Guo Chen, Jiabin Peng, Tianxiang Xu and Lu Xiao
Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by…
Abstract
Purpose
Problem-solving” is the most crucial key insight of scientific research. This study focuses on constructing the “problem-solving” knowledge graph of scientific domains by extracting four entity relation types: problem-solving, problem hierarchy, solution hierarchy and association.
Design/methodology/approach
This paper presents a low-cost method for identifying these relationships in scientific papers based on word analogy. The problem-solving and hierarchical relations are represented as offset vectors of the head and tail entities and then classified by referencing a small set of predefined entity relations.
Findings
This paper presents an experiment with artificial intelligence papers from the Web of Science and achieved good performance. The F1 scores of entity relation types problem hierarchy, problem-solving and solution hierarchy, which were 0.823, 0.815 and 0.748, respectively. This paper used computer vision as an example to demonstrate the application of the extracted relations in constructing domain knowledge graphs and revealing historical research trends.
Originality/value
This paper uses an approach that is highly efficient and has a good generalization ability. Instead of relying on a large-scale manually annotated corpus, it only requires a small set of entity relations that can be easily extracted from external knowledge resources.
Details
Keywords
Yuan-Jian Yang, Guihua Wang, Qiuyang Zhong, Huan Zhang, Junjie He and Haijun Chen
Gas pipelines are facing serious risk because of the factors such as long service life, complex working condition and most importantly, corrosion. As one of the main failure…
Abstract
Purpose
Gas pipelines are facing serious risk because of the factors such as long service life, complex working condition and most importantly, corrosion. As one of the main failure reasons of gas pipeline, corrosion poses a great threat to its stable operation. Therefore, it is necessary to analyze the reliability of gas pipelines with corrosion defect. This paper uses the corresponding methods to predict the residual strength and residual life of pipelines.
Design/methodology/approach
In this paper, ASME-B31G revised criteria and finite element numerical analysis software are used to analyze the reliability of a special dangerous section of a gas gathering pipeline, and the failure pressure and stress concentration of the pipeline under three failure criteria are obtained. Furthermore, combined with the predicted corrosion rate of the pipeline, the residual service life of the pipeline is calculated.
Findings
This paper verifies the feasibility of ASME-B31G revised criteria and finite element numerical analysis methods for reliability analysis of gas pipelines with corrosion defect. According to the calculation results, the maximum safe internal pressure of the pipeline is 9.53 Mpa, and the residual life of the pipeline under the current operating pressure is 38.41 years, meeting the requirements of safe and reliable operation.
Originality/value
The analysis methods and analysis results provide reference basis for the reliability analysis of corroded pipelines, which is of great practical engineering value for the safe and stable operation of natural gas pipelines.
Details
Keywords
Yiming Li, Hongzhuan Chen, Shuo Cheng and Abdul Waheed Siyal
In order to analyze the level of independent controllability and its evolution of high-end equipment manufacturing industry from Jiangsu Province, this article introduces the…
Abstract
Purpose
In order to analyze the level of independent controllability and its evolution of high-end equipment manufacturing industry from Jiangsu Province, this article introduces the dual-excitation control line method to construct a comprehensive evaluation model for independent controllability.
Design/methodology/approach
Through the collection of information of high-end equipment manufacturing industry's independent and controllable capabilities on different indicators, the three aspects of advancement, autonomy and controllability, an empirical evaluation of 10 enterprises in the high-end equipment cluster in Jiangsu Province was conducted in terms of advancement, autonomy and controllability.
Findings
It effectively reveals the area and evolution characteristics of the “reward” and “punishment” of different indicators of each representative enterprise and reflects the development status and different characteristics of each representative enterprise on the three indicators. The research results provide decision-making guidance for enterprises in the management and control of advanced manufacturing systems with independent and controllable capabilities.
Originality/value
Existing research focuses on the evaluation of enterprises' independent controllability only on a single angle or index. This paper maps the dynamic evaluation problem of multiple time-point data to the evaluation problem of single time-point multi-index data and investigates the fluctuation of the performance of the same enterprise under different indexes, so as to comprehensively evaluate the independent controllable level of high-end equipment manufacturing industry and analyze the reasons. Further, this paper first establishes an evaluation index system of independent controllable level of high-end equipment manufacturing industry and quantitatively measures the advanced, independent, controllable and other aspects of typical enterprises in this industry by constructing a double incentive control line evaluation model.