Development of process safety knowledge graph: A Case study on delayed coking process

Mao, Shuai; Zhao, Yunmeng; Chen, Jinhe; Wang, Bing; Tang, Yang

doi:10.1016/j.compchemeng.2020.107094

Cited by 37 publications

(10 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The construction methods of the knowledge graph are mainly divided into bottom-up and bottom-down [ 15 ], and the bottom-up construction method is to perform entity extraction, relationship extraction and attribute extraction on the data first, and then perform knowledge fusion and entity alignment. That is, different representations of unified entities are denoised to obtain a unified representation, then entity disambiguation and attribute matching are performed, and finally ontology construction and knowledge inference are performed to form a knowledge graph.…”

Section: Related Workmentioning

confidence: 99%

Bearing Fault Diagnosis Method Based on Convolutional Neural Network and Knowledge Graph

Sun

et al. 2022

Entropy

View full text Add to dashboard Cite

An effective fault diagnosis method of bearing is the key to predictive maintenance of modern industrial equipment. With the single use of equipment failure mechanism or operation of data, it is hard to resolve multiple complex variable working conditions, multiple types of fault and equipment malfunctions and failures related to knowledge and data. In order to solve these problems, a fault diagnosis method based on the fusion of deep learning with a knowledge graph is proposed in this paper. Firstly, the knowledge rules of bearing data is used for entity extraction. Next, the multiscale optimized convolutional neural network (MOCNN) proposed in this paper is used for fault classification to achieve relationship extraction. Finally, the fault diagnosis graph of the bearing is constructed for fault-assisted decision-making as well as the detailed display of fault information. According to experiment analysis, the fault diagnosis model based on MOCNN proposed in this paper, which integrates the end-to-end convolutional neural network and the attention mechanism, still achieves an accuracy of 97.86% under the data set of 160 types of faults. Compared with the deep learning models such as Resnet and Inception in the noise environment of multiple working conditions and variable working conditions, the model proposed in this paper not only shows a faster convergence speed and stable performance, but also a higher accuracy in evaluation indicators, which is beneficial to practical use.

show abstract

Section: Related Workmentioning

confidence: 99%

Bearing Fault Diagnosis Method Based on Convolutional Neural Network and Knowledge Graph

Sun

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

“…A knowledge graph (KG) serves as a structured representation of information using nodes and edges to illustrate relationships among entities, thus forming a comprehensive knowledge network. In the cases of chemical engineering, KGs depict process details such as chemical substances, equipment, and workflows, along with their interconnections. , Building upon this foundation, Daoutidis et al , abstracted dynamic system processes into network graphs and further decomposed them into several modules using community detection, elucidating the process knowledge and structural relationships within dynamic systems. Analogous to the KG, the causal relationship graph emphasizes causal connections among key process variables .…”

Section: Introductionmentioning

confidence: 99%

Causality Analysis of the Green Ammonia Synthesis Process Using the Convergent Cross Mapping Algorithm

Yang,

Li,

Zhang

et al. 2024

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Ammonia synthesis has been gradually altered from the gray process (using fossil fuels as hydrogen sources) to the green process (directly or indirectly using water electrolytic cells as hydrogen sources powered by renewable energy), with the motivation of sustainable development and carbon neutrality. The fluctuating nature of renewable energy and the location mismatch between power plants and the production complex make gray ammonia production roadmaps likely to fail or embrace the change. Establishing knowledge graphs in the form of causal relationship network diagrams will help enterprise decision-makers and engineers better understand the process and generate correct production operations and scheduling. In this study, a chemical engineeringinformed method is introduced to generate causal networks of multiple load conditions for green ammonia production. Expert knowledge of chemical engineering is embedded in the determination of the existence and corresponding time delay of the causal relationships of variable pairs. In an industrial case study, the skeletal knowledge graphs and evolution of the control mechanisms were identified in a comparison of the derived causal networks. Extended applications are expected with further integration of controlling theory and algorithms.

show abstract

“…It accurately predicted fault diagnosis results and used similarity matching to find suitable solutions in the knowledge graph. Mao [ 21 ] developed a knowledge graph focused on chemical process safety. It allowed retrieval of potential causes based on safety accident phenomena and ranked corresponding solutions by comparing the probability of potential causes.…”

Section: Introductionmentioning

confidence: 99%

Fault Knowledge Graph Construction and Platform Development for Aircraft PHM

Meng,

Jing,

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

To tackle the problems of over-reliance on traditional experience, poor troubleshooting robustness, and slow response by maintenance personnel to changes in faults in the current aircraft health management field, this paper proposes the use of a knowledge graph. The knowledge graph represents troubleshooting in a new way. The aim of the knowledge graph is to improve the correlation between fault data by representing experience. The data source for this study consists of the flight control system manual and typical fault cases of a specific aircraft type. A knowledge graph construction approach is proposed to construct a fault knowledge graph for aircraft health management. Firstly, the data are classified using the ERNIE model-based method. Then, a joint entity relationship extraction model based on ERNIE-BiLSTM-CRF-TreeBiLSTM is introduced to improve entity relationship extraction accuracy and reduce the semantic complexity of the text from a linguistic perspective. Additionally, a knowledge graph platform for aircraft health management is developed. The platform includes modules for text classification, knowledge extraction, knowledge auditing, a Q&A system, and graph visualization. These modules improve the management of aircraft health data and provide a foundation for rapid knowledge graph construction and knowledge graph-based fault diagnosis.

show abstract

Development of process safety knowledge graph: A Case study on delayed coking process

Cited by 37 publications

References 21 publications

Bearing Fault Diagnosis Method Based on Convolutional Neural Network and Knowledge Graph

Bearing Fault Diagnosis Method Based on Convolutional Neural Network and Knowledge Graph

Causality Analysis of the Green Ammonia Synthesis Process Using the Convergent Cross Mapping Algorithm

Fault Knowledge Graph Construction and Platform Development for Aircraft PHM

Contact Info

Product

Resources

About