Abstract：LNG unloading system plays an important role in the transport and storage medium of the process. Once the abnormal unloading system, such as pressure fluctuations, uneven pre-cooling, the temperature rises, these phenomena can affect the safe operation of LNG terminals. The changes of pressure, flow rate, temperature and other parameters have a coupling relationship in the process of LNG unloading. The accurate cause and development direction of abnormal working conditions are conducive to the safe operation and maintenance of the unloading system. According to the accident statistics of 38 LNG receiving stations and peak shaving stations by The LNG International Importer’s Group(GIIGNL), the accident rate of the unloading system was 27%. Therefore, the realization of the extraction and identification of the causality of abnormal working conditions of the LNG unloading system has great significance for the traceability and early warning of the accident.&nbsp; &nbsp; &nbsp; As a crucial type of relationship, causality plays a key role in many fields such as relational reasoning. Therefore, extracting causality is a basic task in text mining. At present, in China, the analysis of abnormal working conditions of LNG unloading system adopts the methods of HAZOP and FMEA, and a large amount of causality is contained in the text data. Aiming at the problem of automatically extracting the causality of the text data of the LNG unloading system, this paper adopts the method of sequence labeling to extract the causal relationship entity and determine its direction, using the sequence to sequence (Seq2Seq) architecture and the bidirectional long short memory network (Bi-LSTM). The input word vector is trained and predicted. In order to solve the problem of unclear objects and inaccurate predictions caused by redundant causal nodes, the algorithm introduces an attention mechanism, and the prediction accuracy reaches 95.23%. In the sensitivity analysis, the recall rate and the granularity of causal relationship information have good effect, which indicates that the algorithm has generalization and applicability in the establishment of the causal knowledge base of abnormal conditions in the unloading system.Keywords: LNG unloading system; Causality extraction; Bidirectional LSTM network; Accident traceability; Causal knowledge base

Causal Relationship Extraction of LNG Unloading System Under Abnormal Conditions Based on Bidirectional LSTM Network

Paper Proceedings: https://asmedigitalcollection.asme.org/PVP/PVP2021/volume/85314

ASME 2021 Pressure Vessels & Piping Conference (PVP2021)

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.