Search

Partial discharge (PD) detection and diagnosis based on the ultra-high frequency (UHF) signals is one of the most widely adopted methods to evaluate the internal insulation status of high voltage equipment. Benefit from the rapid development of computing hardware and data processing algorithms, the intelligent PD fault diagnosis method based on the UHF data has made considerable progress in the past two decades. This two-part paper aims to give a comprehensive review about the application of signal processing and machine learning technologies in UHF PD detection and diagnosis. These technologies are divided into three categories according to their respective purpose, which are the preprocessing technology, source localization technology and pattern recognition technology. As the first one of the two-part review, we focus on the preprocessing and localization approaches in this paper. Specifically, for the preprocessing topic, the methods for signal denoising, multi-source separation, and pulse segmentation are included. While for the localization topic, the time difference of arrival (TDOA) method, direction of arrival (DOA) method, received signal strength indicator (RSSI) method, and other latest methods are reviewed. For each topic, the basic ideas, recent research progresses, advantages and limitations are discussed in detail. Before the conclusion, we also make a discussion about the application effects of the above technologies and prospect some future directions accordingly. In the second paper, the pattern recognition problems based on the UHF PD data will be concentrated, especially the application of deep learning algorithms.

Remote sensing image (RSI) scene classification is the foundation and important technology of ground object detection, land use management and geographic analysis. During recent years, convolutional neural networks (CNNs) have achieved significant success and are widely applied in RSI scene classification. However, crafted images that serve as adversarial examples can potentially fool CNNs with high confidence and are hard for human eyes to interpret. For the increasing security and robust requirements of RSI scene classification, the adversarial example problem poses a serious problem for the classification results derived from systems using CNN models, which has not been fully recognized by previous research. In this study, to explore the properties of adversarial examples of RSI scene classification, we create different scenarios by testing two major attack algorithms (i.e., the fast gradient sign method (FGSM) and basic iterative method (BIM)) trained on different RSI benchmark datasets to fool CNNs (i.e., InceptionV1, ResNet and a simple CNN). In the experiment, our results show that CNNs of RSI scene classification are also vulnerable to adversarial examples, and some of them have a fooling rate of over 80%. These adversarial examples are affected by the architecture of CNNs and the type of RSI dataset. InceptionV1 has a fooling rate of less than 5%, which is lower than the others. Adversarial examples generated on the UCM dataset are easier than other datasets. Importantly, we also find that the classes of adversarial examples have an attack selectivity property. Misclassifications of adversarial examples of RSIs are related to the similarity of the original classes in the CNN feature space. Attack selectivity reveals potential classes of adversarial examples and provides insights into the design of defensive algorithms in future research.

Extending the research on the impact of learning effect on inventory management is of particular importance, this paper studies two different inventory management models with considering stochastic...

Compressed bitmap indexes are increasingly used in databases and search engines. By exploiting bit-level parallelism and bitwise operations, e.g. AND/OR operations, they can significantly accelerate the development of many areas. The Word Aligned Hybrid (WAH) bitmap compression scheme using run-length encoding (RLE), is commonly recognized as the most efficient scheme in terms of CPU-performance. This paper presents a new form of compressed bitmap indexes named Adaptive Partitioned Position List Encoding (APPLE), which uses packed position lists for compression. For experiments, we compare it with Huffman encoding, and two enhanced variants of WAH : Concise and COMPAX. Our empirical results show this scheme achieves significant improvement.

The concept of "Industrial Internet" was first proposed by General Electric in 2012. It aims to promote the intellectualization of the whole service system. However, with the development of the Industrial Internet, some criminals launch attacks on industrial control terminals (such as computers and mobile devices), causing the failure of industrial control terminals or wrong instructions, which resulting in factory losses. Therefore, there is an immediate need to extract valuable information from mobile network streaming, accurately detect abnormal behaviors and timely raise the alarm. In this paper, we propose a method of anomaly detection for mobile devices in Industrial Internet based on knowledge graph and demonstrate the results by using visualization technology. First, we use the optimized data mining algorithm based on frequent item sets to analyse the data, so that our method can accurately detect different kinds of concurrent attacks. Second, this method is able to locate the IP addresses of the attacker and the victim accurately. Third, we design an anomaly alarm module, which can visualize the results in multiple dimensions and assist security administrators to understand complex network situation in real time and take corresponding measures according to the network anomaly.

With the booming of online mobile games (OMGs), game operators need to provide high-quality game service for users. Using relay has become the de factor approach for game streaming today, because it is easy to use (e.g., game sessions can be redirected via CDN servers) and has good scalability. Today, it has become the norm rather than the exception for game operators to hire CDN servers for their game services in a pay-per-use manner to serve massive users. Given the limited resource, selecting game sessions which are relayed has become a critical decision that can significantly affect users' quality of experience (QoE). Conventional strategies are generally rule-based, e.g., assigning game sessions to relay paths according to their past network performance, but cannot guarantee any particular QoE level because network performance dynamically changes. In this paper, we propose using data-driven approach to study network performance of game sessions in temporal and spatial patterns. Our findings indicate that there is obvious regularity for network performance of game sessions in temporal and spatial patterns. We design a machine learning-based predictive model to capture the quality of a game session given particular network performance metrics. Based on that, we strategically assign game sessions to relay paths to maximize the overall QoE. Trace-driven experiments are used to demonstrate the effectiveness and efficiency of our design.

As the only project for CO2 storage in deep saline aquifers in China, the Shenhua CCS demonstration project is of great importance in the geological storage of CO2 in continental sedimentary strata. Despite achieving the designed injection goal of 302,000 tons, the demonstration project currently does not have a widely accepted storage site geological model because of the large overall thickness of the injection layers, low porosity and permeability, and high heterogeneity. Based on geological study of the storage site system, combined with vertical seismic profiling (VSP) seismic monitoring data, we used the well log-constrained seismic inversion method to predict the lithology, porosity and permeability of the storage site. We constructed a new 5 km × 5 km × 1200 m site geological model centered on the injection well. Our new geological modeling method and the related reservoir parameters are innovative compared with previous studies and enhance geological understanding of the site, providing a reference for CO2 migration reservoir simulation and deep geophysical monitoring in the future stages of the project.

The ultra-high frequency (UHF) partial discharge (PD) monitoring is one of the most effective ways to detect the insulation failure in electrical equipment. Although the UHF method avoids the intensive low-frequency noise, various electromagnetic interferences in substation can still influence its effectiveness and reliability. Most existing denoising algorithms, however, are unable to suppress different kinds of noise simultaneously. Meanwhile, the main focus of these algorithms is on the degree of noise reduction, while pay little attention to feature preservation. Therefore, a novel denoising method namely optimised variation mode decomposition and wavelet (OVMDW) is developed in this paper. In OVMDW, an optimised variational mode decomposition (VMD) algorithm is presented firstly to decompose the original signal into several band-limited modes. Then, a determination rule is designed to identify the effective components from these modes. Finally, the wavelet-based denoising method is employed to remove the residual white noise. Denoising results for simulative and experimental data show that the proposed method can remove various interferences from UHF PD signals. Additionally, new indexes are introduced to evaluate the performance of denoising algorithms in practical situations. Comparison results based on these indexes reveal that the proposed method using the VMD approach can preserve quite well the features of original signals.

Ultra-high-frequency (UHF) partial discharge (PD) detection has been proved as a powerful tool to evaluate the status of electrical equipment. Unfortunately, on-site UHF detection suffers from intensive noise interference and great computational burden, which have long been the key bottleneck for its wide utilization in the field environments. In order to provide more valuable information for subsequent processing like PD location, pattern recognition, or severity assessment, a combined preprocessing method for UHF PD detection is proposed in this paper. This scheme integrates a novel Ensemble Empirical Mode Decomposition-based signal reconstruction method and a kurtosis-based pulse window extraction method. To demonstrate the effectiveness of the presented technique, both simulated and laboratory measured PD data are obtained and further tested. Results reveal that this preprocessing method can accurately detect and extract the PD pulse from raw data, which may lessen the computational burden for...

Partial discharge (PD) detection and recognition are of great significance to the condition monitoring of gas-insulated switchgear (GIS). In the current work, ultra-high-frequency (UHF) signals induced by PD current pulses are measured and used to represent PD source. For PD classification, feature parameters need to be extracted from UHF signals. Therefore, this study proposes a new feature extraction method that is based on S-transform (ST) and singular value decomposition (SVD). PD UHF signals generated by four kinds of artificial defects are collected and analysed. ST is used to acquire the joint time–frequency information of the PD UHF signal. SVD is used to acquire the time–frequency characteristics of the UHF signal. Based on the distribution difference of time–frequency characteristics of different kinds of PDs, a 24-demensional feature vector is finally extracted. Support vector machine optimised by particle swarm optimisation algorithm is employed as classifier to recognise the four kinds of PDs. Results show that the proposed feature extraction method can effectively identify the designed four kinds of PDs even with few samples and strong background noise.

As one of the most effective detection methods for partial discharge (PD), analysis of the radiated electromagnetic (EM) signals detected by ultra high frequency (UHF) sensor has gained broad attentions. However, the main bottlenecks for this method are probably the massive storage requirements and various noise interferences. Therefore, this paper is focused on investigating a new pulse segmentation technique, which is capable of separating PD pulses from noisy measured data to save the storage space and improve the signal noise ratio (SNR). First, a designed average multi-scale morphological dilate-erode filter (AMMDEF) is developed to obtain the smooth envelope shape of PD pulses. Then, instantaneous phase (IP) of the envelope shape is calculated by the Hilbert Transform (HT) and further smoothed using AMMDEF. Finally, a robust IP based boundary identification criterion (IPBIC) is proposed to accurately extract PD pulses from raw data. Various experiments have been carried out and results show that this method could achieve an average detection error rate (DER) at 0.1375 and an average absolute precision error (APE) at 23.1 ns respectively, even the SNR of signal is as low as 0 dB. Superiority of the developed method over traditional pulse segmentation techniques is also demonstrated.

Online mobile game (OMG) is booming recently, which has driven user expectations for high-quality game service. Therefore, it is crucial for game operators to understand if and how system factors (i.e. network quality metrics such as delay and mobile phone's rendering performance such as frame rate) affect gaming experience and how to optimize resource allocation to improve it. This paper is a first step towards addressing these problems. Despite the rich literature on multimedia services and Quality of Experience (QoE) measurement, the understanding of gaming experience is limited because the game platform shifts from traditional PC end to the mobile end, which has yet to be explored in depth. Based on a large-scale dataset collected from Honour of Kings, the world's top grossing mobile game, we carry out elaborate studies to explore gaming experience from the aspects of user behavior and game quality. Our key findings are as follows. First, user behavior is mainly limited to the game logic itself, such as I of a game is restricted by game rules. Therefore, it cannot well represent gaming experience. Second, among all system factors, the biggest impact on game quality comes from network performance rather than the frame rate of device, which is different from the influence mode in PC games. Third, some context factors, such as AP/BaseStations used by mobile phones, can have an indirect but huge impact on gaming experience. Based on the above observations, we provide insights that can enhance OMG's system from the perspective of resource allocation and real-time gaming experience monitoring. To the best of our knowledge, we are the first to conduct large-scale measurement to study gaming experience of OMGs in the wild. We believe our study is not only crucial for the understanding of gaming experience, but also helpful for game operators to optimize their systems.

Using content delivery networks (CDNs) for video distribution has become a de facto approach for today's video streaming, due to the easy usage and good scalability. Today, it has become a norm rather than an exception for video providers to hire multiple cloud CDNs for their video services in a pay-per-use manner, to not only serve users at different locations, but also reduce the operation costs. Given the multiple CDNs and their peering servers at many different locations, mapping a user to an edge CDN server has become a critical decision that can affect the quality of experience (QoE) of users. Conventional user mapping strategies are generally rule-based, e.g., assigning users to CDN servers according to only their locations or ISPs, which cannot guarantee any QoE. In this paper, we first propose to use a data-driven approach to study factors determining the streaming QoE in the multi-cloud CDN paradigm. Our findings suggest that the streaming QoE is affected by a combination of not only network factors but also user factors including their preference of video content. Then, we design a machine learning based predictive model to capture the QoE given the network conditions and user preference. Finally, we formulate the user mapping problem as an optimization problem and design algorithms to solve it: our algorithms identify users whose QoE are mostly affected by QoS and assign users to CDN servers so that the overall QoE can be maximized. Trace-driven experiments further verify the effectiveness of our design.