Cloud Manufacturing Research Articles

Bi-objective service composition and optimal selection for cloud manufacturing with QoS and robustness criteria

As an important part of cloud manufacturing, service composition and optimal selection (SCOS) has attracted many scholars’ attentions. Although there are a large number of researches devoted to this field, plenty of challenges still remain, such as the difficulties of coping with real-life uncertainties and improving efficiency in making decisions. To this end, a bi-objective service composition and optimal selection (BoSCOS) problem which takes both QoS and robustness into account is firstly studied in this paper, its mathematical model is established after the two criteria are constructed. Then, a strengthened multi-objective gray wolf optimizer (SMOGWO) is developed to solve the above model with high efficiency, in which three improvement strategies are introduced to the original MOGWO: (1) the opposition based learning (OBL) strategy is adopted to improve the quality of initial population; (2) a leader update strategy is designed to explore better search leaders and balance the exploitation and exploration abilities; (3) an improved archiving strategy is developed to retain all possible dominant individuals, so as to improve the population diversity based on the Pareto dominance. Finally, the effectiveness of the proposed algorithm is verified on 8 BoSCOS problems with different scales and 17 benchmark functions, results show that the improvement strategies are effective and SMOGWO is superior to its competitors in terms of convergence and population diversity.

Logistics-involved service composition in a dynamic cloud manufacturing environment: A DDPG-based approach

Service composition as an important technique for combining multiple services to construct a value-added service is a major research issue in cloud manufacturing. Highly dynamic environments present great challenges to cloud manufacturing service composition (CMfg-SC). Most of previous studies employ heuristic algorithms to solve service composition issues in cloud manufacturing, which, however, are designed for specific problems and lack adaptability necessary to dynamic environment. Hence, CMfg-SC calls for new adaptive approaches. Recent advances in deep reinforcement learning (DRL) provide a new means for solving this issue. Based on DRL, we propose a Deep Deterministic Policy Gradient (DDPG)-based service composition approach to cloud manufacturing, with which optimal service composition solutions can be learned through repeated training. Performance of DDPG in solving CMfg-SC in both static and dynamic environments is examined. Results obtained with another DRL algorithm - Deep Q-Networks (DQN) and the traditional Ant Colony Optimization (ACO) are also presented. Comparison indicates that DDPG has better adaptability, robustness, and extensibility to dynamic environments than ACO, although ACO converges faster and its steady QoS value of the service composition solution is higher than that of DDPG by 0.997%. DDPG outperforms DQN in convergence speed and stability, and the QoS value of the service composition solution of DDPG is higher than that of DQN by 3.249%.

Unrelated parallel machine scheduling with processing cost, machine eligibility and order splitting

Under the background of the emerging of shared manufacturing economics, this work addresses a new production order scheduling problem on unrelated parallel machines. Customer orders with release times are of various types depending on their specific product demands. Unrelated machines may be rented for processing orders via one cloud manufacturing service platform. It occurs a uniform processing cost once any machine is rented (via contract) for a given length time duration to process the orders. Each machine is generally able to process some but not all types of orders, i.e., machine eligibility is considered. Orders can be split into sub-orders and processed on their eligible machines simultaneously. For the objective of minimizing the weighted sum of total completion time of orders and total processing cost of machines being used, we establish a mixed integer linear programming model. We provide a lower bound of the considered problem by constraint relaxation, and present the pseudocode of an approach to obtain the lower bound. CPLEX is employed to generate optimal solutions for small-scale instances. For large-scale instances, two heuristic algorithms named Type-Based Greedy and Improved Differential Evolution are developed. The former algorithm selects a smallest set of machines to process the jobs and makes use of job splitting as much as possible, while the latter one is to acquire a best local optimal solution via finite times random global search in the feasible region. Computational experiments are carried out to demonstrate the efficiency and effectiveness of the proposed heuristics.

Workload balance-based dynamic two-sided matching decision-making approach for cloud manufacturing tasks and services under uncertain preferences

PurposeThis paper aims to develop a dynamic two-sided stable matching method based on preference information of the matching objects in uncertain environments, so as to solve the matching problem of cloud manufacturing tasks and services with load balancing.Design/methodology/approachFor dynamic two-sided matching, due to the complexity of social environment and the limitation of human cognition, hesitation and fuzziness always exist in the process of multi-criteria assessment. First, in order to obtain the accurate preference information of each matching object, uncertain linguistic variables, uncertain preference ordinal and incomplete complementary matrices are used to evaluate multi-criteria preference information. This process is undertaken by considering the probability of each possible matching pair. Second, the preference information at different times is integrated by using the time-series weight to obtain the comprehensive satisfaction degree matrices of the matching objects. Further, the load adjustment parameter is used to increase the satisfaction degree of the matching objects. Afterward, a dynamic two-sided stable matching optimization model is constructed by considering stable matching conditions. The model aims to maximize the satisfaction degree and minimizes the difference in the satisfaction degree of matching objects. The optimal stable matching results can be obtained by solving the optimization model. Finally, a numerical example and comparative analysis are presented to demonstrate the characteristics of the proposed method.FindingsUncertain linguistic variables, uncertain preference orders and incomplete complementary matrices are used to describe multi-criteria preference information of the matching objects in uncertain environments. A dynamic two-sided stable matching method is proposed, based on which a DTSMDM (dynamic two-sided matching decision-making) model of cloud manufacturing with load balancing can be constructed. The study proved that the authors can use the proposed method to obtain stable matching pairs and higher matching objective value through comparative analysis and the sensitivity analysis.Originality/valueA new method for the two-sided matching decision-making problem of cloud manufacturing with load balancing is proposed in this paper, which allows the matching objects to elicit language evaluation under uncertain environment more flexibly to implement dynamic two-sided matching based on preference information at different times. This method is suitable for dealing with a variety of TSMDM (two-sided matching decision-making) problems.

Bibliometric Method for Manufacturing Servitization: A Review and Future Research Directions

To gain sustainable development, it is a trend that manufacturing companies are change the value chain from manufacturing-centric to service-centric. Therefore, the capability of the manufacturing service is as significant as the production ability of enterprises, which reflects the supply chain management (SCM), flexible production, production efficiency, and other indicators of the enterprises. It is the first paper to discuss the sustainability of service-oriented manufacturing using bibliometric analysis. It derives a detailed review and future outlook on the development of manufacturing servitization, indicating the research directions for future development, and provides a valuable reference for researchers in related directions. The bibliometric analysis discusses countries or regions, research areas, authors, keywords, institutions, and journals based on the literature data from the Web of Science (WoS). The results show that research on manufacturing services has gradually received attention since its inception and has become popular since 2008. The papers published from 2008 to 2021 account for 77.62%. The USA is the most studied country on this topic, followed by China and the UK. The International Journal of Production Research regarding the most quantity of articles, and Beihang University is the most influential institution in this field. The largest amount of articles published in the area of “business and economics”, amounting to 1565 articles. In recent years, the main research areas included “Industry 4.0”, “cloud manufacturing (CMfg)”, “Internet of Things (IoT)”, “big data” and “services innovation”. Finally, “digital and intelligent manufacturing” and “product-service systems” are potential research directions for the future.

A Novel Implementation Framework of Digital Twins for Intelligent Manufacturing Based on Container Technology and Cloud Manufacturing Services

Many core technologies of Industry 4.0 have gained substantial advancement in recent years. Digital Twin (DT) has become the key technology and tool for manufacturing industries to realize intelligent cyber-physical integration and digital transformation by leveraging these technologies. Although there have been many DT-related works, there is no standard definition, unified framework, and implementation approach of DT until now. Widely developing DTs for the manufacturing industry is still challenging. Thus, this paper proposes a novel implementation framework of digital twins for intelligent manufacturing, denoted as IF-DTiM, which possesses several distinct merits to distinguish itself from previous works. First, IF-DTiM fully utilizes new-generation container technology so that DT-related applications and services can be packaged in a self-contained way, rapidly deployed, and robustly operated with the capabilities of failover, autoscaling, and load balancing. Second, it leverages existing intelligent cloud manufacturing services to realize the intelligence for DT externally in a scalable and plug-and-play manner instead of using traditional approaches to embed intelligence in DT. Third, IF-DTiM contains Product DT for products, Equipment DT (i.e., EQ DT) for equipment, and Process DT for production lines, which can generically fulfill the demands and scenarios to achieve intelligent manufacturing for various manufacturing industries. Testing results show that IF-DTiM can achieve remarkable performance in rapid deployment and real-time data exchanges of DT-related applications. Finally, we develop an example DTiM system for CNC machining based on IF-DTiM to demonstrate its efficacy and applicability in facilitating the manufacturing industry to build their DT systems. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Developing Digital Twin (DT) systems to realize intelligent manufacturing is challenging. The proposed IF-DTiM (Implementation Framework of Digital Twins for Intelligent Manufacturing) provides a novel container-technology and cloud-manufacturing-service-based systematic methodology for building DTiM. In this paper, we present the system architecture and several operational scenarios (e.g., how to create and use DTs) of IF-DTiM, together with the design of its core functional mechanisms (e.g., rapid deployment scheme for DT, real-time data exchange for DT, DT interface pattern, and general workflow architecture for DT). Also, an example DTiM system for CNC machining based on IF-DTiM is presented to facilitate the practitioners to adopt the designs and niches in IF-DTiM to build their desired DTiM systems.

System and Risk Analysis of Cloud-Manufacturing System

The Cloud manufacturing(C-Mfg) system involves remote distributed manufacturing resources and capabilities collaborating as a single virtual entity. The system receives orders for custom products and provides manufacturing as a service to the end customers. The primary activities of the system, among others, are transaction control, resource allocation and monitoring, distributed manufacturing, quality control, and delivery of consignments to the customers. The actual manufacturing is done by a network of third-party partner manufacturers providing the services to end customers, helping them with cost reduction, shorter time-to-market, and enabling efficient collaboration between manufacturers in the CMfg network. This paper aims to deep dive into C-Mfg as a system and perform a risk analysis to assess and mitigate the risks associated with the system. While cybersecurity and data security-related concerns are deemed the most serious and need immediate management for the system to succeed, the control of data, compliance with manufacturing standards and guidelines, and lack of accountability and ownership are other serious risks that need significant attention. Identifying these factors will help channel the focus on the management and resolution of these risks to establish digital trust in the C-Mfg system leading to the system’s success.

A two-stage method for large-scale manufacturing service stable matching under uncertain environments in Cloud Manufacturing

With the development of Cloud Manufacturing, the scale of manufacturing platforms has increased. Large-scale platforms increase the difficulty of manufacturing sharing, like time consumption and weak matching. To mitigate these problems, a two-stage method is proposed to support large-scale stable matching under uncertain environments. The first level aims to solve the problem of low efficiency. Considering the time-consuming mutual assessment, cloud models are used to present the preference information of the decision-makers. Meanwhile, to reduce the difficulties of sharing, a density-based method was used to elucidate the non-convex preferences of the customers and manufacturing services. Based on the clustering result, a subgroup-to-subgroup matching method is proposed based on the consensus reaching processes. After that, in the second level, game models among customers, manufacturing services, and platforms are established to realize stable matching. Subsequently, to solve the game models, an enhanced grey wolf algorithm with a parallel-searching mechanism has been designed. Finally, a manufacturing sharing platform is considered an example. Also, the proposed method was compared with methods adopted in previous studies to demonstrate the advantages of the proposed model.

A hybrid teaching-learning-based optimization algorithm for QoS-aware manufacturing cloud service composition

A hybrid teaching-learning-based optimization algorithm for QoS-aware manufacturing cloud service composition

Development of public cloud manufacturing markets: a mechanism design approach

Online manufacturing markets are new emerging types of markets that are spreading in the shade of public Cloud Manufacturing. This paper introduces a public Cloud Manufacturing market and denotes its differences from a private one. Public Cloud Manufacturing enables service-oriented manufacturing models for everyone in society. The prosperity of such market is tied to appropriate matching between providers to consumers. This paper elaborates on a mechanism to prescribe an appropriate allocation between resources and demands in this public market. The mechanism exploits the VIKOR method to develop preference lists for providers and consumers, the method also is augmented by the Intuitionistic Fuzzy Sets to remove complexities and uncertainties that exist in the process of ranking; and Deferred Acceptance (DA) algorithm is utilised as the matching algorithm of the mechanism. The performance of the mechanism is analysed under influence of the proposer, resource availability and matching algorithm. The influence of proposer study indicates that the situation of the consumer as the proposer is preferred to the providers’ situation as proposer; the influence of resource availability study indicates a balanced situation is preferred to the scarcity and abundancy situations and the influence of matching algorithm indicates that DA outperforms Top Trading Cycle (TTC) algorithm as the matching algorithm of the mechanism.

Parallel batch processing machines scheduling in cloud manufacturing for minimizing total service completion time

This paper considers the integrated scheduling problem of production and delivery on parallel batch processing machines with non-identical capacities in different locations in cloud manufacturing. It is assumed that the jobs have arbitrary release times, different job sizes, unequal processing times, and unique information of customers submitting jobs. The service completion time of a job is the sum of the production completion time and the delivery duration. The objective of the studied problem is to minimize the total service completion time. A mixed-integer programming (MIP) model is presented to solve this problem. Since the problem is NP-hard, an efficient heuristic algorithm and an improved particle swarm optimization algorithm are proposed. The two proposed algorithms are compared with several state-of-the-art algorithms and the commercial optimization solver (Gurobi) through extensive experiments, verifying the effectiveness of the proposed algorithms.

A novel method for customer-oriented scheduling with available manufacturing time windows in Cloud Manufacturing

Cloud Manufacturing is customer-oriented manufacturing, customers’ satisfaction is important for the platform. To enhance the satisfaction of customers, previous studies aimed at maximizing the Quality of Services, but the timeliness which means delivering the products to customers on time has not been paid enough attention. For timeliness, because the customer is not rational, the satisfaction is not linear with tardiness and earliness, we use the prospect theory, a famous theory of psychology, to calculate the satisfaction based on tardiness and earliness in scheduling, not minimize the total tardiness and earliness like previous studies. Then, the manufacturing services may only provide several available manufacturing time windows to the platform, because part of the time was occupied by the previous customers or the manufacturing services’ own production before. To utilize the potential manufacturing capacity, we study the manufacturing services with time windows. Also, the adjusted speed of the manufacturing services is studied. Finally, to solve the scheduling problem, we proposed an improved hybrid artificial bee colony algorithm. For our proposed algorithm, to guide the evolution of the algorithm on the stage of employer bee, we design a new selecting mechanism based on the grey wolf algorithm. On the onlooker bee, we regard the solver as part of the algorithm, the solver is used to find new effective scheduling sequences. We also verify the algorithm's effectiveness through numerical experiments.

A Survey of Process Monitoring Using Computer-Aided Inspection in Laser-Welded Blanks of Light Metals Based on the Digital Twins Concept

The benefits of laser welding include higher production values, deeper penetration, higher welding speeds, adaptability, and higher power density. These characteristics make laser welding a superior process. Many industries are aware of the benefits of switching to lasers. For example, metal-joining is migrating to modern industrial laser technology due to improved yields, design flexibility, and energy efficiency. However, for an industrial process to be optimized for intelligent manufacturing in the era of Industry 4.0, it must be captured online using high-quality data. Laser welding of aluminum alloys presents a daunting challenge, mainly because aluminum is a less reliable material for welding than other commercial metals such as steel, primarily because of its physical properties: high thermal conductivity, high reflectivity, and low viscosity. The welding plates were fixed by a special welding fixture, to validate alignments and improve measurement accuracy, and a Computer-Aided Inspection (CAI) using 3D scanning was adopted. Certain literature has suggested real-time monitoring of intelligent techniques as a solution to the critical problems associated with aluminum laser welding. Real-time monitoring technologies are essential to improving welding efficiency and guaranteeing product quality. This paper critically reviews the research findings and advances for real-time monitoring of laser welding during the last 10 years. In the present work, a specific methodology originating from process monitoring using Computer-Aided Inspection in laser-welded blanks is reviewed as a candidate technology for a digital twin. Moreover, a novel digital model based on CAI and cloud manufacturing is proposed.

Integrated configuration design and capacity planning in a dynamic cloud manufacturing system

A cloud manufacturing (CMfg) system is presented as a novel service- and customer-oriented manufacturing paradigm that integrates the distributed manufacturing enterprises to share their manufacturing capabilities or resources and collaborate as an interconnected system in a dynamic environment. Since the high performance of this system depends on the formation of a suitable group of manufacturing service providers, this paper develops an integrated c onfiguration design and capacity planning problem for the CMfg system by considering the dynamic environment of this system. In this regard, dynamic service providers and dynamic demand are considered as two aspects of the dynamic nature of this system. A multi-period multi-objective mathematical model is proposed by maximising the utilities of all three stakeholders of the system. Moreover, three extensions of a discrete multi-objective grey wolf optimiser (DMOGWO) algorithm are devised to solve the medium- and large-scale instances. A comprehensive computational experiment is conducted to assess the performance of the developed meta-heuristic algorithms. Furthermore, by carrying out a sensitivity analysis, some managerial insight is suggested for the managers.

Assessing cloud manufacturing applications using an optimally rectified FAHP approach

Cloud Manufacturing (CMfg) is a new manufacturing paradigm that promises to reduce costs, improve data analysis, increase efficiency and flexibility, and provide manufacturers with closer partnerships. However, most past CMfg research has focused on either the information technology infrastructure or the planning and scheduling of a hypothetical CMfg system. In addition, the cost effectiveness of a CMfg application has rarely been assessed. As a result, a manufacturer is not sure whether to adopt a CMfg application or not. To address this issue, an optimally rectified fuzzy analytical hierarchy process (OR-FAHP) approach is proposed in this study to assess a CMfg application. The OR-FAHP approach solves the inconsistency problem of the conventional FAHP method, a well-known technology assessment technique, to make the analysis results more trustable. The OR-FAHP approach has been applied to assess and compare 10 CMfg applications.

A variable-length encoding genetic algorithm for incremental service composition in uncertain environments for cloud manufacturing

Service composition and optimal selection (SCOS) plays a crucial role in cloud manufacturing (CMfg). While the existing service composition methods are hard to address the changes and uncertainties of CMfg dynamic environment. Therefore, a variable-length encoding genetic algorithm for structure-varying incremental service composition (ISC-GA) is proposed in this paper. Specifically, a novel variable-length encoding scheme containing structural information is proposed to describe the uncertain and changing process model. And the improved crossover and mutation algorithm suitable for individuals with nonlinear varying structure and incremental service composition is designed. It is realized by optimizing both the process structure and service instance combinations, and overcomes the drawbacks resulted from single preset process structure. Due to the difficulty of fitness computation caused by uncertain process structures, novelty is introduced as a new evolutionary pressure, and a novel framework for ISC-GA is presented, which helps to find both novel and high-performance solutions. Experimental results indicate the effectiveness of the proposed approach.

Are Industry 4.0 technologies enablers of lean? Evidence from manufacturing industries

PurposeThis study aims to propose a conceptual model indicating the impact of Industry 4.0 (I4.0) technologies on lean tools. Additionally, it prioritizes I4.0 technologies for the digital transformation of lean plants.Design/methodology/approachThe authors conducted a questionnaire-based survey to capture the perception of 115 experts of manufacturing industries from Germany, India, Taiwan and China. The impact of I4.0 on lean tools, using analysis of variance (ANOVA). Further, the authors drew a prioritization map of I4.0 on the employment of lean tools in manufacturing, using the Best–Worst Method (BWM).FindingsThe findings indicate that cloud manufacturing, simulation, industrial internet of things, horizontal and vertical integration impact 100% of the lean tools, while both cyber-security, big data analytics impact 93% of the lean tools and advanced robotics impact 74% of the lean tools. On the other hand, it is observed that augmented reality and additive manufacturing will impact 21% and 14% of the lean tools, respectively.Practical implicationsThe results of this study would help practitioners draw up a strategic plan and roadmap for implementing lean 4.0. The amalgamation of lean with I4.0 technologies in the right combination would enhance speed productivity and facilitate autonomous operations.Originality/valueStudies exploring the influence of I4.0 on lean manufacturing lack comprehensiveness, testing and validation. Importantly, no studies in the recent past have explored mapping and prioritizing I4.0 technologies in the “lean” context. This study thereby attempts to establish a conceptual model, indicating the influence of I4.0 technologies on lean tools and presents the hierarchy of all digital technologies.

High-end equipment: An improved two-sided based S&M matching and a novel Pareto refining method considering consistency

In order to avoid resources waste and monopoly in high-end equipment manufacturing, the concept of a cloud platform was proposed, in which suppliers and manufacturers can match each other in two-sided. As a result of the increasing information complexity and the fuzziness of human cognition, matching evaluation values may contain some hesitancy and ambiguity. To simulate this situation, we consequently propose an improved two-sided-based S&M matching model and a novel Pareto refining method for a high-end equipment cloud manufacturing platform under a hesitant fuzzy environment. Firstly, the traditional maximum deviation method for calculating attribute weights is improved to adapt to multiple agents in S&M matching. Sequentially, the hesitant fuzzy set (HFS) is applied to describe the fuzziness of decision agents. Simultaneously, we innovatively introduce the score and deviation of HFS to comprehensive satisfaction degree calculating as objective functions. Subsequently, considering the matching consistency, we declare a novel Pareto refining method based on an interval-valued satisfaction matrix to deal with Pareto solutions in the two-sided matching multiple objective model. Finally, an illustrative case is employed to prove the practicability and usability of the two-sided-based S&M matching model in the high-end equipment cloud manufacturing platform. It reveals that this model can not only obtain multiple matching pairs with maximal satisfaction but also can select the most consistent S&M portfolio.

A self-learning bee colony and genetic algorithm hybrid for cloud manufacturing services

A self-learning bee colony and genetic algorithm hybrid for cloud manufacturing services

Multi-phase matching mechanism for stable and optimal resource allocation in cloud manufacturing platforms Using IF-VIKOR method and deferred acceptance algorithm

ABSTRACT Public platforms are one of the most important Cloud Manufacturing modes. Public platforms enable an environment for manufacturers and demanders to freely and directly connect with each other. Exploiting the high potentials of public platforms depends on final matching. This paper has developed a multi-phase matching mechanism for stable and optimal resource allocation in public platform. The proposed mechanism grades the demanders using an intuitionistic fuzzy VIKOR method using three measures of quality, time, and sustainability. Then, the mechanism clusters the demanders based on these three measures; and finally, allocates the clusters using the Deferred Acceptance (DA) algorithm to the manufacturers. The mechanism is examined using a case study from the Iranian automotive industry. The paper has extended and examined the model under three directions of: the grading method impact, clustering analysis impact, and the platform mode impact. Based on the experiments, the intuitionistic fuzzy TOPSIS-DA results on average 4.34% better outcome rather than the intuitionistic fuzzy VIKOR-DA. The proposed heuristic and optimized clustering method results on average 1.09% better solution rather than the KM clustering method. Also, the analysis of the PoS reveals that a private platform yields on average 10% better utility rather than a public platform.