Based on the case-based design of smart car system for automotive panel molds, in order to facilitate the implementation of the system, when comparing the similarities of two CAD models, several profile lines are taken as the characteristic curves on the CAD models of each panel. Calculate the similarity of these characteristic curves, and then calculate the similarity of the entire cover from the similarity of these curves. In this way, the case search of the car cover mold CAD is realized.
In 1989 MathaiG. applied BAM neural network to solve the classification problem of power spectral density function PSD in the fiber manufacturing process. Specifically, the discrete PSD curve is first preprocessed to obtain a new discrete point sequence yi(i), where i is the frequency value, and then the yi(i) curve is divided into r equal parts along the amplitude axis and divided into s along the frequency axis. Divide and get [email protected] squares. If the discrete yi(i) value falls within a square, assign the value of 1 or 0 to the element of the corresponding [email protected] binary matrix, as shown. Connecting each row of the above matrix to a single-pole binary vector of [email protected] dimension, then dual-polarizing it and inputting the designed BAM network can realize the classification of the PSD curve.
In the intelligent CAD system based on case study developed by Nakajima Shoji <3> et al., the similarity of the CAD model was calculated by dividing the two-dimensional part drawing into a horizontal space of 5 and a vertical space of 4. , Then set the part to 1 and the part outside to 0 to make the binarization model. Binarization model was used to calculate the area ratio and perimeter ratio of each area. Finally, the similarity of the parts was weighted using these feature weights.
The common point of the above algorithms is that the curve is converted into a binary graph, the memory required for calculation is large, and there is no invariance to the translation, rotation, and scaling of the curve. In particular, it is sensitive to the overall difference in the shape of the curve, and it is not sensitive to the difference in fillet radius, which has a significant effect on the press formability.
In this paper, starting from the influence of the shape of the curve on the stamping formability, the shape of the curve is described by the vector composed of the radius of curvature of the discrete points on the curve, and the curvature radius of the curve is read directly from the curve modulus using the interface function provided by UG. The neural network is used as a classifier to classify and identify the shape of the curve.
The discretized radius of curvature of the curve data is a parameter that directly reflects the shape of the curve. If the curvature radii of the two curves are equal everywhere, then the shape of the two curves must be the same. The use of curvature radius to express the shape of the curve has the following advantages: (1) The radius of curvature is the invariant of the translation and rotation of the curve, and can accurately reflect the shape of the curve. (2) Compared with the features <2, 3> reflecting the overall shape of the curve described above, the curvature radius is a feature that reflects the local shape of the curve, and is more in line with the requirement of formability analysis to identify the shape of the curve. (3) The curvature radius can better reflect the formability of the curve compared with the method of the curve point list curve. The two curves shown are the section lines taken from the two square boxes. If you take a series of coordinate points as the feature quantity of the curve, then the distance between the two curves in the feature space is very small, so it is difficult to distinguish; and taking the radius of curvature of a series of points as the feature vector, the two curves are easier distinguish. In fact, it is the radius of curvature of each point on the curve that actually affects the formability of stampings and its variation.
For sheet metal stamping (as shown in the box drawing), the main factors affecting the forming performance are: arc radius at four corners, the slope of the sidewall, and the height of the sidewall. When using a coordinate point to represent a curve, it is easy to compare the difference in the height of the sidewall, but it is insensitive to changes in the radius of the arc and the slope of the sidewall. When the curve is represented by a radius of curvature, the four peaks indicate the radius of the arc at four corners as shown in the preprocessed graph. Since the large curvature radius value has been transformed to near zero after preprocessing, the shift of the peak position and the distance between the peaks have a significant effect on the comparison result of the curve shape, and both of them exactly reflect the slope of the sidewall. Because of the difference in the height of the sidewalls, the curvature radius representation method is sensitive to all three factors that affect the formability and is an ideal representation method.
TIG Welders,IGBT TIG Welder,Digital Welding Machine
Poney Electric Co., Ltd. , http://www.ponweldingmachine.com