Abstract
High-emission mobile sources are the main contributors to road traffic emission pollution, and how to accurately identify high-emission road mobile sources is of great significance to urban traffic pollution control and environmental protection. On-Board Diagnostics (OBD) is a device that records the operating conditions of a vehicle in real time. Usually, for vehicles with excessive tailpipe emissions, OBD monitoring value is compared with the set threshold to identify high emission vehicles. However, it often leads to misjudgment if a vehicle is judged to be high emission only by its excessive emission value. Because this excessive value may originate from external objective factors (such as vehicle idling, uneven road), resulting in pseudo-high emission states. Faced with this challenge, we propose a self-supervised representation network (SRN) for identifying high-emission mobile sources. A self-supervised learning module is integrated to learn general emission representations. Meanwhile, a representation memory module is introduced to make the module retain key emission representations through iterative learning. By reconstructing the time-series characterization of mobile sources, it is achieved for the classification identification of high and normal emissions. Experiments on a real diesel vehicle OBD emission monitoring sequence dataset show that the present method obtains a higher performance for emission source classification compared to other methods, demonstrating the effectiveness of the proposed method.
This work was supported in part by the National Natural Science Foundation of China (62103124, 62033012, 61725304), Major Special Science and Technology Project of Anhui, China (201903a07020012, 202003a07020009, 2022107020030), China Postdoctoral Science Foundation (2021M703119).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Franco, V., Kousoulidou, M., Muntean, M., et al.: Road vehicle emission factors development: a review. Atmos. Environ. 70, 84–97 (2013)
China Mobile Source Environmental Management Annual Report in 2021 (Excerpt 1). Environ. Protect. 49(Z2), 82–88 (2021)
Xu, Z., Wang, R., Kang, Y., et al.: A deep transfer NOx emission inversion model of diesel vehicles with multisource external influence. J. Adv. Transp. (2021)
Weiss, M., Bonnel, P., Kühlwein, J., et al.: Will Euro 6 reduce the NOx emissions of new diesel cars\(?\)-Insights from on-road tests with Portable Emissions Measurement Systems (PEMS). Atmos. Environ. 62, 657–665 (2012)
Gallus, J., Kirchner, U., Vogt, R., et al.: Impact of driving style and road grade on gaseous exhaust emissions of passenger vehicles measured by a Portable Emission Measurement System (PEMS). Transp. Res. Part D Transp. Environ. 52, 215–226 (2017)
Xu, Z., Kang, Y., Cao, Y., et al.: Spatiotemporal graph convolution multi-fusion network for urban vehicle emission prediction. IEEE Trans. Neural Netw. Learn. Syst. 32(8), 3342–3354 (2020)
McClintock, P.M.: 2007 High Emitter Remote Sensing Project (2007)
Xu, Z., Wang, R., et al.: Unsupervised identification of high-emitting mobile sources based on multi-feature fusion. In: 2021 China Automation Congress (CAC), pp. 652–657. IEEE (2021)
Li, Z., Kang, Y., Lv, W., et al.: High-emitter identification model establishment using weighted extreme learning machine and active sampling. Neurocomputing 441, 79–91 (2021)
Yunyun, W., Guwei, S., Guoxiang, Z., Hui, X.: Unsupervised new set domain adaptation learning based on self-supervised knowledge. J. Softw. 33(04), 1170–1182 (2022)
Gong, D., Liu, L., Le, V., et al.: Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1705–1714 (2019)
Zhang, Y., Wang, J., Chen, Y., et al.: Adaptive memory networks with self-supervised learning for unsupervised anomaly detection. IEEE Trans. Knowl. Data Eng. (2022)
Lucas, J.M., Saccucci, M.S.: Exponentially weighted moving average control schemes: properties and enhancements. Technometrics 32(1), 1–12 (1990)
Chen, H., Liu, H., Chu, X., et al.: Anomaly detection and critical SCADA parameters identification for wind turbines based on LSTM-AE neural network. Renew. Energy 172, 829–840 (2021)
Wang, G.D., Melly, S.K.: Three-dimensional finite element modeling of drilling CFRP composites using Abaqus/CAE: a review. Int. J. Adv. Manuf. Technol. 94(1), 599–614 (2018)
Xu, Z., Kang, Y., Cao, Y., et al.: Man-machine verification of mouse trajectory based on the random forest model. Front. Inf. Technol. Electron. Eng. 20(7), 925–929 (2019)
Chauhan, V.K., Dahiya, K., Sharma, A.: Problem formulations and solvers in linear SVM: a review. Artif. Intell. Rev. 52(2), 803–855 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, R., Xia, X., Xu, Z. (2022). Identification of High Emission Mobile Sources Based on Self-supervised Representation Network. In: Fan, W., Zhang, L., Li, N., Song, X. (eds) Methods and Applications for Modeling and Simulation of Complex Systems. AsiaSim 2022. Communications in Computer and Information Science, vol 1713. Springer, Singapore. https://doi.org/10.1007/978-981-19-9195-0_34
Download citation
DOI: https://doi.org/10.1007/978-981-19-9195-0_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-9194-3
Online ISBN: 978-981-19-9195-0
eBook Packages: Computer ScienceComputer Science (R0)