敏捷制造中基于AI及Internet技术的电火花加工工艺决策

以电火花加工为例提出了一种实现敏捷制造技术的新方法。这种方法基于人工智能及因特网技术与传统制造技术的集成，通过网络化电火花加工工艺智能决策系统的软件以低成本远程快速的使用设计制造专家知识，从而实现设计制造的敏捷化。专家知识包括电火花加工工艺参数的智能选择及推理。通过因特网选择不同应用的加工条件与专家进行动态交互。本文得出结论，基于人工智能技术及因特网的敏捷制造技术的未来应用具有潜在的利益。     

Current status,enablersand barriers of implementing cellular manufacturing system in Indian industries

The cellular manufacturing (CM) has been proved as a well-known manufacturing strategy that helps to improve manufacturing efficiency and productivity by
utilizing the philosophy of group technology. Large number of papers has been published in the area of design issues of CM system. Unfortunately, the issues related to acceptability of CM in Indian industries are typically not examined rigorously as technical issues. This paper presents the results of a survey carried out to find the status, enabler and barrier of implementing CM system in Indian industries.     

Distributed product and facility prototyping in extended manufacturing enterprises

In order to reduce the cost at the early product development stages, the planners need methodologies and tools that would allow them to judge upon the implications of the product design on the required manufacturing processes and facilities for their production. This paper reports on a new theoretical platform and a pilot implementation of a decision-making environment for distributed product and facility prototyping in an extended enterprise. The approach is based on an exchange of requests and information between collaborative autonomous agents that support the design, manufacturing planning and facility formation activities. The decision-making is formalized as iterative matching of design, process and facility attributes using multilevel resource capability representation within the extended enterprise. The system is implemented as an XML/CORBA-based environment for conveying design and manufacture messages across traditional technology boundaries. The reported research aims to provide the designers with a rapid manufacturing feasibility assessment tool to be used at different design and planning stages in extended manufacturing enterprises.     

基于远程服务实现大批量定制生产的网络化系统

网络化支持技术是制造企业实施大批量定制生产的四个关键技术之一。本文在分析了大批量定制生产的网络化组织模式的基础上，提出了基于制造企业远程服务系统的大批量定制生产的网络化支持系统思想，并详细论述了远程服务网络对大批量定制生产中的制造企业、供应商和客户的支持，以及远程服务网络系统对定制产品全生命周期的支持。     

A mathematical model and a heuristic approach for design of the hybrid manufacturing systems to facilitate one-piece flow

One-piece flow is a design rule that entails production in manufacturing cells on a ‘make one, check one, and move-on one’ basis (Black, J.T., 2007. Design rules for implementing Toyota Production System. International Journal of Production Research, 45 (16), 3639–3664), which reduces manufacturing lead time significantly. This paper proposes a sequential methodology comprised of a mathematical model and a heuristic approach (HA) for the design of a hybrid cellular manufacturing system (HMS), to facilitate one-piece flow practice. The mathematical model is employed in the cases of small- and medium-sized problems, and it attempts to minimise the total number of exceptional operations, while considering machine capacities and alternative machines. The machine-part matrix achieved by the mathematical model is input into the flow line design stage of the HA, where backflow within the cells is eliminated. However, for industrial problems, the proposed HA is utilised. After the formation of the cells by clustering, the HA attempts to eliminate exceptional operations of a given cellular configuration together with a functional structure by employing alternative machines, based on the decision rules developed. Later, unidirectional flow within the cells is achieved and the capacity and budget constraints are satisfied. A medium-sized problem is solved by using both of the approaches, namely, the model integrated with the flow-line design stage of the HA and the complete HA. The results are discussed and the limitations are explained.     

Statistical monitoring and diagnosis of automatic controlled processes using dynamic PCA

As manufacturing quality has become a decisive factor in competing in a global market, statistical quality techniques such as statistical process control (SPC) are becoming very popular in industries. With advances in sensing and data capture technology, large volumes of data are being routinely collected in automatic controlled processes. There is a growing need for SPC monitoring and diagnosis in these environments, but an effective implementing scheme is still lacking. This research provides an integrated approach to simultaneously monitor and diagnose an automatic controlled process by using dynamic principal component analysis (DPCA) and minimax distance classifier. Through a step-by-step implementation procedure, the proposed scheme is expected to have an impact on many manufacturing industries with automatic process control (APC) or engineering process control (EPC).     

Strategic capacity management: Meeting technological demands and performance criteria

Although manufacturing contributes a large part to the current performance of companies, few companies deal systematically with issues related to strategic capacity management. As well as decisions on outsourcing and acquisition of resources, this involves triggering process innovation, process development and improving performance by adapting organizational structures. Action Research in companies reveals the importance of capacity management at a strategic level as well as the implementation at tactical and operational levels. The methods of Strategic Capacity Management, as proposed in this paper, provide an industrial company with tools for implementing its manufacturing strategy. Only the design of organizational structures has received attention in the past--little research has been done in the area of manufacturing technology and integral models for sourcing. Through matching product configurations with product-market strategies and product development, the methods point to areas of improvement. The new methods include decision-models for outsourcing and capacity management, product development, and a manufacturing technology scan. All the methods deploy performance evaluations as a base for selecting alternatives to define improvements. These improvements lead to decisions on investments for resources, resource utilization and development of processes, including initiation of manufacturing technologies, as demonstrated by four case studies.     

Innovative manufacturing technology enabling light weighting with steel in commercial vehicles

Improved manufacturing technology is often needed when working with high strength steel.In this respect manufacturing technology has to adapt to the altered(and typically reduced) formability and weldability of modern high strength steel.However,this is a rather passive approach from a manufacturing point of view.An indeed much more powerful approach is to generate synergies between innovative manufacturing technology,design and material enabling additional weight savings and efficiency gains.Laser-based material processing,in particular laser welding,offers a wide range of opportunities in this sense.Furthermore,hot stamping and roll forming open up new possibilities for advanced manufacturing of commercial vehicle components.Applications and examples of these technologies will be given in terms of producing innovative semi-products as well as final components.     

Grouping and selecting products: the design key of Reconfigurable Manufacturing Systems (RMSs)

A Reconfigurable Manufacturing System (RMS) is a new paradigm that focuses on manufacturing a high variety of products at the same system. Having specified a design strategy for an RMS as the first design step at the tactical level, products must be grouped to identify and allocate corresponding manufacturing facilities. An interface between market and manufacturing called reconfiguration link is presented to specify and arrange products for manufacturing. The reconfiguration link incorporates the tasks of determining the products in the production range, grouping them into families and selecting the appropriate family at each configuration stage. The proposed approach of (re)configuring products before manufacturing facilitates assigning product families to the required manufacturing facilities in terms of (re)configuring manufacturing systems. This paper contributes an overall approach of grouping products into families based on operational similarities, when machines are still not identified. Since the problem of product family selection consists of quantitative and qualitative objectives, the Analytical Hierarchical Process (AHP) is then used while considering both market and manufacturing requirements. The AHP model is verified in an industrial case study through using Expert Choice software. The solutions take advantage of monitoring sensitivity analysis while changing the priorities of manufacturing and/or market criteria. The concept of the proposed model is generic in structure and applicable to many firms. However, the model must be adapted according to the specific nature of the company under study. For instance, product family choices may differ from one company to another because of the available technology and the volume and type of existing products in the production range.     

虚拟车间动态重构模型的研究

阐述了敏捷制造模式下，车间的功能除了具有常规的生产管理和控制功能外，还具有实现单元动态重构的功能和通过网络对外合作的功能。在分析了虚拟车间动态重构的系统的关键技术的基础上，提出了基于多代理机的虚拟车间动态重构模型，讨论了Ａｇｅｎｔ之间的协商机制。     

Optimal Design of Fibre-reinforced Laminated Plates Accounting for Manufacturing Uncertainty

A procedure to design symmetrically laminated plates under buckling loads for minimum weight with manufacturing uncertainty (tolerance) in the ply angle and plate thickness, which are the design variables, is described. A minimum buckling load capacity is the design constraint implemented. It is assumed that the probability of any tolerance value occurring within the tolerance band, compared with any other, is equal, and thus the approach is a worst case scenario approach. The effects of bending–twisting coupling are neglected in implementing the procedure, and the Downhill Simplex method is used as the search technique, but the methodology is flexible and allows any appropriate problem formulation and search algorithm to be substituted. Two different tolerance scenarios are used for the purposes of illustrating the methodology, and plates with varying aspect ratios and loading ratios are optimally designed and compared. The results demonstrate the importance of carrying out design optimisation of composite structures with the effects of manufacturing tolerances included.     

DESIGN OF A KNOWLEDGE-BASED ON-LINE SIMULATION SYSTEM TO CONTROL A MANUFACTURING SHOP FLOOR

In this paper, the design principles of a new knowledge-based on-line simulation (KBOLS) architecture for the purpose of integrating the supervisory decision making process with a shop floor control system is discussed. The requirements for implementing the KBOLS architecture in a computer integrated manufacturing environment are presented. The special features of the KBOLS architecture include a knowledge-based controller capable of interacting with the shop floor and a manufacturing simulator, a shared blackboard data structure for knowledge bases, and a learning module. The KBOLS architecture is implemented in a flexible manufacturing system for analyzing interruptions due to machine breakdowns and rush orders.     

Simultaneous optimal selection of design and manufacturing tolerances with different stack-up conditions using genetic algorithms

Tolerance design is one of the most critical aspects of product design and development process as it affects both the product's functional requirements and manufacturing cost. Unnecessarily tight tolerances lead to increased manufacturing cost, while loose tolerances may lead to malfunctioning of the product. Traditionally, this important phase of product development is accomplished intuitively to satisfy design constraints, based on handbooks' data and/or skill and experience of the designers. Tolerance design carried out in this manner does not necessarily lead to an optimum design. Research in this area indicates that, in general, tolerance design is carried out sequentially in two steps; (1) tolerance design in CAD to obtain design or functional tolerances and (2) tolerance design in CAPP to obtain manufacturing tolerances. Such a sequential approach to tolerance design suffers from several drawbacks, such as more time consumption, suboptimality and unhealthy working atmosphere. This paper reports on an integrated approach for simultaneous selection of design and manufacturing tolerances based on the minimization of the total manufacturing cost. The nonlinear multivariable optimization problem formulated in this manner may result in a noisy solution surface, which can effectively be solved with the help of a global optimization technique. A solution methodology using genetic algorithms and applying penalty function approach with proper normalization of the penalty terms for handling the constraints is proposed. The application of the proposed methodology is demonstrated on a simple mechanical assembly with different tolerance stack-up conditions.     

先进制造技术的核心技术

产品设计思想创新和设计技术创新是先进制造技术的核心。在研究先进制造技术的体系和特点的基础上,探讨了先进制造的设计思想和设计技术的主要内容。     

Multi-agent systems applications in manufacturing systems and supply chain management: a review paper

This paper offers a review of the development and use of multi-agent modelling techniques and simulations in the context of manufacturing systems and supply chain management (SCM). The objective of the paper is twofold. First, it presents a comprehensive literature review of current multi-agent systems (MAS) research applications in the field of manufacturing systems and SCM. Second, it aims to identify and evaluate some key issues involved in using MAS methods to model and simulate manufacturing systems. A variety of different MAS applications are reviewed in three different classified research areas: production design and development, production planning and control, and SCM. In presenting a detailed taxonomy of MAS applications, the paper describes MAS application domains from five different perspectives. The review suggests the MAS approach represents a feasible framework for designing and analysing real-time manufacturing operations, since the approach is capable of modelling different levels of agent behaviour and dynamical interactions. The paper also highlights a number of key issues which have to be taken into account in attempting to design MAS-based research paradigms for future applications in manufacturing systems.     

机床的批量定制生产实施策略分析

通过分析机床产品的产品结构、生产过程和客户需求等特点，指出选择型定制是实现机床批量定制的主要类型；研究探讨了机床批量定制生产在产品设计制造技术、生产过程的组织及管理等方面的实施策略，提出了适应机床批量定制生产的ERP系统的组成结构体系。     

Graph-neural network approach in cellular manufacturing on the basis of a binary system

In the past several years, many studies have been carried out on cellular manufacturing. Group technology is a manufacturing philosophy in which similar parts are identified and grouped together to take advantage of their similarities in manufacturing and design. The main problem in the development of cellular manufacturing is that of cell formation. In this paper, a graph-neural network approach is given for cell formation problems in group technology. Effort has been made to develop an algorithm that is more reliable than conventional methods. A graph-neural network has the advantages of fast computation and the ability to handle large scale industrial problems without the assumption of any parameter and the least exceptional elements in the presence of bottleneck machines and/or bottleneck parts. Two examples from the literature have been solved to demonstrate the advantages of the algorithm.     

Object-oriented modelling of manufacturing information system for collaborative design

Object-oriented technology has been widely acclaimed as offering a revolution in computing that is resolving a myriad of problems inherent in developing and managing organisational information processing capabilities. Although its foundations arose in computer programming languages, object-oriented technology has implications for a wide range of business computing activities including: programming, analysis and design, information management, and information sharing. The problematic issues in the development of manufacturing software systems are related to the various characteristics of manufacturing systems, which are wide, dynamic and complex. Design for manufacturing (DFM) is the integrated practice of designing components while considering their manufacturability, and its benefits are widely acknowledged in the industry. A model has been developed using object oriented technology, after analysing the fundamental elements necessary for modelling manufacturing and process planning framework used in collaborative design and manufacturing in machine tool manufacturing. The main components of this model are: process planning model (PPM), manufacturing activity model (MAM), manufacturing resource model (MRM) and manufacturing cost and time model. We are using ontologies in conjunction with specific conceptual models, which can contribute to improve the interoperability between these models. The performance of this model is shown by means of one real world case. The developed manufacturing information based design tool integrated with an intelligence design system can be used for collaborative design and manufacturing, which will support machine tool designers’ to achieve cost effective and timely design.     

A genetic algorithms-based approach for design of manufacturing systems: An industrial application

This paper presents a design methodology and a genetic algorithm-based approach for redesign of a manufacturing system for a small steel pre-fabricated building manufacturer. Through the application of celular manufacturing principles, we discuss the application of the design methodology that takes a topdown approach to determine system needs and a bottom-up integrated design approach to develop the configurations of the manufacturing system. The integrated design approach uses a genetic algorithm and an AutoCAD interface to minimize the inter and intra cell material movements during cell formation. A selected set of solutions obtained are further analysed using discrete event modelling and simulation. The final results presented indicate a substantial improvement in overall performance compared to the original layout. The company has implemented a modified version of the final solution and has achieved the significant improvements in material handling and overall productivity.     

A conceptual framework for the ubiquitous factory

To cope with today's industrial demands requiring (1) coverage of the whole product life cycle, (2) environmentally conscious manufacturing, (3) competitive sustainability manufacturing, etc., a new manufacturing paradigm should be developed. In this paper, we develop a conceptual framework for a new paradigm called ubiquitous factory (u-Factory) by applying ubiquitous computing technology to the manufacturing system. The u-Factory is based on our previously developed paradigm, called UbiDMR [1], meaning product design, manufacturing, and recycling via ubiquitous computing technology. The essence of u-Factory can be represented by three key phrases: (1) information transparency, (2) autonomous control, and (3) sustainable manufacturing. This paper comprises two parts. In the first part, we show the derivation procedure for the framework of the u-Factory using problem analysis of the current manufacturing system, design consideration and derivation of the architecture for the ubiquitous factory. In the second part, to demonstrate the validity and impact of the derived architecture, we develop the TO-BE model for manufacturing resource management. This is followed by a comparison with the AS-IS model.