Search results

This study aims to develop a data fusion method for powder-bed fusion (PBF) process monitoring based on process image information. The data fusion method can help improve process condition identification performance, which can provide guidance for further PBF process monitoring and control system development.

Design of reliable process monitoring systems is an essential approach to solve PBF built quality. A data fusion framework based on support vector machine (SVM), convolutional neural network (CNN) and Dempster-Shafer (D-S) evidence theory are proposed in the study. The process images which include the information of melt pool, plume and spatters were acquired by a high-speed camera. The features were extracted based on an appropriate image processing method. The three feature vectors corresponding to the three objects, respectively, were used as the inputs of SVM classifiers for process condition identification. Moreover, raw images were also used as the input of a CNN classifier for process condition identification. Then, the information fusion of the three SVM classifiers and the CNN classifier by an improved D-S evidence theory was studied.

The results demonstrate that the sensitivity of information sources is different for different condition identification. The feature fusion based on D-S evidence theory can improve the classification performance, with feature fusion and classifier fusion, the accuracy of condition identification is improved more than 20%.

An improved D-S evidence theory is proposed for PBF process data fusion monitoring, which is promising for the development of reliable PBF process monitoring systems.

This paper aims to overcome the defect of single-source temperature measurement method and improve the measurement accuracy of FTR. The friction temperature rise (FTR) of brake affects braking performance seriously. However, it was mainly detected by single-source indirect thermometry, which has obvious deviations.

A three-point temperature measurement system was built based on three kinds of single-resource thermometry. Temperature characteristics of these thermometry were analyzed to achieve a standard FTR curve. Two fusion-monitoring models for FTR based on multi-source information were established by artificial neural network (ANN) and support vector machine (SVM).

Finally, the two models were verified based on the experimental results. The results showed that the fusion-monitoring model of SVM was more accurate than that of ANN in monitoring of FTR.

Then the temperature characteristics of the three single-source thermometry were analyzed, and the fusion-monitoring models based on multi-source information were established by ANN and SVM. Finally, the accuracy of the two models was compared by the experimental results. The more suitable fusion-monitoring model for FTR monitoring was determined which would be of theoretical and practical significance for remedying the monitoring defect of FTR.

Additive manufacturing (AM) processes are the integration of many different science and engineering-related disciplines, such as material metrology, design, process planning, in-situ and off-line measurements and controls. Major integration challenges arise because of the increasing complexity of AM systems and a lack of support among vendors for interoperability. The result is that data cannot be readily shared among the components of that system. In an attempt to better homogenization this data, this paper aims to provide a reference model for data sharing of the activities to be under-taken in the AM process, laser-based powder bed fusion (PBF).

The activity model identifies requirements for developing a process data model. The authors’ approach begins by formally decomposing the PBF processes using an activity-modeling methodology. The resulting activity model is a means to structure process-related PBF data and align that data with specific PBF sub-processes.

This model in this paper provides the means to understand the organization of process activities and sub-activities and the flows among them in AM PBF processes.

The model is for modeling AM activities and data associated with these activity. Data modeling is not included in this work.

After modeling the selected PBF process and its sub-processes as activities, the authors discuss requirements for developing the development of more advanced process data models. Such models will provide a common terminology and new process knowledge that improve data management from various stages in AM.

Fundamental challenges in sharing/reusing data among heterogeneous systems include the lack of common data structures, vocabulary management systems and data interoperability methods. In this paper, the authors investigate these challenges specifically as they relate to process information for PBF – how it is captured, represented, stored and accessed. To do this, they focus on using methodical, information-modeling techniques in the context of design, process planning, fabrication, inspection and quality control.

This study aims to discuss the state-of-the-art digital factory (DF) development combining digital twins (DTs), sensing devices, laser additive manufacturing (LAM) and subtractive manufacturing (SM) processes. The current shortcomings and outlook of the DF also have been highlighted. A DF is a state-of-the-art manufacturing facility that uses innovative technologies, including automation, artificial intelligence (AI), the Internet of Things, additive manufacturing (AM), SM, hybrid manufacturing (HM), sensors for real-time feedback and control, and a DT, to streamline and improve manufacturing operations.

This study presents a novel perspective on DF development using laser-based AM, SM, sensors and DTs. Recent developments in laser-based AM, SM, sensors and DTs have been compiled. This study has been developed using systematic reviews and meta-analyses (PRISMA) guidelines, discussing literature on the DTs for laser-based AM, particularly laser powder bed fusion and direct energy deposition, in-situ monitoring and control equipment, SM and HM. The principal goal of this study is to highlight the aspects of DF and its development using existing techniques.

A comprehensive literature review finds a substantial lack of complete techniques that incorporate cyber-physical systems, advanced data analytics, AI, standardized interoperability, human–machine cooperation and scalable adaptability. The suggested DF effectively fills this void by integrating cyber-physical system components, including DT, AM, SM and sensors into the manufacturing process. Using sophisticated data analytics and AI algorithms, the DF facilitates real-time data analysis, predictive maintenance, quality control and optimal resource allocation. In addition, the suggested DF ensures interoperability between diverse devices and systems by emphasizing standardized communication protocols and interfaces. The modular and adaptable architecture of the DF enables scalability and adaptation, allowing for rapid reaction to market conditions.

Based on the need of DF, this review presents a comprehensive approach to DF development using DTs, sensing devices, LAM and SM processes and provides current progress in this domain.

Traffic congestion is becoming a serious problem that has adverse consequences on the socio-economy, environment, and public health of various cities worldwide. The purpose of this paper is to contribute to the continuous search for new alternative solutions to prevent or alleviate these concerns. It particularly deals with the development of decision support system based on a data fusion for the management and control of traffic at signalized intersections. The role of such systems is to manage the existing infrastructure to ease congestion and respond to crises. The proposed system is based on multi-detector data fusion, a data processing function that combines imperfect information collected from systems involving several detectors. The developed system is then tested on a virtual junction, and the results obtained are reported and discussed.

This paper presents a new traffic light control based on multi-detectors data fusion theory. The system uses a new multi-detectors data fusion method for traffic data analysis. Moreover, the system integrates a method for the estimation of the reliability degree of different detectors taking into account their imperfection and the conflict between them. These estimated reliability degrees are combined using Dempster’s rule of combination.

The paper provides a decision support system for traffic regulation at intersection based on multi-sensors. It suggests the fusion of captured data by many sensors for measuring information. The system use the Belief Functions Theory for information fusion and decision making using combination and decision rules.

The paper proposes a new Adaptive Traffic Control System based on a new data fusion approach that include a method for the estimation of the reliability degree of different detectors taking into account their imperfection and the conflict between them. These estimated reliability degrees are combined using Dempster’s rule of combination.

Marketing managers have strategic choices when forming brand alliances. One such choice is integration, defined as the extent to which the offering is a fusion in the form and function of the partner brands. The paper aims to investigate how integration affects consumer attribution of responsibility to brand alliance partners.

This paper builds on the previous study on brand alliances and attribution theory. Multiple experiments are used to test three hypotheses.

This research shows that consumers are sensitive to the level of alliance integration, which, in turn, affects attributions of responsibility for the joint offering. Consistent with attribution theory, results show that responsibility for each brand varies systematically by integration and lead brand status vis-à-vis the alliance: while consumers perceive both brands as equally responsible for higher integration brand alliances, responsibility attributions diverge in lower integration alliances based on whether the brand is the alliance host. This pattern also holds for product-harm events.

It is important to explore brand alliance characteristics and to date, the level of integration between the partners has not been considered from a consumer standpoint. Consumers are sensitive to the level of partner brand integration and this perception influences perceptions of responsibility.

Managers should be aware that the level of brand alliance integration and lead brand status lead to different attributions of responsibility, which is strategically important, as brands seek to take credit in positive contexts and avoid blame for negative events.

This paper explores brand alliances via the level of integration and leads brand status, which are key determinants of consumer attributions of responsibility.

The purpose of this study is to develop and verify a methodology for a zoned deformation prediction model for super high arch dams, which is indeed a panel data-based regression model with the hierarchical clustering on principal components.

The hierarchical clustering method is used to highlight the main features of the time series. This method is used to select the typical points of the measured ambient and concrete temperatures as predictors and divide the deformation observation points into groups. Based on this, the panel data of each zone can be established, and its type can be judged using F and Hausman tests successively. Then hydrostatic–temperature–time–season models for zones can be constructed. Through the comparative analyses of the distributions and the fitted coefficients of these zones, the spatial deformation mechanism of a dam can be identified. A super high arch dam is taken as a case study.

According to the measured radial displacements during the initial operation period, the investigated pendulums are divided into four zones. After tests, fixed-effect regression models are established. The comparative analyses show that the dam deformation conforms to the natural condition. The factors such as the unstable temperature field and the nonlinear time-dependent effect have obvious effects on the dam deformation. The results show the efficiency of the proposed methodology in zoning and prediction modeling for deformation of super high arch dams and the potential to mining dam deformation mechanism.

A zoned deformation prediction model for super high arch dams is proposed where hierarchical clustering on principal component method and panel data model are combined.

In the last decade, cloud manufacturing (CMfg) has attracted considerable attention from academia and industry worldwide. It is widely accepted that the design and analysis of cloud manufacturing architecture (CMfg-A) are the basis for developing and applying CMfg systems. However, in existing studies, analysis of the status, development process and internal characteristics of CMfg-A is lacking, hindering an understanding of the research hotspots and development trends of CMfg-A. Meanwhile, effective guidance is lacking on the construction of superior CMfg-As. The purpose of this paper is to review the relevant research on CMfg-A via identification of the main layers, elements, relationships, structure and functions of CMfg-A to provide valuable information to scholars and practitioners for further research on key CMfg-A technologies and the construction of CMfg systems with superior performance.

This study systematically reviews the relevant research on CMfg-A across transformation process to internal characteristics by integrating quantitative and qualitative methods. First, the split and reorganization method is used to recognize the main layers of CMfg-A. Then, the transformation process of six main layers is analysed through retrospective analysis, and the similarities and differences in CMfg-A are obtained. Subsequently, based on systematic theory, the elements, relationships, structure and functions of CMfg-A are inductively studied. A 3D printing architecture design case is conducted to discuss the weakness of the previous architecture and demonstrate how to improve it. Finally, the primary current trends and future opportunities are presented.

By analyzing the transformation process of CMfg-A, this study finds that CMfg-A resources are developing from tangible resources into intangible resources and intelligent resources. CMfg-A technology is developing from traditional cloud computing-based technology towards advanced manufacturing technology, and CMfg-A application scope is gradually expanding from traditional manufacturing industry to emerging manufacturing industry. In addition, by analyzing the elements, relationships, structure and functions of CMfg-A, this study finds that CMfg-A is undergoing a new generation of transformation, with trends of integrated development, intelligent development, innovative development and green development. Case study shows that the analysis of the development trend and internal characteristics of the architecture facilitates the design of a more effective architecture.

This paper predominantly focuses on journal articles and some key conference papers published in English and Chinese. The reason for considering Chinese articles is that CMfg was proposed by the Chinese and a lot of Chinese CMfg-A articles have been published in recent years. CMfg is suitable for the development of China’s manufacturing industry because of China’s intelligent manufacturing environment. It is believed that this research has reached a reliable comprehensiveness that can help scholars and practitioners establish new research directions and evaluate their work in CMfg-A.

Prior studies ignore the identification and analysis of development process and internal characteristics for the current development of CMfg-A, including the main layers identification of different CMfg-As and the transformation process analysis of these main layers, and in-depth analysis of the inner essence of CMfg-A (such as its elements, relationships, structure and functions). This study addresses these limitations and provides a comprehensive literature review.