Due to the existing relationship between microstructural properties and magnetic ones of the ferromagnetic materials, the application potential of the magnetic Barkhausen noise (BN) method to non-destructive testing is constantly growing. However, the stochastic nature of the Barkhausen effect requires the use of advanced signal processing methods. Recently, the need to apply time-frequency (TF) transformations to the processing of BN signals arose. However, various TF methods have been used in the majority of cases for qualitative signal conditioning and no extensive analysis of TF-based information has been conducted so far. Therefore, in this paper, the wide analysis of BN TF representation was carried out. Considering the properties of TF transformations, the Short-Time Fourier Transform (STFT) was used. A procedure for definition of the envelopes of the TF characteristic was proposed. To verify the quality of extracted features, an analysis was performed on the basis of BN signals acquired during stress loading experiments of steel elements. First, the preliminary experiments were processed for various parameters of the measuring system and calculation procedures. The feature extraction procedure was performed for different modes of TF representations. Finally, the distributions of TF features over the loading stages are presented and their information content was validated using commonly used features derived from time T and frequency F domains.

The paper presents a new approach to obtain information on magnetic anisotropy in Si–Fe grain oriented ferromagnetic steel based on the observation of the magnetic Barkhausen noise (MBN). Until now, in the literature one can only notice the MBN study of magnetic anisotropy in steels carried out in a single time or frequency domain. However, due to the observed high variability of the dynamics of the MBN phenomenon over its occurrence period, depending on the steel properties, the idea of utilization of combined time and frequency representations to obtain new or supplementary information arises. For this purpose, the MBN phenomenon was observed in various directions for steels with oriented magnetic properties. Then, using the short-time Fourier transform, time-frequency (TF) distributions were determined and features vectors enabling the quantification of crucial information were determined. Before performing the final experiments, a series of tests were carried out for different measuring conditions. As a result, it was possible to adjust the conditions enabling us to obtain the highest possible sensitivity for MBN and discrimination level between directional properties in the material. Then, an algorithm of detailed analysis and division of the TF representation into subranges was proposed, enabling the extraction of more detailed information about the phenomena occurring during the magnetization process. This allowed us to clearly indicate and then separate three areas of MBN main activity. Finally, the obtained angular distributions of selected features were presented and discussed, and further conclusions were given.

In this paper, a combination of Magnetic Barkhausen Noise (MBN) and several classical machine learning (ML) methods were used to evaluate both the grade and the magnetic directions of conventional and high grain oriented electrical sheets subjected to selected surface engineering methods. The presented analysis was conducted to compare the performance of two machine learning approaches, classical ML and deep learning (DL), in reference to the same MBN examination problem and based on the same database. Thus, during the experiment, 26 classical ML algorithms were used including decision trees, discriminant analysis, support vector machines, naïve Bayes, nearest neighbor, artificial neural networks and ensemble classifiers. The experiments were carried out considering a different number of recognized magnetic directions and hence the number of determined classes as well. The results of classification accuracy of the applied ML methods were compared with those obtained for the DL model presented in a previous paper. The highest accuracy was obtained for ML models based on artificial neural networks and ensemble bagged trees. However, the accuracy did not reach 89% in the best case—for the smallest number of determined classes. Nevertheless, the achieved results generally indicated an approx. 10 percent advantage of the deep learning model over the classical ones in terms of accuracy in each of the considered cases.

The paper presents a new approach to non-destructive evaluation of easy/hard magnetization axis in grain-oriented SiFe electrical steels based on the Barkhausen phenomenon and its time-frequency (TF) characteristics. Anisotropy in steels is influenced by a number of factors that formulate the global relationship and affect the Barkhausen effect. Due to the observed high variability in the dynamics of magnetic Barkhausen noise (MBN) over time, obtained for various directions in grain-oriented steel, it becomes justified to conduct MBN signal analyses in the time-frequency domain. This representation allows not only global information from MBN signal over entire period to be expressed, but also detailed relationships between properties in time and in frequency to be observed as well. This creates the opportunity to supplement the information obtained. The main aspect considered in the work is to present a procedure that allows an assessment of the resultant angular characteristics in steel. For this purpose, a sample of a conventional grain-oriented SiFe sheet was used. Measurements were made for several angular settings towards the rolling and transverse directions. A data transformation procedure based on short-time Fourier transform (STFT) as well as quantitative analysis and synthesis of information contained in the TF space was presented. Angular characteristics of selected TF parameters were shown and discussed. In addition, an analysis of the repeatability of information obtained using the proposed procedure under various measurement conditions was carried out. The relationship between the selection of calculation parameters used during transformation and the repeatability of the obtained TF distributions were demonstrated. Then the selection of the final values of the calculation parameters was commented upon. Finally, the conclusions of the work carried out were discussed.

This paper presents a new approach to the extraction and analysis of information contained in magnetic Barkhausen noise (MBN) for evaluation of grain oriented (GO) electrical steels. The proposed methodology for MBN analysis is based on the combination of the Short-Time Fourier Transform for the observation of the instantaneous dynamics of the phenomenon and deep convolutional neural networks (DCNN) for the extraction of hidden information and building the knowledge. The use of DCNN makes it possible to find even complex and convoluted rules of the Barkhausen phenomenon course, difficult to determine based solely on the selected features of MBN signals. During the tests, several samples made of conventional and high permeability GO steels were tested at different angles between the rolling and transverse directions. The influences of the angular resolution and the proposed additional prediction update algorithm on the DCNN accuracy were investigated, obtaining the highest gain for the angle of 3.6°, for which the overall accuracy exceeded 80%. The obtained results indicate that the proposed new solution combining time–frequency analysis and DCNN for the quantification of information from MBN having stochastic nature may be a very effective tool in the characterization of the magnetic materials.