Wyniki wyszukiwania - BazTech

1

The optimal design of micro-punching die by using abductive and SA methods

Lin J.-Ch., Lee K.-S., Lin W.-S.

Archives of Computational Materials Science and Surface Engineering

|

2009

|

Vol. 1, nr 2

92-99

EN

Purpose: Punching process currently plays an important role in industrial mass production. The current study focuses on increasing accuracy, performance and extending service life of punches and dies. Optimizing the design of the punch and die has been a common topic for scholars. Design/methodology/approach: The input parameters (punching times, clearance) and output results (wear) were used to construct a training database. The abductive network formulation established a relationship between input parameters and output results. By using the abductive modeling technique, the complicated and uncertain relationships between the input and output variables can be formulated into a useful mathematical model. Once the abductive network model was constructed, the relationships between input and output parameters variables became available. A simulated annealing algorithm (SA) with a performance index was established to optimize this process and find the best result as compared with the actual experiment values. Findings: This study aims to establish the relationship between punching times, clearance and wear of micro punches using the abductive network, and to find relational model involving input parameters and output result of punching die in composite blanking processes. This model can be used to estimate wear between punch and die for industrial applications. Research limitations/implications: Setting up the relational expression of punching times, clearance and wear requires a well-established database covering sufficient relevant parameters and data. In training the database, it is helpful to establish a good relational model among punching parameters. Incorrect data will cause abnormal wear. As a result, the mathematics model is difficult to converge and the neural network will inaccurately predict wear. In addition, the punching die may be changed prematurely, which increases production costs. Delay in replacing a worn punching die can result in poor quality of products. Originality/value: As electronic production becomes increasingly smaller, the opportunity to use micro punches and dies will expand accordingly. This study established the relational expression of input and output, which can be used to correctly estimate any wear condition. This result is based on an abductive network and SA method.

2

The optimal clearance design of micro-punching die

Lin J. C., Lin W. S., Lee K. S., Tong J. L.

Journal of Achievements in Materials and Manufacturing Engineering

|

2008

|

Vol. 29, nr 1

79-82

EN

Purpose: The purpose of this research paper is focused on the optimal clearance design of micro-punching die by abductive network and SA method. Design/methodology/approach: The punching data (input) and wear size (output) were collected for a training database. In order to select proper clearance to evaluate the wear of die, the abductive network was used to establish an efficient relationship between input parameters and output result. This can help to predict wear size under any degree of clearance and hence to replace worn punches and dies at the right time. A simulated annealing (SA) optimization algorithm with a performance index is then applied to the neural network for searching the optimal clearance parameters, and obtains rather satisfactory result as compared with the corresponding experiment verification. Findings: This study aims to identify the relationship between clearance and service life of micro punches using the Neural Network, and to find relational data involving the service life of punches and punching parameters in non-metal blanking processes. The result can be used to estimate optimal clearance between punch and die for industrial applications. Research limitations/implications: In this study, the practical punching processes with different punching conditions were carried out for a set of training data. A trained model exhibited a relationship between service life and clearance of micro punch and die through an abductive network system. The predicted value of wear by abductive network is very close to the actual experimental value, with an error of less than 8%. This result satisfies the required standard for IC factory production. Originality/value: A good clearance design not only increases the quality of product manufactured, but also reduces product's burr. As a result, the wear of punches and dies can be greatly reduced and the life expectancy of punching dies increased.

3

Minimum additional material volume prediction for preform product by using abductive network and Taguchi method

Lin F. C., Lin S. Y., Hsu Y. C., Lee B. C., Kwan C. T.

Archives of Materials Science and Engineering

|

2008

|

Vol. 33, nr 1

57-60

EN

Purpose: To predict the minimum value of additional material volume for an acceptable preform product. To predict an acceptable preform product without shape defect such as unfilling in a closed-die forging operation. Design/methodology/approach: In order to reduce the number of experiments, an orthogonal array from the Taguchi's experimental method will be utilized to design the process parameter combinations for database sets to promote the prediction precision. Also, in order to reduce the number of experiments to get the minimum additional material volume of preform, the abductive network is applied to synthesize the data sets obtained from the numerical simulation. Findings: The minimum additional material volume can be determined as 7.6% for an acceptable preform product in conjunction with the billet settle position, E, of 11.8 mm and the aspect ratio of width to height, B/H, of 1.4. Research limitations/implications: The Taguchi method can be used to narrow the ranges of process parameters for database sets which can promote the precision of abductive network to search for the the minimum additional material volume for an acceptable preform product. The abductive network is applied to synthesize the data sets obtained from the numerical simulation of the reduced ranges of the process parameters. Practical implications: The combination of the abductive network and Taguchi method can be used as a reference and guidance for the development of searching the minimum or maximum value of one of the process parameters, accompanying by the other suitable parameters. Originality/value: An assessment model of the closed-die forging process is developed using a neural network system and Taguchi method. Based on the developed neural network, the additional material volume of preform product, one of the forging process parameters can be minimum accompanying by the other suitable process parameters to get an acceptable product.