A two-stage hotspot detection method for aerial infrared images is proposed to address the issues of high cost, low efficiency, and low accuracy in traditional photovoltaic power plant detection technology. This method achieves component level localization and fine classification diagnosis of hotspot defects in infrared images. The method proposed in this paper is to integrate deep learning algorithms and traditional image algorithms to better identify defects. Firstly, this paper uses the edge detection algorithm to segment the target contour for the image itself at different scene gray values; Secondly, considering the differentiation of related factors, this paper carefully classifies the correlation factors based on the EfficientNet network. In order to ensure the rapid detection of the model. Experimental results show that the accuracy of the proposed model reaches 97.1%, and the speed is also faster. This shows the superiority of the algorithm model proposed in this paper.
In order to improve the environmental monitoring and operation management level of the power distribution room, this paper launches the construction of an integrated sensing and control system for intelligent power distribution room based on multi-sensors. In this paper, a scheme of integrated sensing and control system for intelligent power distribution room is proposed, and a multi-sensor structure is designed. Each sensor module converts the information related to gas, temperature and humidity into electrical signals or digital signals, and then the microprocessor processes and stores the data at the same time. When the detected parameters have exceeded the threshold set by the system, the upper computer displays the abnormal operation of the power distribution room. Aiming at three data fusion structures of multi-sensor parallel distributed detection fusion system, a soft threshold decision wavelet domain filtering algorithm is adopted, and this algorithm is effectively introduced into the multi-sensor parallel distributed detection data fusion structure. The results show that in the process of temperature and humidity measurement, the maximum relative error between the temperature measured value and the reference value is 2.6%, and the maximum relative error between the humidity measured value and the reference value is 0.3%, both of which are much larger than the relative error of the gas module measurement, but all meet the requirements. It is proved that the sensor meets the field application requirements of sensor equipment.
Various defects of power equipment affect the normal operation of power grid, and serious defects even bring great losses to production and life. Infrared image recognition of power equipment is a necessary prerequisite to realize condition monitoring and fault diagnosis of power equipment under infrared imaging. Because of the imaging characteristics of infrared images, the complexity of background environment and the diversity and difference of power equipment itself, it is difficult to identify infrared images of power equipment. The purpose of this article is to propose a fast and accurate condition monitoring method for power equipment. Based on this, this study proposes an infrared image recognition algorithm of power equipment based on improved Convolutional Neural Network (CNN), which provides technical support for the construction of power equipment condition monitoring system. The simulation results show that the objective function of the improved model can achieve stable payment with fewer iterations, and it is superior to the traditional Support Vector Machine (SVM) algorithm and Ant Colony Optimization (ACO) algorithm in terms of accuracy, recall and running time, thus verifying the effectiveness of the algorithm and the interference to different backgrounds.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.