Intelligent detection method for substation insulator defects based on CenterMask

نویسندگان

چکیده

With the development of intelligent operation and maintenance substations, daily inspection substations needs to process massive video image data. This puts forward higher requirements on processing speed accuracy defect detection. Based end-to-end learning paradigm, this article proposes an detection method for substation insulator defects based CenterMask. First, backbone network VoVNet is improved according residual connection eSE module, which effectively solves problems deep saturation gradient information loss. On basis, mask generation a spatial attention-directed mechanism proposed. Insulators with complex backgrounds are accurately segmented. Then, three strategies pixel-wise regression prediction, multi-scale features, centerness introduced. The anchor-free single-stage target detector locates points insulators. Finally, example analysis carried out power supply company in certain area verify effectiveness robustness proposed method.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Automatic Detection Method for Casting Defects Based on Gradient Features

In this paper, we propose an automated visual inspection method for casting defects. Automatic inspection systems have the potential to significantly improve quality and increase production rates. In our method, the contour discontinuity of casting product and machine-learning-based defect detection are utilized to detect defects on the surface of products. The peripheral vision and involuntary...

متن کامل

An Intelligent Method for Edge Detection based on Nonlinear Diffusion

Edge detection is an important task in the field of image processing with broad applications in image and vision analysis. In this paper, we present a new intelligent computational mechanism using nonlinear diffusion equations for edge detection. Experimental results show that the proposed method outperforms standard edge detectors as well as other methods that deploy inhibition of texture.

متن کامل

Assessment of Intelligent Substation Based on an Improved Fuzzy Sets Method

In the construction process of smart grid, an assessment on primary equipments intelligent transformation is an urgent content in the first batch of intelligent substation pilot project. Wide investigation of intelligent substation pilot projects was conducted seriously in several regional power grids in China. An mathematical model was established to assess the substation primary equipments in...

متن کامل

application of upfc based on svpwm for power quality improvement

در سالهای اخیر،اختلالات کیفیت توان مهمترین موضوع می باشد که محققان زیادی را برای پیدا کردن راه حلی برای حل آن علاقه مند ساخته است.امروزه کیفیت توان در سیستم قدرت برای مراکز صنعتی،تجاری وکاربردهای بیمارستانی مسئله مهمی می باشد.مشکل ولتاژمثل شرایط افت ولتاژواضافه جریان ناشی از اتصال کوتاه مدار یا وقوع خطا در سیستم بیشتر مورد توجه می باشد. برای مطالعه افت ولتاژ واضافه جریان،محققان زیادی کار کرده ...

15 صفحه اول

Glass Product Defects Detection Method Based on Machine Vision

This paper develops the machine vision based detection method to detect glass products defects. The novel segmentation method based on unsupervised learning is proposed to segment the defect regions and background. The fuzzy support vector machine was adopted as classifiers for the extracted features. The experimental results indicated the accuracy rate can reach up to 96.7 % by using the metho...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Frontiers in Energy Research

سال: 2022

ISSN: ['2296-598X']

DOI: https://doi.org/10.3389/fenrg.2022.985600