D Su

Intelligent hybrid system for integration in design and manufacture

Abstract An intelligent hybrid system (IHS) approach has been developed to integrate various stages in the process of design and manufacture, including product design specification, conceptual design, detail design, process planning, costing and CNC manufacture. The IHS approach blends a rule-based system (RBS), artificial neural networks (ANNs), genetic algorithm (GA), hypermedia (HM) and CAD/CAE/CAM packages into a single environment. The design and manufacture expertise is captured by the RBS and ANNs, while the other tasks, such as numerical analysis, design optimisation, engineering drawing and data processing, are performed using GA, HM and CAD/CAE/CAM. The RBS works as a co-ordinator, controlling the whole process. As an application of the approach, an IHS for mechanical power transmission systems has been developed.

A CGI-based approach for remotely executing a large program for integration of design and manufacture over the Internet

This paper proposes an Internet-based system for geographically dispersed teams to collaborate over the Internet for the purpose of integration in design and manufacture. As one of the key issues of the system, a CGI (common gateway interface)-based multi-user method has been developed to remotely execute a large-size software package via the Internet. Agear optimization software package has been chosen as the application area. The package implements genetic algorithms to search the best solution for gear design. The objective is to implement this in the Internet and to collaborate between different locations. The package is located and run on the host server; after the completion of the program, the results are sent back to the client. To accomplish this, a combination of CGI, HTML, JavaScript, Java, multi-user environment and Internet security techniques has been utilized.

Integration of numerical analysis, virtual simulation and finite element analysis for the optimum design of worm gearing

Due to the complicated tooth geometry of worm gears, their design to achieve high capacity and favourable performance is a tedious task, and the optimum design is hardly to obtain. In order to overcome this problem, the authors developed an integrated approach which consists of three modules: numerical analysis, three-dimensional simulation and finite element analysis. It provides a powerful tool for optimum design of worm gears and is a general approach applicable for various types of worm gears. As case studies, two designs using the approach have been conducted, one for cylindrical involute worm gearing and the other for double enveloping worm gearing.

Network support for integrated design

A framework of network support for utilization of integrated design over the Internet has been developed. The techniques presented are also applicable for intranet/extranet. The integrated design system was initially developed for local application in a single site. With the network support, geographically dispersed designers can collaborate a design task throughout the total design process, quickly respond to clients’ requests and enhance the design agility. In this paper, after a brief introduction of the integrated design system, the network support framework is presented, followed by a description of two key techniques involved: Java Servlet approach for remotely executing a large program, and online CAD collaboration.

Integration of a knowledge-based system, artificial neural networks and multimedia for gear design

Abstract Design is a complicated area consisting of a combination of rules, technical information and personal judgement. The quality of design depends highly on the designer’s knowledge and experience. This system attempts to simulate the design process and to capture design expertise by combining artificial neural networks (ANNs) and knowledge-based system (KBS) together with multimedia (MM). It has been applied to the design of gears. Within the system, the KBS handles clearly defined design knowledge, the ANNs capture knowledge which is difficult to quantify and MM provides a user-friendly interface prompting the user to input information and to retrieve results during design process. The finished system illustrates how features of different artificial intelligence techniques, KBS, ANNs and MM, are combined in a hybrid manner to conduct complicated design tasks.

Evolutionary optimization within an intelligent hybrid system for design integration

An intelligent hybrid approach has been developed to integrate various stages in total design, including formulation of product design specifications, conceptual design, detail design, and manufacture. The integration is achieved by blending multiple artificial intelligence (AI) techniques and CAD/CAE/CAM into a single environment. It has been applied into power transmission system design. In addition to knowledge-based systems and artificial neural networks, another AI technique, genetic algorithms (GAs), are involved in the approach. The GA is used to conduct optimization tasks: (1) searching the best combination of design parameters to obtain optimum design of gears, and (2) optimization of the architecture of the artificial neural networks used in the hybrid system. In this paper, after a brief overview of the intelligent hybrid system, the GA applications are described in detail.

Multi‐user Internet environment for gear design optimization

A Web‐based multi‐user system has been developed to remotely execute a large size software package via the Internet. The software implements a genetic algorithm to optimize the design of spur and helical gears. To accomplish this, a combination of HTML, Java servlets, Java applets, Java Script and HTTP protocol has been employed.

Advances in the precision machining of small deep holes

Abstract Based on the analysis of the forces acting on a deep-hole drilling head and the understanding of the burnishing action of the carbide guide pads, an investigation of the precision drilling method of small deep holes in difficult-to-cut materials was carried out. The influence of tool geometry and cutting parameters (cutting speeds and feed rates) on the surface quality of the drilled holes was studied, the results of which indicating that O10–O20 mm small deep holes of high tolerance grades (IT7 to IT9) and lower surface roughness values ( R a ) in the range of 0.2–1.6 μm can be achieved and the problem of axial deviation of holes drilled minimised under optimised cutting parameters by means of the new/improved BTA drill.

Enhancement of speed and efficiency of an internet-based gear design optimisation

An internet-based gear design optimisation program has been developed for geographically dispersed teams to collaborate over the internet. The optimisation program implements genetic algorithm. A novel methodology is presented that improves the speed of execution of the optimisation program by integrating artificial neural networks into the system. The paper also proposes a method that allows an improvement to the performance of the back propagation-learning algorithm. This is done by rescaling the output data patterns to lie slightly below and above the two extreme values of the full range neural activation function. Experimental tests show the reduction of execution time by approximately 50%, as well as an improvement in the training and generalisation errors and the rate of learning of the network.

DEEP HOLE PRECISION MACHINING METHOD OF DIFFICULT-TO-CUT MATERIALS

Abstract The paper presents the result of the investigation into a highly efficient precision machining method of deep hole carried out on difficult-to-cut materials such as nickel chromium (CrNiMo and CrNi3MoV) alloys. This study indicates that the typical precision machining method of deep hole made up of both the precision boring and the honing could be replaced by auto-guide stiff boring-reaming technology. This work led to the development of an advanced auto-guide stiff boring-reaming head, which was a fixed single edge cutting tool with a set of hard metal alloy guides and a set of vibration damping soft bars located by calculating the stability of the head. New cutting tool materials such as coated (single and triple) and ceramic (Al2O3+TiC) tools have been successfully used for deep hole precision machining of difficult-to-cut materials at high speed conditions.