Search

Abstract: The optimization of welding path is one of the most combinatorial problems in robotic welding. This paper is focused on the optimization for both productivity and quality in robotic welding. The productivity related scheduling problem is similar to the well-known traveling salesman problem (TSP). An optimization strategy for TSP based on the “elastic net method” (ENM) and artificial neural network is suggested in this paper. So for the most welding points which have less influence on the final distortion, they can be arranged in a better way that the welding robot can reach all the points and the total distance is the minimum. For the rest of the welding points, distortion and residual stress are the two main factors concerned. A thermo-mechanical model is developed to predict residual stress and distortion, and a welding sequence with minimum distortion has been found using a genetic algorithm (GA). These two solutions are integrated into the whole optimal welding path according to “nearest neighborhood criterion”. Finally, the optimization strategy is successfully carried out on a real product. [Copyright &y& Elsevier]

Abstract: This paper outlines the development of an optimization strategy to determine the optimum cutting parameters for multi-tool milling operations like face milling, corner milling, pocket milling and slot milling. The developed strategy based on the maximum profit rate criterion and incorporates five technological constraints. In this paper, optimization procedures based on the genetic algorithm, hill climbing algorithm and memetic algorithm were demonstrated for the optimization of machining parameters for milling operation. This paper describes development and utilization of an optimization system, which determines optimum machining parameters for milling operations. An objective function based on maximum profit in milling operation has been developed. Results obtained are used in NC machine. An example has been presented at the end of the paper to give clear picture from the application of the system and its efficiency. The results are compared and analyzed with method of feasible directions and handbook recommendations. [Copyright &y& Elsevier]

Abstract: This paper proposes an approach using quality loss functions and multicriteria optimization procedure to determine appropriate process parameter values for producing quality products in a continuous casting system. Quality of a continuously cast product depends on the process conditions during the casting process. From the information available in the literature and industry, 17 critical quality conditions have been identified which have to be satisfied to prevent defect formation during casting. Each of these process conditions are connected to one or more than one process parameters and the process parameter values are to be selected such that all these 17 quality conditions are satisfied simultaneously. The optimization procedure suggested in the present study involves representing the relationship between the responses and the process variables in the form of an objective function and finding the best set of values for the process variables. The objective function is formulated as a loss function, which establishes a functional relationship between the input variables or process parameters and the quality criteria. The optimum values of the process parameters were obtained by minimizing the loss function using simulated annealing optimization algorithm. The details are presented in this paper with the help of a specific case. [Copyright &y& Elsevier]

Abstract: This paper investigates optimization design of the cutting parameters for rough cutting processes in high-speed end milling on SKD61 tool steel. The major characteristics indexes for performance selected to evaluate the processes are tool life and metal removal rate, and the corresponding cutting parameters are milling type, spindle speed, feed per tooth, radial depth of cut, and axial depth of cut. In this study, the process is intrinsically with multiple performance indexes so that grey relational analysis that uses grey relational grade as performance index is specially adopted to determine the optimal combination of cutting parameters. Moreover, the principal component analysis is applied to evaluate the weighting values corresponding to various performance characteristics so that their relative importance can be properly and objectively described. The results of confirmation experiments reveal that grey relational analysis coupled with principal component analysis can effectively acquire the optimal combination of cutting parameters. Hence, this confirms that the proposed approach in this study can be an useful tool to improve the cutting performance of rough cutting processes in high-speed end milling process. [Copyright &y& Elsevier]

Abstract: Finite element analysis and optimization technique have been integrated to solve the optimal process parameters of sheet metal forming by transforming multi-objective problem into a single-objective problem in many studies. In this paper, a Pareto-based multi-objective genetic algorithm was applied to optimize sheet metal forming process. In the proposed optimal model, blank-holding force and draw-bead restraining force were optimized as design variables in order to make objective functions of fracture, wrinkle, insufficient stretching and thickness varying minimized simultaneously. The steps of optimization procedure include the using of Latin hypercube design for sample producing, response surface model for coarse fitting and incremental finite element analysis program for exact solving. An auto-body panel stamping case shows that this approach is more effective and accurate than traditional finite element analysis method and the ‘trial and error’ procedure. [Copyright &y& Elsevier]

Abstract: In this paper, a multiple regression analysis (MRA) and an artificial neural network (ANN) were employed to build a predicting model for cutting Quad Flat Non-lead (QFN) packages by using a Diode Pumped Solid State Laser (DPSSL) System. The predicting model includes three input variables of the current, the frequency and the cutting speed, and six cutting qualities of depths of the cutting line, widths of heat affected zone (HAZ) and cutting line for epoxy and for copper-compounded epoxy. After the training process from 27 sets of training data including input data and its output qualities, the average training error is 0.822% by using a back-propagation (BP) neural network with Levenberg–Marquardt (LM) algorithm, which leads to the best results. The testing accuracy is then verified with extra 14 sets of experimental data and the average predicting error is 1.512%. The results show that the ANN model has the predicting ability to estimate the laser-cutting qualities of QFN packages. Finally, a genetic algorithm (GA) is applied to find the optimal cutting parameters that lead to least HAZ width and fast cutting speed with complete cutting. The optimal combination found is the current of 29A, the frequency of 2.7kHz and the cutting speed of 3.49mm/s. The GA is helpful to determine the ideal laser-cutting parameters in order to meet the desired cutting qualities and to avoid unnecessary adjustments in the subsequent cutting process. [Copyright &y& Elsevier]

Abstract: Wire tension as well as wire feed should be controlled tightly for the geometry and corner accuracy of wire-EDM. In this paper, a closed-loop wire tension control system for Micro-Wire-EDM is presented to guarantee a smooth wire transport and a constant tension value. In order to keep smooth wire transportation and avoid wire breakage during wire feeding, the reel roller is modified and the clip reel is removed from the wire transport mechanism. A genetic algorithm-based fuzzy logic controller is proposed to investigate the dynamic performance of the closed-loop wire tension control system. Experimental results demonstrate that the developed wire transport system can result in satisfactory transient response, steady-state response and robustness. The proposed genetic algorithm-based fuzzy logic controller can obtain faster transient response and smaller steady-state error than a PI controller. [Copyright &y& Elsevier]

Abstract: In this paper, the finite element and abductive network methods were used to obtain a runner-system design to reach minimum warppage on an injection moulded parts with free-form geometry. This study uses the diameter and length of the runner-system as the major control parameters. In the model creation stage, FEM simulation data were used to derivate an accurate abductive network model for predicting wrappage in injection moulded parts corresponding to different control parameters. In the optimization stage, the simulated annealing (SA) method was used. This abductive methodology allows user to efficiently discover an optimal set of parameters without involving complex iteration between the optimization process and FEM simulation. [Copyright &y& Elsevier]

Abstract: In this paper, the finite element and abductive network methods were used to obtain a runner-system design to reach minimum warpage on an injection moulded parts with free-form geometry. This study uses the diameter and length of the runner-system as the major control parameters. In the model creation stage, FEM simulation data were used to derivate an accurate abductive network model for predicting warpage in injection moulded parts corresponding to different control parameters. In the optimization stage, the simulated annealing (SA) method was used. This abductive methodology allows user to efficiently discover an optimal set of parameters without involving complex iteration between the optimization process and FEM simulation. [Copyright &y& Elsevier]

Abstract: In this paper, the finite element and abductive network methods were used to obtain a runner-system design to reach minimum warppage on an injection moulded parts with free-form geometry. This study uses the diameter and length of the runner-system as the major control parameters. In the model creation stage, FEM simulation data were used to derivate an accurate abductive network model for predicting wrappage in injection moulded parts corresponding to different control parameters. In the optimization stage, the simulated annealing (SA) method was used. This abductive methodology allows user to efficiently discover an optimal set of parameters without involving complex iteration between the optimization process and FEM simulation. [Copyright &y& Elsevier]

Abstract: The work presented here describes a method of optimizing the layout of rectangular parts placed on a rectangular sheet to cut out various parts. Two types of cutting problems have been investigated (i) in which guillotine cutting (cutting from edge to edge) is required (mostly metallic sheets where each cut is made individually for one single sheet), and (ii) the one in which guillotine cutting is not essential (e.g. cuts which can be made using a punch) i.e. for materials like paper or rubber where the sheets to be cut can be laid side by side or on top of one another and one single cut can be made. The optimization of the layout of rectangular parts is achieved with respect to two design objectives involving minimization of (i) the length of the mother sheet required, and (ii) also the total number of cuts required to obtain all the parts from the mother sheet. A tree encoded multi-objective genetic algorithm has been used to study both guillotine and non-guillotine cutting cases, using a binary representation of the variables, and it is shown for the known cases that the globally optimum solutions are obtained. [Copyright &y& Elsevier]

Abstract: In the paper an optimisation method for the designing of chemical composition of high-speed steels (HSS) based on genetic algorithms (GA) is presented. The complex optimisation criterion was assumed comprising maximising secondary steel hardness with simultaneously minimising cost of material. Results of the numerical simulation show that genetic algorithm-based optimisation of steel chemical composition is effective and very useful in designing of the new metallic materials. [Copyright &y& Elsevier]

Abstract: The paper presents the new method for forecasting the yield point and the ultimate tensile strength for steel. These parameters are calculated basing on the chemical composition and technological factors of steel manufacturing. The artificial neural network technology was used for development of models making prediction of these properties possible. Software was developed, basing on these models, searching for the optimum chemical composition of steel, so that – at the particular conditions of the technological process – the risk of manufacturing the products that would not meet the requirements of the pertinent standards would be minimised. Search for the optimum chemical composition makes use of the genetic algorithms. [Copyright &y& Elsevier]

Abstract: The paper proposes a new concept for programming of CNC machines. The concept based on genetic algorithms assures evolutionary generation and optimization of NC programs on the basis of CAD models of manufacturing environment. The structure, undergoing simulated evolution, is the population of NC programs. The NC programs control the machine which performs simple elementary motions. During the evolution the machine movement becomes more and more complex and intelligent solutions emerge gradually as a result of the interaction between machine movements and manufacturing environment. The examples of evolutionary programming of CNC lathe and CNC milling machine tool for different complexities of the blanks and products are presented. The proposed concept showed a high degree of universality, efficiency, and reliability and it can be also simply adopted to other CNC machines. [Copyright &y& Elsevier]

Abstract: Electromotion devices are ever present in the contemporary society; without them the society could not function. Nevertheless, expectations exist relating to many aspects such as efficiency and power-to-weight ratio of these devices in their different guises. The object of this paper is to elucidate the effectiveness of multiple objective deterministic design optimisation of electromotion devices in satisfying these expectations. A permanent magnet machine will be used as the vehicle for demonstrating the approach. [Copyright &y& Elsevier]

Abstract: Method of genetic algorithms (GAs) has been started to be widely used, as an optimization technique of electrical machines, in the recent years. In this paper the GA method will be applied on the shaded-pole motor, aiming towards an improvement of its operational and performance characteristics. The authors develop two new improved motor models, starting from the basic one. In the first motor model the electromagnetic torque, as a target function for optimization is suggested, while in the second one the optimization is based on the efficiency factor, used as a target function. The results gained from the both motor models are analyzed and compared to the basic model. The conclusions regarding the more favorable target function for optimization of a single phase shaded-pole motor are presented. [Copyright &y& Elsevier]

Paper describes means and methods for computer based optimisation of production processes using a new approach based on technological database (TDB) with genetic algorithm incorporated into a database management system (DBMS). The TDB serves as a store of tools and machine tools from which they can be assigned to different work operations. Work operations are basic entities of orders placed into queues. The goal of the model is to find available resources from the TDB in order to empty the queue in shortest time with lowest costs. To this purpose the model consist the technological database whose DBMS includes a genetic algorithm based optimiser. It checks the orders queue and searches for appropriate combinations of tools and machine tools from the TDB, which can be combined into needed work operations. It also performs an optimisation of time and costs according to so called static parameters of tools and machine tools. [Copyright &y& Elsevier]

This paper presents a method that can be used to automatically determine and optimize the processing parameters in the EDM sinking process with the application of artificial neural networks (ANN). ANN can be optimized with a genetic algorithm (GA) and node deleting algorithm so that the number of hidden nodes of ANN will be determined automatically and scientifically. ANN can be trained with GA and BP algorithms, so that the local least solution can be avoided and the training speed enhanced. The experiment has proved that the utilization of mirror processing conditions generated from the above method will consequently lead to both good small-area mirror processing results and desired processing precision and efficiency. [Copyright &y& Elsevier]