An efficient recursive least square-based condition monitoring approach for a rail vehicle suspension system

Xiaoyuan Liu, Stefano Alfi, Stefano Bruni

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

A model-based condition monitoring strategy for the railway vehicle suspension is proposed in this paper. This approach is based on recursive least square (RLS) algorithm focusing on the deterministic ‘input–output’ model. RLS has Kalman filtering feature and is able to identify the unknown parameters from a noisy dynamic system by memorising the correlation properties of variables. The identification of suspension parameter is achieved by machine learning of the relationship between excitation and response in a vehicle dynamic system. A fault detection method for the vertical primary suspension is illustrated as an instance of this condition monitoring scheme. Simulation results from the rail vehicle dynamics software ‘ADTreS’ are utilised as ‘virtual measurements’ considering a trailer car of Italian ETR500 high-speed train. The field test data from an E464 locomotive are also employed to validate the feasibility of this strategy for the real application. Results of the parameter identification performed indicate that estimated suspension parameters are consistent or approximate with the reference values. These results provide the supporting evidence that this fault diagnosis technique is capable of paving the way for the future vehicle condition monitoring system.
Original languageEnglish
Pages (from-to)814-830
Number of pages17
JournalVehicle System Dynamics
Volume54
Issue number6
Early online date4 Apr 2016
DOIs
Publication statusPublished - 2016
Externally publishedYes

Fingerprint

Vehicle suspensions
Condition monitoring
Rails
Identification (control systems)
Dynamical systems
Light trailers
Locomotives
Fault detection
Failure analysis
Learning systems
Railroad cars

Cite this

@article{3dc3810a55124009adb59abad8c2ae64,
title = "An efficient recursive least square-based condition monitoring approach for a rail vehicle suspension system",
abstract = "A model-based condition monitoring strategy for the railway vehicle suspension is proposed in this paper. This approach is based on recursive least square (RLS) algorithm focusing on the deterministic ‘input–output’ model. RLS has Kalman filtering feature and is able to identify the unknown parameters from a noisy dynamic system by memorising the correlation properties of variables. The identification of suspension parameter is achieved by machine learning of the relationship between excitation and response in a vehicle dynamic system. A fault detection method for the vertical primary suspension is illustrated as an instance of this condition monitoring scheme. Simulation results from the rail vehicle dynamics software ‘ADTreS’ are utilised as ‘virtual measurements’ considering a trailer car of Italian ETR500 high-speed train. The field test data from an E464 locomotive are also employed to validate the feasibility of this strategy for the real application. Results of the parameter identification performed indicate that estimated suspension parameters are consistent or approximate with the reference values. These results provide the supporting evidence that this fault diagnosis technique is capable of paving the way for the future vehicle condition monitoring system.",
keywords = "Condition monitoring, Fault Diagnosis, parameter estimation, railway vehicle suspension, recursive least square, coupled dynamic system",
author = "Xiaoyuan Liu and Stefano Alfi and Stefano Bruni",
year = "2016",
doi = "10.1080/00423114.2016.1164869",
language = "English",
volume = "54",
pages = "814--830",
journal = "Vehicle System Dynamics",
issn = "0042-3114",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

An efficient recursive least square-based condition monitoring approach for a rail vehicle suspension system. / Liu, Xiaoyuan; Alfi, Stefano; Bruni, Stefano.

In: Vehicle System Dynamics, Vol. 54, No. 6, 2016, p. 814-830.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An efficient recursive least square-based condition monitoring approach for a rail vehicle suspension system

AU - Liu, Xiaoyuan

AU - Alfi, Stefano

AU - Bruni, Stefano

PY - 2016

Y1 - 2016

N2 - A model-based condition monitoring strategy for the railway vehicle suspension is proposed in this paper. This approach is based on recursive least square (RLS) algorithm focusing on the deterministic ‘input–output’ model. RLS has Kalman filtering feature and is able to identify the unknown parameters from a noisy dynamic system by memorising the correlation properties of variables. The identification of suspension parameter is achieved by machine learning of the relationship between excitation and response in a vehicle dynamic system. A fault detection method for the vertical primary suspension is illustrated as an instance of this condition monitoring scheme. Simulation results from the rail vehicle dynamics software ‘ADTreS’ are utilised as ‘virtual measurements’ considering a trailer car of Italian ETR500 high-speed train. The field test data from an E464 locomotive are also employed to validate the feasibility of this strategy for the real application. Results of the parameter identification performed indicate that estimated suspension parameters are consistent or approximate with the reference values. These results provide the supporting evidence that this fault diagnosis technique is capable of paving the way for the future vehicle condition monitoring system.

AB - A model-based condition monitoring strategy for the railway vehicle suspension is proposed in this paper. This approach is based on recursive least square (RLS) algorithm focusing on the deterministic ‘input–output’ model. RLS has Kalman filtering feature and is able to identify the unknown parameters from a noisy dynamic system by memorising the correlation properties of variables. The identification of suspension parameter is achieved by machine learning of the relationship between excitation and response in a vehicle dynamic system. A fault detection method for the vertical primary suspension is illustrated as an instance of this condition monitoring scheme. Simulation results from the rail vehicle dynamics software ‘ADTreS’ are utilised as ‘virtual measurements’ considering a trailer car of Italian ETR500 high-speed train. The field test data from an E464 locomotive are also employed to validate the feasibility of this strategy for the real application. Results of the parameter identification performed indicate that estimated suspension parameters are consistent or approximate with the reference values. These results provide the supporting evidence that this fault diagnosis technique is capable of paving the way for the future vehicle condition monitoring system.

KW - Condition monitoring

KW - Fault Diagnosis

KW - parameter estimation

KW - railway vehicle suspension

KW - recursive least square

KW - coupled dynamic system

U2 - 10.1080/00423114.2016.1164869

DO - 10.1080/00423114.2016.1164869

M3 - Article

VL - 54

SP - 814

EP - 830

JO - Vehicle System Dynamics

JF - Vehicle System Dynamics

SN - 0042-3114

IS - 6

ER -