Deep neural networks have been widely applied to bearing fault diagnosis systems and achieved impressive success *** address the problem that the insufficient fault feature extraction ability of traditional fault diag...
详细信息
Deep neural networks have been widely applied to bearing fault diagnosis systems and achieved impressive success *** address the problem that the insufficient fault feature extraction ability of traditional fault diagnosis methods results in poor diagnosis effect under variable load and noise interference scenarios,a rolling bearing fault diagnosis model combining Multi-Scale Convolutional Neural Network(MSCNN)and Long Short-Term Memory(LSTM)fused with attention mechanism is *** adaptively extract the essential spatial feature information of various sizes,the model creates a multi-scale feature extraction module using the convolutional neural network(CNN)learning *** learning capacity of LSTM for time information sequence is then used to extract the vibration signal’s temporal feature *** parallel large and small convolutional kernels teach the system spatial local *** gathers temporal global features to thoroughly and painstakingly mine the vibration signal’s characteristics,thus enhancing model ***,bearing fault diagnosis is accomplished by using the SoftMax *** experiment outcomes demonstrate that the model can derive fault properties entirely from the initial vibration *** can retain good diagnostic accuracy under variable load and noise interference and has strong generalization compared to other fault diagnosis models.
Aiming at defects such as low contrast in infrared ship images,uneven distribution of ship size,and lack of texture details,which will lead to unmanned ship leakage misdetection and slow detection,this paper proposes ...
详细信息
Aiming at defects such as low contrast in infrared ship images,uneven distribution of ship size,and lack of texture details,which will lead to unmanned ship leakage misdetection and slow detection,this paper proposes an infrared ship detection model based on the improved YOLOv8 algorithm(R_YOLO).The algorithm incorporates the Efficient Multi-Scale Attention mechanism(EMA),the efficient Reparameterized Generalized-feature extraction module(CSPStage),the small target detection header,the Repulsion Loss function,and the context aggregation block(CABlock),which are designed to improve the model’s ability to detect targets at multiple scales and the speed of model *** algorithm is validated in detail on two vessel *** comprehensive experimental results demonstrate that,in the infrared dataset,the YOLOv8s algorithm exhibits improvements in various performance ***,compared to the baseline algorithm,there is a 3.1%increase in mean average precision at a threshold of 0.5(mAP(0.5)),a 5.4%increase in recall rate,and a 2.2%increase in mAP(0.5:0.95).Simultaneously,while less than 5 times parameters,the mAP(0.5)and frames per second(FPS)exhibit an increase of 1.7%and more than 3 times,respectively,compared to the CAA_YOLO ***,the evaluation indexes on the visible light data set have shown an average improvement of 4.5%.
Under the background of 'double carbon', the powersystem is facing green change, and the distribution network is facing the challenge of distributed generation and diversified load. Traditional distribution t...
详细信息
Photovoltaic(PV)and battery energy storage systems(BESSs)are key components in the energy market and crucial contributors to carbon emission reduction *** systems can not only provide energy but can also generate cons...
详细信息
Photovoltaic(PV)and battery energy storage systems(BESSs)are key components in the energy market and crucial contributors to carbon emission reduction *** systems can not only provide energy but can also generate considerable revenue by providing frequency regulation services and participating in carbon *** study proposes a bidding strategy for PV and BESSs operating in joint energy and frequency regulation markets,with a specific focus on carbon reduction benefits.A two-stage bidding framework that optimizes the profit of PV and BESSs is *** the first stage,the day-ahead energy market takes into account potential real-time forecast *** the second stage,the real-time balancing market uses a rolling optimization method to account for multiple ***,a real-time frequency regulation control method is proposed for the participation of PV and BESSs in automatic generation control(AGC).This is particularly relevant given the uncertainty of grid frequency fluctuations in the optimization model of the real-time balancing *** control method dynamically assigns the frequency regulation amount undertaken by the PV and BESSs according to the control interval in which the area control error(ACE)*** case study results demonstrate that the proposed bidding strategy not only enables the PV and BESSs to effectively participate in the grid frequency regulation response but also yields considerable carbon emission reduction benefits and effectively improves the system operation economy.
High availability of wind power data is the basis for wind power research, but there are a large number of abnormal data in actual collected data, which seriously affects analysis of wind power law and reduces predict...
详细信息
High availability of wind power data is the basis for wind power research, but there are a large number of abnormal data in actual collected data, which seriously affects analysis of wind power law and reduces prediction accuracy. Measured power data of wind farm are analyzed, influence of wind speed fluctuation characteristics on wind power is discussed, and abnormal points are identified for data of different wind types. The Cluster-Based Local Outlier Factor (CLOF) algorithm based on K-means is used to identify outlier abnormal points, and conditional constraints based on physical background are used to identify accumulation abnormal points. Reconstructed data segment is divided according to fluctuation of wind speed. The Bidirectional Gate Recurrent Unit (BiGRU) model with wind speed as input reconstructs fluctuation segment data, and bi-directional weighted random forest model reconstructs stationary segment data. Based on analysis of measured data of a wind farm, results show the method can effectively identify various abnormal data, and complete high-quality reconstruction of data, thereby improving accuracy of wind power prediction.
To ensure frequency stability in powersystems with high wind penetration,the doubly-fed induction generator(DFIG)is often used with the frequency fast response control(FFRC)to participate in frequency ***,a certain o...
详细信息
To ensure frequency stability in powersystems with high wind penetration,the doubly-fed induction generator(DFIG)is often used with the frequency fast response control(FFRC)to participate in frequency ***,a certain output power suppression amount(OPSA)is generated during frequency support,resulting in the frequency modulation(FM)capability of DFIG not being fully utilised,and the system’s unbalanced power will be increased during speed recovery,resulting in a second frequency drop(SFD)in the ***,the frequency response characteristics of the powersystem with DFIG containing FFRC are ***,based on the analysis of the generation mechanism of OPSA and SFD,a combined wind-storage FM control strategy is proposed to improve the system’s frequency response *** strategy reduces the effect of OPSA and improves the FM capability of DFIG by designing the fuzzy logic of the coefficients of FFRC according to the system frequency index in the frequency support *** the speed recovery stage,the energy storage(ES)active power reference value is calculated according to the change of DFIG rotor speed,and the ES output power is dynamically adjusted to reduce the ***,taking the IEEE 39-bus test system as an example,real-time digital simulation verification was conducted based on the RTLAB OP5707 simulation *** simulation results showthat theproposedmethodcan improve theFMcapabilityofDFIG,reduce the SFDunder thepremise of guaranteeing the rapid rotor speed recovery,and avoid the overshooting phenomenon so that the systemfrequency can be quickly restored to a stable state.
Currently,both regulated and deregulated power trading exist in China’s powersystem,which has caused imbalanced funds in the electricity *** this paper,a simulation analysis of the electricity market with wind energ...
详细信息
Currently,both regulated and deregulated power trading exist in China’s powersystem,which has caused imbalanced funds in the electricity *** this paper,a simulation analysis of the electricity market with wind energy resources is conducted,and the calculation methods of unbalanced funds are investigated *** detail,the calculation formulas of unbalanced funds are illustrated based on their definition,and a two-track electricity market clearing model is ***,the concept of the dual-track system is explained,and the specific calculation formulas of various types of unbalanced funds are ***,considering the renewableenergy consumption,the market clearing model based on DC power flow is constructed and solved;by combining fitting methods of mid-and long-term curves,the unbalanced funds are calculated based on clearing results and formulas.
Fault detection and location are critically significant applications of a supervisory controlsystem in a smart *** methods,based on random matrix theory(RMT),have been practiced using measurements to detect short cir...
详细信息
Fault detection and location are critically significant applications of a supervisory controlsystem in a smart *** methods,based on random matrix theory(RMT),have been practiced using measurements to detect short circuit faults occurring on transmission ***,the diagnostic accuracy is infuenced by the noise signal in the *** relationship between mean eigenvalue of a random matrix and noise is detected in this paper,and the defects of the Mean Spectral Radius(MSR),as an indicator to detect faults,are theoretically determined,along with a novel indicator of the shifting degree of maximum eigenvalue and its *** comparing the indicator and the threshold,the occurrence of a fault can be ***,an augmented matrix is constructed to locate the fault *** proposed method can effectively achieve fault detection via the RMT without any influence of noise,and also does not depend on system *** experiment results are based on the IEEE 39-bus ***,actual provincial grid data is applied to validate the effectiveness of the proposed method.
Due to the slow dynamic power-regulation characteristics of the electrolyser(EL),a novel integrated three-port DC/DC converter topology based on a phase-shifted full-bridge converter and dual active-bridge converter i...
详细信息
Due to the slow dynamic power-regulation characteristics of the electrolyser(EL),a novel integrated three-port DC/DC converter topology based on a phase-shifted full-bridge converter and dual active-bridge converter is proposed in this ***,the proposed converter can achieve a fast auxiliary response to the *** topology has the features of single-stage conversion,high system integration and compatibility with multiple operation *** operational principles and a hybrid modulation scheme of the proposed converter are analysed in *** addition,the power-transmission characteristics of each port and the soft-switching range are *** these bases,six operation modes suitable for a hydrogen energy-storage system are *** simulation and a 2-kW scaled-down experimental prototype are established to verify the feasibility and effectiveness of the proposed topology in different operation modes.
A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The ne...
详细信息
A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The networkcomprises an encoder module, fusion layer, decoder module, and edge improvementmodule. The encoder moduleutilizes an enhanced Inception module for shallow feature extraction, then combines Res2Net and Transformerto achieve deep-level co-extraction of local and global features from the original picture. An edge enhancementmodule (EEM) is created to extract significant edge features. A modal maximum difference fusion strategy isintroduced to enhance the adaptive representation of information in various regions of the source image, therebyenhancing the contrast of the fused image. The encoder and the EEM module extract features, which are thencombined in the fusion layer to create a fused picture using the decoder. Three datasets were chosen to test thealgorithmproposed in this paper. The results of the experiments demonstrate that the network effectively preservesbackground and detail information in both infrared and visible images, yielding superior outcomes in subjectiveand objective evaluations.
暂无评论