Manufacturing process mining performs various data analyzes of performance on event logs that record production. That is, it analyzes the event log data accumulated in the information system and extracts useful information necessary for business execution. Process data analysis by process mining analyzes actual data extracted from manufacturing execution systems (MES) to enable accurate manufacturing process analysis. In order to continuously manage and improve manufacturing and manufacturing processes, there is a need to structure, monitor and analyze the processes, but there is a lack of suitable technology to use. The purpose of this research is to propose a manufacturing process analysis method using process mining and to establish a manufacturing process mining system by analyzing empirical data. In this research, the manufacturing process was analyzed by process mining technology using transaction data extracted from MES. A relationship model of the manufacturing process and equipment was derived, and various performance analyzes were performed on the derived process model from the viewpoint of work, equipment, and time. The results of this analysis are highly effective in shortening process lead times (bottleneck analysis, time analysis), improving productivity (throughput analysis), and reducing costs (equipment analysis).

효과적으로 공정을 관리하기위하여 제품의 품질특성치에 영향을 주는 데이터를 수집하고 공정을 해석하여한다. 이를 위해서 데이터 마이닝(Data Mining)이 많이 수행되어지고 있다. 본 연구에서는 공정으로부터 수집된 대량의 정보 데이터를 신경망(Neural Network)기법을 통하여 공정의 불량률을 예측하고 불량률이 높게 나타난 데이터를 통해 연관규칙(Association Rule)을 적용하여 불량에 영향을 주는 공정의 패턴을 파악 공정을 개선하고자 한다.

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manuf

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing process. The purpose of this paper is to model the recognition of defect type patterns and prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.