APPARATUS AND METHOD FOR QUALITY CONTROL USING DATAMINING IN MANUFACTURING PROCESS

摘要

Disclosed are an apparatus and a method for quality control in a production process using data mining. The method for quality control in a production process according to an embodiment of the present invention comprises generating ontology indicating a relationship between a factor and quality by receiving a process factor affecting quality in a production process and quality variables of a qualified product and a defective product which are a result of the process factor; determining desired observation positions based on the generated ontology, and receiving observation coordinates and measurement data of a process factor for each observation position in a production process in real time; performing a linear separation for nonlinear values of the inputted observation coordinates and the measurement data, and performing support vector machine (SVM) learning based on the separated linear values; and predicting the current process state from the SVM learning result. [Reference numerals] (310) Generate ontology indicating a relationship between a factor and quality by receiving a process factor and quality variables; (320) Determine desired observation positions based on the ontology, and receive observation coordinates and measurement data on each observation position; (330) Perform a linear separation for nonlinear values of the observation coordinates and the measurement data, and perform SVM learning; (340) Predict the current process state from the SVM learning result; (AA) Start; (BB) End