A simple analytical equation has also been determined to describe the localised flux distributions. The network was tested using untrained data and then minimum correlation coefficient and RMS error for localised flux density were found to be 0.98 and 0.04 respectively due to test results. Minimum correlation coefficients and RMS error for the localised flux density were found to be 0.99 and 0.09 respectively after the network was trained. The previous data obtained experimentally was used for training the proposed ANN model. The input parameters were hole size, cutting method, induction frequency and bulk flux density while the output parameter was localised flux density due to the search coil located at the angles 0º, 25º, 45º and 65º corresponding to the centre of hole and rolling direction. A 4-node input layer, 1-node output layer model with three hidden layers, and full connectivity between nodes was developed by the ANN for prediction of localised flux density distribution. Artificial neural networks (ANN) and MATLAB ® Curve Fitting Toolbox TM are useful tools in prediction and analytical calculation of magnetic properties of electrical steels. Localised flux density distributions are closely related to the degraded area around a cut edge or hole. The smaller hole has less to effect on the flux orientation around than the larger hole, due to their magnetostatic energy. Also, cutting method was significant to deteriorate magnetic properties at the small cross sectional areas under the search coils located. The localised linear flux density concentrated on around both holes was obtained with increasing frequency. The localised flux density was measured over the peak flux density ranges 0.1–0.5 T at 50–400 Hz. Variation of localised flux density distribution due to cutting method and hole size was investigated using the search coils located at 0◦, 25◦, 45◦, and 65◦ angles corresponding to the centre of holes with diameters 10 and 20 mm in non-oriented electrical steel sheet, which was namely N530. The microstructure of the material changes near the edge affecting the magnetic domain structure and domain wall motion during the magnetization process. In the manufacturing of electrical machine cores, there exist various cutting processes for electrical steel laminations such as mechanical, laser, and abrasive waterjet.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |