A cost benefit analysis for industry 4.0 in a job shop environment using a mixed integer linear programming model

As the manufacturing industry is approaching implementation of the 4th industrial revolution, changes will be required in terms of scheduling, production planning and control as well as cost-accounting departments. Industry 4.0 promotes decentralized production and hence, cost models are required to capture costs of products and jobs within the production network considering the utilized manufacturing system paradigm A new mathematical cost model is proposed for assessing the cost-benefit analysis of introducing Industry 4.0 elements to the manufacturing facility, specifically, integrating and connecting external suppliers as strategic partners and establishing an infrastructure for communicating information between the manufacturing company and its strategic suppliers. The mathematical model takes into consideration the bi-directional relationship between hourly rates and total hours assigned to workcentres/activities in a certain production period. A case study, from a multinational machine builder, is developed and solved using the proposed model. Results suggest that though an additional cost is required to establish infrastructure to connect suppliers, the responsiveness and agility achieved resulting from uncertainty outweighs the additional cost.     

A two-layer social network model for manufacturing service composition based on synergy: A case study on an aircraft structural part

Cloud manufacturing is an emerging manufacturing paradigm, with the issue of service composition being one of its most significant challenges. The current researches take the view that all manufacturing services are of equal importance. However, in fact, manufacturing services that owns scarce resources are more important than ordinary one, especially in the production of complex products. Hence, it is significant to meet the requirements of manufacturing services that own scarce resources first. Meanwhile, due to the increasing complexity of products, a high degree of synergy is required in service composition. Our study explores a new framework of social relationships from the perspective of synergy. A two-layer social network model is first proposed for resource allocation that takes synergy and priority into account. The upper layer of this model is occupied by the manufacturing services with scare resources. The lower layer is occupied by ordinary manufacturing services. All services are connected by social relationships. For the master-slave characteristic of the model, the two-layer network is embedded into bi-level programming. Then, an improved genetic algorithm is designed to solve the problem. Finally, the effectiveness of the model and algorithm are verified using a structural part of the Modern Ark 60 as an example.     

Development of real-time sketch-based on-the-spot process modeling and analysis system

Contemporary manufacturing processes require faster real-time controls against dynamic and volatile production environments. While a corresponding simulation model is considered a prerequisite system for the real-time control of a contemporary manufacturing process, simulation modeling and relevant analysis have supported these real-time features comparatively less. These issues might cause procrastination of the simulation modeling, and result in wrong decisions and inaccurate controls. In order to overcome these issues, a new real-time simulation modeling and analysis system is proposed. The proposed system supports sketch-based simulation modeling. The simulation model is constructed using modelers’ sketches of predefined simulation symbols. The sketches are converted automatically into a corresponding stochastic queueing network using Self-organizing Map, a type of neural network. Then, the model is simulated and analyzed using the embedded stochastic queueing analyses. The effectiveness of the proposed system is proven with the modeling, simulation and analyses of several real-time manufacturing cases.     

Mathematical model and discrete artificial Bee Colony algorithm for distributed integrated process planning and scheduling

With the development of the globalization of economy and manufacturing industry, distributed manufacturing mode has become a hot topic in current production research. In the context of distributed manufacturing, one job has different process routes in different workshops because of heterogeneous manufacturing resources and manufacturing environments in each factory. Considering the heterogeneous process planning problems and shop scheduling problems simultaneously can take advantage of the characteristics of distributed factories to finish the processing task well. Thus, a novel network-based mixed-integer linear programming (MILP) model is established for distributed integrated process planning and scheduling problem (DIPPS). The paper designs a new encoding method based on the process network and its OR-nodes, and then proposes a discrete artificial bee colony algorithm (DABC) to solve the DIPPS problem. The proposed DABC can guarantee the feasibility of individuals via specially-designed mapping and switching operations, so that the process precedence constraints contained by the network graph can be satisfied in the entire procedure of the DABC algorithm. Finally, the proposed MILP model is verified and the proposed DABC is tested through some open benchmarks. By comparing with other powerful reported algorithms and obtaining new better solutions, the experiment results prove the effectiveness of the proposed model and DABC algorithm successfully.     

COMBINING A RADIAL BASIS NEURAL NETWORK WITH TIME SERIES ANALYSIS TECHNIQUES TO PREDICT MANUFACTURING PROCESS PARAMETERS

The accurate prediction of the values of critical quality parameters of a product during the production stage is a key factor in the success of a manufacturing operation. Neural network algorithms have been used to successfully predict process parameter values. However, techniques to further improve the predictive capability of neural network models are sought. Thus, an analysis was conducted to determine if the predictive capability of the network would he improved if the prediction from a time series model of a manufacturing process parameter were included in the training data set of a radial basis function neural network model. A manufacturing process data set was evaluated, and the use of the time series model prediction significantly improved the neural network's prediction of critical process parameters. Often in a manufacturing environment, the collection of adequate amounts of data for network training is difficult. This integrated technique offers potential for improving network performance without collecting additional data.     

Determining manufacturing parameters to suppress system variance using linear and non-linear models

Determining manufacturing parameters for a new product is fundamentally a difficult problem, because there has little suggestion information. There are several researches on this topic, and most of them focus on single specific model or the engineer’s experience. As to other approaches, the usage of multiple models may be an alternative approach to help determining the parameters. This research proposed an aggregation of multiple regression and back-propagation neural network to find the manufacturing parameter’s limits (upper and lower limits). A real-problem of a new product parameter setting model in the real Thin Film Transistor-Liquid Crystal Display (TFT-LCD) manufacturing company is demonstrated, where three forecasting models are applied, and t test is used to judge which models are the suitable ones. Finally, we average the computed parameter values from the chosen models to suppress the system variance. The empirical results show that the proposed method is successful in suppressing the system variance and improving the production yields.     

Reliability-based performance indicator for a manufacturing network with multiple production lines in parallel

This paper addresses the system reliability evaluation for a manufacturing system with multiple production lines in parallel, where the system reliability is the possibility that a manufacturing system can satisfy demand. In the manufacturing system, the capacity of each machine is stochastic (i.e., multi-state) due to failure, partial failure, or maintenance. Thus, the manufacturing system can be constructed as a manufacturing network in terms of stochastic-flow network model. With considering reworking actions, we propose a graphical-based methodology to transform the manufacturing system into a manufacturing network. Thereafter, the manufacturing network is decomposed into general manufacturing paths and reworking paths. A simple algorithm is subsequently developed to generate the minimal capacity vectors that machines should provide to satisfy demand. The system reliability is derived in terms of such capacity vectors afterwards.     

二层以太网网络体系结构在汽车涂装生产中的应用

当前分析面向汽车生产线网络控制系统的设计规划,对提升汽车行业企业信息化水平具有重大的意义。本文结合汽车涂装生产工艺特点的基础上,提出汽车涂装网络控制系统的框架结构,研究了基于以太网技术的二层网络体系结构在汽车涂装生产中的应用。     

Modeling of agile intelligent manufacturing-oriented production scheduling system

Agile intelligent manufacturing is one of the new manufacturing paradigms that adapt to the fierce globalizing market competition and meet the survival needs of the enterprises, in which the management and control of the production system have surpassed the scope of individual enterprise and embodied some new features including complexity, dynamicity, distributivity, and compatibility. The agile intelligent manufacturing paradigm calls for a production scheduling system that can support the cooperation among various production sectors, the distribution of various resources to achieve rational organization, scheduling and management of production activities. This paper uses multi-agents technology to build an agile intelligent manufacturing-oriented production scheduling system. Using the hybrid modeling method, the resources and functions of production system are encapsulated, and the agent-based production system model is established. A production scheduling-oriented multi-agents architecture is constructed and a multi-agents reference model is given in this paper.     

A two-phase procedure for the study of computer network reliability in automated manufacturing systems

This paper presents a mathematical model for analyzing computer networks in production systems. The manufacturing facility, which is considered to be the main part of a production system is controlled by a computer network. Every station within a production system is assumed to have a computer and a network interface unit (NIU) as part of the overall computer network. For the system to remain operational, the computer network along with the manufacturing facilities should be extremely reliable. In this paper, we studied the reliability of the former, the computer network. The manufacturing facility is assumed to be reliable. Since every station must be operational for the whole system to function, failure in any network unit (computer of NIU) will halt the system production. For such systems the topology is logically equivalent to that of a system whose stations are connected in series. Hence, series reliability formulae is appropriate for these systems. In other systems, back-up (or stand-by) units are added to the computer and/or to the NIU to enhance the reliability. We consider our model to be a generic one because the reliability analysis it uses is independent of the network topology. It assumes constant failure rates for network components and uses a two-pass procedure in determining the effect of network reliability on the total system cost. A case study is presented to illustrate the importance of reliability considerations during the network design phase. Our analysis of the network reliability reveals that, in most cases, the incremental cost due to network failures will justify the additional units.     

Dynamic recurrent neural networks for a hybrid intelligent decision support system for the metallurgical industry

Knowledge-based modeling and implementation of the various manufacturing processes represent an intensive research area. It is known that it is difficult to analyze the mechanisms of many industrial production processes and build dynamic models by employing classical methods for intelligent systems in manufacturing. This paper describes how to use dynamic recurrent neural networks to provide the model base of a hybrid intelligent system for the metallurgical industry with a quality control model. The hybrid system extracts the features of image sequences obtained through the vision detection subsystem and employs a dynamic recurrent neural network to assess and predict the product qualities to further coordinate the entire production process.     

基于新型制造资源组织模型的生产调度系统研究

为了适应航天制造企业对生产调度系统的要求,提出了新型的制造资源组织模型—–基于虚拟制造单元的制造资源组织模型,探讨了此模式的理论思想以及基于此模型构建的生产调度系统.首先构建了基于虚拟制造单元的资源组织模型结构,并给出虚拟制造单元构建的详细过程;然后,建立了基于此制造资源组织模型的生产调度系统模型;最后,通过应用实例表明了该系统能够有效地简化生产调度过程,提高生产效率.     

Results of the Eureka FAMOS research programme: A European contribution to manufacturing technology

Market competition is leading to direct confrontation between products coming from the main manufacturing areas: Europe, the U.S.A. and Asia, where Japan is leading. For Europe to maintain and improve its role, it is important to develop “winning” products. This requires an advanced, technology based industry (secondary sector) and a highly effective research and innovation network (quaternarium), developing new design tools and new configurations for products and production systems. To foster and strengthen an advanced industry and a highly effective quaternarium, Europe has launched various initiatives, from EEC Programmes to the Eureka initiative.In this paper the contribution of the Eureka FAMOS projects is assessed by using a model linking the research innovation cycle, “actors” (companies and research institutions) and activation mechanisms (programmes and initiatives). With the Eureka FAMOS Umbrella Project acting as an activation mechanism, the analysis of the specific FAMOS projects carried out through MONITECH—an assessment activity set up by IMU-CNR—shows how the “actors” (companies and research institutions) have reacted and launched specific projects (36 at an estimated cost of 600 MECU), in 17 industrial sectors, leading to new production paradigms (production systems and related technologies). Considering the results already achieved (pilot production systems and technologies) the Eureka FAMOS Research Programme may be seen as a relevant European initiative in manufacturing technology.The synergy which the Eureka FAMOS Programme is starting to provide with EEC Programmes will give the European research network and industry further benefits.     

An IIoT-driven and AI-enabled framework for smart manufacturing system based on three-terminal collaborative platform

Smart manufacturing has great potential in the development of network collaboration, mass personalised customisation, sustainability and flexibility. Customised production can better meet the dynamic user needs, and network collaboration can significantly improve production efficiency. Industrial internet of things (IIoT) and artificial intelligence (AI) have penetrated the manufacturing environment, improving production efficiency and facilitating customised and collaborative production. However, these technologies are isolated and dispersed in the applications of machine design and manufacturing processes. It is a challenge to integrate AI and IIoT technologies based on the platform, to develop autonomous connect manufacturing machines (ACMMs), matching with smart manufacturing and to facilitate the smart manufacturing services (SMSs) from the overall product life cycle. This paper firstly proposes a three-terminal collaborative platform (TTCP) consisting of cloud servers, embedded controllers and mobile terminals to integrate AI and IIoT technologies for the ACMM design. Then, based on the ACMMs, a framework for SMS to generate more IIoT-driven and AI-enabled services is presented. Finally, as an illustrative case, a more autonomous engraving machine and a smart manufacturing scenario are designed through the above-mentioned method. This case implements basic engraving functions along with AI-enabled automatic detection of broken tool service for collaborative production, remote human-machine interface service for customised production and network collaboration, and energy consumption analysis service for production optimisation. The systematic method proposed can provide some inspirations for the manufacturing industry to generate SMSs and facilitate the optimisation production and customised and collaborative production.     

Resource planning for direct fabrication of customized orthopedic implants using EBM technology

Medical innovations and patient expectations are pushing healthcare toward personalized medicine. In orthopedics, the concept of patient-specific implants could be economically realized with the use of additive manufacturing. Knee and hip replacements are some of the most common musculoskeletal procedures performed in the United States. Joint replacement implants are typically offered in standard sizes and geometries. The mass customization of theses prostheses, however, can improve patient outcomes and reduce medical costs. Mass customization is not economically feasible with traditional manufacturing methods because of the high fixed tooling costs for each geometry. The freedom of design offered by additive manufacturing presents a viable production alternative for unique personal geometry. The objective of this paper is to develop two new analytic models that can be used to investigate a complex additive manufacturing supply chain. The focus of the model is to provide planning tools and a methodology for the direct production of customized orthopedic implants using electron beam melting, an additive manufacturing technology. First, a production model for an additive manufacturing-based system is created. Next, resource planning for a single customized implant system is performed using a simulation model. A queuing model is developed for rapid systems analysis. The staffing requirement predictions of the two models align closely for production of a singular, customized implant. A detailed systems analysis of an additive manufacturing supply chain is conducted to illustrate the use of these models. The queueing model is analytically tractable, so it is extended to describe the production of standard and customized versions of multiple implant families.     

Exact and metaheuristic algorithms for the vehicle routing problem with a factory-in-a-box in multi-objective settings

Emergencies, such as pandemics (e.g., COVID-19), warrant urgent production and distribution of goods under disrupted supply chain conditions. An innovative logistics solution to meet the urgent demand during emergencies could be the factory-in-a-box manufacturing concept. The factory-in-a-box manufacturing concept deploys vehicles to transport containers that are used to install production modules (i.e., factories). The vehicles travel to customer locations and perform on-site production. Factory-in-a-box supply chain optimization is associated with a wide array of decisions. This study focuses on selection of vehicles for factory-in-a-box manufacturing and decisions regarding the optimal routes within the supply chain consisting of a depot, suppliers, manufacturers, and customers. Moreover, in order to contrast the options of factory-in-a-box manufacturing with those of conventional manufacturing, the location of the final production is determined for each customer (i.e., factory-in-a-box manufacturing with production at the customer location or conventional manufacturing with production at the manufacturer locations). A novel multi-objective optimization model is presented for the vehicle routing problem with a factory-in-a-box that aims to minimize the total cost associated with traversing the edges of the network and the total cost associated with visiting the nodes of the network. A customized multi-objective hybrid metaheuristic solution algorithm that directly considers problem-specific properties is designed as a solution approach. A case study is performed for a vaccination project involving factory-in-a-box manufacturing along with conventional manufacturing. The case study reveals that the developed solution method outperforms the ε-constraint method, which is a classical exact optimization method for multi-objective optimization problems, and several well-known metaheuristics.     

面向网络化制造的产品再配置模型

该文提出一个面向网络化制造的产品再配置概念模型．该模型突出配置过程的动态特性,在分析了基于版本模型的部件、配置模型演化方式以及两者在演化过程中的相互影响的基础上,给出在集成产品配置的产品数据管理系统中对部件演化和模型演化进行跟踪和记录的方法,以实现产品再配置．该模型具有较强的时态描述能力,可广泛应用在网络化制造系统中．最后还提出了一个面向网络化制造的产品再配置结果相关度匹配算法．     

基于改进SA算法在智能制造生产调动模型研究

智能制造生产调动是一个复杂的多目标优化问题,传统的生产调动方法多采用启发式方法,在面对复杂的制造环境,传统方法可能会出现早熟收敛或搜索精度下降的问题；因此为了解决这些问题,研究构建了基于改进SA算法的智能制造生产调动模型；首先对SA算法进行了优化,其次利用优化后的算法构建了生产调动模型,最后通过仿真实验去验证模式算法的性能。实验结果表明,在数据集中,真实值、模型方法和传统方法的平均完成时间分别为85.33min、89.92min和93.81min,其中模型方法与真实值的差距仅为4.59min。这说明模型方法可以用于解决现有生产模式存在拖期的情况,及时完成生产任务。模型算法能够为智能制造生产调动提供新的思路。     

Recurrent neural network approach for cyclic job shop scheduling problem

While cyclic scheduling is involved in numerous real-world applications, solving the derived problem is still of exponential complexity. This paper focuses specifically on modelling the manufacturing application as a cyclic job shop problem and we have developed an efficient neural network approach to minimise the cycle time of a schedule. Our approach introduces an interesting model for a manufacturing production, and it is also very efficient, adaptive and flexible enough to work with other techniques. Experimental results validated the approach and confirmed our hypotheses about the system model and the efficiency of neural networks for such a class of problems.     

Using past manufacturing experience to assist building the yield forecast model for new manufacturing processes

Polarizers are one of the key parts of Thin-Film Transistor Liquid-Crystal Displays (TFT-LCD), and their production requires high material costs. How to reduce manufacturing costs is thus a key task in this highly competitive global market. The precise yield forecast model considering learning effects that is proposed in this work is believed to be an effective approach to reduce both the raw material input-cost and inventory cost of overproduction. Support vector regression (SVR) model is one of the commonly used approaches to forecast the yield trend. However, in the early manufacturing stages for a new product, an SVR model is usually sensitive and unstable because of the use of insufficient data. Faced with this problem, this research aims at enhancing the SVR model by using past manufacturing experience and virtual samples to estimate the yield trend model for pilot products. This paper proposes a novel Quadratic-Curve Diffusion (QCD) method, wherein we derive a quadratic yield function (QYF) of the new manufacturing process for each key manufacturing variable by utilizing past manufacturing experience; and then use the QYF to generate virtual samples to assist building the overall yield forecast model of the new manufacturing process. The results show that the proposed method is superior to the performance of other forecast and virtual sample generation models.