Pattern recognition on diesel engine working condition by using a novel methodology — Hilbert spectrum entropy

Li, H.; Zhou, Peilin; Ma, Xuehu

doi:10.1080/20464177.2005.11020301

Cited by 14 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another case with the imaginary part, this part is an output of hilbert transformation. The hilbert transformation equation is written as follows [12][13][14][15],…”

Section: Methodsmentioning

confidence: 99%

“…where is time, ( ) is time domain signal, and ̃( ) is the result of hilbert transform as imaginary-value signal part. With real part and imaginary part already known, then the complex signal can be form using following Equation [12][13][14][15].…”

Section: Methodsmentioning

confidence: 99%

“…The envelope detection or known as instantaneous amplitude have role to signify any amplitude related signal characteristic. In complex signal absolute value equation is written as follows [12][13][14][15].…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

The condition monitoring of diesel engines using acoustic signal analysis

Prasetyo¹,

Alaydrus²

2019

IJEECS

View full text Add to dashboard Cite

<span>Engine have become one of the supportive asset for many activity and work, therefore engine need attention for its condition. The easiest way to do is through the acoustic sound of the engine itself. Most of the time, the engine sounds are checked using a traditional way that may causing a debate regarding its condition. This is due to no supportive scientific basis to know about engine condition using their own acoustic sound. A value from its frequency pattern is needed as scientific basis to determine an engine condition using acoustic sound. Method of envelope extraction by hilbert transform, fast fourier transform, and correlation coefficient are used to find that value. A series of tests have been carried out on the values that have been found and the result are promising for telling engine condition, but unfortunately the values has not been able to identify type of damage that occur on the engine.</span>

show abstract

“…Another case with the imaginary part, this part is an output of hilbert transformation. The hilbert transformation equation is written as follows [12][13][14][15],…”

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

The condition monitoring of diesel engines using acoustic signal analysis

Prasetyo¹,

Alaydrus²

2019

IJEECS

View full text Add to dashboard Cite

show abstract

“…At present, some recognition algorithms based on vibration signals exist, and most of them focus on designing various handcrafted features, fusing multiple features and training different classifiers. In Reference [12], the Hilbert spectrum entropy, which combines the Hilbert spectrum and information entropy, was proposed for the pattern recognition of diesel engine working conditions. In Reference [13], the frequency domain features of vibration signals were extracted for back propagation (BP) and radial basis function (RBF) neural network training to recognize the cylinder pressure.…”

Section: Introductionmentioning

confidence: 99%

Multi-Factor Operating Condition Recognition Using 1D Convolutional Long Short-Term Network

Jiang

Lai

Zhang

et al. 2019

Sensors

View full text Add to dashboard Cite

For a diesel engine, operating conditions have extreme importance in fault detection and diagnosis. Limited to various special circumstances, the multi-factor operating conditions of a diesel engine are difficult to measure, and the demand of automatic condition recognition based on vibration signals is urgent. In this paper, multi-factor operating condition recognition using a one-dimensional (1D) convolutional long short-term network (1D-CLSTM) is proposed. Firstly, a deep neural network framework is proposed based on a 1D convolutional neural network (CNN) and long short-Term network (LSTM). According to the characteristics of vibration signals of a diesel engine, batch normalization is introduced to regulate the input of each convolutional layer by fixing the mean value and variance. Subsequently, adaptive dropout is proposed to improve the model sparsity and prevent overfitting in model training. Moreover, the vibration signals measured under 12 operating conditions were used to verify the performance of the trained 1D-CLSTM classifier. Lastly, the vibration signals measured from another kind of diesel engine were applied to verify the generalizability of the proposed approach. Experimental results show that the proposed method is an effective approach for multi-factor operating condition recognition. In addition, the adaptive dropout can achieve better training performance than the constant dropout ratio. Compared with some state-of-the-art methods, the trained 1D-CLSTM classifier can predict new data with higher generalization accuracy.

show abstract

“…H. Endo and R. B. Randall from the University of New South Wales in Australia enhanced the AR model based on filter technology by the use of minimum entropy deconvolution filter to detect the localized fault of the transmission devices, especially the gears [2]. W. X. Yang et al from Nottingham Trent University in England proposed the construction entropy as a satisfactory criterion for detecting the singularities occurring in signal construction [3] pattern recognition and fault diagnosis of diesel engines [4]. L. S. Qu et al from Xi'an Jiaotong University in China uses the IE as a quantitative measure of equipment maintainability and uses the orbit complexity of vibration signal to evaluate the dynamics quality of rotor systems, and finally uses the entropy distance as an effective diagnostic feature to discriminate the potential faults inside the operating machinery [5].…”

Section: Introductionmentioning

confidence: 99%

Research on fault diagnosis method of thermal power generating units based on process

Chen

Huang

2008

2008 Third International Conference on Electric Utility Deregulation and Restructuring and Power Technologies

View full text Add to dashboard Cite

At present, in the thermal power generating units, most fault diagnosis methods of rotating machinery rely on extracting eigenvalue from the vibration waveform. The vibration waveform signal is the representation of the condition. If the fault occurs, under certain condition, it is possible that the fault information is not revealed in the vibration waveform, or submerged by other information. Under such circumstance, the fault diagnosis method based on the randomly extractive information of condition can not well differentiate these faults. However, the fault, in any case, is accompanied by some symptoms. Under a condition, the vibration information of the fault may appear decentralized and random, but when the whole process is taken into consideration, the rules stand out. To describe the rule of changes in the vibration process, this paper proposes a new diagnosis method based on the process, with the information entropy (IE) matrix as its identification index.Index Terms-Fault diagnosis, information entropy, information fusion, process, rotating machinery. IX. BIOGRAPHIESFei Chen received the M.S.

show abstract

Pattern recognition on diesel engine working condition by using a novel methodology — Hilbert spectrum entropy

Cited by 14 publications

References 7 publications

The condition monitoring of diesel engines using acoustic signal analysis

The condition monitoring of diesel engines using acoustic signal analysis

Multi-Factor Operating Condition Recognition Using 1D Convolutional Long Short-Term Network

Research on fault diagnosis method of thermal power generating units based on process

Contact Info

Product

Resources

About