《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 可编程逻辑 > 设计应用 > 一种电缆终端头红外识别算法的FPGA实现研究
一种电缆终端头红外识别算法的FPGA实现研究
电子技术应用
吴卫堃1,郑耀华1,曾彦超1,曾祥伟1,巫志安1,李嘉成1,周骞2,袁超2
1.广东电网有限责任公司肇庆供电局;2.湖南大学 电气与信息工程学院
摘要: 针对在电站巡检中电缆终端头识别准确率低、实时性差等问题,设计一种基于粒子群算法(Particle Swarm Optimization,PSO)优化反向传播(Back Propagation,BP)神经网络的现场可编程门阵列(Field Programmable Gate Array,FPGA)红外识别系统。红外识别算法实现包括使用改进区域生长算法对红外图像进行分割,随后计算Hu不变矩作为神经网络输入特征。对于PSO-BP神经网络,选择7-10-1的网络结构,训练后均方误差为0.085,优于BP神经网络的0.136。在FPGA上实现时,采用定点数据量化、流水线结构及并行计算方法,同时对Sigmoid激活函数应用二次方程多段拟合。最终经过仿真验证,该系统识别率达到了92%并且算法速度提高了约6倍。
中圖分類(lèi)號(hào):TN79 文獻(xiàn)標(biāo)志碼:A DOI: 10.16157/j.issn.0258-7998.246172
中文引用格式: 吳衛(wèi)堃,鄭耀華,曾彥超,等. 一種電纜終端頭紅外識(shí)別算法的FPGA實(shí)現(xiàn)研究[J]. 電子技術(shù)應(yīng)用,2025,51(7):95-100.
英文引用格式: Wu Weikun,Zheng Yaohua,Zeng Yanchao,et al. Research on FPGA implementation of an infrared identification algorithm for cable terminals[J]. Application of Electronic Technique,2025,51(7):95-100.
Research on FPGA implementation of an infrared identification algorithm for cable terminals
Wu Weikun1,Zheng Yaohua1,Zeng Yanchao1,Zeng Xiangwei1,Wu Zhian1,Li Jiacheng1,Zhou Qian2,Yuan Chao2
1.Zhaoqing Power Supply Bureau, Guangdong Power Grid Co., Ltd.;2.School of Electrical and Information Engineering, Hunan University
Abstract: To address the issues of low identification accuracy and poor real-time performance of cable terminal heads during power station inspections, a field programmable gate array (FPGA) infrared recognition system based on particle swarm optimization (PSO) to optimize back propagation (BP) neural networks has been designed. The infrared recognition algorithm includes the use of an improved region growing algorithm for segmenting infrared images, followed by the calculation of Hu invariant moments as input features for the neural network. For the PSO-BP neural network, a 7-10-1 network structure was chosen, achieving a mean squared error of 0.085 after training, which is better than the 0.136 of the BP neural network. When implemented on the FPGA, fixed-point data quantization, pipelined architecture, and parallel computing methods were employed, along with a piecewise quadratic fitting for the Sigmoid activation function. Ultimately, through simulation verification, the system achieved a recognition rate of 92% and improved the algorithm's speed by approximately six times.
Key words : FPGA;infrared image recognition algorithm;region growing method;Hu invariant moments;PSO-BP neural network

引言

電纜終端頭是電力系統(tǒng)的重要組成部分,其運(yùn)行狀態(tài)影響電網(wǎng)安全。紅外成像技術(shù)因其非接觸性和穿透力強(qiáng)[1],在電纜終端頭識(shí)別中得到廣泛應(yīng)用。然而,復(fù)雜背景使傳統(tǒng)紅外識(shí)別算法容易出現(xiàn)識(shí)別錯(cuò)誤、實(shí)時(shí)性差等問(wèn)題[2],從而導(dǎo)致其狀態(tài)診斷結(jié)果無(wú)法及時(shí)匹配對(duì)應(yīng)的設(shè)備類(lèi)型,影響運(yùn)行狀態(tài)系統(tǒng)的正常運(yùn)行。

近年來(lái),神經(jīng)網(wǎng)絡(luò)在圖像識(shí)別中廣泛應(yīng)用[3],能夠在復(fù)雜環(huán)境中準(zhǔn)確識(shí)別目標(biāo)物體。將紅外圖像處理算法與神經(jīng)網(wǎng)絡(luò)結(jié)合是更優(yōu)解。目前,電力巡檢中常用的神經(jīng)網(wǎng)絡(luò)包括BP神經(jīng)網(wǎng)絡(luò)、卷積神經(jīng)網(wǎng)絡(luò)和生成對(duì)抗網(wǎng)絡(luò)。然而,這些算法通常依賴(lài)計(jì)算機(jī)平臺(tái),難以滿(mǎn)足電力巡檢對(duì)便攜性和實(shí)時(shí)性的要求,因此需要移植到嵌入式平臺(tái)??紤]到嵌入式硬件資源,BP神經(jīng)網(wǎng)絡(luò)因其簡(jiǎn)潔結(jié)構(gòu)和較低計(jì)算需求,更適合硬件部署,但其容易陷入局部最優(yōu),而PSO算法可以?xún)?yōu)化BP神經(jīng)網(wǎng)絡(luò)的初始權(quán)重和偏置,顯著提升識(shí)別效果[4]。

在硬件設(shè)備的選擇上相比于DSP+ARM架構(gòu),FPGA憑借其并行處理能力和高速計(jì)算優(yōu)勢(shì)[5],更適合進(jìn)行電站中的數(shù)據(jù)處理[6],近年來(lái)已廣泛應(yīng)用于高速圖像處理領(lǐng)域。

本文基于以上分析提出一種基于PSO-BP神經(jīng)網(wǎng)絡(luò)優(yōu)化紅外識(shí)別算法的FPGA系統(tǒng),通過(guò)FPGA并行計(jì)算和流水線(xiàn)結(jié)構(gòu)優(yōu)化,實(shí)現(xiàn)電纜終端頭紅外圖像的實(shí)時(shí)、準(zhǔn)確識(shí)別。


本文詳細(xì)內(nèi)容請(qǐng)下載:

http://ihrv.cn/resource/share/2000006602


作者信息:

吳衛(wèi)堃1,鄭耀華1,曾彥超1,曾祥偉1,巫志安1,李嘉成1,周騫2,袁超2

(1.廣東電網(wǎng)有限責(zé)任公司肇慶供電局,廣東 肇慶526000;

2.湖南大學(xué) 電氣與信息工程學(xué)院,湖南 長(zhǎng)沙410000)


Magazine.Subscription.jpg

此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。