Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered
The mission execution process of a fixed-wing UAV has multiple phases and multiple operation conditions. Its parameters are nonlinear and dynamic. These characteristics make its online fault detection rather complicated. To carry out the fault detection, this paper selects nine key parameters of the...
| Format: | Article |
|---|---|
| Language: | zho |
| Published: |
EDP Sciences
2020-06-01
|
| Series: | Xibei Gongye Daxue Xuebao |
| Subjects: | |
| Online Access: | https://www.jnwpu.org/articles/jnwpu/full_html/2020/03/jnwpu2020383p619/jnwpu2020383p619.html |
| _version_ | 1797428946116018176 |
|---|---|
| collection | DOAJ |
| description | The mission execution process of a fixed-wing UAV has multiple phases and multiple operation conditions. Its parameters are nonlinear and dynamic. These characteristics make its online fault detection rather complicated. To carry out the fault detection, this paper selects nine key parameters of the transverse, longitudinal and velocity control loops of the UAV to characterize its real-time conditions. The core parameters are dynamically preprocessed to construct an augmented matrix so as to describe the dynamic characteristics of the UAV. Then, the improved k-mediods* algorithm is used to cluster the operation conditions of the UAVs by means of augmented dimensions. Neural networks are used to achieve the online matching of operation conditions. To overcome the nonlinearity of the UAV, the fault detection is performed by using the DKPCA algorithm; the fault monitoring is conducted through constructing the compound indexes of SPE and T2, notated as FAI. Furthermore, the fault separation algorithm is proposed to specify the variables of fault from the augmented high-dimensional data set. In order to deal with the erroneous reporting of faults due to measurement errors, the paper conducts the wavelet denoising of FAI, the compound indexes of the DKPCA algorithm. Finally, the data set collected from a real UAV flight is used to verify the effectiveness of the DKPCA algorithm for operation condition clustering and matching, fault detection and wavelet denoising. |
| first_indexed | 2024-03-09T09:06:10Z |
| format | Article |
| id | doaj.art-94fb0d3d418a41a2889fa0aa9b530662 |
| institution | Directory Open Access Journal |
| issn | 1000-2758 2609-7125 |
| language | zho |
| last_indexed | 2024-03-09T09:06:10Z |
| publishDate | 2020-06-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | Xibei Gongye Daxue Xuebao |
| spelling | doaj.art-94fb0d3d418a41a2889fa0aa9b5306622023-12-02T10:23:50ZzhoEDP SciencesXibei Gongye Daxue Xuebao1000-27582609-71252020-06-0138361962610.1051/jnwpu/20203830619jnwpu2020383p619Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered0123School of Ordnance Sergeant, Army Engineering UniversitySchool of Electrical Engineering and Automation, Wuhan UniversitySchool of Ordnance Sergeant, Army Engineering UniversitySchool of Ordnance Sergeant, Army Engineering UniversityThe mission execution process of a fixed-wing UAV has multiple phases and multiple operation conditions. Its parameters are nonlinear and dynamic. These characteristics make its online fault detection rather complicated. To carry out the fault detection, this paper selects nine key parameters of the transverse, longitudinal and velocity control loops of the UAV to characterize its real-time conditions. The core parameters are dynamically preprocessed to construct an augmented matrix so as to describe the dynamic characteristics of the UAV. Then, the improved k-mediods* algorithm is used to cluster the operation conditions of the UAVs by means of augmented dimensions. Neural networks are used to achieve the online matching of operation conditions. To overcome the nonlinearity of the UAV, the fault detection is performed by using the DKPCA algorithm; the fault monitoring is conducted through constructing the compound indexes of SPE and T2, notated as FAI. Furthermore, the fault separation algorithm is proposed to specify the variables of fault from the augmented high-dimensional data set. In order to deal with the erroneous reporting of faults due to measurement errors, the paper conducts the wavelet denoising of FAI, the compound indexes of the DKPCA algorithm. Finally, the data set collected from a real UAV flight is used to verify the effectiveness of the DKPCA algorithm for operation condition clustering and matching, fault detection and wavelet denoising.https://www.jnwpu.org/articles/jnwpu/full_html/2020/03/jnwpu2020383p619/jnwpu2020383p619.htmlfixed-wing uavfault detectiondkpca algorithmoperation condition clusteringmultiple operation conditions |
| spellingShingle | Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered Xibei Gongye Daxue Xuebao fixed-wing uav fault detection dkpca algorithm operation condition clustering multiple operation conditions |
| title | Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered |
| title_full | Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered |
| title_fullStr | Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered |
| title_full_unstemmed | Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered |
| title_short | Online Fault Detection of Fixed-Wing UAV Based on DKPCA Algorithm with Multiple Operation Conditions Considered |
| title_sort | online fault detection of fixed wing uav based on dkpca algorithm with multiple operation conditions considered |
| topic | fixed-wing uav fault detection dkpca algorithm operation condition clustering multiple operation conditions |
| url | https://www.jnwpu.org/articles/jnwpu/full_html/2020/03/jnwpu2020383p619/jnwpu2020383p619.html |