scholarly journals Research on Feature Extraction Method of Engine Misfire Fault Based on Signal Sparse Decomposition

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Canyi Du ◽  
Fei Jiang ◽  
Kang Ding ◽  
Feng Li ◽  
Feifei Yu
Keyword(s):  
Finite Element ◽  
Feature Extraction ◽  
Finite Element Model ◽  
Extraction Method ◽  
Element Model ◽  
Pass Filter ◽  
Sparse Decomposition ◽  
Feature Extraction Method ◽  
Automotive Engine ◽  
Impulse Function

Engine vibration signals are easy to be interfered by other noise, causing feature signals that represent its operating status get submerged and further leading to difficulty in engine fault diagnosis. In addition, most of the signals utilized to verify the extraction method are derived from numerical simulation, which are far away from the real engine signals. To address these problems, this paper combines the priority of signal sparse decomposition and engine finite element model to research a novel feature extraction method for engine misfire diagnosis. Firstly, in order to highlight resonance regions related with impact features, the vibration signal is performed with a high-pass filter process. Secondly, the dictionary with clear physical meaning is constructed by the unit impulse function, whose parameters are associated with engine system modal characteristics. Afterwards, the signals that indicate the engine operating status are accurately reconstructed by segmental matching pursuit. Finally, a series of precise simulation signals originated from the engine dynamic finite element model, and experimental signals on the automotive engine are used to verify the proposed method’s effectiveness and antinoise performance. Additionally, comparisons with wavelet decomposition further show the proposed method to be more reliable in engine misfire diagnosis.

scholarly journals Survey of Marine Organisms Based on Passive Acoustic Technology

2020 ◽  
Vol 15 (5) ◽  
pp. 729-737
Author(s):  
Gong Chen ◽  
Lei Cai ◽  
Lv Zong ◽  
Yan Wang ◽  
Xin Yuan
Keyword(s):  
Feature Extraction ◽  
Acoustic Signal ◽  
Extraction Method ◽  
Acoustic Signals ◽  
Marine Organisms ◽  
Decomposition Algorithm ◽  
Sparse Decomposition ◽  
Feature Extraction Method ◽  
Fish Detection ◽  
Passive Acoustic

Passive acoustic technology (PAT) is an important tool to acquire the passive acoustic signals from marine organisms. In this paper, PAT fish detection is introduced at great length, including the relevant instruments, signal processing methods, and workflow. Focusing on the key tasks of PAT fish detection, the authors proposed a sparse decomposition algorithm that extracts coherent ratio of passive fish acoustic signal, and designed a feature extraction method for that signal based on speech imitation technology. Experimental results demonstrate that the proposed sparse decomposition algorithm can detect fish acoustic signal accurately at low signal-to-noise ratios (SNRs), and the proposed feature extraction method can effectively extract fish acoustic signals from the marine background. The research results shed important new light on the protection and management of fishery resources in the seas and oceans.

Feature Extraction Method for Rolling Bearing’s Week Fault Based on Kalman Filter and FSK

2014 ◽  
Vol 574 ◽  
pp. 684-689
Author(s):  
Zhi Chuan Liu ◽  
Li Wei Tang ◽  
Li Jun Cao
Keyword(s):  
Feature Extraction ◽  
Kalman Filter ◽  
Extraction Method ◽  
Model Parameters ◽  
Band Pass Filter ◽  
Pass Filter ◽  
Feature Extraction Method ◽  
Spectral Kurtosis ◽  
Band Pass ◽  
Fault Feature Extraction

Aiming at the problem that traditional demodulated resonance technology has the deficiency of difficulty to choose the parameters of band-pass filter, Kalman filter technology and fast spectral kurtosis were combined for fault feature extraction of rolling bearing. AR model was firstly built with gearbox original vibration signals, and then model order was ascertained with AIC formula, and finally model parameters were calculated with least-squares method. The original signals were pretreated by Kalman filter. Fast spectral kurtosis (FSK) was used to choose parameters of the best band-pass filter, and finally fault diagnosis was achieved by the energy operator demodulation spectrum analysis of band-pass filtered signal. The analysis result of engineering signals indicated that fault feature extraction method based on Kalman filter and fast spectral kurtosis can primely provide a new feature extraction method for rolling bearing’s week fault.

scholarly journals How well does a linear static finite element analysis predict measured strains from a nuclear package tie-down system during rail transportation?

2016 ◽  
Vol 232 (1) ◽  
pp. 222-237 ◽  
Author(s):  
Andrew Cummings ◽  
Glynn Rothwell ◽  
Christian Matthews
Keyword(s):  
Finite Element ◽  
Finite Element Model ◽  
Element Model ◽  
Radioactive Material ◽  
Element Analysis ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Dangerous Goods ◽  
Codes Of Practice ◽  
Low Pass

Freight rail is often the preferred method for transportation of dangerous goods. One particular application is the use of rail to convey radioactive material in purpose-built packages. During transit, packages are secured to a rail wagon bed with a tie-down system. The design of tie-down systems varies considerably depending on the package type and rail vehicle; for example, shackles, turnbuckles, tie rods, gravity wells or transport frames are all commonly used. There are also a large number of different packages in existence that all vary in size and mass, typically 1–7 m in length and 100 kg–100 t in mass. Despite the uniqueness of many transport configurations, the design of tie-down systems is always carried out using a limited set of design load cases as defined in the appropriate Codes of Practice and Standards. Many authors have suggested that the load cases within the standards need revision or question which load cases should apply to which scenario. In a previous experiment, accelerations and strains have been measured on a freight wagon and transport frame of a heavy package during a routine rail journey. From these data, a new insight into the magnitude and nature of loading has been gained. In the present study, the measured accelerations have been used as input to a finite element model of the transport frame, and a method based on correlation between predicted and measured strains has been developed to determine an appropriate low-pass filter cut-off frequency, fc, which separates quasi-static loading from raw dynamic data. The residual dynamic measurements have been assessed using signal processing techniques to understand their significance. The finite element model has also been used to assess the presence of contact and boundary nonlinearities and how they affect the agreement between measured and predicted strains.

scholarly journals Transfer Learning Based Method for Frequency Response Model Updating with Insufficient Data

Sensors ◽  
2020 ◽  
Vol 20 (19) ◽  
pp. 5615
Author(s):  
Zhongmin Deng ◽  
Xinjie Zhang ◽  
Yanlin Zhao
Keyword(s):  
Finite Element ◽  
Feature Extraction ◽  
Finite Element Model ◽  
Frequency Response ◽  
Transfer Learning ◽  
Model Updating ◽  
Element Model ◽  
Insufficient Data ◽  
Comparison Results ◽  
Small Dataset

Finite element model updating precision depends heavily on sufficient vibration feature extraction. However, adequate amount of sample collection is generally time-consuming in frequency response (FR) model updating. Accurate vibration feature extraction with insufficient data has become a significant challenge in FR model updating. To update the finite element model with a small dataset, a novel approach based on transfer learning is firstly proposed in this paper. A readily available fault diagnosis dataset is selected as ancillary knowledge to train a high-precision mapping from FR data to updating parameters. The proposed transfer learning network is constructed with two branches: source and target domain feature extractor. Considering about the cross-domain feature discrepancy, a domain adaptation method is designed by embedding the extracted features into a shared feature space to train a reliable model updating framework. The proposed method is verified by a simulated satellite example. The comparison results manifest that sample amount dependency has prominently lessened this method and the updated model outperforms the method without transfer learning in accuracy with the small dataset. Furthermore, the updated model is validated through dynamic response out of the training set.

Sign in / Sign up

Export Citation Format

Share Document