Pulsation Signals Analysis of Turbocharger Turbine Blades based on Optimal EEMD and TEO

Wang, Fengli

doi:10.2478/pomr-2019-0048

Cited by 6 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cheng et al [14] effectively diagnosed faults in axle-box bearings in high-speed trains by analyzing the non-stationary vibration signals, with a combination of improved EEMD with adaptive noise (IEEMDAN) and complementary EEMD (CEEMD), which breaks down the signals into several intrinsic mode functions. Wang [15] proposed a fault analysis model for a marine engine turbocharger by decomposing the pulsation signals using ensemble empirical mode decomposition and the Teager energy operator. Unlike the previous studies that focused on acoustic fault analysis in marine engines using blind source separation (BSS) to separate the sources, Liu et al [16] concentrated on applying BSS to vibration signals for decomposition and feature analysis.…”

Section: Vibration Signal Source-based Fault Detection and Diagnosismentioning

confidence: 99%

A Novel Time–Frequency Feature Fusion Approach for Robust Fault Detection in a Marine Main Engine

Je-Gal,

Lee,

Yoon

et al. 2023

JMSE

View full text Add to dashboard Cite

Ensuring operational reliability in machinery requires accurate fault detection. While time-domain vibration pulsation signals are intuitive for pattern recognition and feature extraction, downsampling can reduce analytical complexity, but may result in low-precision data, affecting fault detection performance. To address this, we propose time–frequency feature fusion, combining information from both the time and frequency domains for fault detection. Our approach transforms vibrational pulse data into instantaneous revolutions per minute (RPM) and employs statistical analysis for the time-domain features. For the frequency-domain features, we use the combined method of empirical mode decomposition and independent component analysis (EMD-ICA), along with the Wigner bispectrum method to capture the nonlinear characteristics and phase conjugation. Using a deep neural network (DNN), we classify the anomaly states, demonstrating the effectiveness and versatility of our approach in detecting anomalies and improving diagnostic precision. Compared to using time or frequency features alone, our time–frequency feature fusion model achieves higher accuracy, with 100% accuracy at lower downsampling rates and 96.3% accuracy at a downsampling rate of 100×.

show abstract

Section: Vibration Signal Source-based Fault Detection and Diagnosismentioning

confidence: 99%

A Novel Time–Frequency Feature Fusion Approach for Robust Fault Detection in a Marine Main Engine

Je-Gal,

Lee,

Yoon

et al. 2023

JMSE

View full text Add to dashboard Cite

show abstract

“…For example, in the wavelet transform method, the suitable wavelet bases should be pre-set, meaning that it lacks self-adaptability. On the other hand, empirical mode decomposition is a type of adaptive time-frequency analysis algorithm [13]; Ensemble Empirical Mode Decomposition (EEMD) [14] can overcome the modal aliasing effect of EMD effectively [15]. However, EEMD still has two issues that need to be addressed.…”

Section: Introductionmentioning

confidence: 99%

A Novel Fault Diagnosis Method for Marine Blower with Vibration Signals

Yan

Jiang

2022

Polish Maritime Research

View full text Add to dashboard Cite

The vibration signals on marine blowers are non-linear and non-stationary. In addition, the equipment in marine engine room is numerous and affects each other, which makes it difficult to extract fault features of vibration signals in the time domain. This paper proposes a fault diagnosis method based on the combination of Ensemble Empirical Mode Decomposition (EEMD), an Autoregressive model (AR model) and the correlation coefficient method. Firstly, a series of Intrinsic Mode Function (IMF) components were obtained after the vibration signal was decomposed by EEMD. Secondly, effective IMF components were selected by the correlation coefficient method. AR models were established and the power spectrum was analysed. It was verified that blower failure can be accurately diagnosed. In addition, an intelligent diagnosis method was proposed based on the combination of EEMD energy and a Back Propagation Neural Network (BPNN), with a correlation coefficient method to get effective IMF components, and the energy components were calculated, normalised as a feature vector. Finally, the feature vector was sent to the BPNN for training and state recognition. The results indicated that the EEMD-BPNN intelligent fault diagnosis method is suitable for higly accurate fault diagnosis of marine blowers.

show abstract

“…This is a fundamental problem for researchers, who are interested in simulating the behaviour of diesel engines in unsteady conditions. The results of such an investigation, in turn, are often required for better understanding of the interactions, for example, in the case of propeller-engine, hull-propeller-engine or hull-rudderpropeller-engine interactions, fuel consumption, combustion efficiency, emissions induced by the engine operation, control purposes, etc., see for example [1,2,3,4,5,6].…”

Section: Introduction Definition Of the Problemmentioning

confidence: 99%

Performance and Emission Modelling and Simulation of Marine Diesel Engines using Publicly Available Engine Data

Ghaemi

2021

Polish Maritime Research

View full text Add to dashboard Cite

To analyse the behaviour of marine diesel engines in unsteady states for different purposes, for example to determine the fuel consumption or emissions level, to adjust the control strategy, to manage the maintenance, etc., a goal-based mathematical model that can be easily implemented for simulation is necessary. Such a model usually requires a wide range of operating data, measured on a test stand. This is a time-consuming process with high costs and the relevant data are not available publicly for a selected engine. The present paper delivers a rapid and relatively simple method for preparing a simulation model of a given marine diesel engine, based only on the widely available data in the project guides indicated for steady state conditions. After establishing the framework of the mathematical model, it describes how the parameters of the model can be adjusted for the simulation model and how the results can be verified as well. Conceptually, this is a trial and error method, but the presented case example makes clear how the parameters can be selected to reduce the number of trials and quickly determine the model parameters. The necessary descriptions are given through a case study, which is the MAN-B&W 8S65ME-C8 marine diesel engine. The engine is assumed to be connected to a constant pitch propeller. The presented mathematical model is a mean-value zero-dimensional type with seven state variables. The other variables of the engine are determined based on the state independent variables and the input value, which is the fuel rate. The paper can be used as a guideline to prepare a convenient mathematical model for simulation, with the minimum publicly available data.

show abstract

Pulsation Signals Analysis of Turbocharger Turbine Blades based on Optimal EEMD and TEO

Cited by 6 publications

References 17 publications

A Novel Time–Frequency Feature Fusion Approach for Robust Fault Detection in a Marine Main Engine

A Novel Time–Frequency Feature Fusion Approach for Robust Fault Detection in a Marine Main Engine

A Novel Fault Diagnosis Method for Marine Blower with Vibration Signals

Performance and Emission Modelling and Simulation of Marine Diesel Engines using Publicly Available Engine Data

Contact Info

Product

Resources

About