光电工程, 2009, 36 (9): 35, 网络出版: 2010-01-31
用BP 网的跟踪误差辨识建模及跟踪性能评价
Identification and Modeling of Tracking Error Using BP Neural Network and Evaluation of Tracking Performance
跟踪误差 光电经纬仪 BP 网络 Levenberg-Marquardt 算法 tracking error photoelectric theodolite BP neural network Levenberg-Marquardt algorithm
摘要
提出了一种评价光电经纬仪跟踪性能的新方法。该方法采用BP 网络结构进行系统辨识,得到光电经纬仪跟踪误差等效模型。为了提高BP 网络训练速度,对网络进行训练时采用了LM(Levenberg-Marquardt)算法。将等效正弦信号输入等效模型中,通过对输出数据进行处理,即可获得光电经纬仪跟踪性能评价结果。利用该方法得到的等效模型估计误差均值2.587 2e-006°≈0°,最大误差3.6″,标准差1.6″。结果表明基于BP 网络辨识的等效模型能够满足跟踪性能评价要求,实现了对光电经纬仪跟踪性能进行准确评价。
Abstract
A novel approach for evaluating the tracking ability of photoelectric theodolite is proposed. Equivalent model of theodolite tracking error based on the BP neural network structure is identified. The Levenberg-Marquardt (LM) algorithm is adopted in the training method of BP neural network for the sake of speeding up training process. The equivalent sine signal is inputted to the model, and the output is gotten. The evaluation of tracking performance is obtained based on the statistical calculation of output. The estimate errors of equivalent model including average error, maximum error and standard error are 2.5872e-006°≈0°, 3.6″and 1.6″, respectively. The result shows that the equivalent identification model based on BP neural network meets the needs of evaluating the tracking performance of theodolite. The accurate evaluation of tracking performance is achieved.
张宁, 沈湘衡, 胡剑虹. 用BP 网的跟踪误差辨识建模及跟踪性能评价[J]. 光电工程, 2009, 36(9): 35. ZHANG Ning, SHEN Xiang-heng, HU Jian-hong. Identification and Modeling of Tracking Error Using BP Neural Network and Evaluation of Tracking Performance[J]. Opto-Electronic Engineering, 2009, 36(9): 35.