Neural networks in quality function deployment

Quality Function Deployment (QFD) is a method of product planning in the early phases of the development of new products (pre-CAD phase). A major drawback of its application is the need to input a large amount of data and the necessity to estimate values on a rather subjective basis in order to complete the House of Quality. This data is plentiful and often designers lack the knowledge with satisfying accuracy. This paper suggests a machine learning approach in which a neural network automatically determines the data by learning from examples. Unlike conventional neural networks which are treated as black boxes, the topology and the weight values are not random but represent real circumstances and can directly be interpreted in the terms of the application. A final section discusses problems arising from the small number of training sets which is usually available in the field of product design.