Search Results (2)

Intelligent machinery fault diagnosis is one of the key technologies for the transformation and competitiveness of traditional factories. Complex production environments make it difficult to maintain good prediction performance using traditional methods. This paper proposes a deep convolutional neural network combined with an adaptive environmental noise method to achieve robust fault classification. The proposed method uses six-dimensional physical signals for data fusion and feature fusion, extracts obvious features and enhances subtle features, and uses continuous wavelets and Gramian angular fields to transform signals with different physical and frequency characteristics into time–frequency maps and two-dimensional images. The fusion technology of different signals can provide comprehensive features for fault prediction, improving upon the blind spots of traditional methods to extract features, and then perform prediction and classification through deep convolutional neural networks. In the experiment, the tool failure classification of the dental milling machine is used as a verification case. The results show that the prediction accuracy of the proposed method is nearly 100%, much better than other comparison methods. In addition, white noise was added in the experiment to verify the noise immunity of the model. The results show that the accuracy of the proposed method is 99%, which is better than other comparison methods in terms of accuracy and robustness, proving the effectiveness of the proposed method for fault diagnosis and classification. Full article

The wear phenomenon of a dental milling cutter is studied based on experimental results and data and validated by statistical–mathematical modeling. The results of the statistical–mathematical modeling by the interpolation of the experimental results (data) regarding the wear of the dental milling cutter analyzed and obtained in the work process are presented in this paper. These results (data) are important because they lead to polynomial functions which by interpolation approximate very well the dependent parameter, specifically the wear process (mass lost due to dental milling cutter wear, m_w), considered in the experimental program. The polynomial interpolation functions are valid, only during the experimental testing range of the dental milling cutter, to describe the wear phenomenon; the extrapolations do not lead to satisfactory results. However, by using a controlled interpolation function with an exponential component, the extrapolation of the results is possible. Therefore, the purpose of this paper is the statistical–mathematical modeling by the interpolation of the experimental results of the mass lost due to dental milling cutter wear, m_w, using the deterministic differential model for the work process of it. Thus, interesting conclusions can be drawn relating to the phenomenon. In support of these statements come the results of the statistical–mathematical modeling by the interpolation of the experimental data obtained in the work process of the dental milling cutters, leading to practical applications, such as the extension of the life of dental milling cutter, useful even for its operation optimization; determination of possible criteria for replacing the worn dental milling cutters; the extension of the life of the materials from which dental milling cutters are built; or the provision of ideas for constructive solutions. Based on the modeling results by interpolation, it was found that the dental milling cutter during the milling operation works with high efficiency (mass loss due to wear is very reduced) in the first 11 h of operation, i.e., about a 10% increase in lifetime. After 11 h of operation, mass loss due to wear of the dental milling cutter increases relatively exponentially; thus, it is recommended that, in the normal way, the dental milling cutter be replaced with a new one to ensure high standards of materials processing. Full article