Fault detection for multi‐source integrated navigation system using fully convolutional neural network. Issue 7 (22nd May 2018)

• Record Type: Journal Article
• Authors: Xu, Haowei; Lian, Baowang
• Is Part Of: IET radar, sonar & navigation. Volume 12:Issue 7(2018)
• Page Start: 774
• Page End: 782
• Publication Date: 2018-05-22
• Subjects: neural nets -- fault diagnosis -- feature extraction -- signal classification -- inertial navigation -- satellite navigation -- telecommunication network reliability -- telecommunication computing; multisource integrated navigation system -- fault detection method -- multichannel single‐dimensional fully convolutional neural network -- feature extraction -- signal sequence -- INS‐GNSS‐UWB integrated navigation system -- reliability; Signal processing -- Periodicals; Radar -- Periodicals; Sonar -- Periodicals; Electronics in navigation -- Periodicals; Navigation -- Periodicals; 621.3848
• DOI: 10.1049/iet-rsn.2017.0424
• Languages: English
• ISSNs: 1751-8784

Abstract

Abstract : An accurate fault detection method is critical in preventing the integrity of multi‐source navigation system from the abnormal measurements which may occur any time. Here, a multi‐channel single‐dimensional fully convolutional neural network fault detection method is proposed, where the system measuring residuals sequence is used as the input, and the output is the system operating state, such as normal or fault types, in pointwise. The proposed technique extracts the features with various scales, which contain both the local and the general information of the signal sequence, for making a comprehensive and precise classification. To show the validity of the proposed method, computer simulations and trolley testing based on INS/GNSS/UWB integrated navigation system are carried out. The simulation and experimental results show that the proposed fault detection method is superior to the existing algorithms on the faults detection rate and false alarm rate, and thus, system reliability and navigation precision have been greatly improved.