Search

The feature extraction and state recognition of vibration signals of hydroelectric generating units are of great significance for effectively ensuring the safety and lifespan of unit operation. This paper introduces a novel fault diagnosis approach that leverages a wavelet threshold algorithm for initial signal preprocessing and enhances the Radial Basis Function (RBF) neural network with an optimized Gravitational Search Algorithm (GSA). Initially, the Wavelet Transform (WT) algorithm is employed to denoise the raw signal, which is subsequently decomposed using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN). Intrinsic Mode Function (IMF) components are then selected based on their correlation coefficients for sample entropy calculation. A GSA-optimized RBF neural network is constructed to diagnose faults in hydroelectric units. To further enhance the model’s convergence speed and accuracy, Lévy flight and chaotic sequence optimizations are integrated into the GSA, resulting in the development of the LCGSA-RBF diagnosis model. Experimental results demonstrate that this method achieves a 100% accuracy rate, outperforming other comparative models. Specifically, this approach enhances accuracy by 12.5% over the CEEMDAN-RBF method, showing the highest alignment with actual fault diagnosis results. This research significantly contributes to the advancement of safe and reliable operations in hydroelectric generating units.

To address the issues of low coordination in low-carbon operation between Carbon Capture and Storage (CCS) devices and Power to Gas (P2G) devices in integrated energy systems (IES), as well as the inaccurate characterization of carbon emissions from energy storage devices, this paper proposes an extended carbon emission flow model that integrates the collaborative operation mode of CCS-P2G and the low-carbon characteristics of energy storage. The model establishes a coupling relationship between CCS and P2G on the energy supply side to achieve low-carbon economic operation of P2G. On the energy storage side, the concept of “electricity-carbon ratio (ECR)” is introduced to characterize the carbon emission characteristics of energy storage devices, exploring the potential for coordinated low-carbon dispatch on both the energy supply and energy storage sides. Based on this, a low-carbon economic dispatch model for integrated energy systems is constructed, considering multiple uncertainties such as wind power, electricity prices, and electric-heat-gas loads. To achieve fast and efficient solving of the model, a parallel multi-dimensional approximate dynamic programming algorithm is adopted, which significantly improves solving efficiency by constructing a multi-layer parallel loop nested framework without losing solving accuracy. The effectiveness of the proposed model and algorithm is validated using an improved E14-H6-G6 system, consisting of a 14-node power grid, a 6-node heating network, and a 6-node gas network. The CCS-P2G (Carbon Capture, Storage, and Power-to-Gas) collaborative operation mode discussed in this article significantly enhances the economic and low-carbon performance of the Integrated Energy System (IES) by fully reutilizing CO2. Compared to unmodified coal-fired power units, the total cost is reduced by 137,900 yuan, thereby validating the effectiveness of the CCS-P2G collaborative operation mode in low-carbon scheduling.

Landslides pose a serious threat to human life, safety, and natural resources. Remote sensing images can be used to effectively monitor landslides at a large scale, which is of great significance for pre-disaster warning and post-disaster assistance. In recent years, deep learning-based methods have made great progress in the field of remote sensing image landslide detection. In remote sensing images, landslides display a variety of scales and shapes. In this article, to better extract and keep the multiscale shape information of landslides, a shape-enhanced vision transformer (ShapeFormer) model is proposed. For the feature extraction, a pyramid vision transformer (PVT) model is introduced, which directly models the global information of local elements at different scales. To learn the shape information of different landslides, a shape feature extraction branch is designed, which uses the adjacent feature maps at different scales in the PVT model to improve the boundary information. After the feature extraction step, a decoder with deconvolutional layers follows, which combines the multiple features and gradually recovers the original resolution of the combined features. A softmax layer is connected with the combined features to acquire the final pixel-wise result. The proposed ShapeFormer model was tested on two public datasets—the Bijie dataset and the Nepal dataset—which have different spectral and spatial characteristics. The results, when compared with those of some of the state-of-the-art methods, show the potential of the proposed method for use with multisource optical remote sensing data for landslide detection.

This paper is devoted to the issue of computationally efficient and robust nonlinear model predictive control (NMPC) for ship dynamic positioning (DP) systems subjected to input constraints and unknown environmental disturbances. The Laguerre functions, typically applied to the linear systems, are introduced to the constrained NMPC design of the nonlinear DP system to reduce the computational burden. The unscented Kalman filter is adopted to estimate the unknown disturbances and states; thus, the disturbance estimates are utilized as the cancellation signal to achieve robust offset-free control. Simulations of the proposed Laguerre function-based NMPC scheme are implemented and compared with the performance of typical Laguerre function-based linear model predictive control (LMPC) for the DP system. Simulation results well demonstrate the effectiveness, robustness and superiority of the proposed controller.

The upconversion detection is a promising method to detect infrared radiation. It is proved that the focused beam makes a contribution to improving the upconversion efficiency. A near-infrared detector at room-temperature based on sum frequency generation(SFG) with focused beams is demonstrated. To enhance the upconversion efficiency, the signal and pump beams are tightly focused by the same focal lens. To reduce that the dispersion of the focal lens has a negative effect on upconversion efficiency in a tightly focusing system, the relation between the upconversion efficiency and the focused beams in our system is investigated. In the setup, the signal and pump beams are combined by a polarization maintaining wavelength division multiplexer (PMWDM) that is connected on a collimator. The mixed beam is focused into a periodically poled lithium niobate (PPLN) bulk by a lens of 35 mm focal length. The signal pulse at 1550 nm is converted to 863 nm with a 172 mW continuous-wave pump beam at 1950 nm. The converted signal is measured by a photomultiplier tube(PMT) and results shows the maximum upconversion efficiency is $5.23 \times 10^{-4}$ while the pump power is 172 mW.

With the increasment of epilepsy patients, traditional epileptic seizure recognition is generally completed by encephalography (EEG) technicians, which is time-consuming and labor-intensive, so the automatic detection of seizure is imminent. This paper proposes a method which constructs a multi-layer network and extracts the same features in each network optimized by improved genetic algorithm (IGA). Among them, the multi-layer network refers to the three-layer network constructed by pearson correlation coefficient, mutual information and permutation disalignment index respectively. There is a lack of research on the fusion and comparison of different networks in previous studies. Therefore, this paper analyzes the effectiveness of different networks by studying the fusion relationship of different networks, and further uses IGA for iterative optimization with constraints to weight the network and features, and finally uses the random forest classifier to automatically detect epileptic seizures. On CHB-MIT database, accuracy (ACC), specificity (SPE), sensitivity (SEN) and F1 score (F1) of the method proposed in this paper reach 97.26%, 97.55%, 96.89% and 97.11%, respectively. On Siena scalp database, ACC, SPE, SEN and F1 reach 98.88%, 99.13%, 98.36% and 98.75%, respectively. The results show that the joint detection effect of the multi-layer network is better than the combined effect of other networks, and IGA can improve the effect of seizure detection.

In this paper, a mixed $H_{2}/H_{\infty }$ robust control strategy that considers the weights of the $H_{2}$ and $H_{\infty }$ norm in the optimization process is proposed, and it is used to solve the load frequency control (LFC) problem of the micro-grid (MG). The MG load frequency model established in this paper includes battery energy storage system (BESS), fuel cell (FC), wind turbine (WT), photo-voltaic (PV), and diesel engine generator (DEG). The optimal mixed $H_{2}/H_{\infty }$ robust controller takes the minimum square integral of the system’s frequency fluctuation as the goal of control optimization by integrating the robust performance expressed by the $H_{2}/H_{\infty }$ two norms. The hybrid particle swarm optimization and gravitational search algorithm with chaotic map algorithm (CPSOGSA) is used to optimize the weight value reflecting the $H_{2}$ and $H_{\infty }$ performance of the system and the evaluation function’s weighting matrix of the output performance so that the controller can reach the optimum under the constraints. Simulation experiments show that the robust controller designed by the proposed method has better dynamic performance when compared with $H_{\infty }$ robust controller, $H_{2}$ robust controller, and traditional $H_{2}/H_{\infty }$ robust controller, and the results are very satisfactory.

With the development of artificial intelligence technology, agricultural robot plays a significantly important role for agricultural intelligence. Crop row line detection is a critical and fundamental step for agricultural robot navigation. Although there are some crop row lines detection methods, few of them can meet the real-time requirement for agricultural robot under complex fields conditions. In view of this, a real-time crop detection system implemented on a SoC FPGA (System-on-a-Chip Field Programmable Gate Array) is first proposed in this paper, which contains crop segmentation and crop row detection, where we design parallel pipeline architecture to enhance real-time performance by using line buffer and sliding windows technologies. At the same time, the fixed point representation is used to reduce the memory resource in this system. The proposed system is evaluated and implemented on Xilinx Zynq UltraScale+ MPSoC ZCU102 SoC-FPGA. The experimental results show that the proposed system can process an image with 1920×1080 resolution only within 210 ms with the average accuracy of 89.7%, which satisfies the real-time requirements of the crop rows recognition.

Recent efforts in the network function virtualization (NFV) field have targeted ameliorating end-to-end latency of service function chains (SFCs) using network function (NF) composition. NF composition breaks the NF into building blocks and decides the appropriate combination for these blocks. However, two issues remain in current NF composition methods: (1) In the sequential scope, the fine-grained function's block-level composition eliminates redundancy, but with the drawback of flexibility restriction. (2) In the vertical scope, complete NF parallelism adds overhead in packet copying and reordering. To reconcile this, here we present ParaGraph, a subgraph-level NF composition with delay-balanced parallelism. ParaGraph has three main components: an NF subgraph-extraction module that extrapolates right-grained core function subgraphs from NFs; an orchestrator that dynamically composes subgraphs with delay-balanced parallelism; and an infrastructure performing lightweight packet copying and merging. We implement a ParaGraph prototype based on Click and the Data Plane Development Kit (DPDK); extensive evaluations show that with minimum overhead, ParaGraph reaches line-speed packet processing and reduces latency by up to 55% compared to state-of-the-art methods.

This paper discusses the direction-of-arrival (DOA) estimation problem in multiple-input multiple-output (MIMO) radar with non-orthogonal waveforms. Unlike the traditional orthogonal waveforms-based counterparts, spatially colored noise as well as corrupted virtual direction matrix would appear due to the correlated waveforms in DOA estimation. To tackle these issues, an improved propagator estimator is developed. The spatially colored noise caused by waveform imperfectly is eliminated via cross-correlation technique. Thereafter, DOA is obtained by exploiting the propagator and invariant techniques. The proposed estimator does not involve eigendecomposition of the high dimensional matrix, and it provides closed-form solution for DOA estimation. Compared with the existing frameworks, it is computationally much more economic. Moreover, it offers very close DOA estimation accuracy to the matrix-based methods. Numerical simulations are carried out to show the improvement of the proposed estimator.

To recognize the tender shoots for high-quality tea and to determine the picking points accurately and quickly, this paper proposes a method of recognizing the picking points of the tender tea shoots with the improved YOLO-v3 deep convolutional neural network algorithm. This method realizes the end-to-end target detection and the recognition of different postures of high-quality tea shoots, considering both efficiency and accuracy. At first, in order to predict the category and position of tender tea shoots, an image pyramid structure is used to obtain the characteristic map of tea shoots at different scales. The residual network block structure is added to the downsampling part, and the fully connected part is replaced by a 1 × 1 convolution operation at the end, ensuring accurate identification of the result and simplifying the network structure. The K-means method is used to cluster the dimension of the target box. Finally, the image data set of picking points for high-quality tea shoots is built. The accuracy of the trained model under the verification set is over 90%, which is much higher than the detection accuracy of the research methods.

Epilepsy is a disease in which patients undergo seizures caused by brain functionality disorder. Clinically, it is usually diagnosed by experienced clinicians according to continuous electroencephalography (cEEG), which is time consuming even for experienced doctors. Meanwhile, amplitude integrated electroencephalography (aEEG) has shown potential to detect epileptic seizures. Therefore, the paper proposes a hybrid seizure detection algorithm by combining cEEG-based seizure detection algorithm and aEEG-based seizure detection algorithm to detect seizures. In cEEG-based seizure detection algorithm, cEEG signals are divided into 5 s epoch with 4 s overlap and multi-domain features are extracted from each epoch. Then random forest classification is applied to do seizure detection. In aEEG-based seizure detection algorithm, morphological filter is applied to do spike detection and determine whether there are seizures after transforming the cEEG signals into aEEG signals. In order to evaluate the generality of the proposed method, experiments are performed on two independent datasets, including a publicly available EEG dataset (CHB-MIT) and an epileptic dataset collected by using the EEG device developed by the Hangzhou Neuro Science and Technology Co., Ltd. In the CHB-MIT dataset, the accuracy (AC), specificity (SP), sensitivity based on the event (SE), and false positive ratio based on the event (FPRE) obtained by the hybrid method are 99.36%, 82.98%, 99.41%, and 0.57 times/h, respectively. In the dataset we collected, the AC, SP, SE, and FPRE obtained by the hybrid method are 99.23%, 89.47%, 99.23%, and 0.71 times/h, respectively. The experimental results show that the performance of the proposed method is competitive with state-of-the-art methods and results. Furthermore, basing on the hybrid method, this paper has developed a portable automatic seizure detection system, which can reduce the burden of clinicians in processing the large amounts of cEEG signals by detecting seizure automatically.

In this paper, the problem of the direction of arrival (DOA) estimation for the multiple input multiple output (MIMO) array system is considered as a real-valued sparse signal recover procedure under the condition of unknown nonuniform noise. Then, a real-valued covariance vector-based sparse Bayesian learning framework is proposed, in which the reduced dimensional (RD) transformation is utilized to remove the redundant elements of MIMO array system, and a linear transformation is applied to eliminate the influence of unknown non-uniform noise. Then by supposing that the source powers follow an independent prior Gaussian distribution with zero-mean, a real-valued covariance vector-based sparse Bayesian model is formulated. And considering its unknown variance as hyper-parameters, they can be estimated by adopting the expectation-maximization algorithm. Finally, the DOA can be achieved according to the spatial spectrum of hyper-parameters. Simulation results have demonstrated that our proposed method not only achieves more superior performance but also provides robustness against nonuniform noise, compared with other recently reported sparse signal representation based methods.

A singly-fed circular aperture antenna radiating left-hand circularly polarized conical beam is proposed. The circularly polarized characteristic is realized by exciting TM01 and TE01 modes in a circular waveguide simultaneously. Through optimized design, the antenna provides an impedance bandwidth (\vert S 11 \vert < -10~dB) of 5%, from 12.15 to 12.8 GHz, and an axial ratio bandwidth (AR< 3~dB) of 4.8%, from 12.2 to 12.8 GHz. At the central frequency 12.5 GHz, a flare angle of 28^\circ of the radiation pattern and a measured gain of 7.5 dBic have been achieved. Good agreement has been observed between simulated results and measured ones. [ABSTRACT FROM PUBLISHER]

We have designed and tested a novel electronic tracking antenna array that is formed by 2 x 2 microstrip sub-arrays. Through time sequence phase weighting on each sub-array, the amplitude and phase on each sub-array can be recovered from the output of the resultant single channel. The amplitude and phase on each array can be used to produce the sum and difference radiation pattern by digital signal processing. In comparison with the monopulse system, the RF comparator is eliminated and the number of the receiver channels is reduced from 3 to 1. A proof-of-concept prototype was fabricated and tested. The measured results confirmed the validity and advantages of the proposed scheme. The procedure of channel correction is given. [ABSTRACT FROM AUTHOR]

A new model for coordinated optimal design of power system stabilizers (PSSs) is proposed for damping low frequency power oscillation of interconnected power systems and enhancing overall performance of both transient and small-signal stability. In this model, a novel objective function is constructed using rotor speeds of generators in a post disturbed period. Trajectory sensitivity mapping technique is proposed to evaluate the approximate gradients of the objective function relative to the PSS parameters. With the gradients, conjugate gradient method is employed to assess the PSS parameters for minimizing the objective function. Two schemes of gradient formulation and optimization procedure are suggested and compared. The model and effectiveness of the method are verified by eigenvalue assessments and time domain nonlinear simulations on the IEEE four-generator and the ten-generator New England test systems. [ABSTRACT FROM AUTHOR]

A new 2 × 2 microstrip antenna array is presented. The element used in this array is a tooth-like-slot patch. This patch is electromagnetically coupled by a microstrip feed line. In addition to the easy feeding, the proposed structure possesses the advantages of being wide bandwidth, high gain and the low cross-polarization level. The patch element has the peak gain 10.2 dBi and the cross-polarization is lower than -23 dB within the impedance bandwidth. The measured VSWR of 2 × 2 array show that the impedance bandwidth is 34%. The gain of the array is 14-16.3 dBi at 4.8-6.1 GHz. And the cross-polarization level of the array is lower than -20 dB within the impedance bandwidth. [ABSTRACT FROM AUTHOR]

This paper presents a new generation rescheduling approach for preventive control of power systems, which can optimally reallocate power generations for multiple unstable contingencies. The transient stability constraints used in the optimal rescheduling model are described by a heuristic stability performance index. A backward integration technique is proposed to evaluate gradient of the performance index. Using the gradient, the functional inequality constraints imposed by unstable contingencies are expressed by linear inequalities, and the rescheduling problem is solved iteratively. Effectiveness of the approach is demonstrated by numerical tests on a representation of North-China power system. [ABSTRACT FROM AUTHOR]