Acoustic signal is commonly generated in the thermal runaway process of lithium energy storage batteries. In order to understand the acoustic information of the lithium batteries, an experimental platform is designed ...
Acoustic signal is commonly generated in the thermal runaway process of lithium energy storage batteries. In order to understand the acoustic information of the lithium batteries, an experimental platform is designed to test the thermal runaway sound signals of different type of lithium blade batteries. The sound variance process of thermal runaway is recorded. Time-and-frequency-domain methods are used to analyze the acoustic characteristics of the batteries. It is found that thermal runaway can be detected with sound test method. The research result validates that acoustic method could be used as a new technology for early and ultra-early safety warning of lithium batteries, which is of great significance to the safe operation of energy storage stations.
In the field of data mining, clustering algorithms play a key role in extracting valuable insights from vast datasets without incorporating learning mechanisms. One such classical clustering approach is the spectral c...
In the field of data mining, clustering algorithms play a key role in extracting valuable insights from vast datasets without incorporating learning mechanisms. One such classical clustering approach is the spectral clustering algorithm. This algorithm effectively converts a clustering challenge into the segmentation of an undirected graph, enabling it to handle intricate non-convex datasets adeptly and avoid getting trapped in local optimization pitfalls. Nevertheless, the conventional spectral clustering technique relies on the Gaussian kernel function, which uses Euclidean distance to determine sample similarities. This method proves overly sensitive to the Gaussian kernel's parameters and fails to accurately represent inter-sample relationships. To address the drawbacks related to similarity measurement and the computational inefficiencies inherent in the traditional spectral clustering method, enhancements have been made to refine the clustering outcomes. The enhanced spectral clustering algorithm has been redesigned to be distributed and parallelized, a strategic move intended to bolster the processing ability when handling enormous datasets.
Due to the large amount of computation required for authentication and matching in the data sharing phase, there is a certain delay in the real-time performance of the corresponding efficiency. Therefore, this paper p...
详细信息
This paper designs a power marketing data analysis system based on data mining technology. Then the software and hardware of the scheme are optimized respectively. The main contents of this paper include: data collect...
This paper designs a power marketing data analysis system based on data mining technology. Then the software and hardware of the scheme are optimized respectively. The main contents of this paper include: data collection, data mining and data processing. Then a new multi-level clustering method based on implicit Markov pattern is proposed. The method converts the time series of a time series into a likelihood space in which the likelihood value is identified by a symmetric KL distance. A symmetric KL migration matrix is constructed, and the access modes of users are divided into different levels by the idea of hierarchical clustering. Then a complete power grid enterprise information system is established, which is an important part of the power grid marketing system. Online analysis technology is used to ensure the whole logic input, so as to ensure the normal operation of the power marketing management system. The experiment shows that this method can realize the comprehensive processing of all kinds of electricity information, and will not cause large fluctuations.
In order to overcome the payment delay and the difficulty of verifying frontline worker information, caused by the subcontract and the rapid flow of workers in power infrastructure projects, we propose a power infrast...
In order to overcome the payment delay and the difficulty of verifying frontline worker information, caused by the subcontract and the rapid flow of workers in power infrastructure projects, we propose a power infrastructure payroll system framework based on dual blockchain. The framework consists of an identity authentication chain and a data sharing chain, which communicates through smart contracts. The efficient operation of the framework depends on the timely and accurate reporting of various personnel information of workers and enterprise credit information from subcontractors, thus, we construct a data sharing scheme between the frontline subcontractors and power general contractors in smart grids using the reverse auction theory. Simulation results demonstrate that the proposed dual blockchain framework and data sharing scheme can promote the data sharing efficiency of frontline subcontractors, and the security and efficiency of payroll payment in the power infrastructure system are also improved.
As an important method in data preprocessing, discretization can effectively reduce the size of data, generate concise semantic representation, obtain valuable knowledge and information contained in bigdata, which is...
As an important method in data preprocessing, discretization can effectively reduce the size of data, generate concise semantic representation, obtain valuable knowledge and information contained in bigdata, which is of great significance in the fields of data mining and machine learning. Nevertheless, most of the traditional discretization algorithms don't consider the distribution of sample and difficulty in setting parameters during interval partitioning, which leads to a decrease in efficiency and classification accuracy. A data discretization algorithm based on granular-ball computing and attribute significance is proposed in this paper, which is a multi-granularity method. Firstly, by introducing the granular-ball computing, the difficulty of parameter optimization is reduced and the efficiency of the algorithm is improved. At the same time, interval partitioning adaptively fits the original data distribution, reducing the occurrence of uneven interval partitioning and improving classification accuracy. Then, the randomness of attribute selection leads to instability in interval partitioning results. By introducing attribute significance and prioritizing the selection of attributes with high importance, this paper further improves the classification accuracy. Compared to other excellent discretization algorithms in the experiments, the proposed algorithm shows an ideal performance.
Phishing, a deceptive cyberattack technique, poses a significant threat to online users by tricking them into disclosing personal or financial information through counterfeit web pages that impersonate legitimate ones...
Phishing, a deceptive cyberattack technique, poses a significant threat to online users by tricking them into disclosing personal or financial information through counterfeit web pages that impersonate legitimate ones. This paper explores data enhancement and feature engineering techniques as a means to improve the performance of phishing web page detection methods. data enhancement involves methods like data augmentation, oversampling, and undersampling, which aim to balance class distribution and enhance data diversity and quality. These techniques are essential to mitigate the data imbalance issue often encountered in phishing detection datasets. Feature engineering techniques, including feature selection, extraction, and transformation, are introduced to reduce data dimensionality and enhance the discriminative power of features. The proposed approach is experimentally validated, providing a valuable resource for improving online security in the face of evolving cyber threats. This work lays the foundation for future research in the domain of phishing detection, addressing a critical issue in cybersecurity.
A solar panel recognition method based on YOLOv3 deep learning algorithm is proposed to address issues such as inaccurate recognition of traditional algorithms in space solar panel detection. First, this paper scales ...
A solar panel recognition method based on YOLOv3 deep learning algorithm is proposed to address issues such as inaccurate recognition of traditional algorithms in space solar panel detection. First, this paper scales the dataset images to $\mathbf{416} \times \mathbf{416}$ , then uses Labelme to annotate the data and transform the bounding box position information, and finally uses the YOLOv3 algorithm framework for model training. The results show that the recall, F1 score and accuracy of YOLOv3 algorithm are all above 80%. The YOLOv3 deep learning algorithm meets the requirements for real-time detection of solar panels in terms of accuracy.
With the development of national informatization construction and bigdata technology, the traditional database design can no longer support the efficient storage and real-time analysis of massive data, and it is diff...
详细信息
The on-boarddata of EMU is the parameter information collected by the sensor during the operation of EMU, which plays an important role in evaluating the operating state of EMU and analyzing the cause of fault in dep...
The on-boarddata of EMU is the parameter information collected by the sensor during the operation of EMU, which plays an important role in evaluating the operating state of EMU and analyzing the cause of fault in depth. By analyzing the situation of vehicle data and combining the characteristics of 5G technology, this paper puts forward a method of vehicle data download based on 5G, designs an EMU vehicle data download and application platform, and adopts key technologies such as massive data processing and monitoring, batch efficient data analysis and large amount of data storage. To achieve vehicle data collection and transmission, data monitoring, data analysis, data sharing and comprehensive display and other functions. The realization of the platform is helpful to further promote the application of on-boarddata of EMU, which is of great significance to promote the fault analysis of EMU and the application of state evaluation and prediction.
暂无评论