An efficient tolerance design procedure for yield maximization using optimization techniques and neural network

Various optimization formulations are analyzed for the determination of design parameters and their tolerances to achieve maximum yield and minimum cost. Three approaches for this objective are presented. Through a numerical example, it is concluded that a procedure using a neural network approach followed by a fine tuning algorithm is recommended for efficiency and reliability.<<ETX>>

[1]  R. Hecht-Nielsen,et al.  Theory of the Back Propagation Neural Network , 1989 .

[2]  Y. Wang,et al.  Statistical circuit design using neural network and orthogonal array , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.

[3]  R. Chen,et al.  A least pth optimization algorithm without calculating derivatives , 1981 .

[4]  Robert Hecht-Nielsen,et al.  Theory of the backpropagation neural network , 1989, International 1989 Joint Conference on Neural Networks.

[5]  John A. Nelder,et al.  A Simplex Method for Function Minimization , 1965, Comput. J..

[6]  K. Singhal,et al.  Statistical design centering and tolerancing using parametric sampling , 1981 .

[7]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[8]  Y. M. Lai,et al.  An efficient algorithm for optimum assignment of circuit component tolerances , 1991, China., 1991 International Conference on Circuits and Systems.

[9]  R.M.M. Chen,et al.  Circuit tolerance analysis and yield maximization using SPICE with parallel processing techniques , 1991, China., 1991 International Conference on Circuits and Systems.

[10]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .