Manufacturing Of Complex Products Research Articles

Product Quality Anomaly Recognition and Diagnosis Based on DRSN-SVM-SHAP

Conventional quality control methodologies are inadequate for fully elucidating the aberrant patterns of product quality. A multitude of factors influence product quality, yet the limited number of controlled quality characteristics is insufficient for accurately diagnosing quality abnormalities. Additionally, there are asymmetries in data collection, data pre-processing, and model interpretation. In this context, a quality anomaly recognition and diagnosis model for the complex product manufacturing process is constructed based on a deep residual network, support vector machine (SVM), and Shapley additive explanation (SHAP). Given the numerous complex product quality characteristic indexes and unpredictable accidental factors in the production process, it is necessary to mine the deep relationship between quality characteristic data and quality state. This mining is achieved by utilizing the strong feature extraction ability of the deep residual shrinkage network (DRSN) through self-learning. The symmetry of the data within the model has also been taken into account to ensure a more balanced and comprehensive analysis. The excellent binary classification ability of the support vector machine is combined with the DRSN to identify the quality anomaly state. The SHAP interpretable model is employed to diagnose the quality anomaly problem of a single product and to identify and diagnose quality anomalies in the manufacturing process of complex products. The effectiveness of the model is validated through case analysis. The accuracy of the DRSN-SVM quality anomaly recognition model reaches 99%, as demonstrated by example analysis, and the model exhibits faster convergence and significantly higher accuracy compared with the naive Bayesian model classification and support vector machine classification models.

A BOM model transformation method for hierarchical production planning management process of complex products

The Bill of Materials (BOM) is the core data in the hierarchical production planning management of complex products. In the current competitive market environment and increasing demand for individual customization, complex product manufacturing enterprises are exploring methods that fully use common data and efficiently organize the BOM according to order requirements. However, due to the lack of a unified data modeling method for hierarchical production planning, BOM data at different levels cannot be interpenetrated. Moreover, the single-tree BOM lacks flexibility in describing the dynamic change process of data in different planning management stages (i.e., order receiving, variant design, and manufacturing execution).This paper proposes a BOM model transformation method for hierarchical production planning management to efficiently and accurately organize the data in different planning management stages of complex products. First, the Hierarchical Bill of Materials (HBOMs) model is constructed to integrate BOM data of different levels of planning. Subsequently, to describe the data requirements in HBOMs for different plan management stages, a composite HBOMs containing three types was designed. The Generic-HBOM (G-HBOM) aims to manage the common data of the same product type. The Instance-HBOM before-manufacturing (I-HBOM (BM)) and Instance-HBOM after-manufacturing (I-HBOM (AM)) manage the personality data of single product variant design and manufacturing execution stages, respectively. The transformation process models of HBOMs are constructed by analyzing the transformation logic between three types of HBOMs. To support the transformation process of HBOMs, five transformation operators are summarized, and the node traversal algorithm logic is proposed. Finally, a steam turbine generator product is taken as an example to verify the feasibility and effectiveness of this method. This method can effectively improve the efficiency of BOM construction and reduce data redundancy while helping to ensure the integrity, consistency, and accuracy of BOM data.

Antisuit injunctions in SEP disputes and the recent EU's WTO/TRIPS case against China

AbstractThe existence of standard essential patents (SEPs)—and the associated litigation—has potentially disruptive consequences for the manufacture, marketing and distribution of complex products that incorporate many patented standards, for example, information and communication technology (ICT) products such as smartphones that incorporate a camera, video, web browser, wireless communications, text messaging, and so on, as well as an increasing number of ‘connected’ Internet of Things products such as wearable devices and ‘smart home’ devices. Indeed, SEP owners may use the patent enforcement system to prevent implementers of these technologies from bringing to market competing products that use the same standards. As is known, this raises concerns about competition in the market and the need to maintain interoperability to ensure the development of the ICT industry. One of the legal tools which can be used by implementers to (try to) neutralise SEP holders' anticompetitive behaviours is the ‘antisuit injunction’ (ASI). ASIs are not uncommon in common law jurisdictions while they are foreign to civil law countries within the European Union (EU). ASIs are particularly useful to SEP implementers when patent holders disrespect their commitment to license their patents on a FRAND basis. For example, a judge who is in the process of assessing whether the SEP owner complies with FRAND terms may at the same time grant an ASI to stop the patentee taking patent infringement actions in other jurisdictions until the FRAND litigation has been concluded. In February 2022, the EU filed a complaint at the World Trade Organization (WTO), arguing that China's use of ASIs prevents EU‐based companies from properly protecting their SEPs. Indeed, ASIs have recently been granted in several Chinese disputes, including in Huawei v Conversant and Xiaomi v. InterDigital. More specifically, China's Supreme People's Court held that Chinese courts can use ASIs to prevent SEP owners from filing disputes in any foreign courts to enforce their patents; and that anyone who does not comply with the injunction should be fined €130,000 per day. In the WTO case the EU notes that such a case law jeopardises innovation and growth in Europe, ‘effectively depriving European technology companies of the possibility to exercise and enforce the rights that give them a technological edge’. From a legal perspective, according to the EU, China's conduct is in violation of various Trade‐Related Aspects of Intellectual Property Rights (TRIPS) provisions, including Article 28 which grants exclusive rights to patent owners. The paper focuses on this EU–China WTO/TRIPS dispute and more generally, on the relevance of ASIs within SEP cases.

IDDM: An incremental dual-network detection model for in-situ inspection of large-scale complex product

Appearance inspection is crucial for quality control during the manufacturing of large complex products. In-situ visual inspection based on image processing and machine learning can significantly reduce the production costs by avoiding the stages of transshipment and relocation, etc. However, imaging and model training are challenged by the complex background, illuminance, and changing environment of the production site. In addition, large dataset is hard to be obtained with object-level annotations owing to the high cost of manual annotation in practical situations. In this paper, we proposed an Incremental Dual network Detection Model (IDDM) for efficient and high-precision inspection of the appearance of large complex product base on in-situ images. A dual network structure is used to implement the incremental training of the model based on metric learning and batch labeling of unlabeled data during the training on a small number of well-labeled samples. The regions of interest are extracted based on multi-feature and refined to improve the positional accuracy of the defects in complex background. On the public dataset, the experimental results derived on various annotation scales showed a better performance of the proposed IDDM compared to the supervised object-detection baselines. The mean Average Precision (mAP) was 51.8% with a 25% labeled ratio and the processing speed was 22 frames per second (FPS). In addition, the proposed method was applied to the defect detection of the snow groomer surface as an industrial case.

A gray correlation based Bayesian network model for fault source diagnosis of multistage process – Small sample manufacturing system

Fault source diagnosis methodology is one of the key technologies of quality control and assurance for multi-source & multi-stage manufacturing processes, especially in small sample manufacturing systems. By analyzing the existing research on fault source diagnosis methods, a Bayesian network-based methodology is proposed. Gray correlation theory and mechanism analysis method are used in the process of Bayesian network model construction to reduce the dependence of sample data size for structure learning in the process of small sample manufacturing of complex products. In addition, two fault source diagnosis methods based on manufacturing principle analysis and reverse Bayesian network respectively are proposed. The strategy of the combined use of the two methods in the actual manufacturing scenes is given to cope with the fault source diagnosis scenario in the real manufacturing process. In the end, an example from an actual factory is provided to validate the effectiveness and efficiency of the proposed model and methodologies.

Design-Manufacturing-Operation & Maintenance (O&M) Integration of Complex Product Based on Digital Twin

This paper presents a complex product design-manufacturing-operations and maintenance integration method based on digital twin technology. This method aims to solve the problem of information silos in the design, manufacturing and operation and maintenance phases of complex products in the context of intelligent manufacturing and to integrate the design, manufacturing and operation and maintenance processes of complex products. To address the integration needs of complex product design, manufacturing, operation and maintenance business integration, a framework for complex product design-manufacturing-operation and maintenance integration based on the digital twin is first proposed, in addition to designing a model and operation mechanism for combining the virtual and real of the digital twin model. Then, the implementation of multistage collaborative design technology, data intelligent sensing technology, and data integration and fusion technology for the digital twin-based design-manufacturing-operations and maintenance integration processes are analyzed and discussed. Finally, a case study involving the fault prediction of key components of the bogie of an EMU demonstrated the integrated mode of operation in the design-manufacture-operation and maintenance process of the EMU. It verified the effectiveness of the proposed framework, process and methodology.

Online prediction of automotive tempered glass quality using machine learning

This study explores the application of machine learning algorithms for supporting complex product manufacturing quality through a focus on quality assurance and control. We aim to take advantage of ML technics to solve one of the complex manufacturing problems of the tempered glass manufacturing industry as a first attempt to automate product quality prediction and optimization in this industrial field as an alternative to destructive testing methodologies. The choice of this application field was motivated by the lack of a robust engineering technique to assess the production quality in real time; this arises the need of using advanced smart manufacturing solution as AI to save the extremely high cost of destructive tests. As methodology, this paper investigates the performance of machine learning techniques including Ridge Regression, Linear Regression, Light Gradient Boosting Machine, and Lasso Regression, for predicting the product thermal treatment quality within the selected type of industry. In the first part, we applied the selected machine learning models to a dataset collected manually and made up of the more relevant process parameters of the heating and the quenching process. Evaluating the results of the applied models, based on several performance indicators such as mean absolute error, mean squared error, and r-squared, declared that Ridge Regression was the most accurate model with a mean error of 14.33 which is significantly acceptable in a business point of view and not reachable by any human level experience of prediction. The second part consists of developing a digitalized device connected to the manufacturing process to provide predictions in real time. This device operates as an error-proofing system that sends a reverse signal to the machine in case the prediction shows a non-compliant quality of the current processed product. This study can be expanded to predict the optimal process parameters to use when the predicted values do not meet the desired quality and can advantageously replace the trial-and-error approach that is generally adopted for defining those parameters. The contribution of our work relies on the introduction of a clear methodology (from idea to industrialization) for the design and deployment of an industrial-grade predictive solution within a new field which is the glass transformation.

Graphical design based on digital twin and interaction generation

In the process of product design transformation, some problems arise, such as inefficient management, lack of accuracy in decision analysis of various operation and maintenance events, and the degree of intelligence to be improved, so this paper designs a graphical design based on digital twin and interaction generation. Digital twin is an important tool to achieve deep integration of graphic design, and the physical integration of complex product design and manufacturing information is the most important part of it, which focuses on shop floor operations and product O&M, but there is less research on the application of digital twin technology to complex product design and manufacturing integration. We analyze the problems of equipment monitoring and video monitoring, and systematically explain the feasibility, design ideas, technical routes and key technologies of applying digital twin technology to intelligent production process monitoring.

Influence of inclination angle, shape and size of the flow channels on the AlSi10Mg complex products fabricated by selective laser melting

The design and manufacture of complex products with flow channels produced by the Selective Laser Melting (SLM) have attracted much attention due to its influence on the practicability of products. In this research, the inclination angle, shape and size of channel were compared on the complex products produced by SLM. Besides, the surface quality and forming difficulty of AlSi10Mg were investigated. As shown by the results, the overhang length played a key role in collapse, which was determined by inclination angle. In addition, the limited inclination angle was attributed to the position relationship between the inclination plane and the moving direction of the scraper. Meanwhile, the ridge-shaped flow channels had an advantage on surface quality and dimensional accuracy over the circular channel. No matter whether the section of the flow channels is circular or ridge-shaped, the size of the flow channels should be designed equal or >2 mm. The complex product with flow channels had been successfully produced by SLM without remaining powder or defects, which could withstand 2 MPa for 5 min. Furthermore, the CT test is suitable to investigate the forming quality of the flow channels, especially whether there is remaining powder inside the flow channels. Especially for the complex product with flow channels, it provides an integrated detection method based on X ray test and CT test for remaining powder, internal surface quality or internal defects. In addition, the design idea and criteria of three-dimensional flow channels based on the SLM technology provide a basis for the design of other products with flow channels.

Common Structure Mining of 3D Model Assembly Model Based on Frequent Subgraphs

As an important data source of complex product design and manufacturing, 3D assembly model has accumulated a large number of 3D assembly models in various manufacturing industries under the background of widely used digital design technology. In order to make better use of reusable common structure information about 3D assembly model, reduce repetitive labor, and shorten product development cycles, a common structure mining method of 3D assembly models was proposed. Firstly, based on the attribute neighbourhood diagram of individual parts of the 3D assembly model, the information of the assembly feature attributes is maintained and the nonassembly feature attributes are simplified to form an attributed assembly feature neighbourhood diagram; then, based on the assembly relationship between the parts of the 3D assembly model, the attributed assembly feature neighbourhood diagrams of the parts are combined to form a 3D assembly model attribute neighbourhood diagram. Secondly, the common structure of the 3D assembly model is extracted by the frequent subgraph mining algorithm. Finally, a set of fixture models is used to verify the results, which show that this 3D assembly model common structure mining method can accurately and effectively explore the common structure information of the product and has good results.

Problems of System Dynamics model development for complex product manufacturing process

Computer simulations are applied in enterprises for different purposes. They are used to support decision making at different levels of management. System Dynamics (SD) method is successfully used to model and simulate complex systems (including enterprises and manufacturing lines), but its applications are limited mostly to the policy and strategy level. This is due to the fact that SD approach assumes a low level of details and perceiving the system as a whole, and on the other hand, the reason may be the lack of examples of modelling manufacturing lines and workstations, at a higher level of detail. Based on a case study of a complex manufacturing system, this work presents examples of SD models of workstations and manufacturing line elements. Problems that were discussed in the frame of this paper are: process discretization, information flow with the use of kanban cards, processing of various components in one process, work of many employees at one workstation and assembly kit completion. The presented work may encourage researchers to use SD to model and simulate manufacturing lines at the operational level, and the presented solutions will be used in industrial practice to analyse and improve production systems.

Integration of Design, Manufacturing, and Service Based on Digital Twin to Realize Intelligent Manufacturing

Complex product design, manufacturing, and service are the key elements of a product’s life cycle. However, the traditional manufacturing processes of design, manufacturing, and service are independent of each other, so lack deep integration. The emergence of digital twins offers an opportunity to accelerate the integration of complex product design, manufacturing, and services. For intelligent manufacturing, physical entity and virtual entity transformation can be realized through digital information. A collaborative framework for complex product design, manufacturing, and service integration based on digital twin technology was proposed. The solutions of process integration, data flow, modeling and simulation, and information fusion were analyzed. The core characteristics and key technologies of service-oriented manufacturing, design for service and manufacturing, and manufacturing monitoring based on the deep integration of the digital twin were discussed. Finally, the feasibility of the framework was verified by a self-balancing multistage pump manufacturing case. The performance of the upgraded pump under the framework was tested, and the test results proved the effectiveness of the integrated framework.

EVALUATION OF PERFORMANCE EFFICIENCY OF PACKING A GROUP OF PRODUCTS IN THE WORKPLACE OF ADDITIVE MACHINE USING A GENETIC ALGORITHM

Research results of possibilities of packing a group of 3D-models of products in a layered build space using a genetic algorithm are presented. It is proposed to determine the efficiency of the optimization problem of rational arrangement of 3D-models group in the workspace of additive machines depending on the number of loaded products. Condition for efficient use of the layered build workspace is the minimum number of layers per product and the largest relative filling. Such criteria are important, for example, for SLS/SLM technologies. Examples of evaluation based on the analysis of derived voxel 3D model of the workspace with located products are considered. Industrial products with different geometrical complexity were selected as test 3D models. This approach allowed to perform a comparative analysis of the results depending on the design features of products. The practical realization was performed in the subsystem of packing 3D-models in a workspace, which is part of the technological preparation system for the manufacture of complex products by additive methods. This system was developed at the Department of "Integrated Technologies of Mechanical Engineering" named after M. Semko of NTU "KhPI".

A modified Q-learning algorithm for robot path planning in a digital twin assembly system

Product assembly is an important stage in complex product manufacturing. How to intelligently plan the assembly process based on dynamic product and environment information has become a pressing issue that needs to be addressed. For this reason, this research has constructed a digital twin assembly system, including virtual and real interactive feedback, data fusion analysis, and decision-making iterative optimization modules. In the virtual space, a modified Q-learning algorithm is proposed to solve the path planning problem in product assembly. The proposed algorithm speeds up the convergence speed by adding a dynamic reward function, optimizes the initial Q table by introducing knowledge and experience through the case-based reasoning algorithm, and prevents entry into the trapped area through the obstacle avoiding method. Finally, the six-joint robot UR10 is taken as an example to verify the performance of the algorithm in the three-dimensional pathfinding space. The experimental results show that the performance of the modified Q-learning algorithm is significantly better than the original Q-learning algorithm in both convergence efficiency and the optimization effect.

Towards a smart reconfiguration process for complex product manufacturing based on industrial robot cells

Towards a smart reconfiguration process for complex product manufacturing based on industrial robot cells

Effects of economic complexity, economic growth, and renewable energy technology budgets on ecological footprint: the role of democratic accountability.

The economic structure of countries can influence economic growth, energy demand, and environmental footprints. However, the literature on economic complexity and ecological footprint (EFP) nexus is scarce. Besides, democracy is an important factor that may affect environmental policies and environmental sustainability. Hence, this paper investigates the effect of democracy, economic complexity, and renewable energy technology budgets on the EFP in G7 countries controlling income and financial development from 1985 to 2017. The findings from Westerlund (J Appl Econ 23:193-233, 2008) and other cointegration methods depict cointegration among variables. The long-run estimates from the continuously updated fully modified method unfold that economic complexity contributes to reducing the EFP. However, greater democratic accountability boosts the EFP figures rather than reducing them. On the flipside, renewable energy technology budgets and financial development are evidenced to mitigate EFP. Moreover, the study unveils a U-shaped linkage between economic growth and EFP, which indicates that an increase in income level will boost EFP. Further, the study found causality from economic complexity, democracy, and renewable energy budgets to EFP. Based on these findings, it is pertinent for the G7 countries to increase the manufacturing of sophisticated and complex products. In addition, enhancing renewable energy technology budgets is essential to ensure environmental well-being.

Complex product manufacturing and operation and maintenance integration based on digital twin

Complex product manufacturing and operation and maintenance integration based on digital twin

Editorial

I am very pleased to announce that we have a new editorial structure for the journal, as I had noted in my column in our last issue in 2020. Consequently, since November 2020, seven experienced editors have joined the journal as Senior Editors in order to distribute the papers in their areas of expertise to Associate Editors, and monitor the review process in a more focused manner. Moving forward, authors can now consult a list of keywords representing the expertise of each Senior Editor at the time of submission in order to select the one whose expertise best aligns with their paper. I am grateful to these Senior Editors for their dedication to the IEEE SYSTEMS JOURNAL and for their commitment to elevate the journal's standing in the systems engineering community. This current issue spans diverse topics in complex systems and system-of-systems engineering, and, as always, it also includes many interdisciplinary papers. These topics include complex product manufacturing (as illustrated on the cover page), collaborative resource sharing, vehicular ad hoc networks, fault detection in different types of power grids, energy management in smart cities and smart distribution systems, road safety improvement, radar sensor networks, digital data markets, body area networks, and many others as well. There are also several papers on the application of machine learning to various types Digital Object Identifier 10.1109/JSYST.2021.3059465 of complex systems such as mobile networks, IoT-enabled systems, and wireless charging systems. I am certain that some of these articles will initiate further research in related topics, an established trend that we are now familiar with in the IEEE SYSTEMS JOURNAL.

Reliability Evaluation of Bogie Assembly Process Based on FMEA-FTA

Assembly is crucial in the manufacturing of complex products, and assembly quality directly affects product quality. In order to verify the assembly reliability of high-speed train bogies, taking the drive device as a research object, the assembly reliability of the drive device was evaluated and the weak links in the assembly process were obtained based on the comprehensive analysis method of FMEA-FTA. And an assembly process visualization system was developed to realize the real-time monitoring of the assembly process and improve the reliability of the assembly process. It has certain reference significance for the reliability evaluation of assembly process of similar complex products.

ABOUT IMPROVEMENT OF SETS OF REPLACEABLE GEARS GUITARS METAL CUTTING MACHINES

The article is devoted to the problems of modernization of the existing fleet of metal-cutting machines. The purpose and objectives-to determine ways and practical recommendations for resource saving in the production of machine components for the manufacture of complex products. The methods used are comparative computational experiments to determine the performance characteristics of sets of replaceable gears. The presented material contains practical recommendations on the choice of evaluation indicators and improvement of sets of replaceable gears of two-pair guitars of various gear-processing machines (5B12, 5A308P, 5111 and 5K32) based on the results of research. Confirmed the possibility of improving the characteristics of kits while maintaining the number of wheels in the kits. In conclusion, it is noted that the proposed solutions contribute to an increase in the integral quality index by 1,2857 – 6,3742 times, a decrease in the total weight of the wheels of the set by 1,4824 – 3,3093 times, an increase in the number of realized gear ratios by 1,2622 – 3,7525 times, an increase in the average density of the values of the gear ratios by 1,2136 – 3,7781 times.