Multi-Source Uncertainty Perception and Spatiotemporal Graph Fusion for Defect-Elimination Robots in Strong Electromagnetic Environments
Main Article Content
Abstract
To address perception distortion, difficulties in heterogeneous data fusion, and missed detection of small faults in defect-elimination robots for ultra-high-voltage transmission lines under strong electromagnetic interference, a physics-aware spatiotemporal graph fusion network PA-STGFN is proposed. The Middleton Class-A model is employed to estimate the parameters of non-Gaussian impulsive noise, combined with robust statistics for adaptive suppression. EfficientNet enhanced with coordinate attention and MS-TCN are used to extract visual and vibration–acoustic features, respectively. Modality uncertainty is quantified based on Dirichlet evidence, enabling dynamic reconstruction of graph connections and multi-source confidence-weighted fusion. The model is jointly trained using focal loss, reconstruction loss, and uncertainty regularization. Validation on transmission-line data shows that the feature-matching accuracy and anomaly-detection rate reach 95.8% and 96.5%, respectively, with a performance degradation of less than 3% at 10 dB and a single-frame inference latency of 78 ms. The proposed method can improve the perception reliability of defect-elimination robots in strong electromagnetic environments.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
A. B. Alhassan et al., “Power transmission line inspection robots: A review, trends and challenges for future research,” Int. J. Electr. Power Energy Syst., vol. 118, 2020, Art. no. 105862, doi: 10.1016/j.ijepes.2020.105862.
A. Pagnano, M. Höpf, and R. Teti, “A roadmap for automated power line inspection, maintenance and repair,” Procedia CIRP, vol. 12, pp. 234–239, 2013, doi: 10.1016/j.procir.2013.09.041.
X. Liu, X. Miao, H. Jiang, et al., “Data analysis in visual power line inspection: An in-depth review of deep learning for component detection and fault diagnosis,” Annu. Rev. Control, vol. 50, pp. 253–277, 2020, doi: 10.1016/j.arcontrol.2020.09.002.
D. Middleton, “Statistical-physical models of electromagnetic interference,” IEEE Trans. Electromagn. Compat., vol. EMC-19, no. 3, pp. 106– 127, Aug. 1977, doi: 10.1109/TEMC.1977.303527.
S. V. Zhidkov, “Analysis and comparison of several simple impulsive noise mitigation schemes for OFDM receivers,” IEEE Trans. Commun., vol. 56, no. 1, pp. 5–9, Jan. 2008, doi: 10.1109/TCOMM.2008.050391.
H. Oh, H. Nam, and S. Park, “Adaptive threshold blanker in an impulsive noise environment,” IEEE Trans. Electromagn. Compat., vol. 56, no. 5, pp. 1045–1052, Oct. 2014, doi: 10.1109/TEMC.2014.2311853.
P. J. Huber, “Robust estimation of a location parameter,” Ann. Math. Statist., vol. 35, no. 1, pp. 73–101, 1964, doi: 10.1214/aoms/1177703732.
F. R. Hampel, “The influence curve and its role in robust estimation,” J. Amer. Statist. Assoc., vol. 69, no. 346, pp. 383–393, 1974, doi: 10.1080/01621459.1974.10482962.
M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proc. 36th Int. Conf. Mach. Learn. (ICML), 2019, pp. 6105–6114.
Q. Hou, D. Zhou, and J. Feng, “Coordinate attention for efficient mobile network design,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2021, pp. 13713–13722.
Y. Abu Farha and J. Gall, “MS-TCN: Multi-stage temporal convolutional network for action segmentation,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2019, pp. 3575–3584.
S. Yan, Y. Xiong, and D. Lin, “Spatial temporal graph convolutional networks for skeleton-based action recognition,” in Proc. AAAI Conf. Artif. Intell., 2018, vol. 32, no. 1, pp. 7444–7452, doi: 10.1609/aaai.v32i1.12328.
P. Veliˇckovi´c, G. Cucurull, A. Casanova, et al., “Graph attention networks,” in Proc. 6th Int. Conf. Learn. Represent. (ICLR), 2018.
W. Peng, X. Hong, H. Chen, et al., “Learning graph convolutional network for skeleton-based human action recognition by neural searching,” in Proc. AAAI Conf. Artif. Intell., 2020, vol. 34, no. 3, pp. 2669–2676, doi: 10.1609/aaai.v34i03.5652.
T. Baltrušaitis, C. Ahuja, and L. P. Morency, “Multimodal machine learning: A survey and taxonomy,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 2, pp. 423–443, Feb. 2019, doi: 10.1109/TPAMI.2018.2798607.
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in Proc. 5th Int. Conf. Learn. Represent. (ICLR), 2017.
M. Sensoy, L. Kaplan, and M. Kandemir, “Evidential deep learning to quantify classification uncertainty,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2018, vol. 31, pp. 3179–3189.
B. Lakshminarayanan, A. Pritzel, and C. Blundell, “Simple and scalable predictive uncertainty estimation using deep ensembles,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2017, vol. 30, pp. 6402–6413.
C. Guo, G. Pleiss, Y. Sun, et al., “On calibration of modern neural networks,” in Proc. 34th Int. Conf. Mach. Learn. (ICML), 2017, pp. 1321– 1330.
A. Kendall and Y. Gal, “What uncertainties do we need in Bayesian deep learning for computer vision?,” in Proc. Adv. Neural Inf. Process. Syst. (NIPS), 2017, vol. 30, pp. 5574–5584.
J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 7132–7141.
S. Woo, J. Park, J. Y. Lee, et al., “CBAM: Convolutional block attention module,” in Proc. Eur. Conf. Comput. Vis. (ECCV), Cham, Switzerland: Springer, 2018, pp. 3–19, doi: 10.1007/978-3-030-01234-2_1.
C. Lea, M. D. Flynn, R. Vidal, et al., “Temporal convolutional networks for action segmentation and detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 156–165.
A. Kendall, Y. Gal, and R. Cipolla, “Multi-task learning using uncertainty to weigh losses for scene geometry and semantics,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2018, pp. 7482–7491.
T. Y. Lin, P. Goyal, R. Girshick, et al., “Focal loss for dense object detection,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 2980– 2988.
I. Loshchilov and F. Hutter, “Decoupled weight decay regularization,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2019.