基于多尺度網(wǎng)絡(luò)的絕緣子自曝狀態(tài)智能認(rèn)知方法研究
2021年電子技術(shù)應(yīng)用第8期
萬(wàn) 濤1,吳立剛1,陸 燁2,,王 浩2,,張 瀟2,范葉平1,楊德勝1
1.國(guó)網(wǎng)信息通信產(chǎn)業(yè)集團(tuán)安徽繼遠(yuǎn)軟件有限公司,安徽 合肥230088; 2.國(guó)網(wǎng)江蘇省電力公司徐州供電分公司,,江蘇 徐州221005
摘要: 針對(duì)已有絕緣子狀態(tài)識(shí)別模型,以及深層網(wǎng)絡(luò)尺度和交叉熵?fù)p失函數(shù)的缺陷,,仿照運(yùn)維人員檢修模式,,即依據(jù)評(píng)測(cè)結(jié)果的可信度動(dòng)態(tài)決策,基于多尺度網(wǎng)絡(luò)構(gòu)建了一種絕緣子自曝狀態(tài)智能認(rèn)知方法,。首先,,面向定位歸一化化預(yù)處理后的絕緣子圖像,基于ResNet-18增加不同結(jié)構(gòu)的網(wǎng)絡(luò)分支提高網(wǎng)絡(luò)適應(yīng)不同分辨率的能力,,同時(shí)在網(wǎng)絡(luò)末端添加多尺度信息融合模塊,;其次,隨機(jī)配置網(wǎng)絡(luò)面向多個(gè)尺度特征,,構(gòu)建了泛化的自曝狀態(tài)分類認(rèn)知準(zhǔn)則,;最后,為了評(píng)測(cè)自曝狀態(tài)分類認(rèn)知結(jié)果的可信度,,基于定義的誤差指標(biāo)自調(diào)節(jié)多尺度網(wǎng)絡(luò)架構(gòu),,重構(gòu)不確定認(rèn)知結(jié)果約束下的特征向量和分類認(rèn)知準(zhǔn)則,以進(jìn)行自曝狀態(tài)再認(rèn)知,。實(shí)驗(yàn)結(jié)果顯示,,與其他方法相比,所提出的智能認(rèn)知方法增強(qiáng)了模型的泛化能力和認(rèn)知精度,。
中圖分類號(hào): TP391
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.200223
中文引用格式: 萬(wàn)濤,,吳立剛,陸燁,,等. 基于多尺度網(wǎng)絡(luò)的絕緣子自曝狀態(tài)智能認(rèn)知方法研究[J].電子技術(shù)應(yīng)用,,2021,47(8):91-96.
英文引用格式: Wan Tao,,Wu Ligang,,Lu Ye,et al. Research on intelligent cognition method of insulator self-blast state based on multi-scale network[J]. Application of Electronic Technique,,2021,,47(8):91-96.
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.200223
中文引用格式: 萬(wàn)濤,,吳立剛,陸燁,,等. 基于多尺度網(wǎng)絡(luò)的絕緣子自曝狀態(tài)智能認(rèn)知方法研究[J].電子技術(shù)應(yīng)用,,2021,47(8):91-96.
英文引用格式: Wan Tao,,Wu Ligang,,Lu Ye,et al. Research on intelligent cognition method of insulator self-blast state based on multi-scale network[J]. Application of Electronic Technique,,2021,,47(8):91-96.
Research on intelligent cognition method of insulator self-blast state based on multi-scale network
Wan Tao1,Wu Ligang1,,Lu Ye2,,Wang Hao2,Zhang Xiao2,,F(xiàn)an Yeping1,,Yang Desheng1
1.Anhui Jiyuan Software Co.,Ltd.,State Grid Communication Industry Group Co.,,Ltd.,,Hefei 230088,China,; 2.State Grid Xuzhou Electric Power Supply Company,,Xuzhou 221005,China
Abstract: In view of the drawbacks of the existing insulator state recognition models, and the scale and softmax loss function of deep network, imitating the mode of personnel operation and maintenance, that is, dynamic decision-making based on the credibility of the evaluation results, this paper constructs an intelligent cognition method of insulator self-blast states based on the multi-scale network. Firstly, for the pre-processed insulator images with localization and normalization, based on ResNet-18, branches with different network structure are added to improve the network ability to adapt to different resolutions. At the same time, the multi-scale information fusion module is added at the end of the network. Secondly, facing multiple scale features, stochastic configuration network(SCN) constructs a generalized cognition criterion of self-blast state classification. Finally, in order to evaluate the credibility of the self-blast state cognition result, based on the defined error index, the multi-scale network architecture is self-adjusted to reconstruct the feature vector and classification cognition criterion under the constraint of the uncertain cognition result, which carries out the self-blast state renewal cognition.The experimental results show that the proposed intelligent cognition method enhances the generalization ability and cognition accuracy compared with other methods.
Key words : insulator state,;ResNet,;feedback cognition;multi-resolution,;multi-scale
0 引言
絕緣子作為輸電電路中的重要器件,,被安裝在非等電位或?qū)w與接地器件之間,其自爆與否會(huì)嚴(yán)重影響輸電線路的安全[1-3]?,F(xiàn)代輸電線路運(yùn)維檢修機(jī)制通?;谥鄙龣C(jī)或無(wú)人機(jī)按照預(yù)定軌跡拍攝的視頻,由人對(duì)每幀圖像進(jìn)行自爆絕緣子位置辨識(shí),。然而,,人的主觀因素,以及運(yùn)維成本和復(fù)雜環(huán)境的客觀因素,,使得現(xiàn)代輸電線路運(yùn)維檢修模式費(fèi)時(shí)耗力,。因此,亟待研究絕緣子自曝狀態(tài)的智能認(rèn)知方法,。
本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000003708,。
作者信息:
萬(wàn) 濤1,吳立剛1,,陸 燁2,,王 浩2,張 瀟2,,范葉平1,,楊德勝1
(1.國(guó)網(wǎng)信息通信產(chǎn)業(yè)集團(tuán)安徽繼遠(yuǎn)軟件有限公司,,安徽 合肥230088;
2.國(guó)網(wǎng)江蘇省電力公司徐州供電分公司,,江蘇 徐州221005)
此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。