Combination of VMD Mapping MFCC and LSTM: A New Acoustic Fault Diagnosis Method of Diesel Engine

Abstract

Diesel engines have a wide range of functions in the industrial and military fields. An urgent problem to be solved is how to diagnose and identify their faults effectively and timely. In this paper, a diesel engine acoustic fault diagnosis method based on variational modal decomposition mapping Mel frequency cepstral coefficients (MFCC) and long-short-term memory network is proposed. Variational mode decomposition (VMD) is used to remove noise from the original signal and differentiate the signal into multiple modes. The sound pressure signals of different modes are mapped to the Mel filter bank in the frequency domain, and then the Mel frequency cepstral coefficients of the respective mode signals are calculated in the mapping range of frequency domain, and the optimized Mel frequency cepstral coefficients are used as the input of long and short time memory network (LSTM) which is trained and verified, and the fault diagnosis model of the diesel engine is obtained. The experimental part compares the fault diagnosis effects of different feature extraction methods, different modal decomposition methods and different classifiers, finally verifying the feasibility and effectiveness of the method proposed in this paper, and providing solutions to the problem of how to realise fault diagnosis using acoustic signals.

Prediction of runner eccentricity and Alford force of a Kaplan turbine based on variational mode decomposition

“…VMD is a nonrecursive decomposition method based on variational problems, which can effectively decompose nonstationary and nonlinear sequences and avoid the appearance of mode mixing phenomenon. 28 VMD assumes that the signal sequence can be decomposed into k intrinsic mode function (IMF) components {u k (t)}, each with its own central frequency and limited bandwidth. The variational problem 29 can be described as follows: minimize the sum of estimated bandwidths of each IMF component {u k (t)}, subject to the constraint that the sum of these k mode functions equals the original signal x(t), which is mathematically represented as 30…”

Fault Diagnosis of Mine Hoist Based on MFCC-SVDD

“…Improve the mechanical and electrical machine, the probability of failure is much higher than other systems, improve the mechanical and electrical machine is the core component of the hoisting system, according to the literature [2] of mine fault motor type, choose the representative from different fault types of three kinds of fault types as the research object, including motor overload, motor current fault bearing failure. The samples with large noise volume and more noise areas are eliminated to construct the sample library of effective signals.…”

“…According to the size relationship between 2 d and 2 r , it is determined whether the fault test data of the hoist is inside the hypersphere, and the criterion is:…”

“…Mine hoist is one of the important equipment connecting mine underground and surface [1][2]. The safety and stability of hoist directly affect the economic benefit of coal mine and the safety of underground workers.…”

Construction of multi-features comprehensive indicator for machinery health state assessment

“…Yao et al [16] developed a multi-scale CNN based on acoustic signals for gear fault diagnosis. Yan et al [17] combined VMD mapping MFCC and LSTM to detect diesel engine faults. Vashishtha et al [18] extracted the single-valued neutrosophic cross-entropy of adaptive chirp mode decomposition based on acoustic signal to identify the impeller defects in the centrifugal pump.…”