اعمال استدلال مبتنی بر مورد برای برنامه ریزی عملیات نوع فشرده سازی سرد
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|27228||2001||5 صفحه PDF||سفارش دهید||2489 کلمه|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Journal of Materials Processing Technology, Volume 112, Issue 1, 3 May 2001, Pages 12–16
On the basis of the practical situation of cold forging process planning, the disadvantages of a rule-based solution are discussed, and a case-based reasoning-based cold forging process planning (CFPP) system model is proposed. Several key problems involved are analyzed, among which a feature-based part representation scheme and a two-level retrieval mechanism are introduced to solve the problems of case representation and case retrieval. It is established in this paper that case-based reasoning-based CFPP is a promising technology for both long-term research and the promotion of efficiency for current cold process planning systems.
Cold forging is a metal forming process which shapes a workpiece between dies at room temperature. It has advantages over machining such as little material waste, higher productivity, good dimensional and form error tolerance, and improved properties of the workpiece. Usually, cold forging needs several “preforming” operations to make the required formable part from an initial round slug without product- and die-defects. Determining the feasible or optimum serial preforming operations for making a part has been called process planning. This task is usually considered as an “art” to be undertaken by highly experienced die designers who use both empirical judgement and established (but mostly not well documented) design or technology rules which were obtained through many years of experimentation. By process planning, usually people mean machining process planning since much research has been conducted in this area. However, according to recent developments in cold forging technology and computer technology, the application of computers in cold forging process planning (CFPP) has been growing rapidly, the initial development being led by Noack . After the expert system approach was introduced to engineering applications, several knowledge-based systems , , ,  and  were developed for CFPP. Since the nature of the heuristic knowledge and experience is fragile, and not well structured, it is not acquired easily and represented well in an expert system. In addition, to build an expert system, a knowledge engineer has to interview molding personnel and try to elicit appropriate knowledge in the form of rules. This knowledge is difficult to uncover and the knowledge acquisition becomes a bottleneck in the construction of the expert system. In this paper, a new approach, case-based reasoning (CBR), is adopted to solve the problem. CBR can mean old solutions to meet new demands, using old cases to explain new situations, and using old cases to critique new solutions. There are several benefits of applying CBR technology in computer-aided CFPP. It allows the reasoner to propose solutions quickly, hence reducing the time needed to work them out. In addition, remembering previous experience helps to avoid the repetition of past mistakes. The learning process available with a CBR system enables it to become more efficient by increasing its memory of old solutions and adapting them.
نتیجه گیری انگلیسی
Computer-aided CFPP has been a focal point in both the scientific and the industrial world. This paper has analyzed the practical situation of CFPP and the disadvantages of rule-based solution, and proposed a CBR-based CFPP model. Several key problems involved have been analyzed, among which feature-based part representation and a two-level retrieval mechanism are introduced to solve the representation and retrieval problem. It has been established in this paper that CBR-based CFPP is a promising technology for both long-term research and the promotion of efficiency for current cold process planning systems. Related research is being carried out, along with relatively small scale, applications, but these can serve as the foundation for future research.