雷达科学与技术2025，Vol.23Issue(1)：101-108,118,9.DOI:10.3969/j.issn.1672-2337.2025.01.011
基于深度卷积神经网络的雷达伺服转台消隙策略
Anti-Backlash Strategy of Radar Servo Turntable Based on Deep Convolutional Neural Networks
摘要
Abstract
The transmission mechanism of the precision radar servo turntable will gradually wear with continuous equipment operation,resulting in an increase in backlash.While the traditional dual motor anti-backlash control strate-gy can eliminate the backlash,it depends on the control experience and initial gear backlash configuration,leading to a gradual decline in the effectiveness of backlash elimination as the wear of the mechanism and affecting radar tracking accuracy.To overcome this limitation,an anti-backlash strategy of precision radar servo turntable based on deep convo-lutional neural network(DCNN)is proposed in this paper.By collecting the vibration data of the position closed-loop transmission shaft and utilizing continuous wavelet transform(CWT)to generate time-frequency graphs.After training,a recognition model is obtained.Finally,using this model to identify the degree of wear in the servo turntable transmis-sion mechanism and adjust bias current and inflection point current of the dual motor anti-backlash control.Compara-tive experiments confirm that the adjusted anti-backlash effect is superior to the traditional method,significantly enhanc-ing the equipment reliability and reducing the maintenance cost of radar servo turntable.关键词
深度卷积神经网络/精密雷达伺服转台/双电机消隙/可靠性Key words
deep convolutional neural networks/precision radar servo turntable/dual motor anti-backlash/relia-bility分类
信息技术与安全科学引用本文复制引用
鲍子威,吴影生,房景仕..基于深度卷积神经网络的雷达伺服转台消隙策略[J].雷达科学与技术,2025,23(1):101-108,118,9.基金项目
安徽省重点研究与开发计划项目(No.2022b13020003) （No.2022b13020003）
