基于神经网络的数据融合算法在管道缺陷损伤识别上的应用

Based on Neural Network Data Fusion Algorithm Defects in the Pipeline Damage Identification on the Application

本文研究了基于BP神经网络的多传感器数据融合算法,并对BP算法进行改进,利用D-S证据理论进行分析,针对多传感器检测数据的不确定性,提出了神经网络和D-S证据理论相结合的数据融合模型及融合算法应用于输油管道检测系统,通过对他们进行检测、关联、相关、估计和综合等多方面、多级别的处理,进而得到被检测状态的准确评估。它可以克服单一管道检测技术的不足,融合多种检测结果以提高检测精度。

This paper studies the characteristics of BP neural network and studied the BP neural network based data fusion method On this basis, this paper briefly introduces the basic concepts of D-S evidence theory, The article proposed a fusion integration algorithm combination of neural networks and D-S evidence theory data for multi-sensor data for the uncertainty .The theory is analyzed through cases, the combination of the neural network and D-S evidence theory data fusion algorithm is applied to pipeline inspection system o Finally, the combination of the neural network and D-S evidence theory data fusion algorithm is applied to pipeline inspection system. Through their detection, association, correlation, estimation and other aspects of comprehensive, multi-level processing, then get an accurate assessment of the state of being detected o It can overcome the lack of a single pipeline inspection technology, the integration of a variety of test results in order to improve detection accuracy.