Efficient and accurate insulator defect detection is essential for maintaining the safe and stable operation of transmission ***,the detection effectiveness is adversely impacted by complex and changeable environmenta...
详细信息
Efficient and accurate insulator defect detection is essential for maintaining the safe and stable operation of transmission ***,the detection effectiveness is adversely impacted by complex and changeable environmental backgrounds,particularly under extreme weather that elevates accident ***,this research proposes a high-precision intelligent strategy based on the synthetic weathera* algorithm and improved YOLOv7 for detecting insulator defects under extreme *** proposed meth-odology involves augmenting the dataset with synthetic rain,snow,and foga* algorithm ***,the original dataset undergoes augmentation through affine and colour transformations to improve model's generalisation performance under complex power inspection *** achieve higher recognition accuracy in severe weather,an improved YOLOv7a* algorithm for insulator defect detection is proposed,integrating focal loss with SIoU loss function and incorporating an optimised decoupled head *** results indicate that the synthetic weathera* algorithm processing significantly improves the insulator defect detection accuracy under extreme weather,increasing the mean average precision by 2.4%.Furthermore,the authors’improved YOLOv7 model achieves 91.8%for the mean average precision,outperforming the benchmark model by 2.3%.With a detection speed of 46.5 frames per second,the model meets the requirement of real-time detection of insulators and their defects during power inspection.
The gravitational lensing wave effect generated by a microlensing field embedded in a lens galaxy is an inevitable phenomenon in strong lensed gravitational waves(SLGWs).This effect presents both challenges and opport...
详细信息
The gravitational lensing wave effect generated by a microlensing field embedded in a lens galaxy is an inevitable phenomenon in strong lensed gravitational waves(SLGWs).This effect presents both challenges and opportunities for the detection and appli-cation of ***,investigating this wave effect requires computing a complete diffraction integral over each microlens in the *** is extremely time-consuming due to the large number of microlenses(10^(3)-10^(6)).Therefore,simply adding all the microlenses is ***,the complexity of the time delay surface makes the lens plane resolution a crucial factor in controlling numerical *** this paper,we propose a trapezoid approximation-based adaptive hierarchical tree algo-rithm to meet the challenges of calculation speed and *** find that thisa* algorithm accelerates the calculation by four orders of magnitude compared to the simple adding method and is one order of magnitude faster than the fixed hierarchical treea* algorithm proposed for electromagnetic *** importantly,oura* algorithm ensures controllable numerical errors,increasing confidence in the *** with our previous work(***.66,239511,2023),this paper addresses all numerical issues,including integral convergence,precision,and computational time1).Finally,we conducted a population study on the microlensing wave effect of SLGWs using thisa* algorithm and found that the microlensing wave effect cannot be ignored,especially for Type II SLGWs(from saddle position of the time delay surface)due to their intrinsic geometric structures and their typical intersection with a denser microlensing ***,more than 33%(11%)of SLGWs have a mismatch larger than 1%(3%)compared to the unlensed ***,we found that the mismatch between signal pairs in a doubly imaged GW is generally larger than 10^(−3),and 61%(25%)of signal pairs have a mismatch larger than 1%(3%).Theref
Signal detection plays an essential role in massive Multiple-Input Multiple-Output(MIMO)***,existing detection methods have not yet made a good tradeoff between Bit Error Rate(BER)and computational complexity,resultin...
详细信息
Signal detection plays an essential role in massive Multiple-Input Multiple-Output(MIMO)***,existing detection methods have not yet made a good tradeoff between Bit Error Rate(BER)and computational complexity,resulting in slow convergence or high *** address this issue,a low-complexity Approximate Message Passing(AMP)detectiona* algorithm with Deep Neural Network(DNN)(denoted as AMP-DNN)is investigated in this ***,an efficient AMP detectiona* algorithm is derived by scalarizing the simplification of Belief Propagation(BP)***,by unfolding the obtained AMP detectiona* algorithm,a DNN is specifically designed for the optimal performance *** the proposed AMP-DNN,the number of trainable parameters is only related to that of layers,regardless of modulation scheme,antenna number and matrix calculation,thus facilitating fast and stable training of the *** addition,the AMP-DNN can detect different channels under the same distribution with only one *** superior performance of the AMP-DNN is also verified by theoretical analysis and *** is found that the proposeda* algorithm enables the reduction of BER without signal prior information,especially in the spatially correlated channel,and has a lower computational complexity compared with existing state-of-the-art methods.
The deployment of intelligent surveillance systems to monitor tomato plant growth poses substantial challenges due to the dynamic nature of disease patterns and the complexity of environmental conditions such as backg...
详细信息
The deployment of intelligent surveillance systems to monitor tomato plant growth poses substantial challenges due to the dynamic nature of disease patterns and the complexity of environmental conditions such as background and *** this study,an integrated cascade framework that synergizes detectors and trackers was introduced for the simultaneous identification of tomato leaf diseases and fruit *** applied an autonomous robot with smartphone camera to collect images for leaf disease and fruits in greenhouses.
Fibre optic F-P sensor has become one of the mainstream detection methods for partial discharge faults due to their advantages of good insulation,high sensitivity,resistance to electromagnetic interference,simple stru...
详细信息
Fibre optic F-P sensor has become one of the mainstream detection methods for partial discharge faults due to their advantages of good insulation,high sensitivity,resistance to electromagnetic interference,simple structure and inexpensive *** first-order resonant frequency of the acoustically sensitive diaphragm of the F-P sensor is given based on the theory of plate and shell vibration,and the fibre optic F-P sensing array is designed based on the Fabry–Perot interference principle.A sensor installation method is also proposed for introducing a fibre optic F-P probe into the power transformer interior using a fibre optic penetrator through flange at the power transformer oil change valve.A system of non-linear equations is developed by utilising the time difference of arrival(TDOA)of the partial discharge ultrasound signal propagation to the F-P sensing *** Chan-WLSa* algorithm is used to convert the non-linear equations in the TDOA localisation method into a non-linear optimisation problem to be solved and experi-mentally verified on the 220 kV real power *** experimental results show that the error in the partial discharge fault localisation is solved based on the Chan-WLSa* algorithm and the actual location is 20.27 cm,which is within the acceptable error.
For the space charge measurement method with optical excitation for electrical insulation,the distortion of the excitation laser on the measurement signal and the accumulation of space charge have not been discussed *...
详细信息
For the space charge measurement method with optical excitation for electrical insulation,the distortion of the excitation laser on the measurement signal and the accumulation of space charge have not been discussed *** experiment and simulation results show that three types of distorted components introduced by optical excitation can lead to distortion of the upper interface ***,the factors causing distortion of the measured signal and the formation mechanism are analysed.A virtual electrode potential compensation method and a distorted component extraction method are ***,an attenuation restoration and charge conversion correction factor is intro-duced,leading to a novel signal processinga* algorithm adapted to space charge optical measurement *** with the traditionala* algorithm,the novela* algorithm has an error of less than 1%in the calculation of charge and electric field strength,with an increase in accuracy of 47.7%and 9.81%,*** applying the novel restorationa* algorithm,the comparison shows that the space charge accumulation does not change significantly under laser irradiation,verifying the reliability of the optical *** givena* algorithm can provide a theoretical and technical foundation for the realisation of the optical measurement method for space charge.
Quantuma* algorithms are emerging tools in the design of functional materials due to their powerful solution space search *** to balance the high price of quantum computing resources and the growing computing needs has ...
详细信息
Quantuma* algorithms are emerging tools in the design of functional materials due to their powerful solution space search *** to balance the high price of quantum computing resources and the growing computing needs has become an urgent problem to be *** propose a novel optimization strategy based on an active learning scheme that combines the Quantum-inspired Genetica* algorithm(QGA)with machine learning surrogate model *** Random Forests as the surrogate model circumvents the time-consuming physical modeling or experiments,thereby improving the optimization ***,a genetica* algorithm embedded with quantum mechanics,combines the advantages of quantum computing and genetica* algorithms,enabling faster and more robust convergence to the *** the design of planar multilayer photonic structures for transparent radiative cooling as a testbed,we show superiority of oura* algorithm over the classical genetica* algorithm(CGA).Additionally,we show the precision advantage of the Random Forest(RF)model as a flexible surrogate model,which relaxes the constraints on the type of surrogate model that can be used in other quantum computing optimizationa* algorithms(e.g.,quantum annealing needs Ising model as a surrogate).
Electronic nose is a bionic technology that uses sensor arrays and pattern recognitiona* algorithms to mimic the human olfactory system. This study developed a thermal desorption-photoionization ion mobility-electronic ...
详细信息
Electronic nose is a bionic technology that uses sensor arrays and pattern recognitiona* algorithms to mimic the human olfactory system. This study developed a thermal desorption-photoionization ion mobility-electronic nose (TD-PIM-Nose) system, employing thermal desorption for direct sampling and humidity control, with a photoionization ion mobility tube as virtual sensor array for component separation and detection, and pattern recognitiona* algorithms for signal processing to differentiate and identify samples. Furthermore, it was applied to assess four quality grades of Daqu samples ("Excellent+", "Excellent", "Grade I", and "Grade II") determined by the Check-All-That-Apply (CATA) method. Characteristic compound differences among these grades were identified using fingerprint spectra and reduced mobility values. A distance-probability joint decision support vector machine (SVM)a* algorithm model was established, validated against sensory CATA standards. Results showed identification accuracies: 90 %, 90 %, 96.88 %, and 100 % for respective grades. These findings demonstrated the promising potential of the TD-PIM-Nose system in Daqu quality grading.
Production scheduling is a strategic process that organizes the execution of jobs on available resources to optimize specific objectives. One significant scheduling challenge is the Cost-based Hybrid Flow Shop (CHFS) ...
详细信息
Production scheduling is a strategic process that organizes the execution of jobs on available resources to optimize specific objectives. One significant scheduling challenge is the Cost-based Hybrid Flow Shop (CHFS) problem, which involves optimizing job scheduling across multiple stages to minimize scheduling-related costs. However, limited attention has been given to CHFS when considering holistic cost models using efficienta* algorithms. This paper presents a novel Greedy-Assisted Teaching-Learning-Based Optimization (GTLBO)a* algorithm for CHFS. Unlike previous studies that focus on isolated cost factors, this research formulated an integrated mathematical model for CHF holistically capturing labor, energy consumption, maintenance, and late penalty costs. The GTLBOa* algorithm incorporates a unique hybrid initialization strategy, generating 10 % of the initial population using a Greedya* algorithm to enhance exploration efficiency. The performance of GTLBO was evaluated through computational experiments involving 12 test instances, with comparativea* algorithms included for analysis. Results from the Wilcoxon rank-sum test indicated a significant difference between the outputs of GTLBO and othera* algorithms, with GTLBO outperforming the comparativea* algorithms in 75 % of the test instances. Additionally, the case study validation showed that GTLBO can reduce costs by 0.23 % to 4.31 % compared to othera* algorithms. This research offers valuable insights for manufacturers seeking to optimize CHFS scheduling to reduce production expenses.
Precise assessment of Space-speed time delay (TD) is critical for distinguishing between anticipation and reaction behaviors within pedestrian motion. Besides, the TD scale is instrumental in the evaluation of potenti...
详细信息
Precise assessment of Space-speed time delay (TD) is critical for distinguishing between anticipation and reaction behaviors within pedestrian motion. Besides, the TD scale is instrumental in the evaluation of potential collision tendency of the crowd, thereby providing essential quantitative metrics for assessing risk. In this consideration, this paper introduced the CosIna* algorithm for evaluating TD during pedestrian motion, which includes both the CosIn-1 and CosIn-2a* algorithms. CosIn-1a* algorithm analytically calculates TD, replacing the numerical method of discrete cross-correlation, whereas the CosIn-2a* algorithm estimates the TD from a statistical perspective. Specifically, the CosIn-1a* algorithm addresses the precise computation of TD for individual pedestrians, while the CosIn-2a* algorithm is employed for assessing TD at the crowd scale, concurrently addressing the imperative of real-time evaluation. Efficacy analyses of the CosIn-1 and CosIn-2a* algorithms are conducted with data from single-file pedestrian experiments and crowd-crossing experiments, respectively. During this process, the discrete cross-correlation method was employed as a baseline to evaluate the performance of botha* algorithms, which demonstrated notable accuracy. Thisa* algorithm facilitate the precise evaluation of behavior patterns and collision tendency within crowds, thereby enabling us to understand the crowds dynamics from a new perspective.
暂无评论