Image Enhancement Based Detection Method of Non-soluble Deposit Density Levels of Porcelain Insulators

被引：0
|
作者：
Huang X. [1 ]
Yang L. [1 ]
Zhang Y. [1 ]
Cao W. [1 ]
Li L. [2 ]
机构：
[1] School of Electronics and Information, Xi'an Polytechnic University, Xi'an
[2] School of Electric Power, South China University of Technology, Guangzhou
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2018年 / 42卷 / 14期
基金：
中国国家自然科学基金;
关键词：
Back propagation (BP) neural network; Feature extraction; Fisher criterion; Insulator; Multiple scale Retinex with color restoration (MSRCR) algorithm; Non-soluble deposit density (NSDD) level detection;
D O I：
10.7500/AEPS20170614017
中图分类号：
学科分类号：
摘要：
It is difficult to gather the high-definition and readable images of insulators in bad conditions such as foggy day and dim light. The available contamination detection methods of visible images does not have generality due to the difficulty of extracting insulator objects and color features of surface region. Therefore, this paper proposes a image enhancement based detection method of non-soluble deposit density (NSDD) levels of porcelain insulators. Firstly, the improved multiple scale Retinex with color restoration (MSRCR) algorithm is used to enhance the clarity and contrast of the collected insulator images. Secondly, the two-dimensional minimum error algorithm and the morphological filter algorithm are combined to segment and extract the surface region of insulators. And seven characteristic values in six channels are extracted, such as mean value, maximum value, minimum value. Then the Smean, Smax and Svar with highly classification ability are selected as the identify features of NSDD levels by using the Fisher criterion function. Finally, the back propagation (BP) neural network optimized by the mind evolutionary algorithm (MEA) is used for simulation and forecast. The experiment results show that the recognition accuracy rates of the probabilistic neural network algorithm and the BP neural network optimized by particle swarm optimization (PSO) algorithm are 88.00% and 93.00%, respectively. In comparison, the accuracy rate of the proposed method is 95.00%, which shows that it can accurately identify the NSDD levels of insulators in bad conditions. © 2018 Automation of Electric Power Systems Press.
引用
收藏
页码：151 / 157
页数：6
相关论文
共 32 条
  • [21] Miao H., Liang G., Liu R., Et al., Segmentation method of color white blood cell image based on HSI modified space information fusion, Journal of Biomedical Engineering, 33, 2, pp. 303-307, (2016)
  • [22] Wang J., Pang W., Application of Fisher discriminant analysis in steady-state power quality evaluation of grid-connected photovoltaic system, Electric Power Automation Equipment, 37, 3, pp. 50-54, (2017)
  • [23] Zhang H., Sun Y., Liu Y., Et al., Distribution regularity of TCM syndromes in patients with polycystic ovary syndrome based on Fisher discriminant analysis, Beijing Biomedical Engineering, 36, 1, pp. 82-86, (2017)
  • [24] Qian Z., Ren G., Chu F., Et al., Rock mass quality classification based on PCA and Fisher discrimination analysis, Rock and Soil Mechanics, 37, 2, pp. 427-432, (2016)
  • [25] Wu Z., Zhao Y., Luo Z., Et al., License plate recognition technology based on PSO-BP neural network, Acta Scientiarum Naturalium Universitatis Sunyatseni, 56, 1, pp. 46-52, (2017)
  • [26] Yu F., Kang H., Zhang H., Fault diagnosis for hydraulic drilling rig based on BP neural network optimized by PSO, Process Automation Instrumentation, 4, pp. 42-46, (2016)
  • [27] Yang L., Zhu Y., High voltage circuit breaker fault diagnosis of probabilistic neural network, Power System Protection and Control, 43, 10, pp. 62-67, (2015)
  • [28] Zhang D., Huang D., Zhang C., Application of BP neural network based on genetic algorithm in the inversion of density interface, Journal of Jilin University (Earth Science Edition), 47, 2, pp. 580-588, (2017)
  • [29] Gao J.L., Modeling of photovoltaic cell based on BP neural networks improved by MEA, Applied Mechanics and Materials, 217-219, pp. 809-814, (2012)
  • [30] Zhang Y., Lai H., Li Y., Et al., Short-term gas load forecasting based on MEA optimized BP neural network, Automation & Instrumentation, 5, pp. 15-19, (2016)
1234