A constraint network approach to design for assembly

Design for assembly (DFA) involves the consideration of the assembly process while designing. It is important in that it is at the design stage that significant decisions about the assembly process are made. This paper overviews the background to DFA and presents an approach to DFA that operates by analyzing a design using constraint networks. This approach gives advice to the designer on changes that should be made to improve the design. The designer can interact with the constraint network system to make gradual improvements. The approach has been implemented as a prototype using the constraint language SPARK. The use of constraint networks for DFA has a number of advantages over more conventional techniques: advice is given on how to improve the design, the designer can interact with the DFA system to improve the design, and the designer can approach the problem from any viewpoint in that a rigid procedure does not have to be followed. The result is a flexible DFA system that can be adapted relatively easily to a particular environment.     

Neural computing-based design of components for cellular manufacturing

In this paper, a neuro computing approach for integrating design and manufacturing engineering is developed. Products and components have been traditionally designed without considering constraints imposed by a manufacturing system. With the introduction of concurrent engineering, design and manufacturing engineering are viewed as an integrated area. A three layer neural network that integrates several manufacturing functions is constructed for designing a cellular manufacturing system. The neuro computing system proposed provides a designer with the desired features that meet the current manufacturing constraints for design of a new component. The proposed methodology overcomes the typical limitations of neutral networks such as the internal representation and training problem, and proves to be appropriate for concurrent engineering.     

用户感性认知与产品感性设计方法及应用

目的梳理用户感性认知测量及其设计应用,提出人工智能驱动的产品感性设计方法,并以验光仪设计验证其有效性。方法分析国内外文献,归纳总结用户感性认知测量及应用方法,通过验光仪设计验证所提出的产品感性设计方法。结果人工智能驱动的产品感性设计方法能提升设计效率,更好地满足用户感性需求。结论用户感性认知测量能转化为设计规范,并能为产品设计提供有效指导。随着计算机科学的发展,针对传统用户感性认知测量中样本采集量较少、测量不够全面等问题,提出了人工智能驱动的产品感性设计方法,并以验光仪的设计验证了其有效性。研究结果表明,通过文本挖掘提取用户感性认知能引导设计师更加全面地了解用户感性需求,从而使设计出的产品更贴近用户的预期满意度。人工智能与人类智慧相结合的感性设计方法是一种能提高用户对产品的心理接受度,从而提升产品竞争力的设计方法。     

Concurrent engineering in a high variety label printing environment

Here an attempt is made to use the principles of concurrent engineering in high variety label printing industry. The existing approach to label printing in the company is basically what is known as serial engineering approach. This approach leads to serious problems of high levels of work-in-process and increased requirements of cutter capacity. We attempt to make a case for the application of concurrent engineering by introducing the multifunctional team concept at the design stage which helps reduce WIP inventory as well as the cutting capacity requirements. For this purpose we develop a heuristic algorithm. The concurrent engineering approach and the algorithm are illustrated by an example.     

USE OF COUNTERPROPAGATION NEURAL NETWORKS TO ENHANCE THE CONCURRENT SUBSPACE OPTIMIZATION STRATEGY

The paper explores the use of artificial neural networks in a concurrent optimization strategy that derives from a decomposition based approach to design of large-scale engineering systems. These problems are characterized by complex couplings that render parametric design methods inappropriate as solution tools. Decomposition methods reduce the large dimensionality problem into a sequence of smaller, more tractable optimization problems, each with a smaller set of design variables and constraints. The decomposed subproblems are rarely decoupled completely, and design changes in one subproblem have a profound influence on changes in another subproblem. Essential components of decomposition based design methods are strategies to identify a topology for problem decomposition, and to develop coordination strategies which account for couplings among the decomposed problems. The paper examines the effectiveness of artificial neural networks as a tool to both account for the coupling, and to develop methods to coordinate the solution in the different subproblems to a converged optimal design     

Developing a fuzzy proportional–derivative controller optimization engine for engineering design optimization problems

In real world engineering design problems, decisions for design modifications are often based on engineering heuristics and knowledge. However, when solving an engineering design optimization problem using a numerical optimization algorithm, the engineering problem is basically viewed as purely mathematical. Design modifications in the iterative optimization process rely on numerical information. Engineering heuristics and knowledge are not utilized at all. In this article, the optimization process is analogous to a closed-loop control system, and a fuzzy proportional–derivative (PD) controller optimization engine is developed for engineering design optimization problems with monotonicity and implicit constraints. Monotonicity between design variables and the objective and constraint functions prevails in engineering design optimization problems. In this research, monotonicity of the design variables and activities of the constraints determined by the theory of monotonicity analysis are modelled in the fuzzy PD controller optimization engine using generic fuzzy rules. The designer only needs to define the initial values and move limits of the design variables to determine the parameters in the fuzzy PD controller optimization engine. In the optimization process using the fuzzy PD controller optimization engine, the function value of each constraint is evaluated once in each iteration. No sensitivity information is required. The fuzzy PD controller optimization engine appears to be robust in the various design examples tested.     

Concurrent process planning for finish milling and dimensional inspection of sculptured surfaces in die and mould manufacturing

With the introduction of computer-aided tools, traditional manufacturing tasks such as design, machining and inspection are now highly automated. However, due to the complexity and enormous knowledge involved in each process, most of these activities are still dealt with separately. Recent development of concurrent engineering emphasizes the importance of bringing manufacturing knowledge into the early design stage for optimum product and process design. In this paper, a knowledge-based CAD/CAM system which integrates process planning for finish milling and dimensional inspection of sculptured surfaces in die and mould manufacturing is presented. Optimum production plans are determined by minimizing the integral cost of machining and inspection. NC path generation and inspection planning are then verified by dynamic geometric simulations which provide the designer with the evaluations of machinability and inspectability. The implied significance is that strong inter-dependency may exist among various design life-cycle activities and that optimum solutions can be obtained by taking into account the interactions of the life-cycle events.     

Cumulative author index for volumes 99–110

The problems facing the engineering designer in the selection and specification of surface coatings are outlined. In particular the benefits and difficulties of the systems concept in coating selection are discussed. A computer-based technique utilizing artificial intelligence principles has been developed to assist the designer in this area. Two programs POLYCOAT and TRIBCOAT are under development which can be interrogated in an interactive response-oriented mode by the non-expert designer. Knowledge is encoded in a series of rules of the situation→action form which can represent the scientifically inexact factors in coating selection. In effect these “expert systems” emulate the performance of a human consultant in the field, having a capability for decision making in open-ended domains.     

人工智能在感性工学研究中的应用与趋势

目的 梳理人工智能(AI)技术在感性工学研究中的应用现状,对关键技术、存在问题、研究趋势进行分析。方法 通过归纳整理国内外相关文献,分析人工智能基础研究领域,以感性工学研究的一般流程为主线,探讨人工智能在用户情感意向获取、产品设计特征提取、映射模型构建3个环节中的应用。结论 人工智能在感性工学研究中的广泛应用,极大地提高了设计效率,加快了设计的自动化和智能化的步伐,但也存在着局限性。在未来,感性工学通过与生成式AI相结合将成为新的趋势,更加强大和高效的人工智能将会给设计行业带来新的机遇和挑战。     

Knowledge Engineering Application in maintainability Design and Analysis

１ＩｎｔｒｏｄｕｃｔｉｏｎＭａｉｎｔａｉｎａｂｉｌｉｔｙｉｓｔｈｅｉｎｈｅｒｅｎｔｃｈａｒａｃｔｅｒｉｓｔｉｃｏｆｔｈｅｅｑｕｉｐｍｅｎｔａｎｄｗｉｌｂｅａｃｈｉｅｖｅｄｔｈｒｏｕｇｈｄｅｓｉｇｎｐｒｏｃｅｓ．Ｔｈｅｒｅａｒｅｍａｎｙｃｅｒｔａｉｎ...     

人工智能产品设计伦理探究

目的 分析当今人工智能产品设计伦理.方法 运用文献法和案例分析方法从设计的伦理出发,分析当代设计中与人工关智能产品的设计伦理问题.从弱人工智能产品和强人工智能产品两个层面来探究产生的影响,从设计师和设计伦理准则以及人工智能产品三者的协同关系做出思考,同时给出相关问题的具体建议.结论 人工智能产品无法替代设计师的全部功能,设计师应该参与人工智能产品设计伦理,设法赋予其对人类友善的动机,使其具备特定的道德品质,做出合乎道德的行为.     

基于群智能与案例推理的民宿酒店服务设计探究

目的 为了提高设计师对以往知识与用户评价的服务设计管理,通过人工智能与管理学科的技术辅助实现群智能服务设计系统。方法 使用CBR(Case-Based Reasoning)与感性工学服务设计原理为前期研究框架,采用网络爬虫技术收集用户评语,使用人工智能知识图谱作为评价词汇数据库,实现对于服务设计知识的管理。通过TRIZ推理与原理整理作为设计创意输出依据主体。利用KANO研究方法确定用户需求并对输出设计功能进行实验验证。结果 KANO实验结果较为理想,本研究方法具有一定的参考意义。结论 知识图谱对于领域服务设计知识管理有可观的效果,通过一定可溯源推理方式让创意输出具有依据性,符合未来服务设计快速发展的需求。     

Information supported design for manufacture of injection-moulded rotational products

Whilst the concurrent engineering philosophy has been embraced by a wide range of engineering companies as a means to remaining competitive, the design software tools which are commercially available are limited in their ability to offer concurrent support. This paper describes research which has investigated how design for manufacture information can be provided back to designers as concurrently as possible. The paper, using injection moulding as its focus, illustrates how a design for manufacture environment can be structured to utilize company product and manufacturing information. In particular, the need for appropriate information translation mechanisms and design support strategies is described. An example, highlighting the potential of the approach and utilizing an experimental object-oriented system, is discussed.     

面向并行工程的约束管理信息系统的研究与开发

介绍了一个自主开发的面向并行工程的约束管理信息系统，该系统能为ＣＩＭ企业实施并行工程提供有效的技术支持，适用于不同层次、类型的并行工程问题。文中讨论了系统的原理、结构、主要功能及开发方面的相关问题。     

Dynamic control in automated manufacturing: a knowledge integrated approach†

Flexibly automated facilities permit a wider variety of products as well as objectives for making those products—thus requiring manufacturing control strategies to face an environment of ever present change. To operate in this environment, a system composed of hard automation, flexible automation and humans, which can be responsive to product and process requirements, machine breakdowns and delays, engineering changes and improvement opportunities, is needed. Such a system does not fall into the realm of any current manufacturing solution techniques. Something more than exact optimization, heuristic algorithms or stochastic estimates must be utilized. The research discussed herein describes a dynamic solution strategy to operate in this changing environment with adaptive self-improving characteristics. The proposed methodology for optimizing the control of an automated manufacturing facility is an integrated approach utilizing real-time feedback from the operating facility, direct feedback from a simulation of the facility and guidance from a historical knowledge base. This system is being implemented in a knowledge based environment called CAYENE. CAYENE is a hybrid artificial intelligence system, written in Lisp, based on the idea of using object oriented programming as a unifying principle for functional, frame and rule-based programming.     

Well-controlled engineering change propagation via a dynamic inter-feature association map

Currently, engineering companies face the challenge of delivering complex engineering project in a compressed time frame, which warrants concurrent and collaborative engineering. Due to the tedious dependencies embedded in collaborative domains, engineering change propagation is commonly a challenge and the procedure is carried out by engineers manually without systematic consistency check. Design change impacts are difficult to predict. To address the above challenge, an explicit and comprehensive engineering constraint modeling method is investigated according to a feature-based engineering scheme. To represent the network of constraints, a dynamically generated feature parameter association map is developed to analyze the associations among those parameters. Then, a dynamic mechanism of identifying the locally admissible value ranges of those related constraint parameters has been proposed in order to quickly accept design changes or to identify potential design conflicts. This mechanism then determines the admissible domain for the variable arrays in the formulated constraint satisfaction problem (CSP). Consequently, a well-controlled and progressively expanded change propagation method is proposed. This progressively expanded CSP solving approach is dynamic and incremental based on the association map. This proposed method is demonstrated to be effective to assist engineers with a typical intelligent change propagation solution.     

Feature-based design: Four hypotheses for future CAD systems

Features are meaningful abstractions of geometry that engineers use to reason about components, products, and processes. For design activity, features are design primitives, serve as the basis for product representations, and can incorporate information relevant to life-cycle activities such as manufacturing. Research on feature-based design has matured to the point that results are being incorporated into commercial CAD systems. The intent of this paper is to look forward. Hence, this paper does not play the role of a standard survey, which necessarily only reviews the past. Nevertheless, an appropriate historical context is provided as a basis for these particular futuristic projections. Applications of feature-based design and technologies of feature representations are reviewed, then open research issues are identified and put in the context of past and current work. Features are prominent as catalysts for computer-based design tools, but the vision presented expands upon this basis, delving beyond features. For that future design environment, four hypotheses are proposed as research challenges: two on the existence of fundamental subfeature elements and relationships for features, one that presents a new definition of design features, and one that argues for the successful development of concurrent engineering languages. Evidence for these hypotheses is provided from recent research results and from speculation about the future of feature-based design.     

Innovative design method of mapping from user needs to internet biological texts

Bionic innovation design refers to the innovative design of products by extracting biological information in nature, which has great application prospects. The traditional bionic innovative design method mostly applies a small amount of biological information, which is difficult to efficiently retrieve a large amount of biological information, and it is difficult to produce innovative design solutions due to the limitations of designer’s thinking and related professional knowledge. To solve the above problems, it is necessary to propose an integrated innovative design method based on a large number of biological texts from website to assist designers in making bionic innovative design. Based on this, an innovative design method was proposed for mapping network biological texts by user requirements to obtain multi-disciplinary requirements and multi-mapping targets design scheme. Firstly, based on the neural network model, the knowledge in the internet biological text was extracted and stored in the database. Then, the keywords of product design were obtained according to the multi-disciplinary requirement mapping method, which was mapped to internet biological texts by using the fuzzy mapping method to obtain engineering design solutions. Finally, the code was programmed and the corresponding user interface was designed according to the above method, and the feasibility of proposed method was verified by taking the innovative design of the tubeular type air heater as an example. The results showed that the heating effect of optimized tubular type air heater was significantly improved, which indicated that the proposed method could solve the current key problems of traditional innovative bionic design, such as the lack of biological text information, the limitation of designer’s own thinking, the lack of integrate interdisciplinary expertise and the unsatisfactory generation of product solution. The proposed method can assist the designer to complete the bionic innovative design of products.     

A cross-disciplinary technology transfer for search-based evolutionary computing: from engineering design to software engineering design

Although object-oriented conceptual software design is difficult to learn and perform, computational tool support for the conceptual software designer is limited. In conceptual engineering design, however, computational tools exploiting interactive evolutionary computation (EC) have shown significant utility. This article investigates the cross-disciplinary technology transfer of search-based EC from engineering design to software engineering design in an attempt to provide support for the conceptual software designer. Firstly, genetic operators inspired by genetic algorithms (GAs) and evolutionary programming are evaluated for their effectiveness against a conceptual software design representation using structural cohesion as an objective fitness function. Building on this evaluation, a multi-objective GA inspired by a non-dominated Pareto sorting approach is investigated for an industrial-scale conceptual design problem. Results obtained reveal a mass of interesting and useful conceptual software design solution variants of equivalent optimality—a typical characteristic of successful multi-objective evolutionary search techniques employed in conceptual engineering design. The mass of software design solution variants produced suggests that transferring search-based technology across disciplines has significant potential to provide computationally intelligent tool support for the conceptual software designer.     

Safeguarding information intensive critical infrastructures against novel types of emerging failures

The complexity of information intensive critical infrastructures, like electricity networks, telecommunication networks and public transportation networks is today augmented much more than in the past: such complexity augments the number of possible failures and anomalous working conditions and consequently decreases the survivability of the infrastructures.In this paper, the possibility is investigated to detect early anomalies and failures inside information intensive critical infrastructures by the introduction of anomaly detectors being “self-aware” about the normal working conditions of the infrastructure itself. This approach has the objective to improve the performance of the most popular signature-based algorithms for intrusion detection, and makes use of different classes of time-oriented algorithms based on artificial intelligence paradigm. It has the advantage to work also in presence of unknown and unexpected types of attacks or failures.The tests, to evaluate the performance of the utilised detectors, are executed inside an emulated supervisory control and data acquisition (SCADA) system of an electrical power transmission grid, and a proposal for the future integration inside real SCADA systems is also reported.