面向位置敏感器件的反馈堆叠信号滤波

为解决位置敏感器件(PSD)提取光斑位置信息的不准确性, 克服元器件、信号处理电路等带来的随机噪声干扰, 本文提出了一种基于极限学习机(ELM)的反馈堆叠模型(FsELM)。该模型使用ELM作为基本训练块, 以单层预测结果与目标真值的偏差作为依据对输入数据进行更新, 并进行循环训练, 形成反馈堆叠的结构, 从而实现PSD信号有效信息的深度提取。同时设计进行了基于一维PSD的激光三角位移检测实验验证算法的性能, 比较了传统滤波算法、经典学习算法、ELM及其变体和本文提出的FsELM方法对数据的处理效果。实验结果表明: FsELM预测精度明显优于其他处理方法, 预测结果均方误差可达1.4×10-5, 预测精度为0.78%; 除ELM等单次训练结构外, FsELM模型的运算速度比其他处理方法更快。该结果证明了FsELM在应对随机噪声干扰的优异性能, 以及不确定环境下突出的预测能力。

Abstract

To minimize position information extraction inaccuracy while using Position Sensitive Devices (PSD), and to overcome noise jamming resulting from components and signal processing circuits, a Feedback stacking model based on Extreme Learning Machine (FsELM) was proposed. FsELM employed Extreme Learning Machine (ELM) as the basic training block, updated the input data based on the differences between the truth values and monolayer predicted results, developed the feedback stacking models by cyclic training, and realized the effective depth extraction information of the PSD signals. Further, a one-dimensional PSD-based laser triangular displacement detection experiment was designed to evaluate the performance of the algorithm. The processing abilities of traditional filtering methods, such as classical learning algorithm, ELM, its variants and the proposed FsELM were compared. The FsELM exhibited a significantly higher prediction accuracy compared to other processing methods. The mean square error and prediction accuracy are 1.4×10-5 and 0.78%, respectively. In addition, the operating speed of the FsELM is higher than that of all the other methods, except for the models with single training structures, such as ELM. The results demonstrate the efficient management of random noise interference and accurate prediction ability of the FsELM in uncertain environments.

参考文献

[1] 张晨, 孙世磊, 石文轩, 等. 工业线阵CCD相机系统测试与噪声评估［J］.光学精密工程, 2016, 24(10): 2532-2539.

ZHANG CH, SUN SH L, SHI W X, et al.. Linear CCD camera System for industry measurement and its noise evaluation ［J］. Opt. Precision Eng., 2016, 24(10): 2532-2539. (in Chinese)

[2] 高玉娥, 刘伟, 吕世猛, 等. 基于位置敏感探测器的六自由度精密位姿测量系统［J］.光学精密工程, 2018, 26(12): 2930-2939.

GAO Y E, LIU W, L SH M, et al.. Six-degree-of-freedom displacement and angle measurement system based on two-dimensional position-sensitive detector ［J］. Opt. Precision Eng., 2018, 26(12): 2930-2939. (in Chinese)

[3] DUTTA A K, HATANAKA Y. A study of the transient response of position-sensitive detectors ［J］. Solid-State Electronics, 1989, 32(6): 485-492.

[4] WANG W, BUSCH V, I J. The linearity and sensitivity of lateral effect position sensitive devices-an improved geometry ［J］. IEEE Transactions on Electron Devices, 1989, 36(11): 2475-2480.

[5] 张红颖, 王汇三, 胡文博. 基于双模型的相关滤波跟踪算法［J］. 光学精密工程, 2019, 27(11): 2450-2458.

ZHANG H Y, WANG H S, HU W B. Correlation filter tracking algorithm based on double model ［J］. Opt. Precision Eng., 2019, 27(11): 2450-2458. (in Chinese)

[6] 张赫, 乔川, 匡海鹏. 基于激光测距的机载光电成像系统目标定位［J］. 光学精密工程, 2019, 27(1): 8-16.

ZHANG H, QIAO CH, KUANG H P. Target geo-location based on laser range finder for airborne electro-optical imaging systems ［J］. Opt. Precision Eng., 2019, 27(1): 8-16. (in Chinese)

[7] WU E Q, KE Y L, DU B J. Noncontact laser inspection based on a PSD for the inner surface of minidiameter pipes ［J］. IEEE Transactions on Instrumentation and Measurement, 2009, 58(7): 2169-2173.

[8] 邹永宁, 姚功杰. 自适应窗口形状的中值滤波［J］.光学精密工程, 2018, 26(12): 3028-3039.

ZOU Y N, YAO G J. Median filtering algorithm for adaptive window shape ［J］. Opt. Precision Eng., 2018, 26(12): 3028-3039. (in Chinese)

[9] 陈键, 郑绍华, 余轮, 等. 基于方向的多阈值自适应中值滤波改进算法［J］.电子测量与仪器学报, 2013, 27(2): 156-161.

CHEN J, ZHENG SH H, YU L, et al.. Improved algorithm for adaptive median filter with multi-threshold based on directional information ［J］. Journal of Electronic Measurement and Instrumentation, 2013, 27(2): 156-161. (in Chinese)

[10] AGRAWAL N, KUMAR A, BAJAJ V. A new method for designing of stable digital IIR filter using hybrid method ［J］. Circuits, Systems, and Signal Processing, 2019, 38: 2187-2226.

[11] 杨媛, 袁蕾, 王庆军, 等. 改进型高压脉冲轨道电路数字滤波算法［J］.信息与控制, 2018, 47(6): 641-649.

YANG Y, YUAN L, WANG Q J, et al.. Modified digital filter algorithm for high-voltage impulse track circuit ［J］. Information and Control, 2018, 47(6): 641-649. (in Chinese)

[12] ZHAO CH Y, XIONG H, LIU Y Y, et al.. A new digital filter based on sinusoidal function for gamma spectroscopy ［J］. Nuclear Instruments and Methods in Physics Research A, 2019, 944: 162582.

[13] KAR R. Optimal designs of analogue and digital fractional order filters for signal processing applications ［J］. CSI Transactions on ICT, 2019, 7(5): 00225.

[14] 叶国阳, 徐科军. 基于中位值和小波两级滤波的气相色谱分析仪数据预处理方法［J］.电子测量与仪器学报, 2015, 29(11): 1711-1717.

YE G Y, XU K J. Median and wavelet two-stage filters based pretreatment method for gas chromatography analyzer data ［J］. Journal of Electronic Measurement and Instrumentation, 2015, 29(11): 1711-1717. (in Chinese)

[15] HUANG G B, ZHU Q Y, CHEE-KHEONG SIEW. Extreme learning machine: a new learning scheme of feedforward neural networks ［J］. IEEE International Joint Conference on Neural Networks, 2004, 2: 985-990.

[16] DING S, ZHAO H, ZHANG Y. Extreme learning machine: algorithm, theory and applications ［J］. Artificial Intelligence Review, 2013, 44(1): 103-115.

[17] HUANG G B, WANG D H, LAN Y. Extreme learning machines: a survey ［J］. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107-122.

[18] HUANG G B, ZHOU H M, DING X J, et al.. Extreme learning machine for regression and multiclass classification ［J］. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2012, 42(2): 513-529.

[19] YU W C, ZHUANG F Z, HE Q, et al.. Learning deep representations via extreme learning machines ［J］. Neurocomputing, 2015, 149: 308-315.

[20] TANG J X, DENG CH W, HUANG G B. Extreme learning machine for multilayer perceptron ［J］. IEEE Transactions on Neural Networks and Learning Systems, 2016, 27(4): 809-821.

[21] JIA X, LI X, JIN Y, et al.. Region-enhanced multi-layer extreme learning machine ［J］. Cognitive Computation, 2018: 9596-9598.

[22] 王晓嘉, 高隽, 王磊. 激光三角法综述［J］. 仪器仪表学报, 2004, 25(4): 601-608.

WANG X J, GAO J, WANG L. Survey on the laser triangulation ［J］. Journal of instruments and apparatus, 2004, 25(4): 601-608. (in Chinese)

[23] CUI J Y, ZHANG H, HAN H, et al.. Improving 2D face recognition via discriminative face depth estimation ［J］. International Conference on Biometrics (ICB), 2018, 140-147.

崔昊, 郭锐, 李兴强, 冯克建, 张飞飞. 面向位置敏感器件的反馈堆叠信号滤波[J]. 光学精密工程, 2020, 28(7): 1568. CUI Hao, GUO Rui, LI Xing-qiang, FENG Ke-jian, ZHANG Fei-fei. Complex signal filter method for position sensitive devices application using a feedback stacking model based on extreme learning machine[J]. Optics and Precision Engineering, 2020, 28(7): 1568.

面向位置敏感器件的反馈堆叠信号滤波

关于本站 Cookie 的使用提示

全站搜索

面向位置敏感器件的反馈堆叠信号滤波

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索