Wei Zhang

Dr. Wei Zhang


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2023 in Processes
Verified
Journal Article
Open access
PDF file
TXTaiwu Xia
Taiwu Xia
ZDZhixiang Dai
Zhixiang Dai
ZHZhan Huang
Zhan Huang
LLLi Liu
Li Liu
MLMing Luo
Ming Luo
JZJun Zhou
Jun Zhou
In recent years, oil and gas field surface engineering construction projects tend to be large in scale, large in quantity, and short in cycle. The task of surface construction management has increased significantly. In the process of project construction, corresponding standards and specifications are required to provide sufficient technical guidance and support for design, construction, and management personnel to ensure project management and control towards compliance, safety, and quality. However, the oil and gas field engineering standards are numerous and specialized, involving different levels of national standards, enterprise standards, and industry standards, which leads to the inefficiency of the actual use of standards and specifications. To solve them, this paper uses knowledge graph technology, OCR recognition, and natural language processing technology to conduct systematic research on the knowledge classification mechanism, data extraction, database construction mechanism, data structuring, and intelligent retrieval matching of oil-gas field surface engineering construction standards. In this study, the structured identification, storage, and information warehousing of standards are realized, and a highly sharable library of standards and specifications is formed, which realizes the intelligent retrieval and pushing of technical standards for surface engineering construction. This paper creates conditions for the realization of intelligent push and benchmarking management of standards and specifications, providing support for digital transformation and intelligent development of oil–gas fields.

25 May 2024 in Processes
Verified
Journal Article
Open access
PDF file
TXTaiwu Xia
Taiwu Xia
ZDZhixiang Dai
Zhixiang Dai
YZYihua Zhang
Yihua Zhang
FWFeng Wang
Feng Wang
WZWei Zhang
Wei Zhang
JZJun Zhou
Jun Zhou
To address the challenge of quickly and efficiently accessing relevant management experience for a wide range of ground engineering construction projects, supporting project management with information technology is crucial. This includes the establishment of a case database and an application platform for intelligent search and recommendations. The article leverages Optical Character Recognition (OCR) technology, knowledge graph technology, and Natural Language Processing (NLP) technology. It explores the mechanisms for classifying construction cases, methods for constructing a case database, structuring case data, intelligently retrieving and matching cases, and intelligent recommendation methods. This research forms a complete, feasible, and scalable method for deconstructing, storing, intelligently retrieving, and recommending construction cases, providing a theoretical basis for the establishment of a construction case database. It aims to meet the needs of digital project management and intelligent decision-making support in the oil and gas sector, thereby enhancing the efficiency and accuracy of project construction. This work offers a theoretical foundation for the development of an intelligent management platform for ground engineering projects in the oil and gas industry, supporting the sector’s digital transformation and intelligent development.

6 June 2025 in Systems
Verified
Journal Article
Open access
PDF file
WZWei Zhang
Wei Zhang
ZDZhixiang Dai
Zhixiang Dai
TXTaiwu Taiwu xia
Taiwu Taiwu xia
GCGangping Chen
Gangping Chen
YZYihua Zhang
Yihua Zhang
CLCui Liu
Cui Liu
To address the challenges of data fragmentation, inconsistent standards, and weak interactivity in oil and gas field surface engineering, this study proposes an intelligent delivery system integrated with three-dimensional dynamic modeling. Utilizing a layered collaborative framework, the system combines optimization algorithms and anomaly detection methods during data processing to enhance the relevance and reliability of high-dimensional data. The model construction adopts a structured data architecture and dynamic governance strategies, supporting multi-project secure collaboration and full lifecycle data management. At the application level, it integrates three-dimensional visualization and semantic parsing capabilities to achieve interactive display and intelligent analysis of cross-modal data. Validated through practical engineering cases, the platform enables real-time linkage of equipment parameters, documentation, and three-dimensional models, significantly improving data integration efficiency and decision-making capabilities. This advancement drives the transformation of oil and gas field engineering toward intelligent and knowledge-driven practices.

14 August 2025 in Applied System Innovation
Verified
Journal Article
Open access
PDF file
ZDZhixiang Dai
Zhixiang Dai
JZJun Zhou
Jun Zhou
WZWei Zhang
Wei Zhang
JZJinrui Zhong
Jinrui Zhong
FWFeng Wang
Feng Wang
XCXi Chen
Xi Chen
The design of automatic control systems is critical for ensuring safety in gas field surface engineering production. However, over-reliance on standardized design approaches within the context of automation technology can compromise system flexibility and neglect individualized cost-effectiveness considerations. This paper identifies a comprehensive evaluation method as the preferred approach for assessing station control systems by comparing the advantages and disadvantages of various common evaluation techniques. We propose an integrated semi-quantitative and quantitative evaluation method designed to comprehensively and accurately assess the effectiveness of station automatic control systems. For the semi-quantitative framework, we first establish a specific indicator system for the control system and employ the Analytic Hierarchy Process (AHP) to determine indicator weights tailored to different station types, achieving a scientific quantification of evaluation criteria. Additionally, we utilize quantitative calculation methods, specifically reliability and availability analyses, to evaluate the station’s automatic control system. Differential research is conducted to customize the evaluation based on the distinct process characteristics of various gas field stations. Differential design calculations and analyses were performed for a single station, improving the economy and adaptability of the automatic control system design. The proposed comprehensive evaluation method ensures the safe and stable operation of control system designs and provides a new approach for the automation and intelligent transformation of gas field surface engineering.

18 August 2025 in Information
Verified
Journal Article
Open access
PDF file
TXTaiwu Taiwu xia
Taiwu Taiwu xia
FWFeng Wang
Feng Wang
ZHZhan Huang
Zhan Huang
WZWei Zhang
Wei Zhang
GCGangping Chen
Gangping Chen
CLCui Liu
Cui Liu
The current digital delivery of surface engineering in oil and gas fields faces challenges such as difficulty in integrating multiple heterogeneous data sources, low efficiency in quality reviews, and a lack of unified evaluation standards, which seriously restrict the implementation of intelligent operation and maintenance. Based on this, this study constructs multi-dimensional control rules for data quality covering the entire lifecycle. Based on the characteristics of structured, semi-structured, and unstructured data, five-dimensional review criteria and quantification methods for normative, integrity, consistency, accuracy, and timeliness were developed. At the same time, by integrating the analytic hierarchy process (AHP) and the entropy weight method (EWM), a combined subjective and objective weight evaluation model was established to achieve scientific quantitative calculation of quality indicators. Verification with a project by Southwest Oil and Gas Field shows that the system effectively achieves quantifiable diagnosis and traceability of engineering data quality, revealing the differentiation characteristics of different data types in the quality dimension. The research results provide core methodological support for the establishment of an integrated data governance paradigm of “collection—review—operation and maintenance” in oil and gas fields, facilitating the implementation of intelligent operation and maintenance.

30 October 2026 in Modelling
Verified
Journal Article
Open access
PDF file
WZWei Zhang
Wei Zhang
FWFeng Wang
Feng Wang
YSYuwei Sun
Yuwei Sun
PLPengzheng Lei
Pengzheng Lei
GCGangping Chen
Gangping Chen
JZJun Zhou
Jun Zhou
Radiographs of girth welds in oil and gas pipelines exhibit substantial variations in imaging conditions, while small defects are prone to missed detection and visually similar defect classes remain difficult to distinguish. Existing studies often focus on a single detection or classification task and rarely address the integrated multistage processing of full radiographs. To address these issues, this study proposes a multistage intelligent defect detection method consisting of weld region localization, defect instance detection, and defect type classification. YOLOv10 (You Only Look Once, version 10), an end-to-end object detection model, is first employed to localize and extract the weld region from each radiograph. Overlapping image slicing, bounding box fusion, and interference region filtering are then incorporated to improve defect localization, particularly for small defects and those with low contrast. To enhance the classification of highly similar defect classes, knowledge distillation with adaptive class temperature (KD-ACT) is introduced to dynamically adjust the distillation temperature according to the classification difficulty of each class. A dataset comprising 4396 digitized X-ray radiographs collected from engineering practice was used for multistage evaluation, with annotation review and result verification performed by expert radiographic interpreters. The proposed method achieved a weld region detection rate of 99.67%, a defect detection rate of 98.6%, and end-to-end recall of 91.8% across nine defect classes.