Smart machine fault diagnostics based on fault specified discrete wavelet transform

This paper describes the use of a single hydrophone to estimate the motion parameters of an autonomous underwater vehicle (AUV) from the underwater acoustic signal excited by its propulsion motor. First, the frequency range of the hydroacoustic signal radiated by the AUV motor is determined, and a detection and recognition model is designed. In the case of uniform linear motion of the AUV, the geometric relationship between the Doppler frequency shift curve of the sound source is derived and the motion model of the sound source and sound line propagation is established. An estimation algorithm for the motion parameters of multiple AUVs based on data from a single hydrophone is derived. Then, for Doppler underwater acoustic signals disturbed by independent identically distributed noise with an arbitrary probability distribution, a cumulative phase difference power amplification instantaneous frequency estimation method is proposed. This method is based on the sum of multiple logarithmic functions. Finally, the effectiveness and accuracy of the algorithm in estimating the motion parameters of multiple AUVs are verified through simulations and experiments.

/pdf/motion-parameter-estimation-of-auv-based-on-underwater-3q8h5qtf.pdf

Motion parameter estimation of AUV based on underwater acoustic Doppler frequency measured by single hydrophone

Recently skew-t mixture models have been introduced as a flexible probabilistic modeling technique taking into account both skewness in data clusters and the statistical degree of freedom (S-DoF) to improve modeling generalizability, and robustness to heavy tails and skewness. In this paper, we show that the state-of-the-art skew-t mixture models fundamentally suffer from a hidden phenomenon named here as"S-DoF explosion,"which results in local minima in the shapes of normal kernels during the non-convex iterative process of expectation maximization. For the first time, this paper provides insights into the instability of the S-DoF, which can result in the divergence of the kernels from the mixture of t-distribution, losing generalizability and power for modeling the outliers. Thus, in this paper, we propose a regularized iterative optimization process to train the mixture model, enhancing the generalizability and resiliency of the technique. The resulting mixture model is named Finite Mixture of Multivariate Regulated Skew-t (FiMReSt) Kernels, which stabilizes the S-DoF profile during optimization process of learning. To validate the performance, we have conducted a comprehensive experiment on several real-world datasets and a synthetic dataset. The results highlight (a) superior performance of the FiMReSt, (b) generalizability in the presence of outliers, and (c) convergence of S-DoF.

FiMReSt: Finite Mixture of Multivariate Regulated Skew-t Kernels - A Flexible Probabilistic Model for Multi-Clustered Data with Asymmetrically-Scattered Non-Gaussian Kernels

It is very important to accurately extract the instantaneous frequency (IF) of complex non-stationary signals, so the signal processing methods based on IF are widely used in engineering. However, in non-stationary complex vibration signals, it is difficult to extract the instantaneous frequency under strong noise because the frequency changes rapidly. This paper proposes an improved multi-ridge extraction method based on differential synchro-squeezing wavelet transform (DSWT). First, an improved method DSWT is proposed to reduce the computation time and image noise of synchro-squeezing wavelet transform (SWT). The running time of the algorithm can be further reduced by segmenting the signal and compressing the time-frequency matrix. The image noise can be significantly reduced by differentiating SWT time-frequency matrix. It lays a good foundation for the extraction of the time-frequency ridge line. Secondly, an improved multi-ridge extraction method is proposed. The ridge jump due to end effect can be eliminated adaptively in segmented extraction. It further improves the time-frequency aggregation and extraction effect of the wavelet ridgeline image. Finally, the improved multi-ridge extraction method based on DSWT (DSWT-IMRE) is verified by the simulation data and experimental data under different conditions. Compared with the method proposed in previous study, the results show that DSWT-IMRE has higher extraction accuracy.

An Improved Multi-Ridge Extraction Method Based on Differential Synchro-Squeezing Wavelet Transform

The safety and reliability of the mechanical system in the industrial process determines the quality of products. Whether the fault can be identified and classified in time is the key to ensure the safe operation of the system and arrange the appropriate maintenance plan to restrain the deterioration of the fault. However, with the rapid development of manufacturing digitization, how to process large amounts of data quickly and accurately is faced with many problems. In this paper, a pattern recognition method of cyclic GMM-FCM (CGF) based on joint time-domain features is proposed. Firstly, the concept of joint time-domain features based on Vold-Kalman filter (VKF) is proposed. It retains the integrity of the signal components and avoids the problem of dimension disaster caused by anomaly detection, which laid a foundation for the accurate classification of sensitive feature sets. Secondly, a pattern recognition method of cyclic GMM-FCM is proposed. It can eliminate global and local outliers in sensitive feature sets and determine the number of FCM categories adaptively. It makes the classification result more reasonable and accurate. Finally, the effectiveness and superiority of the pattern recognition algorithm are verified by the gearbox vibration experiments in various states. The result shows that the method is feasible in engineering practice.

/pdf/research-on-a-pattern-recognition-method-of-cyclic-gmm-fcm-1m39hpn14w.pdf

Research on a Pattern Recognition Method of Cyclic GMM-FCM Based on Joint Time-Domain Features

This paper has proposed a novel bearing fault detection method about adaptive Sparse-spike Deconvolution based on Curvelet Transform (CTSSD), where the novel technique about adaptive Sparse-spike Deconvolution names after ASSD. Its purpose is to recover the pulse sequence from a vibration signal including complex noise, and to evaluate the periodic pulse position and pulse amplitude. Firstly, in order to make the results sparse and improves the stability of the result, the L1 norm regularization method is proposed in this paper, which is used to constrain the signal pulse sequence sparsely. Secondly, considering that regularization parameters are not adaptive, the Quantum behavior Particle Swarm Optimization (QPSO) algorithm is proposed to determine the optimal regularization parameters, adaptively. Finally, considering that the periodic features of ASSD extraction are not continuous, the Curvelet transform is further introduced. The fault signal is transformed into the Curvelet domain, and the Curvelet coefficient is used to characterize the fault signal pulse sequence. This method proposed in this paper is applied to the simulation signal and the vibration signal of rolling bearing fault, and is compared with the ASSD and the minimum entropy deconvolution (MED) to verify the reliability and effectiveness.

/pdf/novel-adaptive-sparse-spike-deconvolution-bearing-fault-4k3l0325cb.pdf

Yanfeng Li

Papers

An Improved Multi-Ridge Extraction Method Based on Differential Synchro-Squeezing Wavelet Transform

Research on a Pattern Recognition Method of Cyclic GMM-FCM Based on Joint Time-Domain Features

Novel Adaptive Sparse-Spike Deconvolution Bearing Fault Detection Method Based on Curvelet Transform