基于全連接神經(jīng)網(wǎng)絡(luò)的車輛短預(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.中國地質(zhì)大學(xué)(武漢) 自動化學(xué)院,湖北 武漢430074; 2.復(fù)雜系統(tǒng)先進控制與智能自動化湖北省重點實驗室,湖北 武漢430074
摘要: 電磁導(dǎo)引是一種車輛自動導(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)引方案對車輛機械結(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)用于小型自動導(dǎo)引車輛的問題,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)計和訓(xùn)練全連接神經(jīng)網(wǎng)絡(luò)模型,對車身姿態(tài)及車后道路的信息進行全面預(yù)測,以彌補傳感器短預(yù)瞄所造成的前向道路探測能力的不足。經(jīng)模擬和實際測試,該方案能極大改善較小體積車輛的短預(yù)瞄電磁導(dǎo)引系統(tǒng)的控制效果,實現(xiàn)車輛的穩(wěn)定快速運行。
中圖分類號: TN609;TP242.6;TP249
文獻標識碼: 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.
文獻標識碼: 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)線附近會產(chǎn)生磁場。電磁導(dǎo)引利用這一特性,通過預(yù)先鋪設(shè)在路面的電磁線,實現(xiàn)對車輛的導(dǎo)引[1]。相較于視覺、雷達、衛(wèi)星定位等引導(dǎo)方式[2],電磁導(dǎo)引方案對環(huán)境的抗干擾能力較強,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)、物流等路徑相對固定的場景中[4]。
為實現(xiàn)車輛電磁導(dǎo)引,文獻[5]通過一行緊密排布的傳感器,檢測車身相對路面電磁線的位置。文獻[6]利用最小二乘法,對當(dāng)前位置處的電磁感應(yīng)強度與車身側(cè)向偏移量的函數(shù)關(guān)系進行曲線擬合,從而確定車身相對路面的位置。文獻[7]提出一種“差比和”算法,用兩傳感器值之差除以兩傳感器值之和來描述車身的側(cè)向偏移量,然后使用PID控制器實現(xiàn)跟隨。
但上述方案仍未解決阻礙電磁導(dǎo)引發(fā)展的根本問題,即:電磁傳感器的探測距離十分有限,導(dǎo)引速度難以提高,若使用延長桿等機械結(jié)構(gòu)增大電磁傳感器探測距離,會導(dǎo)致車輛體積龐大、機械性能變差。
本文詳細內(nèi)容請下載:http://theprogrammingfactory.com/resource/share/2000003996。
作者信息:
楊豫龍1,趙 娟1,2,黃 原1
(1.中國地質(zhì)大學(xué)(武漢) 自動化學(xué)院,湖北 武漢430074;
2.復(fù)雜系統(tǒng)先進控制與智能自動化湖北省重點實驗室,湖北 武漢430074)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。