摘要 |
PROBLEM TO BE SOLVED: To provide a method for estimating a characteristic value based on a factor condition and also, efficiently and easily calculating an optimum value of factor data to produce optional characteristic data by using a method of a neural network and learning a mapping relation between a factor group and a characteristic group of experimental data of design/combination, etc. SOLUTION: This method prepares a learning data table in which each experimental data in combination/design is united in a tabular format subjected to attribute division between a factor and an attribute, selects each column of the learning data table, allocates the each column to an input layer or output layer, learns the mapping relation between a factor group and a characteristic group of the experimental data, estimates both a factor on the basis of a characteristic and a factor on the basis of a characteristic, also realizes the simulation of design/combination in a GUI environment, and learns the neural network and estimates a factor value and a characteristic value by selecting a function tab on a computer screen.
|