For extracting features of the Chinese text, we utilize the Jieba (Junyi 2022) as the tokenizer to cut the whole sentence of Chinese text into several segmentations. As stated in Table 4, we count the ten most frequent words in our dataset. After that, we use N-gram, GloVe, Word2vec (CBOW model), and BERT as embedding.
Contact online >>
Distributed energy generation increases the need for smart grid monitoring, protection, and control. Localization, classification, and fault detection are essential for addressing any problems immediately and resuming the smart grid as soon as possible. Simultaneously, the capacity to swiftly identify smart grid issues utilizing sensor data and easily accessible
In this article, a real-time fault prediction method combining cost-sensitive logistic regression (CS-LR) and cost-sensitive support vector machine classification (CS-SVM) is proposed. CS-LR is first used to classify the fault data of smart charging piles, then the CS-SVM is adopted to predict the faults based on the classified data. The
Table 1 Charging-pile energy-storage system equipment parameters Component name Device parameters Photovoltaic module (kW) 707.84 DC charging pile power (kW) 640 AC charging pile power (kW) 144 Lithium battery energy storage (kW·h) 6000 Energy conversion system PCS capacity (kW) 800 The system is connected to the user side through the inverter
This paper aims to measure the capability of supervised and semi-supervised machine learning techniques in assessing the risk state of EV charging piles. We investigate 8 algorithms, including Support Vector Machine (SVM), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Self-Training based on SVM (ST
We verified that the CNN-SVM-based V2G charging pile diagnostic model proposed in this paper has a more accurate classification effect than the CNN-SoftMax model,
To the best of our knowledge, there are not many papers dealing with the provision of a summary view of faults and failures types in SGs. We collected the major previous studies in Table 1.With the ongoing interest for SG cybersecurity, several studies providing a list of main attack types against SGs including countermeasures were published, such as Mathas
即时翻译文本&完整的文档文件。为个人和团队提供准确的翻译。每天有数百万人使用DeepL进行翻译。
This paper aims to fill this gap and consider 8 types of fault data for diagnosing, at least including physical installation error fault, charging-pile mechanical fault,...
Aiming at the problems that convolutional neural networks (CNN) are easy to overfit and the low localization accuracy in fault diagnosis of V2G charging piles, an improved
In this study, to develop a benefit-allocation model, in-depth analysis of a distributed photovoltaic-power-generation carport and energy-storage charging-pile project was performed; the model was
This paper proposes an error detection procedure of charging pile founded on ELM method. Different from the traditional charging pile fault detection model, this method constructs data for common features of the charging pile and establishes a classification prediction frame work that relies on the Extreme Learning Machine (ELM) algorithm
The most common fault type in the charging module is the short circuit and open circuit of each component in the operation of DC charging pile. The short circuit fault is a very serious fault, which will cause a large amount of overcurrent and will burn the components in a short time. Therefore, most of the circuits are equipped with
We verified that the CNN-SVM-based V2G charging pile diagnostic model proposed in this paper has a more accurate classification effect than the CNN-SoftMax model, and the fault simulation under different noises was carried out on the circuit topology of Figure 3; the fault type and component parameters are shown in Table 1.
The charging pile energy storage system can be divided into four parts: the distribution network device, the charging system, the battery charging station and the real-time monitoring system . On the charging side, by applying the corresponding software system, it is possible to monitor the power storage data of the electric vehicle in the charging process in
5 天之前· In order to improve the situation that the fault data set of electric vehicle charging pile has unbalanced data distribution under each fault and the small amount of data leads to the
5 天之前· In order to improve the situation that the fault data set of electric vehicle charging pile has unbalanced data distribution under each fault and the small amount of data leads to the inconspicuous data features, this paper proposes a method of SAE-MLP model for fault diagnosis of charging pile fault data. This paper firstly utilizes AE to
With the continuous development of electric vehicles (EV), large-scale distributed charging piles have been deployed in the wild. Therefore, it is extremely essential to evaluate the risk state of
This paper aims to fill this gap and consider 8 types of fault data for diagnosing, at least including physical installation error fault, charging-pile mechanical fault,...
The most common fault type in the charging module is the short circuit and open circuit of each component in the operation of DC charging pile. The short circuit fault is a very
Energy storage includes pumped storage, electrochemical energy storage, compressed air energy storage, molten salt heat storage etc . Among them, electrochemical energy storage based on lithium-ion battery
Compared to AC charging piles, DC charging piles have higher failure rates due to more components, larger operating power, and long-term outdoor exposure. Currently,
Aiming at the problems that convolutional neural networks (CNN) are easy to overfit and the low localization accuracy in fault diagnosis of V2G charging piles, an improved fault classification
Aiming at the problems that convolutional neural networks (CNN) are easy to overfit and the low localization accuracy in fault diagnosis of V2G charging piles, an improved fault...
This paper proposes an error detection procedure of charging pile founded on ELM method. Different from the traditional charging pile fault detection model, this method constructs data
Compared to AC charging piles, DC charging piles have higher failure rates due to more components, larger operating power, and long-term outdoor exposure. Currently, preliminary operation and maintenance work has been carried out, but there are still issues such as rough planning, excessive dependence on experience, and unclear targets.
This paper aims to measure the capability of supervised and semi-supervised machine learning techniques in assessing the risk state of EV charging piles. We investigate 8
This paper aims to fill this gap and consider 8 types of fault data for diagnosing, at least including physical installation error fault, charging-pile mechanical fault, charging-pile program fault, user personal fault, signal fault (offline), pile compatibility fault, charging platform fault, and other faults. We aim to find out how to combine
This manuscript addresses the critical challenge of fault classification and localization within smart distribution networks, exacerbated by the complex integration of distributed energy resources and the dynamic nature of modern power systems. Traditional methods fall short in accurately and efficiently managing these tasks due to their reliance on
Fault characteristic diagnosis of the charging pile is essentially fault diagnosis of the power electronic circuits, and the current fault diagnosis methods can be divided into two types : diagnostic methods based on analytical models or methods based on process data. The analytical-model-based approach is by building a mathematical model.
CS-LR is first used to classify the fault data of smart charging piles, then the CS-SVM is adopted to predict the faults based on the classified data. The feasibility of the proposed model is illustrated through the case study on fault prediction of real-world smart charging piles.
During the operation of DC charging pile, faults are easy to occur, mainly including communication faults, charging gun faults, charging module faults, etc. Among the possible faults of the DC charging post, the charging module failure rate is extremely high.
The research purpose of this paper is to make better and faster diagnosis of the fault of the charging pile using technology based on deep learning. Compared with the traditional machine learning algorithm, this paper does not need to calibrate the fault characteristics manually.
It is necessary to accurately judge the fault state of the charging module of DC charging pile in order to ensure the safe and reliable operation of DC charging pile. However, the fault signal processing of the fault detection method is poor, resulting in low fault detection accuracy.
In this article, a real-time fault prediction method combining cost-sensitive logistic regression (CS-LR) and cost-sensitive support vector machine classification (CS-SVM) is proposed. CS-LR is first used to classify the fault data of smart charging piles, then the CS-SVM is adopted to predict the faults based on the classified data.
We are deeply committed to excellence in all our endeavors.
Since we maintain control over our products, our customers can be assured of nothing but the best quality at all times.