| 초록 |
Petrochemical plants are designed and managed through engineering drawings which are prepared with certain rules to facilitate the design and construction of the plant. Accurate drawings are very important in terms of cost and safety because they have a significant impact on the purchase of equipment and construction. Previously, errors in engineering drawings were manually checked including the QC(Quality Control) phase, which can take a lot of time and cause human errors. In this work, we propose a methodology for learning the process structure by making the existed drawings into data to perform drawing abnormality diagnosis considering that there is a typical process structure for each unit process. It consists of a step of extracting drawing symbol data, creating a process structure by giving sequence between the detected symbols, and classifying process anomalies for a given drawing. |
