查看更多>>摘要：? 2022Product service systems (PSSs) are accelerating the shift in value in the creation of cloud manufacturing (CMfg), from product design and production to providing solutions that integrate products and services. Cyber-physical systems (CPSs) are taking center stage in CMfg, thereby integrating cyberspace and dynamic manufacturing physical spaces. Selecting the best combination of services to fulfil customer requirements is the most important issue in the CMfg platform. To address this issue, symbiotic simulations have been proposed to bridge the gap between cyberspace and the physical space. Cyberspace works by establishing a symbiotic relationship between users in physical space and information resources (e.g., computational algorithms and data) in cyberspace. In this study, we propose symbiotic simulations to perform efficient service combinations in CMfg, adopting computational algorithms ranging from operations research (OR) to machine learning (ML). This can overcome the inherent heterogeneity and complexity of these services in terms of functionality, quality, and execution paths. Several test cases were conducted to validate the performance of the multiagent-based symbiotic simulation platform, and the results of the symbiotic simulations demonstrate the performance of the approach in terms of reduced combined resources and wait times.
查看更多>>摘要：? 2022 Elsevier B.V.OMiLAB is a community of practice which offers a digital ecosystem bringing together open technologies to investigate and apply conceptual modeling methods for varying purposes and domains. One of the core value propositions is a dedicated Digital Innovation environment comprising several toolkits and workspaces, designed to support Product-Service Systems (PSS) prototyping – a key ingredient for PSS lifecycle management. At the core of this environment is a notion of Agile Digital Twin – a conceptual representation that can be tailored with knowledge engineering means to bridge the semantic and functional gap between a business perspective (focusing on value creation) and an engineering perspective (focusing on cyber-physical proofs-of-concept). To facilitate this bridging, the hereby proposed environment orchestrates, across three abstraction layers, methods such as Design Thinking, Agile Modeling Method Engineering and Model-driven Engineering to turn Ideation into smart Product-Service Systems experiments, in a laboratory setting. The proposed environment was built following Design Science principles. It addresses the problem of historically-disconnected skills required for Digital Innovation projects and it provides a testbed for feasibility experimentation. For design-oriented, artifact building research, a higher Technology Readiness Level can thus be achieved (compared to the level that idea development methods typically attain).
查看更多>>摘要：? 2022 Elsevier B.V.Industry 4.0 promotes the advance of several key areas in manufacturing. Industrial metrology, and associated activities such as Quality Assurance are receiving constant pressure to enhance integration, interoperability, and availability of measurement information to other operations. This promotes a trusted Internet of Things (IoT) or Cyber-Physical Systems (CPS) environment where reliable measurement data is accurate and available to different stakeholders This work addresses the integration of measuring devices in an IoT architecture using open standards. It provides a framework, based on IEC 62264 for Quality Operations Management (QOM) and ISO 23952:2020 - Quality Information Framework (QIF) to describe the activities of Quality Assurance and Quality Control and provides a generic interface using OPC UA to receive and send information to the QOM activities, enabling the integration with upper systems such as an ERP and the creation of quality oriented Key Performance Indicators (KPIs). An experimental scenario in the steel manufacturing industry is provided, demonstrating, how the generic interface can support custom software applications by using metrology data to support, reducing product and process defects leading to Zero-Defect Manufacturing (ZDM).
查看更多>>摘要：? 2022 Elsevier B.V.As an essential part of the Product Life Cycle (PLC), the time-to-market of products is influenced by Engineering Change Management (ECM) processes. An Engineering Change (EC) is part of a formal process in industry to describe, rationalize, determine, release components for final production or make changes to already released design. It includes information about shape, functionality, production location, cost, and other relevant data entries. The duration from creation to the approval of a change request can take weeks or even months, without apparent reasons for the bottleneck. In addition, changes to one component can lead to unexpected chain reactions to other components. Therefore, identifying impacts of changes is challenging for all Original Equipment Manufacturers (OEMs). To address the above challenges, the authors have developed and built a machine learning-based decision support solution in this article. Community detection and stacking algorithms were applied to build more robust models. Impacts and lead time of Engineering Change Requests (ECRs) are predicted and explained by Local Interpretable Model-agnostic Explanations (LIME). A case study was conducted on real-world data from an automotive company. After evaluation with industry experts, the solution approach was proved to have positive contributions to increasing the quality, efficiency, and transparency of the existing ECM processes.
查看更多>>摘要：? 2022 The AuthorsMany high-level technical products are associated with changing requirements, drastic design changes, lack of design information, and uncertainties in input variables which makes their design process iterative and simulation-driven. Regression models have been proven to be useful tools during design, altering the resource-intensive finite element simulation models. However, building regression models from computer-aided design (CAD) parameters is associated with challenges such as dealing with too many parameters and their low or coupled impact on studied outputs which ultimately requires a large training dataset. As a solution, extraction of hidden features from CAD is presented on the application of volume simulation of curtain airbags concerning geometric changes in design loops. After creating a prototype that covers all aspects of a real curtain airbag, its CAD parameters have been analyzed to find out the correlation between design parameters and volume as output. Next, using the design of the experiment latin hypercube sampling method, 100 design samples are generated and the corresponding volume for each design sample was assessed. It was shown that selected CAD parameters are not highly correlated with the volume which consequently lowers the accuracy of prediction models. Various geometric entities, such as the medial axis, are used to extract several hidden features (referred to as sleeping parameters). The correlation of the new features and their performance and precision through two regression analyses are studied. The result shows that choosing sleeping parameters as input reduces dimensionality and the need to use advanced regression algorithms, allowing designers to have more accurate predictions (in this case approximately 95%) with a reasonable number of samples. Furthermore, it was concluded that using sleeping parameters in regression-based tools creates real-time prediction ability in the early development stage of the design process which could contribute to lower development lead time by eliminating design iterations.
查看更多>>摘要：? 2022 Elsevier B.V.Flower and fruit count is a critical metric in developing crop-load management and harvesting strategies during flower/fruit development and harvest seasons. Growers currently rely on their prior experience and/or manual count in sample areas/trees to estimate the number of flowers/fruits in orchards. In this work, we propose a simplified yet robust deep learning-based weakly-supervised flower/fruit Counting Network (CountNet) and investigate its accuracy in commercial orchard images. Unlike detection-based counting methods, which require individual object detection, CountNet learns from image-level annotation with the number of objects (flowers or fruits) as input without explicitly specifying the object's signature and location. Experiments were conducted in images acquired in an unstructured commercial orchard environment. Results showed a minimum Mean Absolute Error (MAE)/Root Mean Square Error (RMSE) of 12.0/18.4 and 2.9/4.3 for the apple flower and fruit dataset respectively. Activated region/feature visualization techniques revealed that CountNet is looking into different apple flower/fruit edges and features to make the count decisions. The results are promising in simplifying the automated methods for flower/fruit counting which can lead to reduced manual counting in the field, manual image annotation, and computational complexity and memory requirement of the object counting system.
查看更多>>摘要：? 2022 Elsevier B.V.The development of driver assistance and autonomous driving systems for vehicles has started to revolutionize the transportation sector, offering comfort and safety. While significant technological progress has already been made in this area, the road ahead is littered with many challenges. Among these challenges, ensuring driver safety has become even more critical due to the increasing use of complex, communicating and reconfigurable embedded software. Current approaches to document-based safety analysis have reached their limit and the time has come to rethink them. To this end, we propose to rely on model-driven engineering to conduct safety analyses. This paper makes a methodological proposal that improves current practices in terms of time, analysis quality and reusability, and that has been validated on the study of an automotive software component.
查看更多>>摘要：? 2022 Elsevier B.V.This study offers a Systematic Literature Review of the main applications of Industry 4.0 technologies in the wood sector, from forest management and raw materials production to the manufacturing of finished wood and paper products. The review, based on a rigorous and structured process, includes 106 papers published between January 2011 and December 2020. The analysis and categorization of the selected papers brings to the creation of a summary framework, which identifies (1) the needs of the wood sector that can be addressed with Industry 4.0, (2) the actions to be implemented to satisfy each need and (3) the specific Industry 4.0 technologies to be adopted for the implementation of the identified actions. Overall, the analyses conducted show that Industry 4.0 is mainly applied in previous literature to collect, share and analyze different types of data through network and data processing technologies, thus supporting decision-making processes along the entire wood supply chain. The aforementioned summary framework, which provides a complete overview of the contribution of Industry 4.0 to the wood sector, is used for the development of promising future research opportunities, deriving mainly from the investigation of underexploited Industry 4.0 technologies (i.e., blockchain, augmented reality, autonomous and collaborative robots). The research provides contributions to both academics and practitioners interested in the application of the new technologies to the different wood supply chain processes.
查看更多>>摘要：? 2022 Elsevier B.V.Tool wear monitoring (TWM) is critical in modern high-speed milling, and an effective TWM system will improve machining precision, increase tool life and reduce production costs. As a novel data-driven approach with strong learning capability, deep learning has been introduced and studied for manufacturing process monitoring, but it is rarely applied as an independent method in practice for TWM due to the poor interpretability of the monitoring results. In this study, a multi-scale pyramid attention network (MPAN) is proposed. MPAN can not only accurately monitor tool wear based on sensory signals, but also introduce the interpretability from both the aspect of network structure design and feature extraction. With the prior knowledge of signal periodicity is introduced into the structure design, the extracted multi-scale features can cover almost all the characteristic periods. In addition, the periodicity of interest can be studied based on the attention distribution. The effectiveness and feasibility of this method are verified on high-speed milling experiments. This is the first attempt to interpret deep-learning based approach for TWM.
查看更多>>摘要：? 2022 Elsevier B.V.The present study presents an Industry 4.0 measurement model that is applied to a sample of Portuguese companies from several economic sectors beyond manufacturing. An Industry 4.0 measurement scale is developed through a three-step methodology that relies on a mixed-methods approach. Five constructs are identified from literature, together with respective measurement indicators: IT strategy and cybersecurity, enablers, smart factory, value proposition and customer experience. These constructs are subsequently deepened in a qualitative study where second order dimensions are identified and the measurement scale is extended and validated. The model is applied in a quantitative study, the conclusions of which suggest some realignment in the initial constructs. Finally, an Industry 4.0 maturity index is derived. Industry 4.0 maturity is measured from the firms' ability to deploy capabilities and resources to impact on the value chain.
NSTL
Elsevier