Print Email Facebook Twitter Digitization of chemical process flow diagrams using deep convolutional neural networks Title Digitization of chemical process flow diagrams using deep convolutional neural networks Author Theisen, M.F. (TU Delft ChemE/Product and Process Engineering) Nishizaki Flores, K.F. (TU Delft ChemE/Product and Process Engineering) Schulze Balhorn, L. (TU Delft ChemE/Product and Process Engineering) Schweidtmann, A.M. (TU Delft ChemE/Product and Process Engineering) Date 2023 Abstract Advances in deep convolutional neural networks led to breakthroughs in many computer vision applications. In chemical engineering, a number of tools have been developed for the digitization of Process and Instrumentation Diagrams. However, there is no framework for the digitization of process flow diagrams (PFDs). PFDs are difficult to digitize because of the large variability in the data, e.g., there are multiple ways to depict unit operations in PFDs. We propose a two-step framework for digitizing PFDs: (i) unit operations are detected using a deep learning powered object detection model, (ii) the connectivities between unit operations are detected using a pixel-based search algorithm. To ensure robustness, we collect and label over 1000 PFDs from diversified sources including various scientific journals and books. To cope with the high intra-class variability in the data, we define 47 distinct classes that account for different drawing styles of unit operations. Our algorithm delivers accurate and robust results on an independent test set. We report promising results for line and unit operation detection with an Average Precision at 50 percent (AP50) of 88% and an Average Precision (AP) of 68% for the detection of unit operations. Subject Deep convolutional neural networkDigitalizationFlowsheet digitizationMachine learningObject detectionProcess flow diagrams (PFD) To reference this document use: http://resolver.tudelft.nl/uuid:0f1ac556-4319-4eee-9147-290d49bb0fe4 DOI https://doi.org/10.1016/j.dche.2022.100072 Source Digital Chemical Engineering, 6, 11 Part of collection Institutional Repository Document type journal article Rights © 2023 M.F. Theisen, K.F. Nishizaki Flores, L. Schulze Balhorn, A.M. Schweidtmann Files PDF 1_s2.0_S2772508122000631_main.pdf 4.79 MB Close viewer /islandora/object/uuid:0f1ac556-4319-4eee-9147-290d49bb0fe4/datastream/OBJ/view