Search

Big data technology and predictive analytics exhibit advanced potential for business intelligence (BI), especially for decision-making. This study aimed to explore current research studies, historic developing trends, and the future direction. A bibliographic study based on CiteSpace is implemented in this paper, 681 non-duplicate publications are retrieved from databases of Web of Science Core Collection (WoSCC) and Scopus from 2000 to 2021. The countries, institutions, cited authors, cited journals, and cited references with the most academic contributions were identified. Social networks and collaborations between countries, institutions, and scholars are explored. The cross degree of disciplinaries is measured. The hotspot distribution and burst keyword historic trend are explored, where research methods, BI-based applications, and challenges are separately discussed. Reasons for hotspots bursting in 2021 are explored. Finally, the research direction is predicted, and the advice is delivered to future researchers. Findings show that big data and AI-based methods for BI are one of the most popular research topics in the next few years, especially when it applies to topics of COVID-19, healthcare, hospitality, and 5G. Thus, this study contributes reference value for future research, especially for direct selection and method application.

Abstract Conceptual design is the crucial stage of selecting and determining product composition and configuration, which greatly affects product performance and cost. In conceptual design stage, designers have the maximum design freedom in order to put forward to the optimal design solution in terms of assembly, manufacturing and cost. However, the above product aspects are analyzed independently in current industry, and a guided decision-making method based on multi-objective criteria is missing. Therefore, it is necessary to introduce a multi-objective analysis method to obtain an optimal conceptual scheme considering various aspects of product. Due to the complexity of product conceptual solution generation, this study divides the multi-objective analysis process into multi-objective solution optimization and multi-objective solution selection. The non-dominated solution set can be obtained from all the potential solutions in the former step. Then, the optimal conceptual solution can be obtained from the non-dominated solutions set in the latter step. The two-stage multi-objective analysis method has two advantages: (1) large dominated solutions can be quickly eliminated which can reduce the workload of solution selection; (2) TOPSIS method is easy to implement, which can work with attribute weights and scores of each design option. Finally, using the conceptual design of a centrifugal compressor as an example, the method's availability and practicality are demonstrated.

Abstract Whether the design of product innovation can highly match the customer demand is the key to extend the product life cycle, and it is also the basis for enterprises to carry out continuous production and operation. The first step of product innovation is to identify the relationship between customer demands and design factors of product innovation. This paper focuses on the problems of market control, due to the wide range and deep level of knowledge from customer demands in the process of product innovation. To better meet the customer demands, combined with Entropy Theorem, Prospect Theory and Grey Correlation Method, this paper puts forward a method of importance of design factors of product innovation considering customer demands. First, the Entropy Theorem and Prospect Theory are introduced to calculate the importance of demand factors from the perspective of customers and experts. Second, the priority ranking of design factors of product innovation from the perspective of customer demand is calculated through Gray Correlation Method and Fuzzy TOPSIS. Finally, this method is availability and feasibility thought taking the continuous innovation of electric vehicle as an example.

With the development of specialization, coordination and intelligence in the manufacturing service process, the issue of how to quickly extract potential resources or capabilities for distributed manufacturing service requirements, and how to carry out resource matching for manufacturing service requirements with correlated mapping characteristics, have become the critical issues to be addressed in the cloud manufacturing environment. Through the combination of the characteristics of relevance, synergy and diversity of manufacturing service tasks on the intelligent cloud platform, a matching decision method for manufacturing service resources is proposed in this paper based on multidimensional information fusion. On the basis of integrating multidimensional information data in cloud manufacturing resource, the information entropy and rough set theory are applied to classify the importance of manufacturing service tasks, while the matching capability are analyzed by using a hybrid collaborative filtering (HCF) algorithm. Then, the information of function attribute, reliability and preference is employed to match and push manufacturing service resources or capabilities actively, so as to realize the matching decision of manufacturing service resources with precise quality, stable service and maximum efficiency. At last, a case study of resources matching decision for body & chassis manufacturing service in a new energy automobile enterprise is presented, in which the experimental results show that the proposed approach is more accuracy and effective compared with other different recommendation algorithms.

Active participation closely associates with the sustainable operation of co-creation communities. Different from recent studies on the promotion of sustainable operation by identifying the internal and external motivations of user participation, this paper aims to analyze the mechanism regarding how different motivations affect the decision of user participation from group-level perspective. To better understand the mechanism, internal and external motivations are, respectively, captured by return-cost analysis and user interactive network. Afterwards, a network evolutionary game model was formulated to analyze the dynamic strategy selection (e.g., active participation and passive participation) of all users. In addition, the stable equilibrium and evolutionary path of strategies are analyzed through computational experiments. Results indicate the following: (a) Rewards have an influence on the promotion of active participation. However, with the continued growth of rewards, this promotion does not make sense sustainably. (b) The promotional effect of information noise on the selection of active participation can be found when passive participation is the dominant strategy. However, the inhibitory effect can be seen in populations that mainly adopt active participation. (c) The scale-free feature of user interactive network inhibits the selection of active participation when active participation is the dominant strategy in populations. Results found here is beneficial for managers to implement the specified policies and thus to achieve the sustainability of co-creation community.

The identification and evaluation of important parts play an important role in effective production arrangement and shortening the product development in the product design stage. In this paper, a complex product node importance evaluation method based on multilayer network is proposed to identify and evaluate importance parts faster. First, a complex product design expression network based on “function behavior structure (FBS)” multilayer complex network is established. Second, the evaluation index system of important design parts for complex products based on multilayer network is constructed. Third, a three-parameter grey relational model based on the fuzzy analytic hierarchy process and the Gini coefficient method is proposed. Finally, this method is available and feasible through taking the large permanent magnet synchronous centrifugal unit as an example.

Among the inherent problems in recommendation systems are data sparseness and cold starts; the solutions to which lie in the introduction of knowledge graphs to improve the performance of the recommendation systems. The results in previous research, however, suffer from problems such as data compression, information damage, and insufficient learning. Therefore, a DeepFM Graph Convolutional Network (DFM-GCN) model was proposed to alleviate the above issues. The prediction of the click-through rate (CTR) is critical in recommendation systems where the task is to estimate the probability that a user will click on a recommended item. In many recommendation systems, the goal is to maximize the number of clicks so the items returned to a user can be ranked by an estimated CTR. The DFM-GCN model consists of three parts: the left part DeepFM is used to capture the interactive information between the users and items; the deep neural network is used in the middle to model the left and right parts; and the right one obtains a better item representation vector by the GCN. In an effort to verify the validity and precision of the model built in this research, and based on the public datasets ml1m-kg20m and ml1m-kg1m, a performance comparison experiment was designed. It used multiple comparison models and the MKR and FM_MKR algorithms as well as the DFM-GCN algorithm constructed in this paper. Having achieved a state-of-the-art performance, the experimental results of the AUC and f1 values verified by the CTR as well as the accuracy, recall, and f1 values of the top-k showed that the proposed approach was excellent and more effective when compared with different recommendation algorithms.

In view of the common and difficult to solve vehicle vibration problem, taking a large truck manufacturing enterprise in China as an example, an improved model for solving truck vibration problem is established by using the G8D method, and the unbalanced excitation force of the wheel system is analysed. The coupling of the excitation frequency and the natural frequency of the system leads to the resonance phenomenon, as well as the inadequate damping function of the system, is the fundamental cause of the vibration problem. After verifying and implementing permanent correction measures at the same time at the three levels of components, devices, and the entire vehicle, the acceleration of the seat guide rails for the vibration performance of the truck reduces from the original state 1.04 m/s2 to 0.6 m/s2, a decrease of 42.3%, which reaches the best level of mainstream cars in the country and is close to the optimal level of 0.5 m/s2 among the same kinds of cars in Germany. Therefore, the improved model can improve the sustainability of product manufacturing, provide industry guidance for solving the quality problem of truck vibration, and provide a sustainable guarantee for social public transport safety.

Fracture behaviors of 42CrMo ultrahigh strength steel-based bolt have been experimentally studied including macroscopic and microscopic fracture observation, metallographic test, mechanical property testing, and energy spectrum analysis. The results show that a large amount of structure defects, such as sulfide inclusions, band, and carbon depletion, appear in the fracture origin region and matrix of the bolt. Such defects reduce fatigue strength of materials and easily yields fatigue fracture origin. In addition, sulfide inclusions provide easy access to crack growth, gradually reducing the effective cross section of the bolt accompanying with increasing stress and finally causes fracture when stress exceeds the material fracture strength. The fracture mechanism is also explored based on fracture failure criterion and fatigue crack growth curve.

Customer returns are a common phenomenon in many industries, and they have a significant impact on business organizations and their supply chains. False failure returns are returned products that have no functional or cosmetic defects, and they represent a large body of customer returns in practice. In this paper, we develop a mixed-integer nonlinear programming model to study a multicommodity location-inventory problem in a forward-reverse logistics network. This model minimizes the total cost in this network by considering false failure returns, and it also considers many real-world business scenarios in forward and reverse logistics flows. Moreover, we design a new heuristic approach to solve the model efficiently. Finally, numerical experiments are conducted to validate our solution approach and provide meaningful managerial insights.

Facility location, inventory management, and vehicle routing are three important decisions in supply chain management, and location-inventory-routing problems consider them jointly to improve the performance and efficiency of today’s supply chain networks. In this paper, we study a location-inventory-routing problem to minimize the total cost in a closed-loop supply chain that has forward and reverse logistics flows. First, we formulate this problem as a nonlinear integer programming model to optimize facility location, inventory control, and vehicle routing decisions simultaneously in such a system. Second, we develop a novel heuristic approach that incorporates simulated annealing into adaptive genetic algorithm to solve the model efficiently. Last, numerical analysis is presented to validate our solution approach, and it also provides meaningful managerial insight into how to improve the closed-loop supply chain under study.

To mitigate or reduce various losses and improve efficiency of disaster response, the focus of this paper is to design optimized strategies of emergency organization allocation regarding sustainability. Firstly, an integrated framework including several elements such as emergency organization, task, decision-agents, environment and their relations is developed from a systematic perspective. Then, this problem is formulated as a novel multi-objective 0-1 integer programming model to minimize total weighted completion times, total carbon emissions and total emergency costs. Next, branch and bound approach and handling strategies for multiple objectives are designed to solve this model. Finally, a case study from the Wenchuan earthquake is presented to illustrate the proposed model and solution strategies. Computational results demonstrate their significant potential advantages on allocating emergency organization from the perspectives of best practice, objective functions, preferences of decision-agents, and problem size. [ABSTRACT FROM AUTHOR]

The reluctance or incapability of further increasing production resources has made many enterprises suffering from high resource-workload situation. Production dynamics thus cannot be resolved by single resource independently, yet have to make an integral use of the adjustable capability of multiple resources of the whole system in a synchronized way. This paper considers a dynamic production logistics (PL) process comprising multiple independently operated PL stages, which adopts Internet of Things to capture real-time execution dynamics and rely on plan (re)scheduling and cloud-based resources re-configuration to cope with dynamics. A generic dynamic production logistics synchronization (PLS) solution is proposed. Qualitatively, a multi-phase multi-stage multi-degree synchronization control mechanism is put forward toward a PL system with generic structure and typical execution dynamics. Quantitatively, collaborative optimization is applied to assist the PLS to obtain the synchronization results. With a real-life case study, the effectiveness of the proposed mechanism and method has been verified. A set of sensitivity analysis is also conducted toward dynamics of different degree and different time, which provides significant managerial implication to PL managers to better deal with dynamics. [ABSTRACT FROM AUTHOR]

For improving the current pricing mode of medical services, the present study seeks to explore the pricing elements and processes, and establish the dynamic pricing model of involving both the government and hospitals. The pricing process and mathematical model show the logical relationships between medical prices and pricing elements. The causal relationship model reveals how to accomplish dynamic equilibrium between elements. The simulation model has been built based on system dynamics theory. Results of the simulation and sensitivity tests show that different grades of hospitals while applying the pricing model may better perform their respective responsibilities and continuously improve core strengths. [ABSTRACT FROM AUTHOR]