A discrete event simulation-based methodology for building a digital twin of patient pathways in the hospital for near real-time monitoring and predictive simulation

Background: Discrete Event Simulation (DES) is one of the many tools and methods used in the analysis and improvement of healthcare services. Indeed, DES provides perhaps the most powerful and intuitive method for analyzing, evaluating, and improving complex healthcare systems. This paper highlights the process of developing a Digital Twin (DT) framework based on online DES to run the DES model in parallel with the real world in real-time. Methods: This paper suggests a new methodology that uses DES connected to the Internet of Things (IoT) devices to build a DT platform of patient pathways in a hospital for near real-time monitoring and predictive simulation. An experimental platform that mimics the behavior of a hospital has been used to validate this methodology. Results: The application of the proposed methodology allowed us to test the monitoring functionality in the DT. Therefore, we noticed that the DT behaves exactly as the emulator does in near real-time, we also tested the prediction functionality and we noticed that the DT provides us with a proactive overview for the near future of the patient pathways. The predictive functionality of this DT must be improved depending on the various reasons mentioned in this article. Conclusions: This paper presents a new methodology called HospiT'Win that uses DES and IoT devices to develop a DT of patient pathways in hospitals. This DT consists of two real-time models, a DT for Monitoring (DTM) and a DT for Predicting (DTP). An experimental platform with an emulator of a real hospital was used to validate this methodology before connecting to the real hospital. In the DTP, "dynamic" empirical distributions were used to perform a predictive simulation for the near future. In future research, some additional features and machine learning algorithms will be used to improve the proposed DT models.

Artificial intelligence in the digital twins: State of the art, challenges, and future research topics

Advanced computer technologies such as big data, Artificial Intelligence (AI), cloud computing, digital twins, and edge computing have been applied in various fields as digitalization has progressed. To study the status of the application of digital twins in the combination with AI, this paper classifies the applications and prospects of AI in digital twins by studying the research results of the current published literature. We discuss the application status of digital twins in the four areas of aerospace, intelligent manufacturing in production workshops, unmanned vehicles, and smart city transportation, and we review the current challenges and topics that need to be looked forward to in the future. It was found that the integration of digital twins and AI has significant effects in aerospace flight detection simulation, failure warning, aircraft assembly, and even unmanned flight. In the virtual simulation test of automobile autonomous driving, it can save 80% of the time and cost, and the same road conditions reduce the parameter scale of the actual vehicle dynamics model and greatly improve the test accuracy. In the intelligent manufacturing of production workshops, the establishment of a virtual workplace environment can provide timely fault warning, extend the service life of the equipment, and ensure the overall workshop operational safety. In smart city traffic, the real road environment is simulated, and traffic accidents are restored, so that the traffic situation is clear and efficient, and urban traffic management can be carried out quickly and accurately. Finally, we looked forward to the future of digital twins and AI, hoping to provide a reference for future research in related fields.

The modelling and application of cross-scale human behavior in realizing the shop-floor digital twin

The digital twin shop-floor has received much attention from the manufacturing industry as it is an important way to upgrade the shop-floor digitally and intelligently. As a key part of the shop-floor, humans' high autonomy and uncertainty leads to the difficulty in digital twin modeling of human behavior. Therefore, the modeling system for cross-scale human behavior in digital twin shop-floors was developed, powered by the data fusion of macro-behavior and micro-behavior virtual models. Shop-floor human macro-behavior mainly refers to the role of the human and their real-time position. Shop-floor micro-behavior mainly refers to real-time human limb posture and production behavior at their workstation. In this study, we reviewed and summarized a set of theoretical systems for cross-scale human behavior modeling in digital twin shop-floors. Based on this theoretical system, we then reviewed modeling theory and technology from macro-behavior and micro-behavior aspects to analyze the research status of shop-floor human behavior modeling. Lastly, we discuss and offer opinion on the application of cross-scale human behavior modeling in digital twin shop-floors. Cross-scale human behavior modeling is the key for realizing closed-loop interactive drive of human behavior in digital twin shop-floors.

TAD-Net: An approach for real-time action detection based on temporal convolution network and graph convolution network in digital twin shop-floor

Background: Intelligent monitoring of human action in production is an important step to help standardize production processes and construct a digital twin shop-floor rapidly. Human action has a significant impact on the production safety and efficiency of a shop-floor, however, because of the high individual initiative of humans, it is difficult to realize real-time action detection in a digital twin shop-floor. Methods: We proposed a real-time detection approach for shop-floor production action. This approach used the sequence data of continuous human skeleton joints sequences as the input. We then reconstructed the Joint Classification-Regression Recurrent Neural Networks (JCR-RNN) based on Temporal Convolution Network (TCN) and Graph Convolution Network (GCN). We called this approach the Temporal Action Detection Net (TAD-Net), which realized real-time shop-floor production action detection. Results: The results of the verification experiment showed that our approach has achieved a high temporal positioning score, recognition speed, and accuracy when applied to the existing Online Action Detection (OAD) dataset and the Nanjing University of Science and Technology 3 Dimensions (NJUST3D) dataset. TAD-Net can meet the actual needs of the digital twin shop-floor. Conclusions: Our method has higher recognition accuracy, temporal positioning accuracy, and faster running speed than other mainstream network models, it can better meet actual application requirements, and has important research value and practical significance for standardizing shop-floor production processes, reducing production security risks, and contributing to the understanding of real-time production action.

Digital twin-driven complexity management in intelligent manufacturing

Complexity management is one of the most crucial and challenging issues in manufacturing. As an emerging technology, digital twin provides an innovative approach to manage complexity in a more autonomous, analytical and comprehensive manner. This paper proposes an innovative framework of digital twin-driven complexity management in intelligent manufacturing. The framework will cover three sources of manufacturing complexity, including product design, production lines and supply chains. Digital twin provides three services to manage complexity: (1) real-time monitors and data collections; (2) identifications, diagnoses and predictions of manufacturing complexity; (3) fortification of human-machine interaction. A case study of airplane manufacturing is presented to illustrate the proposed framework.

Artificial cognitive systems: the next generation of the digital twin. An opinion.

The digital twin is often presented as the solution to Industry 4.0 and, while there are many areas where this may be the case, there is a risk that a reliance on existing machine learning methods will not be able to deliver the high level cognitive capabilities such as adaptability, cause and effect, and planning that Industry 4.0 requires. As the limitations of machine learning are beginning to be understood, the paradigm of strong artificial intelligence is emerging. The field of artificial cognitive systems is part of the strong artificial intelligence paradigm and is aimed at generating computational systems capable of mimicking biological systems in learning and interacting with the world. This paper presents an argument that artificial cognitive systems offer solutions to the higher level cognitive challenges of Industry 4.0 and that digital twin research should be driven in the direction of artificial cognition accordingly. This argument is based on the inherent similarities between the digital twin and artificial cognitive systems, and the insights that can already be seen in aligning the two approaches.

Towards a shape-performance integrated digital twin for lumbar spine analysis

Background: With significant advancement and demand for digital transformation, the digital twin has been gaining increasing attention as it is capable of establishing real-time mapping between physical space and virtual space. In this work, a shape-performance integrated digital twin solution is presented to predict the real-time biomechanics of the lumbar spine during human movement. Methods: A finite element model (FEM) of the lumbar spine was firstly developed using computed tomography (CT) and constrained by the body movement which was calculated by the inverse kinematics algorithm. The Gaussian process regression was utilized to train the predicted results and create the digital twin of the lumbar spine in real-time. Finally, a three-dimensional virtual reality system was developed using Unity3D to display and record the real-time biomechanics performance of the lumbar spine during body movement. Results: The evaluation results presented an agreement (R-squared > 0.8) between the real-time prediction from digital twin and offline FEM prediction. Conclusions: This approach provides an effective method of real-time planning and warning in spine rehabilitation.

Digital twins for well-being: an overview

Digital twin (DT) has gained success in various industries, and it is now getting attention in the healthcare industry in the form of well-being digital twin (WDT). In this paper, we present an overview of WDT to understand its potential scope, architecture and impact. We then discuss the definition and the benefits of WDT. After that, we present the evolution of DT frameworks. Subsequently we discuss the challenges, the different types, the drawbacks, and potential application areas of WDT. Finally we present the requirements for a WDT framework extracted from the literature.

Mechanical movement data acquisition method based on the multilayer neural networks and machine vision in a digital twin environment

Background: Digital twin requires virtual reality mapping and optimization iteration between physical devices and virtual models. The mechanical movement data collection of physical equipment is essential for the implementation of accurate virtual and physical synchronization in a digital twin environment. However, the traditional approach relying on PLC (programmable logic control) fails to collect various mechanical motion state data. Additionally, few investigations have used machine visions for the virtual and physical synchronization of equipment. Thus, this paper presents a mechanical movement data acquisition method based on multilayer neural networks and machine vision. Methods: Firstly, various visual marks with different colors and shapes are designed for marking physical devices. Secondly, a recognition method based on the Hough transform and histogram feature is proposed to realize the recognition of shape and color features respectively. Then, the multilayer neural network model is introduced in the visual mark location. The neural network is trained by the dropout algorithm to realize the tracking and location of the visual mark. To test the proposed method, 1000 samples were selected. Results: The experiment results shows that when the size of the visual mark is larger than 6mm, the recognition success rate of the recognition algorithm can reach more than 95%. In the actual operation environment with multiple cameras, the identification points can be located more accurately. Moreover, the camera calibration process of binocular and multi-eye vision can be simplified by the multilayer neural networks. Conclusions: This study proposes an effective method in the collection of mechanical motion data of physical equipment in a digital twin environment. Further studies are needed to perceive posture and shape data of physical entities under the multi-camera redundant shooting.

A digital twin network solution for end-to-end network service level agreement (SLA) assurance

With the gradual development of the 5G industry network and applications, each industry application has various network performance requirements, while customers hope to upgrade their industrial structures by leveraging 5G technologies. The guarantee of service level agreement (SLA) requirements is becoming more and more important, especially SLA performance indicators, such as delay, jitter, bandwidth, etc. For network operators to fulfill customer’s requirements, emerging network technologies such as time-sensitive networking (TSN), edge computing (EC) and network slicing are introduced into the mobile network to improve network performance, which increase the complexity of the network operation and maintenance (O&M), as well as the network cost. As a result, operators urgently need new solutions to achieve low-cost and high-efficiency network SLA management. In this paper, a digital twin network (DTN) solution is innovatively proposed to achieve the mapping and full lifecycle management of the end-to-end physical network. All the network operation policies such as configuration and modification can be generated and verified inside the digital twin network first to make sure that the SLA requirements can be fulfilled without affecting the related network environment and the performance of the other network services, making network operation and maintenance more effective and accurate.