Levenberg-Marquardt backpropagation training of multilayer neural networks for state estimation of a safety critical cyber-physical system

Simple item page
dc.contributor.authorLv, Chen
dc.contributor.authorXing, Yang
dc.contributor.authorZhang, Junzhi
dc.contributor.authorNa, Xiaoxiang
dc.contributor.authorLi, Yutong
dc.contributor.authorLiu, Teng
dc.contributor.authorCao, Dongpu
dc.contributor.authorWang, Fei-Yue
dc.date.accessioned2018-02-13T11:55:19Z
dc.date.available2018-02-13T11:55:19Z
dc.date.issued2017-11-24
dc.description.abstractAs an important safety critical cyber-physical system (CPS), the braking system is essential to the safe operation of the electric vehicle. Accurate estimation of the brake pressure is of great importance for automotive CPS design and control. In this paper, a novel probabilistic estimation method of brake pressure is developed for electrified vehicles based on multilayer Artificial Neural Networks (ANN) with Levenberg-Marquardt Backpropagation (LMBP) training algorithm. Firstly, the high-level architecture of the proposed multilayer ANN for brake pressure estimation is illustrated. Then, the standard backpropagation (BP) algorithm used for training of the feed-forward neural network (FFNN) is introduced. Based on the basic concept of backpropagation, a more efficient training algorithm of LMBP method is proposed. Next, real vehicle testing is carried out on a chassis dynamometer under standard driving cycles. Experimental data of the vehicle and the powertrain systems are collected, and feature vectors for FFNN training collection are selected. Finally, the developed multilayer ANN is trained using the measured vehicle data, and the performance of the brake pressure estimation is evaluated and compared with other available learning methods. Experimental results validate the feasibility and accuracy of the proposed ANN-based method for braking pressure estimation under real deceleration scenarios.en_UK
dc.identifier.citationC. Lv, Yang Xing, Junzhi Zhang. Levenberg-Marquardt backpropagation training of multilayer neural networks for state estimation of a safety critical cyber-physical system. IEEE Transactions on Industrial Informatics, Volume 14, Issue 8, August 2018, pp3436-3446en_UK
dc.identifier.issn1551-3203
dc.identifier.urihttp://dx.doi.org/10.1109/TII.2017.2777460
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/12991
dc.language.isoenen_UK
dc.publisherIEEEen_UK
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectCyber-Physical Systemen_UK
dc.subjectSafety Critical Systemen_UK
dc.subjectArtificial Neural Networksen_UK
dc.subjectLMBPen_UK
dc.subjectBrake Pressure Estimationen_UK
dc.subjectElectric Vehicleen_UK
dc.titleLevenberg-Marquardt backpropagation training of multilayer neural networks for state estimation of a safety critical cyber-physical systemen_UK
dc.typeArticleen_UK

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Levenberg-Marquardt_backpropagation_training-2017.pdf
Size:
982.35 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Staff publications (SATM)