网络对抗训练混合虚拟化平台设计研究

讨论了虚拟化技术实现原理及其在网络对抗教学中的应用上,分析了各类虚拟化技术的优缺点和构建网络对抗训练环境存在的问题。提出了一种混合虚拟化平台设计,该平台利用Libvirt虚拟化的应用程序编程接口（API）调用两种虚拟化技术同时运行在同一物理主机上。并详细叙述了混合虚拟化平台的实现过程和方法,并在多个虚拟机内同时运行测试基准,分析其可扩展性。多种虚拟化技术在同一物理机上的混合,实现了复杂实验环境的创建,对构建大规模的网络实验平台具有一定的参考价值。     

New Paradigm of Data-Driven Smart Customisation through Digital Twin

Big data is one of the most important resources for the promotion of smart customisation. With access to data from multiple sources, manufacturers can provide on-demand and customised products. However, existing research of smart customisation has focused on data generated from the physical world, not virtual models. As physical data is constrained by what has already occurred, it is limited in the identification of new areas to improve customer satisfaction. A new technology called digital twin aims to achieve this integration of physical and virtual entities. Incorporation of digital twin into the paradigm of existing data-driven smart customisation will make the process more responsive, adaptable and predictive. This paper presents a new framework of data-driven smart customisation augmented by digital twin. The new framework aims to facilitate improved collaboration of all stakeholders in the customisation process. A case study of the elevator industry illustrates the efficacy of the proposed framework.     

Digital Twin-driven machining process for thin-walled part manufacturing

Thin-walled parts are widely used in the aerospace, shipbuilding, and automotive industry, but due to its unique structure and high accuracy requirements, which leads to an increase in scrapped parts, high cost in production, and a more extended period in the trial machining process. However, to adapt to fast production cycles and increase the efficiency of thin-walled parts machining, this paper presents a Digital Twin-driven thin-walled part manufacturing framework to allow the machine operator to manage the product changes, make the start-up phases faster and more accurate. The framework has three parts: preparation, machining, and measurement, driven by Digital Twin technologies in detail. By establishing and updating the workpiece Digital Twin under a different status, various manufacturing information and data can be integrated and available to machine operators and other Digital Twins. It can serve as a guideline for establishing the machine tool and workpiece Digital Twin and integrating them into the machining process. It provides the machine operator opportunities to interact with both the physical manufacturing process and its digital data in real-time. The digital representation of the physical process can support them to manage the trial machining from different aspects. In addition, a demonstrative case study is presented to explain the implementation of this framework in a real manufacturing environment.     

LearningADD: Machine learning based acoustic defect detection in factory automation

Defect inspection of glass bottles in the beverage industrial is of significance to prevent unexpected losses caused by the damage of bottles during manufacturing and transporting. The commonly used manual methods suffer from inefficiency, excessive space consumption, and beverage wastes after filling. To replace the manual operations in the pre-filling detection with improved efficiency and reduced costs, this paper proposes a machine learning based Acoustic Defect Detection (LearningADD) system. Moreover, to realize scalable deployment on edge and cloud computing platforms, deployment strategies especially partitioning and allocation of functionalities need to be compared and optimized under realistic constraints such as latency, complexity, and capacity of the platforms. In particular, to distinguish the defects in glass bottles efficiently, the improved Hilbert-Huang transform (HHT) is employed to extend the extracted feature sets, and then Shuffled Frog Leaping Algorithm (SFLA) based feature selection is applied to optimize the feature sets. Five deployment strategies are quantitatively compared to optimize real-time performances based on the constraints measured from a real edge and cloud environment. The LearningADD algorithms are validated by the datasets from a real-life beverage factory, and the F-measure of the system reaches 98.48 %. The proposed deployment strategies are verified by experiments on private cloud platforms, which shows that the Distributed Heavy Edge deployment outperforms other strategies, benefited from the parallel computing and edge computing, where the Defect Detection Time for one bottle is less than 2.061 s in 99 % probability.     

Intelligent tool wear monitoring based on parallel residual and stacked bidirectional long short-term memory network

Effective tool wear monitoring (TWM) is essential for accurately assessing the degree of tool wear and for timely preventive maintenance. Existing data-driven monitoring methods mainly rely on complex feature engineering, which reduces the monitoring efficiency. This paper proposes a novel TWM model based on a parallel residual and stacked bidirectional long short-term memory (PRes–SBiLSTM) network. First, a parallel residual network (PResNet) is used to extract the multi-scale local features of sensor signals adaptively. Subsequently, a stacked bidirectional long short-term memory (SBiLSTM) network is used to obtain the time-series features related to the tool wear characteristics. Finally, the predicted tool wear value is outputted through a fully connected network. A smoothing correction method is applied to improve the prediction accuracy. The proposed model is experimentally verified to have a high prediction accuracy without sacrificing its generalization ability. A TWM system framework based on the PRes–SBiLSTM network is proposed, which has a certain reference value for TWM in actual industrial environments.     

Framework and deployment of a cloud-based advanced planning and scheduling system

Many small and medium-sized manufacturing enterprises (SMEs) have already implemented enterprise resource planning (ERP) and manufacturing execution system (MES) and began to start the journey of cloud manufacturing; however, the high cost of hardware and software investment, implementation, and maintenance usually hinder SMEs from adopting an advanced planning and scheduling (APS) system. This paper aims to develop a cloud-based APS (C-APS) system framework, the service structure, and approach of deploying the C-APS system in a public cloud infrastructure platform and service provider or hybrid cloud platform. The package diagram is proposed for building the C-APS system's virtual factory model to improve modeling efficiency and data stability. The C-APS system is a cloud-based and object-oriented software; its simulation-based scheduling engine can generate the significant production and operations schedule, and has the characteristics of on-demand self-service, quickly expanding and adjusting to the virtual plant model. The C-APS system's application in a leading automotive part assembly company's printed circuit board production scheduling shows that the input planning data model is easy to maintain. The scheduling quality is high; the computing time is short and acceptable for practical application.     

Accurate positioning of a drilling and riveting cell for aircraft assembly

Modern aircraft assembly demands assembly cells or machines with higher machining efficiency and accuracy. Thus, a dual-machine drilling and riveting cell is developed in this paper. We firstly discuss its physical design, as well as the automatic drilling and riveting process. With the automatic drilling and riveting cell, drilling and riveting production line of aircraft panels can be expected. The frame chain of the drilling and riveting cell is constructed to link the assembly cell to its task space, which is the kinematics base. System calibrations, including task space calibration, the sensor calibration of an orientation alignment unit, the floating calibration of the implicit hand-eye relationship, are explored. For high positioning accuracy, a multi-sensor servoing method is proposed for cell positioning. An orientation-based laser servoing strategy, which uses the feedback of the orientation errors measured by laser displacement sensors, is used to align drilling direction and camera shooting direction. Besides, A single-camera-based visual servoing is applied to align the tool center point (TCP) to reference holes, to obtain their coordinates for drilling position modification. Experiments of multi-sensor servoing for cell positioning are performed on an automatic drilling and riveting machine developed for the panel assembly of an aircraft in China. With the cell positioning method, the automatic drilling and riveting cell can approximately achieve an accuracy of 0.05 mm, which can adequately fulfill the requirement for the assembly of the aircraft.     

Mental imagery classification using one-dimensional convolutional neural network for target selection in single-channel BCI-controlled mobile robot

Neural Computing and Applications - This paper introduces the use of the one-dimensional convolutional neural network (1D-CNN) for end-to-end EEG decoding with application towards a BCI system with...     

A steel surface defect inspection approach towards smart industrial monitoring

Journal of Intelligent Manufacturing - With the advance in Industry 4.0, smart industrial monitoring has been proposed to timely discover faults and defects in industrial processes. Steel is widely...