scholarly journals A Method for Segmentation of Transformer Oil Level Region Based on Infrared Image

2021 ◽  
Vol 898 (1) ◽  
pp. 012027
Author(s):  
Ying Chen ◽  
Songhai Fan ◽  
Yicen Liu ◽  
Xiaomin Ma ◽  
Zhu Shi
Keyword(s):  
Maximum Entropy ◽  
Rapid Development ◽  
Infrared Image ◽  
Electrical Equipment ◽  
Segmentation Algorithm ◽  
Transformer Oil ◽  
Target Area ◽  
State Monitoring ◽  
Threshold Segmentation ◽  
Artificial Intelligence Technology

Abstract With the rapid development of computer and artificial intelligence technology, infrared images are playing a higher and higher value in the state monitoring of electrical equipment in substations. Aiming at the detection of the oil level area of the oil conservator in the substation, in order to accurately obtain the oil level information, this paper proposes a transformer oil level detection method combining maximum entropy threshold segmentation algorithm and SLIC (simple linear iterativeclustering) segmentation algorithm. First, the original infrared image is pre-processed by image cutting technology to obtain the infrared image of the oil pillow area; the green channel image is extracted, and then the infrared image is segmented by the maximum entropy threshold segmentation algorithm to remove the background interference and obtain the target area of the electrical equipment. Finally, SLIC is used to super the pixel segmentation algorithm performs segmentation to obtain the oil level area. Experiments show that the algorithm can clearly segment the oil level area of the oil pillow, and it has certain practical value.

scholarly journals Infrared image-based detection method of electrical equipment overheating area in substation

2020 ◽  
Vol 185 ◽  
pp. 01034
Author(s):  
Songhai Fan ◽  
Tianyu Li ◽  
Yicen Liu ◽  
Yiyu Gong ◽  
Kunjian Yu
Keyword(s):  
Active Contour ◽  
Clustering Algorithm ◽  
Active Contour Model ◽  
Infrared Image ◽  
Electrical Equipment ◽  
Detection Algorithm ◽  
Target Area ◽  
Detection Range ◽  
Edge Points ◽  
Fcm Clustering

For the detection of overheated areas of electrical equipment, in order to accurately segment out the overheated areas and reduce the fault detection range, this paper proposes a new overheated area detection algorithm. Firstly, the Ostu algorithm is used to remove the background and segment the general area of the electrical equipment area; secondly, the active contour model is used to refine the edge of the target area to remove the redundant edge points; finally, FCM clustering algorithm is used to suppress over segmentation and accurately divide the overheated area. The experiment proves that the algorithm can accurately divide the overheated area, and has certain practical value.

scholarly journals Thermal Fault Detection and Diagnosis of Electrical Equipment Based on the Infrared Image Segmentation Algorithm

2021 ◽  
Vol 2021 ◽  
pp. 1-7
Author(s):  
Hongzhao Li
Keyword(s):  
Image Segmentation ◽  
Fault Detection ◽  
Infrared Imaging ◽  
Infrared Image ◽  
Electrical Equipment ◽  
Fault Detection And Diagnosis ◽  
Segmentation Algorithm ◽  
Imaging Technology ◽  
Infrared Image Segmentation ◽  
Image Segmentation Algorithm

With the advancement of social economy, electricity has gradually entered thousands of households and become a commonly used energy source. However, it cannot be ignored that electricity is dangerous in itself and should be used rationally and effectively. The fault detection of power equipment has become a top priority because they are essential tools for storing, transmitting, and transferring electric power. Based on infrared imaging technology, the principle of infrared imaging technology is introduced in this paper, and effective diagnosis methods are analyzed and summarized in detail. The effectiveness of the proposed infrared image segmentation algorithm is verified through the practical application of the infrared image segmentation algorithm in the detection of interior and exterior faults of electrical equipment.

scholarly journals Predicting the influence of the non-sinusoidal network mode on power transformers

2019 ◽  
Vol 114 ◽  
pp. 04005
Author(s):  
Ngo Van Cuong ◽  
Lidiia I. Kovernikova
Keyword(s):  
Service Life ◽  
Electric Power ◽  
Power Quality ◽  
Electrical Equipment ◽  
Operating Conditions ◽  
Transformer Oil ◽  
Power Transformers ◽  
Electrical Network ◽  
Electrical Networks ◽  
Current Harmonics

The parameters of electrical network modes often do not meet the requirements of Russian GOST 32144-2013 and the guidelines of Vietnam. In the actual operating conditions while there is the non-sinusoidal mode in electrical networks voltage and current harmonics are present. Harmonics result in overheating and damage of power transformers since they cause additional active power losses. Additional losses lead to the additional heat release, accelerating the process of insulating paper, transformer oil and magnetic structure deterioration consequently shortening the service life of a power transformer. In this regard there arises a need to develop certain scientific methods that would help demonstrate that low power quality, for instance could lead to a decrease in the electrical equipment service life. Currently we see a development of automated systems for continuous monitoring of power quality indices and mode parameters of electrical networks. These systems could be supplemented by characteristics calculating programs that give out a warning upon detection of the adverse influence of voltage and current harmonics on various electrical equipment of both electric power providers and electric power consumers. A software program presented in the article may be used to predict the influence of voltage and current harmonics on power transformers.

An Image Segmentation Method Based on Two-Dimensional Entropy and Chaotic Lightning Attachment Procedure Optimization Algorithm

2020 ◽  
Vol 34 (11) ◽  
pp. 2054030 ◽  
Author(s):  
Wei Liu ◽  
Shuai Yang ◽  
Zhiwei Ye ◽  
Qian Huang ◽  
Yongkun Huang
Keyword(s):  
Image Segmentation ◽  
Maximum Entropy ◽  
Optimization Algorithm ◽  
Search Algorithm ◽  
Computational Time ◽  
Two Dimensional ◽  
Threshold Segmentation ◽  
Grasshopper Optimization Algorithm ◽  
Grasshopper Optimization ◽  
Competitive Algorithms

Threshold segmentation has been widely used in recent years due to its simplicity and efficiency. The method of segmenting images by the two-dimensional maximum entropy is a species of the useful technique of threshold segmentation. However, the efficiency and stability of this technique are still not ideal and the traditional search algorithm cannot meet the needs of engineering problems. To mitigate the above problem, swarm intelligent optimization algorithms have been employed in this field for searching the optimal threshold vector. An effective technique of lightning attachment procedure optimization (LAPO) algorithm based on a two-dimensional maximum entropy criterion is offered in this paper, and besides, a chaotic strategy is embedded into LAPO to develop a new algorithm named CLAPO. In order to confirm the benefits of the method proposed in this paper, the other seven kinds of competitive algorithms, such as Ant–lion Optimizer (ALO) and Grasshopper Optimization Algorithm (GOA), are compared. Experiments are conducted on four different kinds of images and the simulation results are presented in several indexes (such as computational time, maximum fitness, average fitness, variance of fitness and other indexes) at different threshold levels for each test image. By scrutinizing the results of the experiment, the superiority of the introduced method is demonstrated, which can meet the needs of image segmentation excellently.

Research on the Forward Kinematics of Stewart Platform Using Memetic Algorithms

2012 ◽  
Vol 268-270 ◽  
pp. 1416-1421
Author(s):  
Yu Hui Zhang ◽  
Li Wen Guan ◽  
Li Ping Wang ◽  
Yong Zhi Hua
Keyword(s):  
Nonlinear Equations ◽  
Rapid Development ◽  
Memetic Algorithms ◽  
Stewart Platform ◽  
Global Optimum ◽  
General Purpose ◽  
Forward Kinematics ◽  
Systems Of Nonlinear Equations ◽  
Artificial Intelligence Technology ◽  
Difficult Issue

The forward kinematics analysis of parallel manipulator is a difficult issue, which has been studied by many researchers recently. In this paper, in order to solve the difficult issue, a new computing method with higher calculation accuracy, good operation steadiness and faster speed is mentioned. Firstly, the mathematical model of direct kinematics of the Stewart platform is founded, which is nonlinear equations. Secondly, with the rapid development of artificial intelligence technology, Memetic algorithms (MA) are applied to solve the systems of nonlinear equations more and more, replacing the traditional algorithms. MA is a kind of meta-heuristic algorithm combined genetic algorithms (GA) with local search at the end of iteration. Finally, the validity of this algorithm has been testified by simulating iteration operation. The numerical simulation shows that MA can surely and rapidly get global optimum solution and greatly improve convergence rate. Thereby, MA can be widely used as a general-purpose algorithm for solving the forward kinematics of parallel mechanism.

The Detection Method of Lane Line Based on the Improved Otsu Threshold Segmentation

2015 ◽  
Vol 741 ◽  
pp. 354-358 ◽  
Author(s):  
Yang Shan Tang ◽  
Dao Hua Xia ◽  
Gui Yang Zhang ◽  
Li Na Ge ◽  
Xin Yang Yan
Keyword(s):  
Image Segmentation ◽  
Processing Time ◽  
Detection Method ◽  
Segmentation Algorithm ◽  
Test Results ◽  
Threshold Segmentation ◽  
Otsu Method ◽  
Time Requirements ◽  
Lane Line ◽  
Center Distance

For overcoming the shortage of Otsu method, proposed an improved Otsu threshold segmentation algorithm. On the basis of Otsu threshold segmentation algorithm, the gray level was divided into two classes according to the image segmentation, to determine the best threshold by comparing their center distance, so as to achieve peak line recognition under the condition of multiple gray levels. Then did experiments on image segmentation of the lane line with MATLAB by traditional Otsu threshold segmentation algorithm and the improved algorithm, the threshold of traditional Otsu threshold segmentation algorithm is 144 and the threshold of the improved Otsu threshold segmentation algorithm is 131, the processing time is within 0.453 s. Test results show that the white part markings appear more, the intersection place of white lines and the background is more clear, so this method can identify lane markings well and meet the real-time requirements.

Sign in / Sign up

Export Citation Format

Share Document