scholarly journals Application of Deep Learning and Symmetrized Dot Pattern to Detect Surge Arrester Status

2022 ◽  
Vol 12 (2) ◽  
pp. 650
Author(s):  
Meng-Hui Wang ◽  
Shiue-Der Lu ◽  
Chun-Chun Hung

Surge arresters primarily restrain lightning and switch surges in the power system to avoid damaging power equipment. When a surge arrester fails, it leads to huge damage to the power equipment. Therefore, this study proposed the application of a convolutional neural network (CNN) combined with a symmetrized dot pattern (SDP) to detect the state of the surge arrester. First, four typical fault types were constructed for the 18 kV surge arrester, including its normal state, aging of the internal valve, internal humidity, and salt damage to the insulation. Then, the partial discharge signal was measured and extracted using a high-speed data acquisition (DAQ) card, while a snowflake map was established by SDP for the features of each fault type. Finally, CNN was used to detect the status of the surge arrester. This study also used a histogram of oriented gradient (HOG) with support vendor machine (SVM), backpropagation neural network (BPNN), and k-nearest neighbors (KNN) for image feature extraction and identification. The result shows that the proposed method had the highest accuracy at 97.9%, followed by 95% for HOG + SVM, 94.6% for HOG + BPNN, and 91.2% for HOG + KNN. Therefore, the proposed method can effectively detect the fault status of surge arresters.

2013 ◽  
Vol 367 ◽  
pp. 541-543
Author(s):  
Yun Peng Li

This article focuses on research and implementation of a kind of solid storage system that is based on NAND flash which can store the data with high speed and huge capacity. A design with quad 1.25Gsps ADC and flash storage array with 1TB is demonstrated in the paper. The design is applied widely in many fields such as radar, communication and speech recognition. The detail of hardware development is also introduced in the thesis. In addition, a method is discussed to approve the reading and writing bandwidth by parallel operations on multiple pieces of flash. By using the method, the data bandwidth is arrived 6GB/S.


2012 ◽  
Vol 229-231 ◽  
pp. 1543-1546
Author(s):  
Xiao Bo Zhou ◽  
Min Xia ◽  
Hai Long Cheng

To improve data transmission performance of the data acquisition card, a design of high-speed data transmission system is proposed in the thesis. Using FPGA of programmable logic devices, adopting Verilog HDL of hardware description language, the design of modularization and DMA transmission method is implemented in FPGA. Eventually the design implements the data transmission with high-speed through PCI Express interface. Through simulation and verification based on hardware system, this design is proved to be feasible and can satisfy the performance requirements of data transmission in the high-speed data acquisition card applied in high-speed railway communication. The design also has some value of application and reference for a universal data acquisition card.


2014 ◽  
Vol 7 (6) ◽  
pp. 1693-1700 ◽  
Author(s):  
V. Fung ◽  
J. L. Bosch ◽  
S. W. Roberts ◽  
J. Kleissl

Abstract. Changing cloud cover is a major source of solar radiation variability and poses challenges for the integration of solar energy. A compact and economical system is presented that measures cloud shadow motion vectors to estimate power plant ramp rates and provide short-term solar irradiance forecasts. The cloud shadow speed sensor (CSS) is constructed using an array of luminance sensors and a high-speed data acquisition system to resolve the progression of cloud passages across the sensor footprint. An embedded microcontroller acquires the sensor data and uses a cross-correlation algorithm to determine cloud shadow motion vectors. The CSS was validated against an artificial shading test apparatus, an alternative method of cloud motion detection from ground-measured irradiance (linear cloud edge, LCE), and a UC San Diego sky imager (USI). The CSS detected artificial shadow directions and speeds to within 15° and 6% accuracy, respectively. The CSS detected (real) cloud shadow directions and speeds with average weighted root-mean-square difference of 22° and 1.9 m s−1 when compared to USI and 33° and 1.5 m s−1 when compared to LCE results.


2012 ◽  
Vol 468-471 ◽  
pp. 920-923
Author(s):  
Ya Ping Bao ◽  
Li Liu ◽  
Yuan Wang ◽  
Qian Song

This paper introduced a fast fingerprint identification system based on TMS320VC5416 DSP chip and MBF200 solidity fingerprint sensor. It precipitates fingerprint identification device developing into the direction of miniaturization, embedded and automatic.It recommends fingerprint identification system hardware and software design and the main system processing flow, aim at fingerprint identification arithmetic, the influence of system operation speed is being researched at the same time. High-speed data acquisition system is been built in order to achieve a DSP fingerprint identification system with high efficiency and low cost.


Sign in / Sign up

Export Citation Format

Share Document