Article
Chemistry, Analytical
Sriraamshanjiev Natarajan, Mohanraj Thangamuthu, Sakthivel Gnanasekaran, Jegadeeshwaran Rakkiyannan
Summary: A technique based on Digital Twins is proposed to achieve accurate monitoring and prediction of tool conditions. By collecting vibration and sound signal data from physical systems, such as milling machines, and training the data with machine learning algorithms, the tool condition can be accurately monitored and predicted.
Article
Energy & Fuels
Mingfei Hu, Xinyi Hu, Zhenzhou Deng, Bing Tu
Summary: In this paper, a kernel extreme learning machine (KELM) based on an adaptive variation sparrow search algorithm (AVSSA) is proposed for fault detection and diagnosis in large industrial systems. The performance of the fault classifier is improved by optimizing the dataset and the network hyperparameters, and the effectiveness of the proposed method is verified using multidimensional diagnostic metrics in a chemical process.
Article
Multidisciplinary Sciences
Kejia Zhuang, Zhenchuan Shi, Yaobing Sun, Zhongmei Gao, Lei Wang
Summary: This study presents a method based on Digital Twin (DT) to achieve high precision in monitoring and predicting tool wear. The framework of the cutting tool system DT is designed, key enabling technologies are elaborated, and a case study of the turning process is presented to verify the feasibility of the framework.
Article
Engineering, Industrial
Zexuan Zhu, Xiaolin Xi, Xun Xu, Yonglin Cai
Summary: This paper introduces a Digital Twin-driven thin-walled part manufacturing framework, which utilizes Digital Twin technology to improve the efficiency of thin-walled parts machining and manage trial machining processes in real-time through interactive digital data.
JOURNAL OF MANUFACTURING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Ravitej Bhagavathi, D. Kwame Minde Kufoalor, Agus Hasan
Summary: This paper presents a digital twin-driven fault diagnosis approach for autonomous surface vehicles. An adaptive extended Kalman filter algorithm is proposed to estimate the magnitude of the faults by calculating the parameter estimation gains directly from the sensor systems. The algorithm is tested in an autonomous surface vehicle called the Otter and is able to accurately detect and estimate actuator faults.
Article
Business
Pratik Maheshwari, Sachin Kamble, Amine Belhadi, Mani Venkatesh, Mohammad Zoynul Abedin
Summary: In this study, the digital twin approach was applied to optimize the production flexibility and enhance the level of digitization in a food processing company. The results showed that the digital twin model improves supply chain productivity by optimizing various indicators such as production time, data redundancy, optimal scheduling plan, overall operations effectiveness, and capacity utilization. Moreover, implementing the procurement, production, and distribution strategies (PPDs) led to significant benefits, including improved equipment utilization and reduced backlog, ultimately streamlining operations and improving efficiency.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Automation & Control Systems
Ruijuan Xue, Peisen Zhang, Zuguang Huang, Jinjiang Wang
Summary: This paper proposes a digital twin-driven fault diagnosis method for CNC machine tools, which establishes and validates a digital twin model and uses model data fusion method and decision tree algorithm to achieve fault diagnosis. Experimental results show that the proposed method can effectively diagnose the stiffness deterioration fault of CNC machine tools.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)
Article
Engineering, Industrial
Sheng Li, Qiubo Jiang, Yadong Xu, Ke Feng, Yulin Wang, Beibei Sun, Xiaoan Yan, Xin Sheng, Ke Zhang, Qing Ni
Summary: This paper introduces a digital twin approach to generate synthetic data for enhancing the quality and availability of training data in deep learning methods. The proposed method overcomes the challenge of acquiring all potential failure mode samples in specific industrial settings and achieves improved diagnostic performance.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Computer Science, Software Engineering
Christopher Reinartz, Thomas T. Enevoldsen
Summary: pyTEP is an open-source simulation API for the Tennessee Eastman process in Python. It simplifies the setup of complex simulation scenarios and provides the option of interactive simulation. Through the pyTEP API, users can easily configure and operate simulations without needing to understand the underlying mechanics.
Article
Engineering, Industrial
Shiau-Cheng Shiu, Ke-Er Tang, Chun -Wei Liu
Summary: Traditional centering method for glass lenses cannot meet the high precision requirements of materials with high hardness and low ductility, resulting in common defects such as circularity errors, edge cracks, and optical axis errors. Manual inspection is needed to identify these defects, leading to high scrap rates and production costs. To address this issue, a digital twin-driven centering process optimization system for high-precision glass lenses was developed, which integrates an omnidirectional information model, a virtual process model, and a design of experiment-based genetic algorithm. The proposed system reduces process development time from 4 hours to 1 hour, decreases inspection from full to 10% sampling, and improves yield rate by 20% according to real-world production line tests.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Lilan Liu, Xiangyu Zhang, Xiang Wan, Shuaichang Zhou, Zenggui Gao
Summary: A digital twin-driven surface roughness prediction and process parameter adaptive optimization method is proposed to address the inconsistency between quality and efficiency in the machining process. The method combines real-time monitoring, accurate prediction, and optimization decision-making, effectively optimizing process parameters in intelligent manufacturing.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Automation & Control Systems
Jianguo Duan, Xiangrong Gong, Qinglei Zhang, Jiyun Qin
Summary: With the development of intelligent factories, collaborative robotic arms have become critical equipment for flexible production lines. Digital twin is the best way to achieve intelligent and digitized collaborative robotic arms. This paper presents a collaborative robotic arm monitoring system based on digital twin and proposes a six-dimensional system architecture. Key technologies such as equipment twin modeling, multi-source heterogeneous data acquisition, and digital twin-driven real-time monitoring are studied. The system effectively integrates models and data to realize real-time monitoring of the assembly process and support intelligent decision-making. The effectiveness and feasibility of the system are verified through application testing on UR5 and UR10 collaborative robotic arm assembly test benches.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Computer Science, Information Systems
Weifeng Ge, Rui He, Qibing Wu, Baoping Cai, Chao Yang, Fei Zhang
Summary: The digital twin driven fault diagnosis method shows good performance in subsea control systems by effectively improving diagnostic performance.
Article
Computer Science, Artificial Intelligence
Xin Tong, Qiang Liu, Yinuo Zhou, Pengpeng Sun
Summary: This study introduces digital twin technology into cutting force adaptive control to improve the robustness and efficiency of the system. By indirectly measuring cutting force and identifying unknown parameters in the estimation model, a virtual machining system model is established. Based on the integrated digital twin technology, the machining state is predicted and an adaptive control algorithm is introduced for cutting force constraint control.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Computer Science, Interdisciplinary Applications
Ildar Lomov, Mark Lyubimov, Ilya Makarov, Leonid E. Zhukov
Summary: This paper investigates advanced approaches using deep learning methods in the field of fault detection in chemical processes, showing that with the recent advent of deep learning neural network methods and abundance of available sensor data, it became possible to develop advanced approaches to early fault detection and prediction that do not require feature engineering and provide more accurate and timely results. The proposed temporal CNN1D2D architecture achieved overall better performance on the dataset than any referenced method, and the use of Generative Adversarial Network GAN was suggested to extend and enrich data used in training.
JOURNAL OF INDUSTRIAL INFORMATION INTEGRATION
(2021)
Article
Engineering, Chemical
Xinhong Li, Guoming Chen, Shengyu Jiang, Rui He, Changhang Xu, Hongwei Zhu
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES
(2018)
Article
Engineering, Environmental
Rui He, Xinhong Li, Guoming Chen, Yanchun Wang, Shengyu Jiang, Chenxiao Zhi
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2018)
Article
Engineering, Industrial
Rui He, Yiyang Dai, Jiachen Lu, Chuanlin Mou
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2018)
Article
Engineering, Chemical
Rui He, Guoming Chen, Shufeng Sun, Che Dong, Shengyu Jiang
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
(2020)
Article
Automation & Control Systems
Rui He, Guoming Chen, Xiaoyu Shen, Shengyu Jiang, Guoxing Chen
Article
Computer Science, Artificial Intelligence
Rui He, Xinhong Li, Guoming Chen, Guoxing Chen, Yiwei Liu
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Engineering, Environmental
Jingyu Zhu, Guoming Chen, Faisal Khan, Ming Yang, Xinhong Li, Xiangkun Meng, Rui He
Summary: The study introduces a sequence-based dynamic reliability assessment method for the MPD system, which focuses on dynamic modeling of sequential operations by integrating GO-FLOW and dynamic Bayesian Network (DBN).
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Engineering, Chemical
Shengyu Jiang, Guoming Chen, Yuan Zhu, Xinhong Li, Xiaoyu Shen, Rui He
Summary: A real-time risk assessment model is proposed for analyzing release accidents, combining Fault Tree-Event Tree, Bayesian network, and Computational Fluid Dynamics to describe and handle the risk of escalation into combustion or explosion. This methodology can be used for facility layout optimization and ignition sources control based on testing with a case of release accidents on a production platform.
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES
(2021)
Article
Engineering, Mechanical
Rui He, Zhigang Tian, Ming J. Zuo
Summary: This paper proposes a semi-supervised generative adversarial network (GAN) regression model for RUL predictions, considering both failure and suspension histories. The method can improve model generalization by matching statistical information for training, providing credibility in cases of scarce failure data.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
