scispace - formally typeset
Search or ask a question
Author

Yue Song

Bio: Yue Song is an academic researcher from Beihang University. The author has contributed to research in topics: Computer science & Automotive engineering. The author has an hindex of 2, co-authored 6 publications receiving 31 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: The results of comparative experiments prove that the Digital Twin approach based on nonparametric Bayesian Network has a good model self-learning ability, which improves the accuracy of health monitoring.

59 citations

Journal ArticleDOI
TL;DR: This paper breaks traditional procedures and presents a DT-based optimization strategy on the consideration of both machining efficiency and aerodynamic performance, as well as builds a reified 5-dimensional DT model.

51 citations

Proceedings ArticleDOI
Yue Song1, Jinsong Yu1, Diyin Tang1, Danyang Han1, Sen Wang 
15 Oct 2020
TL;DR: A novel anomaly detection method based on Generative Adversarial Networks for telemetry data anomaly detection that captures the latent representation amongst multi-dimensional time series, and proposes a novel anomaly score called GDScore which comprehensively considers the reconstruction error of the generator and the output of the discriminator.
Abstract: The telemetry data of spacecraft is an ultra-high dimensional time series used to indicate on-orbit operation status, and anomaly detection can effectively ensure safety and reliability. Aiming at the characteristics and complex correlation of high dimensional telemetry data, this paper proposes a novel anomaly detection method based on Generative Adversarial Networks (GAN) for telemetry data anomaly detection. Instead of treating each variable independently, our proposed method captures the latent representation amongst multi-dimensional time series. For normal data, the GAN-based anomaly detection method can obtain a reconstructed time series similar to the original time series, learning the probability distribution model of normal data. For abnormal data, the reconstructed time series deviates greatly from the original time series. In the GAN framework, we use Long Short-Term Memory (LSTM) as the network structure of generator for time series reconstruction and discriminator for calculating the probability of being the real time series, which can learn the temporal features of telemetry data. We also propose a novel anomaly score called GDScore, which comprehensively considers the reconstruction error of the generator and the output of the discriminator. We conduct experiments with two telemetry datasets, which verifies that our proposed GAN-based anomaly detection method can effectively detect outliers.

5 citations

Journal ArticleDOI
TL;DR: In this article , a comprehensive review of the development of the tractor electro-hydraulic hitch system by investigating the research methods, technical characteristics and emerging trends in three key aspects that include the tillage depth adjustment method, the tilage depth control algorithm and the core components of the EH system is presented.
Abstract: A tractor electro-hydraulic hitch system is considered one of the most important systems that play a strategic role in the power transmission and operation depth control of a tractor’s field operation. Its performance directly affects the operation quality of the whole work unit of the tractor. Furthermore, a tractor electro-hydraulic hitch system has gained the interest of many in the agricultural machinery sector because of its stable performance, high production efficiency, good operation quality and its low energy consumption. To fully benefit from the potential of the tractor electro-hydraulic hitch system, it is significant to understand and address the problems and challenges associated with it. This study, therefore, aims to contribute to the development of the tractor electro-hydraulic hitch system by investigating the research methods, technical characteristics and emerging trends in three key aspects that include the tillage depth adjustment method, the tillage depth control algorithm and the core components of the electro-hydraulic hitch system. The characteristics and applicable conditions of the different tillage depth adjustment methods of the electro-hydraulic hitch system were summarized. The realization methods and the control characteristics of the different algorithms were elaborated and discussed for both the PID control algorithm and the intelligent control algorithm. The working characteristics of the core components of the electro-hydraulic hitch system were analyzed based on the hydraulic control valves and sensing elements. The results have shown that the multi-parameter tillage depth adjustment method met the operation quality standard while taking the engine load stability and traction efficiency into account, and it has a greater research significance and value. The working quality can be improved effectively by introducing the intelligent algorithm. In addition, the study of smart valves with built-in sensing elements and how to improve the anti-interference ability of sensing elements, are the aspects that requires further consideration. Aiming to improve the working quality and reduce energy consumption, further research into the tractor electro-hydraulic hitch system is necessary. The results of this comprehensive review provide a reference for the intelligent operation of tractors under the precision agriculture.

4 citations

Journal ArticleDOI
Yu Zhou1, Yue Song1, Tong Xing1, Yan Wang1, Qi Zhang1, Longtao Shao1, Farong Du1, Shuiting Ding1 
TL;DR: A novel approach for automatic extraction of SSL and MS from a RCI 3D model or workpiece is presented and can interactively construct a parameterized RCI platform, which inputs and outputs the presented RCI parameters to existing CFD and CAM systems rapidly and effectively.
Abstract: Radial compressor impeller (RCI) manufacturing is moving toward to improve competitiveness through smart manufacturing. Although current CAD (computer-aided design) and CAM (computer-aided manufacturing) techniques provide multiple tools to construct and optimize complicated geometries of RCI, an adjustment of blade shape often leads to nonparametric geometric reconstruction. As the key geometric elements in RCI, set of streamlines (SSL) and meridional section (MS) play vital roles in modeling and aerodynamic optimization. This paper presents a novel approach for automatic extraction of SSL and MS from a RCI 3D model or workpiece. Furthermore, the presented method can interactively construct a parameterized RCI platform, which inputs and outputs the presented RCI parameters to existing CFD and CAM systems rapidly and effectively. An integrated acquisition is employed. The straight generatrix vectors (SGVs) are identified and their boundary points are defined. After the uniform partition of SGV segments, the sequent equant points along spanwise direction are packaged to fit SSL. To manipulate the smoothness and approximation, a double-fitting method is performed to generate SSL. A parameterized system for extracting SSL and modeling RCI is developed. The validities of the presented method in different systems are demonstrated. Furthermore, the presented method breaks conventional RCI development procedure and shortens RCI product cycles, which is desirable and significative for integrated RCI design and manufacturing.

4 citations


Cited by
More filters
Journal ArticleDOI
23 Sep 2021-Sensors
TL;DR: In this paper, a survey comprehensively reviews over 300 manuscripts on AI-driven DT technologies of Industry 4.0 used over the past five years and summarizes their general developments and the current state of AI-integration in the fields of smart manufacturing and advanced robotics.
Abstract: Digital twin (DT) and artificial intelligence (AI) technologies have grown rapidly in recent years and are considered by both academia and industry to be key enablers for Industry 4.0. As a digital replica of a physical entity, the basis of DT is the infrastructure and data, the core is the algorithm and model, and the application is the software and service. The grounding of DT and AI in industrial sectors is even more dependent on the systematic and in-depth integration of domain-specific expertise. This survey comprehensively reviews over 300 manuscripts on AI-driven DT technologies of Industry 4.0 used over the past five years and summarizes their general developments and the current state of AI-integration in the fields of smart manufacturing and advanced robotics. These cover conventional sophisticated metal machining and industrial automation as well as emerging techniques, such as 3D printing and human–robot interaction/cooperation. Furthermore, advantages of AI-driven DTs in the context of sustainable development are elaborated. Practical challenges and development prospects of AI-driven DTs are discussed with a respective focus on different levels. A route for AI-integration in multiscale/fidelity DTs with multiscale/fidelity data sources in Industry 4.0 is outlined.

54 citations

Journal ArticleDOI
TL;DR: A solution to existing challenging issues is proposed by introducing the digital twin (DT) technology into the OWT support structures and this new DT framework will enable real-time monitoring, fault diagnosis and operation optimization of the O WT support structures, which may provide a useful application prospect in the reliability analysis in the future.

51 citations

Journal ArticleDOI
TL;DR: Shortening product development cycles and fully customisable products pose major challenges for production systems as mentioned in this paper, and these not only have to cope with an increased product diversity but also enable h.....
Abstract: Shortening product development cycles and fully customisable products pose major challenges for production systems. These not only have to cope with an increased product diversity but also enable h...

44 citations

Journal ArticleDOI
TL;DR: A multi-level cloud computing enabled digital twin system for the real-time monitor, decision and control of a synchronized production logistics system and the PLS optimization model of production and storage is presented with an industrial case, and the effectiveness is demonstrated and analyzed.

41 citations

Journal ArticleDOI
Xin Yang1, Yan Ran1, Genbao Zhang1, Hongwei Wang1, Zongyi Mu1, Shengguang Zhi 
TL;DR: A hybrid approach framework driven by digital twin technology (DT), to predict performance degradation of transmission system using the complementary advantages offered by the fusion of these methods to bridge the link between data-driven prediction and model-based prediction.
Abstract: Precision performance prediction of transmission system is considered as a key technology to modern equipment health management. Given the importance of maintaining a transmission system's precision, this paper presents a hybrid approach framework driven by digital twin technology (DT), to predict performance degradation. Firstly, a DT model based on meta-action theory is established, and real-time monitoring and digital simulation, driven by DT data, is realized in order to analyze the precision of the transmission units in machine tools. Secondly, the wear of gear in transmission unit is studied through Achard wear theory, which considered the comprehensive influence of gear load and speed on surface wear of the gear pair tooth, based on the model driving method. The performance degradation of the transmission unit is obtained by using the RBF neural network algorithm based on the data-driven method to extrapolate the wear data to the field-measurable precision index value. In addition, the hybrid predictive approach of the performance degradation model through the particle filter algorithm is built, and the real-time data is used to update the current state estimation to improve the prediction accuracy. By combining the mechanism of the physical degradation processes with the real-time and historical data and turning them into a cooperative architecture, this prediction method uses the complementary advantages offered by the fusion of these methods to bridge the link between data-driven prediction and model-based prediction. Finally, the method has been successfully applied to the precision prediction of the transmission unit in CNCMT turntable, and it is compared with the single prediction method to verify the effectiveness and feasibility.

37 citations