In-situ point cloud fusion for layer-wise monitoring of additive manufacturing

Additive manufacturing (AM) has received an increasing attention in the manufacturing sector, owing to its high-level design freedom and enhanced capability to produce parts with complex geometries. With advances in AM technologies, the role of AM has been shifting from rapid prototyping to viable production-worthy manufacturing of functional parts. However, AM processes are highly inconsistent, and the lack of quality assurance significantly hampers the broader adoption of AM. Most existing techniques for AM online monitoring focus on the detection of conspicuous defects, such as under-fills and cracks. They are limited in their ability to detect layer surface variations induced by miniature process shifts. The objective of this study is to develop a new layer-wise monitoring framework for AM quality assurance based on in-situ point cloud fusion. Specifically, online 3D structured-light scanning is used to capture the surface morphology from each printed layer. The collected point cloud is partitioned, and the morphological patterns in local regions are delineated with a new affinity measure to evaluate the conformity to the reference. A deep cascade model is further introduced to leverage the local affinities for the identification of abnormal patterns on the printed layers. Finally, a statistical control chart is constructed for process monitoring and the identification of miniature shifts. Simulation and real-world case studies using the fused filament fabrication (FFF) process are conducted, and experimental results have demonstrated the effectiveness of the developed framework. It has a great potential to be implemented in diverse AM processes with a wide variety of materials for mission-critical applications.     

The HORSE framework: A reference architecture for cyber-physical systems in hybrid smart manufacturing

In the Industry 4.0 era, manufacturers strive to remain competitive by using advanced technologies such as collaborative robots, automated guided vehicles, augmented reality support and smart devices. However, only if these technological advancements are integrated into their system context in a seamless way, they can deliver their full potential to a manufacturing organization. This integration requires a system architecture as a blueprint for positioning and interconnection of the technologies. For this purpose, the HORSE framework, resulting from the HORSE EU H2020 project, has been developed to act as a reference architecture of a cyber-physical system to integrate various Industry 4.0 technologies and support hybrid manufacturing processes, i.e., processes in which human and robotic workers collaborate. The architecture has been created using design science research, based on well-known software engineering frameworks, established manufacturing domain standards and practical industry requirements. The value of a reference architecture is mainly established by application in practice. For this purpose, this paper presents the application and evaluation of the HORSE framework in 10 manufacturing plants across Europe, each with its own characteristics. Through the physical deployment and demonstration, the framework proved its goal to be basis for the well-structured design of an operational smart manufacturing cyber-physical system that provides horizontal, cross-functional management of manufacturing processes and vertical control of heterogeneous technologies in work cells. We report on valuable insights on the difficulties to realize such systems in specific situations. The experiences form the basis for improved adoption, further improvement and extension of the framework. In sum, this paper shows how a reference architecture framework supports the structured application of Industry 4.0 technologies in manufacturing environments that so far have relied on more traditional digital technology.     

Making costly manufacturing smart with transfer learning under limited data: A case study on composites autoclave processing

The integration of advanced manufacturing processes with ground-breaking Artificial Intelligence methods continue to provide unprecedented opportunities towards modern cyber-physical manufacturing processes, known as smart manufacturing or Industry 4.0. However, the “smartness” level of such approaches closely depends on the degree to which the implemented predictive models can handle uncertainties and production data shifts in the factory over time. In the case of change in a manufacturing process configuration with no sufficient new data, conventional Machine Learning (ML) models often tend to perform poorly. In this article, a transfer learning (TL) framework is proposed to tackle the aforementioned issue in modeling smart manufacturing. Namely, the proposed TL framework is able to adapt to probable shifts in the production process design and deliver accurate predictions without the need to re-train the model. Armed with sequential unfreezing and early stopping methods, the model demonstrated the ability to avoid catastrophic forgetting in the presence of severely limited data. Through the exemplified industry-focused case study on autoclave composite processing, the model yielded a drastic (88%) improvement in the generalization accuracy compared to the conventional learning, while reducing the computational and temporal cost by 56%.     

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.     

Mathematical model and discrete artificial Bee Colony algorithm for distributed integrated process planning and scheduling

With the development of the globalization of economy and manufacturing industry, distributed manufacturing mode has become a hot topic in current production research. In the context of distributed manufacturing, one job has different process routes in different workshops because of heterogeneous manufacturing resources and manufacturing environments in each factory. Considering the heterogeneous process planning problems and shop scheduling problems simultaneously can take advantage of the characteristics of distributed factories to finish the processing task well. Thus, a novel network-based mixed-integer linear programming (MILP) model is established for distributed integrated process planning and scheduling problem (DIPPS). The paper designs a new encoding method based on the process network and its OR-nodes, and then proposes a discrete artificial bee colony algorithm (DABC) to solve the DIPPS problem. The proposed DABC can guarantee the feasibility of individuals via specially-designed mapping and switching operations, so that the process precedence constraints contained by the network graph can be satisfied in the entire procedure of the DABC algorithm. Finally, the proposed MILP model is verified and the proposed DABC is tested through some open benchmarks. By comparing with other powerful reported algorithms and obtaining new better solutions, the experiment results prove the effectiveness of the proposed model and DABC algorithm successfully.     

Real-time integrated production-scheduling and maintenance-planning in a flexible job shop with machine deterioration and condition-based maintenance

The introduction of modern technologies in manufacturing is contributing to the emergence of smart (and data-driven) manufacturing systems, known as Industry 4.0. The benefits of adopting such technologies can be fully utilized by presenting optimization models in every step of the decision-making process. This includes the optimization of maintenance plans and production schedules, which are two essential aspects of any manufacturing process. In this paper, we consider the real-time joint optimization of maintenance planning and production scheduling in smart manufacturing systems. We have considered a flexible job shop production layout and addressed several issues that usually take place in practice. The addressed issues are: new job arrivals, unexpected due date changes, machine degradation, random breakdowns, minimal repairs, and condition-based maintenance (CBM). We have proposed a real-time optimization-based system that utilizes a modified hybrid genetic algorithm, an integrated proactive-reactive optimization model, and hybrid rescheduling policies. A set of modified benchmark problems is used to test the proposed system by comparing its performance to several other optimization algorithms and methods used in practice. The results show the superiority of the proposed system for solving the problem under study. The results also emphasize the importance of the quality of the generated baseline plans (i.e., initial integrated plans), the use of hybrid rescheduling policies, and the importance of rescheduling times (i.e., reaction times) for cost savings.     

Decision-based process planning for wire and arc additively manufactured and machined parts

The conventional manufacturing of aircraft components is based on the machining from bulk material and the buy-to-fly ratio is high. This, in combination with the often low machinability of the materials in use, leads to high manufacturing costs. To reduce the production costs for these components, a process chain was developed, which consists of an additive manufacturing process and a machining process. To fully utilize the process chain’s capabilities, an integrated process planning approach is necessary. As a result, the work sequence can be optimized to achieve the economically most suitable sequence. In this paper, a method for a joint manufacturing cost calculation and subsequent decision-based cost minimization is proposed for the wire and arc additive manufacturing (WAAM) & milling process chain. Furthermore, the parameters’ influence on the results and the magnitude of their influence are determined. These results make it possible to design an economically optimal work sequence and to automate the process planning for this process chain.     

Scalable framework for blockchain-based shared manufacturing

Shared Manufacturing is a new mode of social manufacturing based on the principles of a sharing economy. This paper presents a scalable framework for blockchain-based Shared Manufacturing that preserves the transparency and immutability characteristics of transaction records, which is critical to building trust between entities in blockchain-based systems. We define a blockchain-based protocol for the service execution according to the design principles of the sharing economy. We present a scalable integration of blockchain technology into the concept of Shared Manufacturing by employing cross-chain solutions. We discuss existing cross chain technologies regarding the requirements of Shared Manufacturing and propose hybrid approach. We compare implementations of the proposed framework on two different blockchain networks: Ethereum public network and Xdai sidechain network. We conduct user-oriented test to explore the performance (cost and time) of the implementations in realistic situations in order to justify the use of the sidechain technology. Results indicate that the implementation on the sidechains provides greater scalability than the implementation on the public blockchain network.     

众筹项目推荐:面向隐式反馈的深度学习协同过滤

目前,在推荐系统研究中,用户的隐式反馈,以及极度稀疏的数据,已成为影响协同过滤推荐效果的主要问题.针对这一现象,本文提出了深度学习协同过滤算法,先利用卷积神经网络,对用户-项目矩阵的隐层特征进行学习,再结合协同过滤,对用户-项目的交互信息进行建模,并将两种特征融合预测推荐列表.以众筹平台的数据为实验对象,比较模型中各参数对推荐效果的影响,并设计与基线方法的对比实验.实验结果表明:均匀采集负反馈,并在一定卷积层数的网络中,数据稀疏度越高,效果越好;对比基线方法,本文提出的算法在公开数据集(Yahoo!Movie)上取得了最好的推荐结果.本文提出的算法有助于提高众筹平台的融资成功率,同时也丰富了推荐系统的研究体系.