and 2.2% respectively. This method can be used for voltage measurement of transmission lines.

Coal gangue recognition of top coal caving is one of the important links in the process of intelligent coal mine construction. However, the recognition accuracy of this technology in practical application is still challenging, because the recognition model is not perfect in the following aspects: 1) the filtering scale is not suitable for signal noise reduction;, 2) the selected features have no obvious difference in vibration signals of coal and gangue; and 3) the overall relevance of the model input data to the target classification is insufficient. The purpose of this paper is to establish a coal gangue recognition model with effective filtering, feature extraction and classification capabilities, which can adaptively carry out purposive feature extraction while retaining relevant information to improve the recognition accuracy. Firstly, hierarchical filtering (HF) method was proposed. Secondly, an effective information correlation fusion based coal gangue recognition model (EICF-coal gangue recognition model) was established by coupling wrapper feature selection method and recognition algorithm. Then, 2223 groups of vibration impact tests were carried out on the coal gangue mixture with gangue content of 0 to 50%, and two kinds of coal gangue recognition sample sets of “caving category” and “shutdown category” were established. Finally, coal gangue recognition experiments were carried out on 9 hierarchical filter sample sets by coupling wrapper and 5 recognition algorithms. Under the combined effect of the HF method, wrapper feature selection method and Stacking, coal gangue recognition accuracy reaches 99%. This paper demonstrates the effectiveness of the EICF-coal gangue recognition model.

In this paper, we give a construction of strongly regular Cayley graphs on the finite field $\mathbb {F}_{q^{n}}$ . As applications of these strongly regular Cayley graphs, a class of codebooks is presented and proved to be asymptotically optimal with respect to the Welch bound. Further more, these constructed codebooks have new parameters.

The human-machine function allocation (HFA) strategy of manned submersibles is an important factor that affects the reliability of oceanauts. However, the uncertainty of the HFA strategy makes its optimization very complicated. To this end, a non-cooperative game-based HFA method is proposed, which transforms the multi-objective optimization model of mental workload and situation awareness (SA) under the allocation strategy into a non-cooperative game model and forms a mapping relationship. Mental workload and situation awareness are used as non-cooperative game players. Assignable functions are attributed to the players by fuzzy clustering analysis and combined with non-assignable functions to construct the utility matrix by utility functions. The optimal allocation strategy combination is obtained through the Nash equilibrium analysis of the utility matrix. The proposed method was applied to the optimization of the HFA strategy of the manned submersible during the navigation.

As an advanced metrology technology, three-dimensional (3D) gear measurement using linear laser techniques is susceptible to the influence of multiple coupling factors. Consequently, there exists an urgent need for new principles to effectively decouple the effects of each factor. Digital twins realize the connection between physical and virtual spaces. By fusing multi-source data from the existing system, a high-fidelity digital model is established to realize the simulation of the gear measurement process in this paper. Moreover, simulation of the light reflections of tooth flanks and the dynamic error coupling process can effectively clarify the coupling mechanism of measurement errors. This paper presents a method of constructing a digital twin model of a 3D measurement system for gears and realizes the expression of the actual measurement processing. It provides the foundation for subsequently studying the reflection characteristics of the tooth flank at different incident angles and searching for the optimum incident attitude of the line structured light sensor.

Digital microfluidic, as an emerging and potential technology, diversifies the biochemical applications platform, such as protein dilution sewage detection. At present, a vast majority of universal cyberphysical digital microfluidic biochips (DMFBs) transmit data through wires via personal computers and microcontrollers (like Arduino), consequently, susceptible to various security threats and with the popularity of wireless devices, losing competitiveness gradually. On the premise that security be ensured first and foremost, calls for wireless portable, safe, and economical DMFBs are imperative to expand their application fields, engage more users, and cater to the trend of future wireless communication. To this end, a new cyber-physical DMFB called PortableLab is proposed in this paper, which guarantees data security through wireless sensors at low cost. After considering the security, computing consumption, and cost, a mobile module is added. In addition, the improved Advanced Encryption Standard (AES) and Cyclic Redundancy Check (CRC) algorithms are utilized to ensure the integrity and confidentiality of data transmission. Ultimately, all the security analysis, cost analysis, and experimental results on multiple protocols demonstrate the feasibility of the proposed PortableLab DMFB in time and space.

Presents corrections to the paper, (Corrections to “Two Methods With Bidirectional Similarity for Optimal Selections of Supplier Portfolio and Supplier Substitute Based on TOPSIS and IFS”).

Electricity is the foundation of the entire national economy, and nuclear power has become an important part of the power system with its unique advantages. The main process of nuclear power is the process of the nuclear fuel cycle, including the source and preparation of nuclear fuel, nuclear power plants and nuclear spent fuel processing. In the whole process, nuclear safety is the top priority and the key to the sustainable development of nuclear power. In this paper, aiming at the objective reality of high security risk and strict security requirements for nuclear fuel storage used in nuclear power, based on the analysis of nuclear fuel radiation characteristics and safety monitoring requirements, a nuclear fuel embedded system is designed from the aspects of system overall, software, hardware, data processing, etc. Security intelligent monitoring system. The system uses MCU as the control core, is equipped with motion detection and electronic seal devices, and realizes alarm functions such as identity authentication, unauthorized movement, and illegal unpacking real-time monitoring. Experiments and use show that the system can be easily integrated, installed and deployed on the nuclear fuel packaging container, and the operation is stable and reliable, which effectively promotes the steady improvement of the operating efficiency and operating quality of the nuclear energy system.

With the implementation of “photovoltaic power stations for poverty alleviation”， it becomes a new idea of earning extra income for farmer households with access to photovoltaic power and incorporating solar panels with power grid. In view of the characteristics of rural distribution networks， large-scale integration of photovoltaic power aggravates voltage quality. Firstly， given PV output fluctuations and complex distribution of rural loads， a typical system scenario is established using a clustering method based on AP （affinity propagation）. Secondly， the paper establishes a voltage quality control and planning model of double-layer hybrid distribution networks based on constraints of active power sources and reactive power sources， including bi-directional power flow， voltage constraint， PV， energy storage， and SVG. Finally， the paper presents a comprehensive solution to line loss rate and voltage quality control using distributed robust planning algorithms based on typical system scenarios. The results show that the proposed voltage control scheme can reduce costs and line loss rate without exceeding the voltage limit， and is proved safe and economical.

Abstract The 2050 carbon‐neutral vision spawns a novel energy structure revolution, and the construction of the future energy structure is based on equipment innovation. Insulating material, as the core of electrical power equipment and electrified transportation asset, faces unprecedented challenges and opportunities. The goal of carbon neutral and the urgent need for innovation in electric power equipment and electrification assets are first discussed. The engineering challenges constrained by the insulation system in future electric power equipment/devices and electrified transportation assets are investigated. Insulating materials, including intelligent insulating material, high thermal conductivity insulating material, high energy storage density insulating material, extreme environment resistant insulating material, and environmental‐friendly insulating material, are categorised with their scientific issues, opportunities and challenges under the goal of carbon neutrality being discussed. In the context of carbon neutrality, not only improves the understanding of the insulation problems from a macro level, that is, electrical power equipment and electrified transportation asset, but also offers opportunities, remaining issues and challenges from the insulating material level. It is hoped that this paper envisions the challenges regarding design and reliability of insulations in electrical equipment and electric vehicles in the context of policies towards carbon neutrality rules. The authors also hope that this paper can be helpful in future development and research of novel insulating materials, which promote the realisation of the carbon‐neutral vision.

Abstract The gas‐insulated switchgear (GIS) has been widely used in modern ultra‐high voltage systems. However, once it fails, its fully enclosed feature brings challenges in its diagnosis and maintenance. As the failure rate of GIS due to insulator failure has been increasing in recent years, it is necessary and important to understand the commonly existing defects presented in the insulator. First, the manufacturing process of GIS insulators is introduced here. The defect types commonly existing in the insulator are categorised. The failure of GIS due to insulator defects that occurred in recent years are reviewed and discussed. The content in this study is useful for engineers and scientists to study on the GIS solid insulation defects and their failure mechanisms.

Due to the randomness of load and renewable energy generation (REG), microgrids face multiple uncertainties. These uncertainties lead to the uncertainty of microgrid operation and bring more challenges to the economic evaluation of microgrids. In this paper, an economic evaluation method for determining microgrid revenue distribution is proposed. Considering the dual uncertainties of source-load and forecast, and temporal autocorrelation of time series, the probabilistic model of uncertainties is established by multivariate kernel density estimation (KDE). Then the random scenarios including forecasting values are generated and used in optimal dispatch calculation for the detailed production simulation. The probabilistic revenue is derived with a method based on Monte Carlo method. Finally, a case study is carried out based on the real data of an industrial park. The results demonstrate the necessity and effectiveness of the probabilistic revenue analysis proposed in this paper. This method can reveal the actual values of each component of a microgrid (e.g., device or algorithm) in specific scenes and provides more insights into investment decisions.

With the increase of travel demands in the networked metro system, more and more metro transfer stations are suffering from oversaturated situations, leading to the accumulation of passengers in the transfer corridor and boarding area with potential accident risks. To further improve the transfer efficiency and passenger accumulation safety at transfer stations, the joint operation strategy is adopted. Metro trains are allowed to run across different metro lines and passengers switch other lines without transfer. This paper proposes 1) a meaningful, yet simple, way for defining the running strategy of trains for joint operation with two intersecting metro lines and 2) an optimal model for the train frequency to minimize indicators associated with the passenger service and train capacity. Regulation constraints such as waiting time of through and transfer passengers, number of available trains, load factor, and departure interval are taken into account. Finally, a case study of the joint operation in the Beijing metro system is implemented to demonstrate the performance and effectiveness of the proposed approaches.

The three-coil loosely coupled inductive power transfer (IPT) charging system can achieve constant current (CC) to constant voltage (CV) output automatically and smoothly during battery charging process. However, due to cross-coupling that existed between the assistive and receiver coils, a voltage deviation will generate in CV output compared with the ideal CV charging voltage threshold of battery. In this paper, the practical effect of the cross-coupling between the assistive and receiver coils and the impedance matching at full load for efficiency optimization are further taken into consideration based on three-coil coupler design. Four design schemes of the assistive coil are compared by finite-element analysis (FEA) and an effective design approach is provided. Then, the proposed approach is theoretically analyzed to relieve the cross-coupling issue on the CV output even with efficiency optimization. Also, it decreases the space occupancy of the three-coil coupler. Finally, an experimental prototype is built to verify the proposed design method and the theoretical analysis.

Automatic License Plate Recognition (ALPR) is one of the applications that hugely benefited from Convolutional Neural Network (CNN) processing which has become the mainstream processing method for complex data. Many ALPR research proposed new CNN model designs and post-processing methods with various levels of performances in ALPR. However, good performing models such as YOLOv3 and SSD in more general object detection and recognition tasks could be effectively transferred to the license plate detection application with a small effort in model tuning. This paper focuses on the design of experiment (DOE) of training parameters in transferring YOLOv3 model design and optimising the training specifically for license plate detection tasks. The parameters are categorised to reduce the DOE run requirements while gaining insights on the YOLOv3 parameter interactions other than seeking optimised train settings. The result shows that the DOE effectively improve the YOLOv3 model to fit the vehicle license plate detection task.

Visual tracking remains an open challenge, as it requires real-time and long-term accurate target prediction. Siamese network has been widely studied due to its excellent accuracy and speed. Since long-term tracking may lead to model degradation and drift, most existing algorithms cannot well solve this problem. This article proposes a new Siamese Network based on Fast Attention Network named SiamFA. This method designs an attention model, which can enhance the key and global information of the target, to obtain a more robust target model and achieve long-term tracking. At the same time, the attention model is used to obtain the potential position information of the target when calculating the similarity between the template and the search area. In addition, the attention network we design reduces many redundant operations and effectively improves computational efficiency. We utilize a multi-layer perceptron to forecast the bounding box to avoid excessive hyper-parameters. In order to verify the effectiveness of our network, we conduct tests on many commonly used datasets, such as OTB100, GOT-10k, LaSOT, TrackingNet, UAV123. Our method can achieve a success rate of 62.7% and the precision rate of 64.3% on LaSOT. At the same time, it can run at about 100fps, which exceeds the comparison network, proving that our network can run in real-time.

With the rapid development of Social Networking Services (SNSs), linking online user IDs is becoming increasingly important to internet service providers. Existing methods can achieve matching adjacent IDs between different services, where adjacent IDs mean the IDs that send message loggings at the same physical location. However, nonadjacent IDs also need to be matched in reality, which is a key challenge. In this paper, a new method based on users social behaviors and contact graph is put forward to realize linking of IDs across domains. This method can be used for matching both adjacent IDs and nonadjacent IDs. Specifically, all the IDs are mapped to contact graph. And we utilize a set matching algorithm based on the contact graph to find out the set of candidate IDs and generate confidence score by means of this algorithm to select the most appropriate matching. Our experimental results show that our algorithm is capable of identifying not only the set of adjacent IDs that belong to one same user but also the set of nonadjacent IDs that belong to one same user.

In this work, we present the optimal design method of multimodal traffic strategies in emergency evacuations by considering the background traffic. First, the lane use configuration of public-oriented transport in multimodal evacuation that considers the background traffic is presented. Then, the feasible strategies are proposed based on the application conditions of five evacuation traffic strategies in feasible strategy proposal. Furthermore, the feasible strategies are transformed into optimal strategies by using the optimal strategy design model to minimize the weighted sum of public transport, private cars, and background traffic target values. Finally, the previous case study of Wenling is used to discuss the strategy evolution process, compare other strategies, and analyze the sensitivity of weights. The results presented in this work provide a reference for other researchers on the design and formulation of multimodal evacuation traffic strategies.

The objective of this research is to explore the temporal importance of community-scale human activity features for rapid assessment of flood impacts. Ultimate flood impact data, such as flood inundation maps and insurance claims, becomes available only weeks and months after the floods have receded. Crisis response managers, however, need near-real-time data to prioritize emergency response. This time lag creates a need for rapid flood impact assessment. Accordingly, community-scale big data (such as satellite imagery) has been utilized for the early estimation of end flood impacts. Some recent studies have shown promising results for using human activity fluctuations as indicators of flood impacts. Existing studies, however, used mainly a single community-scale activity feature for the estimation of flood impacts and have not investigated their temporal importance for indicating flood impacts. Hence, in this study, we examined the importance of heterogeneous human activity features (such as human mobility, visits to points-of-interest, and social media posts) in different flood event stages. Using four community-scale big data categories we derived ten features related to the variations in human activity (e.g., travel, credit card transactions, and online communications) and evaluated their temporal importance for rapid assessment of flood impacts. Using multiple random forest models, we examined the temporal importance of each feature in indicating the extent of flood impacts (measured by the flood insurance claims and flood inundations) in the context of the 2017 Hurricane Harvey in Harris County, Texas. Our findings reveal that 1) fluctuations in human activity index and percentage of congested roads are the most important indicators for rapid flood impact assessment during response and recovery stages; 2) variations in credit card transactions assumed a middle ranking in both response and recovery stages; and 3) patterns of geolocated social media posts (Twitter) were of low importance across flood stages. Insights derived from data analysis reveal the potential for harnessing community-scale data characterizing human activity fluctuations for rapid assessment of flood impacts. The results of this research could rapidly forge a multi-tool enabling crisis managers to identify hotspots with severe flood impacts at various stages then to plan and prioritize effective response strategies.