Abstract
Predictive Maintenance (PdM) of automobiles requires the storage and analysis of large amounts of sensor data. This requirement can be challenging in deploying PdM algorithms onboard the vehicles due to limited storage and computational power on the hardware of the vehicle. Hence, this study seeks to obtain low dimensional descriptive features from high dimensional data using Representation Learning. The low dimensional representation can then be used for predicting vehicle faults, in particular a component related to powertrain. A Parallel Stacked Autoencoder based architecture is presented with the aim of producing better representations when compared to individual Autoencoders with focus on vehicle data. Also, Embeddings are employed on Categorical Variables to aid the performance of the Artificial Neural Networks (ANN) models. This architecture is shown to achieve excellent performance, and in close standards to the previous state-of-the-art research. Significant improvement in powertrain failure prediction is obtained along with reduction in size of input data using our novel deep learning ANN architecture.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Automotive Sensors and Electronics Expo 2017 (2017). http://www.automotivesensors2017.com/. Accessed 13 June 2020
Big data and Analytics in the Automotive Industry - Automotive Analytics Thought Piece. The Creative Studio at Deloitte, London (2015)
Hinton, G.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006). https://doi.org/10.1126/science.1127647
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems 19 (2007). https://doi.org/10.7551/mitpress/7503.003.0024
Maggipinto, M., Masiero, C., Beghi, A., Susto, G.: A convolutional autoencoder approach for feature extraction in virtual metrology. Procedia Manuf. 17, 126–133 (2018). https://doi.org/10.1016/j.promfg.2018.10.023
Vaiciukynas, E., Ulicny, M., Pashami, S., Nowaczyk, S.: Learning low-dimensional representation of bivariate histogram data. IEEE Trans. Intell. Transp. Syst. 19(11), 3723–3735 (2018). https://doi.org/10.1109/tits.2018.2865103
Xu, B., Ding, X., Hou, R., Zhu, C.: A feature extraction method based on stacked denoising autoencoder for massive high dimensional data. In: 2018 14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Huangshan, China, pp. 206–210 (2018). https://doi.org/10.1109/FSKD.2018.8687138
Pirbazari, A.M., Chakravorty, A., Rong, C.: Evaluating feature selection methods for short-term load forecasting. In: 2019 IEEE International Conference on Big Data and Smart Computing (BigComp), Kyoto, Japan, pp. 1–8 (2019). https://doi.org/10.1109/BIGCOMP.2019.8679188
Prytz, R., Nowaczyk, S., Rögnvaldsson, T., Byttner, S.: Predicting the need for vehicle compressor repairs using maintenance records and logged vehicle data. Eng. Appl. Artif. Intell. 41, 139–150 (2015). https://doi.org/10.1016/j.engappai.2015.02.009
Khoshkangini, R., Pashami, S., Nowaczyk, S.: Warranty claim rate prediction using logged vehicle data. In: Moura Oliveira, P., Novais, P., Reis, L.P. (eds.) EPIA 2019. LNCS (LNAI), vol. 11804, pp. 663–674. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30241-2_55
Khoshkangini, R., Mashhadi, P., Pashami, S., Nowaczyk, S., et al.: Early prediction of quality issues in automotive modern industry. Information 11(7), 354 (2020)
Mashhadi, P., Nowaczyk, S., Pashami, S.: Stacked ensemble of recurrent neural networks for predicting turbocharger remaining useful life. Appl. Sci. 10(1), 69 (2019). https://doi.org/10.3390/app10010069
Du, T., Liao, L.: Deep neural networks with parallel autoencoders for learning pairwise relations: handwritten digits subtraction. In: 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA) (2015). https://doi.org/10.1109/icmla.2015.175
Ledesma, D., Liang, Y., Wu, D.: Adaptive generation of phantom limbs using visible hierarchical autoencoders. arXiv preprint arXiv:1910.01191 (2019)
Wang, R., Li, L., Li, J.: A novel parallel auto-encoder framework for multi-scale data in civil structural health monitoring. Algorithms 11(8), 112 (2018). https://doi.org/10.3390/a11080112
Cerda, P., Varoquaux, G.: Encoding high-cardinality string categorical variables (2019)
Guo, C., Berkhahn, F.: Entity embeddings of categorical variables. arXiv, abs/1604.06737 (2016)
Dong, G., Liu, H.: Feature Engineering for Machine Learning and Data Analytics. CRC Press (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Revanur, V., Ayibiowu, A., Rahat, M., Khoshkangini, R. (2020). Embeddings Based Parallel Stacked Autoencoder Approach for Dimensionality Reduction and Predictive Maintenance of Vehicles. In: Gama, J., et al. IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning. ITEM IoT Streams 2020 2020. Communications in Computer and Information Science, vol 1325. Springer, Cham. https://doi.org/10.1007/978-3-030-66770-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-66770-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66769-6
Online ISBN: 978-3-030-66770-2
eBook Packages: Computer ScienceComputer Science (R0)