《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 基于全連接神經(jīng)網(wǎng)絡(luò)的車(chē)輛短預(yù)瞄電磁導(dǎo)引方案
基于全連接神經(jīng)網(wǎng)絡(luò)的車(chē)輛短預(yù)瞄電磁導(dǎo)引方案
2022年電子技術(shù)應(yīng)用第3期
楊豫龍1,趙 娟1,2,黃 原1
1.中國(guó)地質(zhì)大學(xué)(武漢) 自動(dòng)化學(xué)院,湖北 武漢430074; 2.復(fù)雜系統(tǒng)先進(jìn)控制與智能自動(dòng)化湖北省重點(diǎn)實(shí)驗(yàn)室,湖北 武漢430074
摘要: 電磁導(dǎo)引是一種車(chē)輛自動(dòng)導(dǎo)引方案,廣泛應(yīng)用于工業(yè)、物流等領(lǐng)域。為解決現(xiàn)有電磁導(dǎo)引方案對(duì)車(chē)輛機(jī)械結(jié)構(gòu)要求較高、易受傳感器預(yù)瞄距離短的限制、難以應(yīng)用于小型自動(dòng)導(dǎo)引車(chē)輛的問(wèn)題,提出了一種基于全連接神經(jīng)網(wǎng)絡(luò)的導(dǎo)引方案。通過(guò)數(shù)據(jù)分析尋找有限預(yù)瞄距離內(nèi)的最優(yōu)傳感器排布方案,設(shè)計(jì)和訓(xùn)練全連接神經(jīng)網(wǎng)絡(luò)模型,對(duì)車(chē)身姿態(tài)及車(chē)后道路的信息進(jìn)行全面預(yù)測(cè),以彌補(bǔ)傳感器短預(yù)瞄所造成的前向道路探測(cè)能力的不足。經(jīng)模擬和實(shí)際測(cè)試,該方案能極大改善較小體積車(chē)輛的短預(yù)瞄電磁導(dǎo)引系統(tǒng)的控制效果,實(shí)現(xiàn)車(chē)輛的穩(wěn)定快速運(yùn)行。
中圖分類(lèi)號(hào): TN609;TP242.6;TP249
文獻(xiàn)標(biāo)識(shí)碼: A
DOI:10.16157/j.issn.0258-7998.211665
中文引用格式: 楊豫龍,趙娟,黃原. 基于全連接神經(jīng)網(wǎng)絡(luò)的車(chē)輛短預(yù)瞄電磁導(dǎo)引方案[J].電子技術(shù)應(yīng)用,2022,48(3):22-26.
英文引用格式: Yang Yulong,Zhao Juan,Huang Yuan. Electromagnetic guidance scheme for limited-preview vehicles based on fully connected neural network[J]. Application of Electronic Technique,2022,48(3):22-26.
Electromagnetic guidance scheme for limited-preview vehicles based on fully connected neural network
Yang Yulong1,Zhao Juan1,2,Huang Yuan1
1.School of Automation,China University of Geosciences,Wuhan 430074,China; 2.Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems,Wuhan 430074,China
Abstract: As one of the autopilot schemes of automatic guided vehicle(AGV), electromagnetic guidance is widely used in industry, logistics and other fields. Traditional electromagnetic guidance schemes have high requirements on mechanical structure and are easily limited by the small preview range of sensors. Thus, it is difficult to apply them to small AGV. In order to remedy the defect of limited detection ability, which is caused by limited preview, a fully connected neural network model is designed and trained to detect both vehicle′s posture and rear road information. Both simulation and actual tests show that the presented scheme greatly improves the control effect of electromagnetic guidance system with small size and limited-preview sensors. In the whole process, the vehicle runs rapidly and steadily.
Key words : neural network;supervised learning;limited preview;electromagnetic guiding;AGV

0 引言

    通有交變電流的導(dǎo)線(xiàn)附近會(huì)產(chǎn)生磁場(chǎng)。電磁導(dǎo)引利用這一特性,通過(guò)預(yù)先鋪設(shè)在路面的電磁線(xiàn),實(shí)現(xiàn)對(duì)車(chē)輛的導(dǎo)引[1]。相較于視覺(jué)、雷達(dá)、衛(wèi)星定位等引導(dǎo)方式[2],電磁導(dǎo)引方案對(duì)環(huán)境的抗干擾能力較強(qiáng),不易受外界光照、天氣等條件的影響[3],廣泛應(yīng)用于工業(yè)、物流等路徑相對(duì)固定的場(chǎng)景中[4]

    為實(shí)現(xiàn)車(chē)輛電磁導(dǎo)引,文獻(xiàn)[5]通過(guò)一行緊密排布的傳感器,檢測(cè)車(chē)身相對(duì)路面電磁線(xiàn)的位置。文獻(xiàn)[6]利用最小二乘法,對(duì)當(dāng)前位置處的電磁感應(yīng)強(qiáng)度與車(chē)身側(cè)向偏移量的函數(shù)關(guān)系進(jìn)行曲線(xiàn)擬合,從而確定車(chē)身相對(duì)路面的位置。文獻(xiàn)[7]提出一種“差比和”算法,用兩傳感器值之差除以?xún)蓚鞲衅髦抵蛠?lái)描述車(chē)身的側(cè)向偏移量,然后使用PID控制器實(shí)現(xiàn)跟隨。

    但上述方案仍未解決阻礙電磁導(dǎo)引發(fā)展的根本問(wèn)題,即:電磁傳感器的探測(cè)距離十分有限,導(dǎo)引速度難以提高,若使用延長(zhǎng)桿等機(jī)械結(jié)構(gòu)增大電磁傳感器探測(cè)距離,會(huì)導(dǎo)致車(chē)輛體積龐大、機(jī)械性能變差。




本文詳細(xì)內(nèi)容請(qǐng)下載:http://ihrv.cn/resource/share/2000003996。




作者信息:

楊豫龍1,趙  娟1,2,黃  原1

(1.中國(guó)地質(zhì)大學(xué)(武漢) 自動(dòng)化學(xué)院,湖北 武漢430074;

2.復(fù)雜系統(tǒng)先進(jìn)控制與智能自動(dòng)化湖北省重點(diǎn)實(shí)驗(yàn)室,湖北 武漢430074)




wd.jpg

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