The magnetic Barkhausen noise (MBN) signal provides interesting clues about the evolution of microstructure of the magnetic material (internal stresses, level of degradation, etc.). This makes it widely used in non-destructive evaluation of ferromagnetic materials. Although researchers have made great effort to explore the intrinsic random characteristics and stable features of MBN signals, they have failed to provide a deterministic definition of the stochastic quality of the MBN signals. Because many features are not reproducible, there is no quantitative description for the stochastic nature of MBN, and no uniform standards to evaluate performance of features. We aim to make further study on the stochastic characteristics of MBN signal and transform it into the quantification of signal uncertainty and sensitivity, to solve the above problems for fatigue state prediction. In the case of parameter uncertainty in the prediction model, a prior approximation method was proposed. Thus, there are two distinct sources of uncertainty: feature(observation) uncertainty and model uncertainty were discussed. We define feature uncertainty from the perspective of a probability distribution using a confidence interval sensitivity analysis, and uniformly quantize and re-parameterize the feature matrix from the feature probability distribution space. We also incorporate informed priors into the estimation process by optimizing the Kullback–Leibler divergence between prior and posterior distribution, approximating the prior to the posterior. Thus, in an insufficient data situation, informed priors can improve prediction accuracy. Experiments prove that our proposed confidence interval sensitivity analysis to capture feature uncertainty has the potential to determine the instability in MBN signals quantitatively and reduce the dispersion of features, so that all features can produce positive additive effects. The false prediction rate can be reduced to almost 0. The proposed priors can not only measure model parameter uncertainties but also show superior performance similar to that of maximum likelihood estimation (MLE). The results also show that improvements in parameter uncertainties cannot be directly propagated to improve prediction uncertainties.
14 September 2023 in Measurement Science and Technology
Low-power electromagnetic-acoustic transducer (EMAT) is crucially important for safety-critical equipment in industry, especially for potential explosives and inflammable petrochemical equipment and facilities. When the excitation power is very low, the corresponding echoes are overwhelmed in noise and related measurement would be inaccurate. To solve this problem, this paper presents a new echo reconstruction method based on a deep stacked denoising autoencoder (DSDAE) for nondestructive evaluation. First, the uses of reference signals and new data structure are to improve the training efficiency. A hybrid method based on variational mode decomposition and wavelet transform is used to obtain clean reference signals as inputs of the deep network. Then, the modified network structure and loss function aim to improve the ability of feature extraction and reconstruct clean echoes from low-power EMAT signals. To validate the effectiveness of the proposed method, the experiments of self-excitation and receiving A-scan inspections of stepped specimens with different thicknesses are conducted at some excitation voltages, as low as 25 V. The results indicate that the proposed DSDAE shows better and more stable denoising performance than some popular processing methods for different specimens and excitation voltages. It greatly improves the signal-to-noise ratio of the reconstructed signal to 20 dB. When applying to thickness measurement of specimens, its relative error is lower than 0.3%, which provides a practical and accurate tool for low-power EMAT testing.
Evaluating fatigue states of metallic materials is essential for predicting their failures and ensuring structural safety. Magnetic Barkhausen noise (MBN) analysis, a non-destructive testing method, provides efficient and reliable methods for identifying and categorising material parameters such as hardness and residual stresses. To establish a quantitative relationship between MBN signals and fatigue states, an improved hidden Markov model (HMM) is proposed based on optimised Gaussian mixture features (GMFs) and the Kullback–Leibler (KL) divergence measure for fatigue prediction. The MBN-GMFs replicate the probability characteristics of MBN signals and track the fatigue degradation trend throughout the fatigue life; thus, they are superior to some widely used statistical features. A Gaussian component optimisation algorithm is proposed to automatically adjust the appropriate number of components in the Gaussian mixture model and enhance the representation of MBN-GMFs. Then, the KL divergence is introduced to quantify the similarity and accurately classify the degree of MBN-GMF migration. The HMM is constructed to obtain the probability transfer relationship between the observations and states and obtain accurate fatigue predictions. Experiments on two 20R metallic materials at three excitation frequencies are conducted to collect the MBN signals. The experimental results and comparisons indicate that the proposed HMM can accurately predict fatigue states and provide a practical and robust analysis tool for MBN-based fatigue predictions.
18 March 2026 in Measurement Science and Technology
Accurate fatigue life prediction is crucial to maintain the safety and structural integrity of mechanical structures. Magnetic Barkhausen Noise (MBN), a non-destructive testing (NDT) technique, is sensitive to microstructural changes induced by fatigue loading in ferromagnetic materials. It shows potential for processing vast and temporally dynamic data from MBN signals. However, accurate prediction of fatigue life of structures is still a challenge. This paper presents a multivariate time series analysis method using hybrid Transformers, named as MetaTran, for spatio-temporal feature fusion and improvement of fatigue life prediction using MBN signals. First, an adaptive window segmentation (AWS) method is designed to partition the preprocessed MBN signal to effectively capture intricate patterns and temporal dynamics. Then, a multi-domain feature selection using the Boruta algorithm identifies the most relevant features. Finally, based on multi-source features, a novel multi-perspective hybrid Transformer (MPHT) is constructed for fatigue life prediction. It consists of a feature tower and a time tower. The former employs weighted embeddings and self-attention mechanism to enhance feature extraction. The latter obtains temporal dependencies of multivariate data. Experimental data were collected from two specimens 20R and Q345 structural steels. Experimental results demonstrate that the proposed MetaTran has higher prediction accuracy in various tests. It is a robust and practical prediction model for both multivariate time series analysis and fatigue life assessment.
1 June 2018 in IEICE Transactions on Information and Systems
In this paper, the problem of lifetime extension of wireless sensor networks (WSNs) with redundant sensor nodes deployed in 3D vegetation-covered fields is modeled, which includes building communication models, network model and energy model. Generally, such a problem cannot be solved by a conventional method directly. Here we propose an Artificial Bee Colony (ABC) based optimal grouping algorithm (ABC-OG) to solve it. The main contribution of the algorithm is to find the optimal number of feasible subsets (FSs) of WSN and assign them to work in rotation. It is verified that reasonably grouping sensors into FSs can average the network energy consumption and prolong the lifetime of the network. In order to further verify the effectiveness of ABC-OG, two other algorithms are included for comparison. The experimental results show that the proposed ABC-OG algorithm provides better optimization performance.