Deep-learning-based recognition of symbols and texts at an industrially applicable level from images of high-density piping and instrumentation diagrams

Kim, Hyungki; Lee, Wonyong; Kim, Mijoo; Moon, Yoochan; Lee, Taekyong; Cho, Mincheol; Mun, Duhwan

doi:10.1016/j.eswa.2021.115337

Cited by 30 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Against the traditional methods which rely on hand-crafted feature engineering, these DL methods are fully automated in their architecture to perform both feature engineering and classification (and regression) tasks efficiently. This transition to DL-based models has greatly improved process efficiencies [7], equipment condition monitoring [4], spatiotemporal forecasting [8], and a host of many other solutions [5,[9][10][11]; however, they are faced with challenges ranging from over-fitting, interpretability, optimal hyperparameter selection (and optimization), standardized weight initialization paradigm, and finding the optimal decision criteria between power consumption and performance [1,12]. Nonetheless, considering the need for accurate real-time solutions for ICPS components especially with the growing need for uncertainty modeling, sensor data discrepancies, dynamic environmental and operating conditions, etc., DL methods remain preferable even at the cost of computational power.…”

Section: Introductionmentioning

confidence: 99%

D-dCNN: A Novel Hybrid Deep Learning-Based Tool for Vibration-Based Diagnostics

Akpudo

Hur

2021

Energies

View full text Add to dashboard Cite

This paper develops a novel hybrid feature learner and classifier for vibration-based fault detection and isolation (FDI) of industrial apartments. The trained model extracts high-level discriminative features from vibration signals and predicts equipment state. Against the limitations of traditional machine learning (ML)-based classifiers, the convolutional neural network (CNN) and deep neural network (DNN) are not only superior for real-time applications, but they also come with other benefits including ease-of-use, automated feature learning, and higher predictive accuracies. This study proposes a hybrid DNN and one-dimensional CNN diagnostics model (D-dCNN) which automatically extracts high-level discriminative features from vibration signals for FDI. Via Softmax averaging at the output layer, the model mitigates the limitations of the standalone classifiers. A diagnostic case study demonstrates the efficiency of the model with a significant accuracy of 92% (F1 score) and extensive comparative empirical validations.

show abstract

Section: Introductionmentioning

confidence: 99%

D-dCNN: A Novel Hybrid Deep Learning-Based Tool for Vibration-Based Diagnostics

Akpudo

Hur

2021

Energies

View full text Add to dashboard Cite

show abstract

“…In the proposed line recognition method, the results of recognizing symbols and texts included in P&ID are used as input. Therefore, using the method in [40], the symbols and texts included in the test P&IDs were recognized prior to the experiment.…”

Section: Methodsmentioning

confidence: 99%

“…To date, several studies [33][34][35] have reported the recognition of various types of diagrams, such as electrical diagrams, engineering diagrams, logic diagrams, and piping and instrumentation diagrams (P&ID). With recent developments in deep learning algorithms, there has been active research on the application of CNN-based deep learning methods in the process of diagram recognition [36][37][38][39][40]. In [36] recognition of a simple logic diagram with general application targets was done.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning-Based Method to Recognize Line Objects and Flow Arrows from Image-Format Piping and Instrumentation Diagrams for Digitization

et al. 2021

Self Cite

View full text Add to dashboard Cite

As part of research on technology for automatic conversion of image-format piping and instrumentation diagram (P&ID) into digital P&ID, the present study proposes a method for recognizing various types of lines and flow arrows in image-format P&ID. The proposed method consists of three steps. In the first step of preprocessing, the outer border and title box in the diagram are removed. In the second step of detection, continuous lines are detected, and then line signs and flow arrows indicating the flow direction are detected. In the third step of post-processing, using the results of line sign detection, continuous lines that require changing of the line type are determined, and the line types are adjusted accordingly. Then, the recognized lines are merged with flow arrows. For verification of the proposed method, a prototype system was used to conduct an experiment of line recognition. For the nine test P&IDs, the average precision and recall were 96.14% and 89.59%, respectively, showing high recognition performance.

show abstract

“…Yun et al [23] apply region-based convolutional neural networks on P&IDs and find a 98% symbol recognition rate in their experiments. Kim et al [15] perform deep learning and object character recognition on a data set of P&IDs and report a 97.2% precision for symbol recognition. A study by Kim at al.…”

Section: Related Workmentioning

confidence: 99%