دانلود مقاله ISI انگلیسی شماره 27007
ترجمه فارسی عنوان مقاله

روش های هوشمند برای تخصیص تالرانس و انتخاب عملیات تولید در برنامه ریزی فرایند

عنوان انگلیسی
Intelligent approaches to tolerance allocation and manufacturing operations selection in process planning
کد مقاله سال انتشار تعداد صفحات مقاله انگلیسی
27007 2001 9 صفحه PDF
منبع

Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)

Journal : Journal of Materials Processing Technology, Volume 117, Issues 1–2, 2 November 2001, Pages 75–83

ترجمه کلمات کلیدی
برنامه ریزی فرایند به کمک کامپیوتر - شبکه های عصبی - الگوریتم ژنتیک - تخصیص تحمل - انتخاب عملیات ساخت -
کلمات کلیدی انگلیسی
Computer aided process planning, Hopfield neural network, Genetic algorithm, Tolerance allocation, Manufacturing operations selection,
پیش نمایش مقاله
پیش نمایش مقاله  روش های هوشمند برای تخصیص تالرانس و انتخاب عملیات تولید در برنامه ریزی فرایند

چکیده انگلیسی

In the modern manufacturing environment, alternative sets of manufacturing operations can normally be generated for machining one feature of a part. Each set of manufacturing operations results in a specific manufacturing cost in terms of the allocated tolerances, and requires a specific set of manufacturing resources, such as machines, fixtures/jigs and cutting tools. In this paper, the problems of allocating tolerances to the manufacturing operations and selecting exactly one representative from the alternative sets of manufacturing operations for machining one feature of the part are formulated. The purpose is to minimize, for all the features to be machined, the sum of the costs of the selected sets of manufacturing operations and the dissimilarities in their manufacturing resource requirements. The techniques of the genetic algorithm and the Hopfield neural network are adopted as possible approaches to solve these problems. The genetic algorithm is utilized to generate the optimal tolerance for each of the manufacturing operations, and the Hopfield neural network is adopted to solve the manufacturing operations selection problem. An illustrative example is given to demonstrate the efficiency of the proposed approaches. Indeed, the proposed approaches show the potential of working towards the optimal solutions to the tolerance allocation problem and the manufacturing operations selection problem in process planning.

مقدمه انگلیسی

With the emergence of the global manufacturing era, the manufacturing environment has become increasingly competitive, as markets become more dynamic and customer-driven. As a result, the need for flexibility, efficiency, and quality has imposed a major change on manufacturing industries. Indeed, the product cost has a surging effect on manufacturing performance and competitiveness. The tolerance allocation and the manufacturing operations selection in process planning are two essential factors governing the product cost in manufacturing. In this connection, the development of more efficient approaches has become an impending necessity in solving the tolerance allocation problem and the manufacturing operations selection problem in process planning. Computer aided process planning (CAPP) has assumed an important role in manufacturing, in particular, to cope with the demands for flexibility, efficiency, and quality in the modern dynamic industrial environment. CAPP can be defined as the use of computers to determine systematically the procedures of manufacturing a product, so that the end product will be functional, economical, and of an acceptable quality [1]. However, most generative CAPP systems normally assume that only one set of sequenced manufacturing operations can be generated to machine one feature. Each set of sequenced manufacturing operations is composed of several manufacturing operations so ordered to machine the feature to meet design requirements. The tolerance of each manufacturing operation is pre-determined and unchangeable. This study proposes a more practical and flexible point of view, where a number of alternative sets of sequenced manufacturing operations are generated for each feature. The tolerance of each operation is not pre-determined, and can be optimized in order to minimize the manufacturing cost to machine each feature. Each alternative set of manufacturing operations results in a specific manufacturing cost, and requires a specific set of manufacturing resources, e.g., machines, fixtures/jigs, and cutting tools. The objective of this research is therefore to: (1) determine the tolerance for each sequenced manufacturing operation, so as to minimize the manufacturing cost for machining a feature; (2) select exactly one representative from the alternative sets of manufacturing operations for each feature, so as to minimize the sum of the manufacturing costs of the selected sets of manufacturing operations, and the dissimilarities in their manufacturing resource requirements, for the total number of features in one part. The tolerance allocation and manufacturing operations selection problems have received relatively little attention in the literature. Dong [2] proposed a mathematical model to select the optimal set of manufacturing operations for each feature according to the manufacturing costs associated with the tolerances. However, the tolerance levels in Dong’s model were pre-determined, and were the same for every set of manufacturing operations. Zhang and Wang [3] suggested a mathematical model to identify the optimal representative from a number of alternative sets of manufacturing operations by minimizing the manufacturing cost in terms of tolerances. At the same time, the tolerance and the intermediate manufacturing dimension are decided. Zhang and Wang [4] also used the same mathematical model to determine the optimal tolerance for a given set of manufacturing operations by using simulated annealing. However, simulated annealing often takes a long time to obtain the optimal solution to the problem. Knapp and Wang [5] utilized the back-propagation neural network to select one set of manufacturing operations for each feature. However, none of the approaches discussed above has attempted to solve both the tolerance allocation problem and the manufacturing operations selection problem simultaneously, for minimizing the sum of the manufacturing costs of the selected sets of manufacturing operations in terms of the allocated tolerances, and the dissimilarities in their manufacturing resource requirements for machining all the features in a part. In this study, two mathematical models are constructed to represent the behavior of the tolerance allocation problem and the manufacturing operations selection problem. A genetic algorithm is introduced to solve the optimal tolerance allocation problem. By using the results from the tolerance allocation procedure, a Hopfield neural network is proposed to select the optimal sets of manufacturing operations for all the features of the part. The detailed energy function of the Hopfield neural network specially constructed for solving such a problem is established. An illustrative example is presented to demonstrate the efficiency of the approaches developed in this paper. Indeed, the results show that the approaches proposed in this paper are powerful but simple means to provide high quality solutions to the tolerance allocation problem and the manufacturing operations selection problem in process planning.

نتیجه گیری انگلیسی

In this paper, the tolerance allocation problem and the manufacturing operations selection problem are delineated, and two mathematical models describing the characteristics of such problems have been established. The techniques of the genetic algorithm and the Hopfield neural network are adopted to solve the above two problems. The details of the genetic algorithm, e.g., individual representation, fitness evaluation, parent selection, reproduction, and mutation, have been presented to illustrate the procedure for solving the tolerance allocation problem. The energy function of the Hopfield neural network, which is specially designed to solve the manufacturing operations selection problem, has also been constructed. The advantages of the proposed algorithms can therefore be summarized as follows: (1) the development of an efficient approach to obtain the optimal tolerances for alternative sets of manufacturing operations to machine features in a part; (2) the ability to generate optimal sets of manufacturing operations by considering not only the manufacturing cost in terms of the tolerances, but also the dissimilarities in the manufacturing resource requirements among the selected sets of manufacturing operations. An example of machining hole features is presented to demonstrate the effectiveness of the proposed approaches. Indeed, the results clearly indicate that the approaches proposed in this paper show potential in working towards the optimal solutions to the tolerance allocation problem and the manufacturing operations selection problem.