# Journal of Optimization in Industrial Engineering 13 (2013) 49-54

Save this PDF as:

Size: px
Start display at page:

## Transcription

1 Journal of Optimization in Industrial Engineering 13 (2013) Optimization of Plastic Injection Molding Process by Combination of Artificial Neural Network and Genetic Algorithm Abstract Mohammad Saleh Meiabadi a, *, Abbas Vafaeesefat b, Fatemeh Sharifi c a Instructor, Industrial Engineering department, Islamic Azad University, Malayer Branch,, Malayer, Iran b AssociateProfessor,Mechanical Engineering Department, Imam Hussein University C Instructor, Computer Engineering Department, Chamran University, Ahvaz, Iran Received 25 April, 2012; Revised 15August, 2012; Accepted 18 November, 2012 Injection molding is one of the most important and common plastic formation methods. Combination of modeling tools and optimization algorithms can be used in order to determine optimum process conditions for the injection molding of a special part. Because of the complication of the injection molding process and multiplicity of parameters and their interactive effects on one another, analytical modeling of the process is either impossible or difficult. Therefore Artificial Neural Network (ANN) is used for modeling the process. Process conditions data is needed for modeling the process by the neural network. After modeling step, the model is combined with the Genetic Algorithm (GA). Based on the injection molding goals that have been turned into fitness function, the optimized conditions are obtained. Keywords: Optimization; Solution space; Control variable; Neural network; Genetic algorithm. 1. Introduction Plastic injection molding is one of the well known manufacturing techniques that should be able to produce complex- shaped and large-sized products in short time at low cost. To avoid the high costs and time delays associated with problems discovered at the start of manufacturing, it is necessary to consider the combined effects of part geometry, material characteristics, mold design and processing conditions on the manufacturability of a part. The factors that affect the part manufacturability are shown in Fig. 1. Fig. 1. Parameters influence on part manufacturability Final optimal process parameter setting are recognized as one of the most important steps in injection molding for improving the quality of molded products. Since the quality of injection molded plastic parts are mostly influenced by process conditions, how to determine the optimum process parameters becomes the key to improving the part quality. Previously, production engineers used trial-and-error or Taguchi s parameter design method to determine optimal process parameters setting for plastic injection molding. Trial-and-error method is costly and time consuming. Besides, the optimum process parameters may not be achievable by this method. Chen et al.(2008, 2009) declared that application of conventional Taguchi parameter design method is unsuitable when one of the process parameter variables is continuous and it cannot help engineers obtain optimal results for process parameter settings. Hybrid system of artificial intelligence is a scientific approach for obtaining optimum process conditions in plastic injection molding. The following can be cited from previously researches that have used hybrid system of artificial intelligence for optimization injection molding process. Hamedietal(2006)used a hybrid system of artificial intelligence to optimize the dimensional contradictions in the plastic injection process. Spina (2006) introduced evaluation of the Finite Element (FE) simulation results through the ANN system. They found artificial neural network system as an efficient method for the assessment of the influence of process parameter variation on part manufacturability, and possible adjustments to improve part quality. * Corresponding author 49

2 Mohammad Saleh Meiabadi et al./ Optimization of Plastic Injection... Kurtaranet al.(2005) determined the best injection molding process conditions for a bus ceiling lamp using FE software MoldFlow and ANN. Genetic optimization reduced the maximum warpage of the initial model by 46.5%. Changyuetal(2007) expressed that the combination of artificial neural network and genetic algorithm gives satisfactory results to improve the quality index of the volumetric shrinkage variation in the part. Ozceliketal(2006) confirmed that the use of artificial neural network and genetic algorithm is an efficient optimization methodology in minimizing warpage of thin shell plastic parts manufactured by injection molding. Chavanatnusorn(2009) presented a systematic approach to determine the optimal processing conditions by optimizing the quality of plastic injection-molded parts and their process cycle time. Two plastic parts were used as study cases, a rectangular lid and a roof tile. Six process parameters in injection molding including material type, melt temperature, injection speed, packing pressure, packing time and cooling time, were optimized by using Computer-Aided Engineering (CAE) software, the Design of Experiments (DOE) technique, the ANN model, and the GA method. In most researches the purpose was minimizing injection defects like shrinkage and warpage but the purpose of this research is obtaining process parameters ensure accurate part weight, less process cycle time and injection pressure. In this study the most important control variables affecting specified injection goals are recognized by statistical design of experiments feature of MoldFlow software. The combination of the full factorial and random approach is used to create the solution space, since both are advantageous. Optimum structure of neural network is determined by Nerosolution software. Plastic injection molding process is modeled by neural network and then the fitness function optimized by Genetic algorithm. Finally efficiency of optimization method is confirmed by experimental fabrication. The material type is SABIC PP 512MN10. Material properties are reported in Table 1. Table 1 Material properties Density 905kg/m 3 Melt Flow Rate: at 230 C and 2.16 kg 37g/10min Tensile test: tensile stress at yield(iso 527) 26N/mm 2 Heat distortion temperature: at 0.45 MPa(ISO 75/B) 89 o C model with GA is a promising natural computation technique for optimization because ANN has become a practical method for predictive capability to very complex non-linear systems. GA can be used to find the optimum value of the process parameters. The proposed method should be used when multi-response quality characteristics is needed. Fig. 2 shows the optimization steps in the proposed method. Fig. 2. Flow chart of combining ANN/GA 2.1. Choose Injection Goals One of the main goals in injection molding is the improvement of quality of molded parts besides the reduction of process cycle time. The purpose of this research is to obtain process parameters ensuring accurate part weight, less process cycle time and injection pressure. Chen et al. (2008) are among the researchers which showed that product weight is a critical quality characteristic and a good indication of the stability of the manufacturing process in plastic injection molding. Part weight is closely associated with the other quality criteria such as surface quality, mechanical properties and dimensional specifications. Economically, process cycle time should be short without negative effects on the quality. Another criterion is the injection pressure that forces more material into the injection mold. The hydraulic pressure limit is set high enough to allow the machine to maintain the set injection speed. A sharper and more changing pressure curve causes more fluctuations in produced parts weight. 2. Optimization Steps Optimization steps is a systematic approach to determine the optimum process conditions in plastic injection molding using CAE, DOE, ANN, and GA. CAE software was used to simulate the manufacturing process and DOE involves in determining the significant control variables in the injection molding process. Using ANN 2.2. Simulation of Part and Runner System in MoldFlow Computer-aided engineering software is used to simulate practical experiments for the cost and time saving. Moldflow Plastics Insight(MPI) is one of the commercial CAE softwares for plastic injection molding process. MoldFlow software represents the most comprehensive suite of definitive tools for simulating, 50

3 Journal of Optimization in Industrial Engineering 13 (2013) analyzing, optimizing, and validating plastics part and mold designs. The CAD model of the product was initially imported and converted into a FE mesh but runner system is modeled in MoldFlow. Due to low thickness of the part, two-dimensional surface (fusion) element is selected. The simulation results of the injection process are used into modeling injection process by neural network. But results of the software should be confirmed with experimental validation. Also the most important control variables affecting injection goals are recognized by statistical design of experiments features of MoldFlow. Fig. 3 shows the part and the runner system in MoldFlow. Fig.3. Part and runner system modeled and meshed in MoldFlow 2.3. Determine Main Process Parameters In this step, the most important process parameters affecting the injection goals are determined.this greatly increase the efficiency of optimization method. Persentage impacte of considered parameters on injection goals can be determined by statistical design of experiment feature of MoldFlow. Table 2 shows the percentage impact of parameters on part weight, process cycle time and maximum injection pressure. Melt temperature, packing time, packing pressure and mold wall temperature are considered as the main process parameters. Table 2 Percentage impact of considered parameters Rank Process parameter percentage 1 Melt temperature Packing time Packing pressure Mold wall temperature Injection time Define Solution Space The most important parameters affecting the injection goals are considered as control variables and the selected criteria for injection goals considered as response variables. Response variables data are obtained by control variables test. Sets of the control variables are called solution space. Solution space is defined in two approaches. In the first approach, a regular solution space equal to that obtained with a 3 n Full Factorial technique was defined. In this way, the influence of each process parameter on selected responses can be evaluated. The parameter ranges are reported in Table 3. The second approach considered an initial solution set in which control variables were randomly distributed. The advantage of this approach is the definition of a solution space in which regions leading to unfeasible solutions were avoided. The solution space is consisted of 81 sets created by permuting the minimum, middle and maximum levels of the process parameters, plus 16 sets randomly generated. Table 3 Process parameter ranges Process parameter Melt temperature (C) Mold wall temperature (C) Packing time (s) Packing pressure (MPa) Max Mid Min Injection speed was set to 20 mm/s and net cooling time equal to 15 s in MoldFlow process setting. The net cooling time is the time after the pressure phase and before the part is ejected from the mold. The relationship between control variables and response variables are identified by several tests performed by MoldFlow Modeling Plastic Injection Molding Process by Neural Network The complex relationships between control variables and response variables could not be determined by any analytic model. Bhartiet al (2010)declared that neural networks have been shown to be an effective technique for modeling complex nonlinear processes. They are useful for functional prediction and system modeling where the processes are not understood or are highly complex. Neural networks are composed of simple elements operating in parallel. These elements are inspired by biological nervous systems. As in nature, the connections between elements largely determine the network function (Matlab help). The neural network can be trained to perform a particular function by adjusting the values of the connections (weights) between elements. Typically, neural networks are adjusted, or trained, so that a particular input leads to a specific target output. The artificial neural network used in this study is a Feed Forward network consisting of one input, two hidden and one output layers. Hidden layers have ten neurons, whereas input and output layers have four and three neurons, respectively. The neuron number of the input layer of neural network is determined by the number of control variables and the neuron number of the output layer is determined by the number of the response 40 51

4 Mohammad Saleh Meiabadi et al./ Optimization of Plastic Injection... variables. The transfer function between the input layer and the hidden layer is Tansig, while the transfer function between the hidden layer and the output layer is Purelin. The learning rule was based on the Levenberg- Marquardt algorithm while the performance function was the Mean Square Error (MSE) minimization of the network errors on the training set. The samples of control variables and response variables are then assigned as input output data to train and test the neural network. The dataset used in this study consist of 97 sets, which is divided to 75%, 15% and 15% used for training, testing and cross validation respectively. The neural network architecture is shown in Fig. 4. The optimal neural network architecture is obtained by Nero solution software. Based on the results of Neuro solution software the best structure of the network is obtained by ten neurons for each hidden layer Define Fitness Function The trained neural network is capable of predicting maximum injection pressure, process cycle time and part weight while control variables is applied to the ANN. Suitability of control variables are determined when the outputs of the neural network(response variables) are applied to the fitness function. When process parameters (control variables) satisfy injection goals, fitness function will produce a smaller number. Fitness function is defined as follows: y f(y, y, y ) = [Abs(y )] 2 Fig. 4. AAN Architecture + y 55 y 1 : Maximum injection pressure y 2 : Desired weight of the part y 3 : Process cycle time The maximum injection pressure is (Mpa) in response variables data. The desirable part weight is (g). Maximum difference between desirable part weight and worst weight in response variables data is 2.274(g) and the maximum process cycle time is 55(s) Finding Optimum Process Parameters by Genetic Algorithm Optimum values of the main process parameters are efficiently obtained by genetic algorithm. Accurate part weight and less process cycle time and injection pressure can be achieved by setting optimum process conditions. The genetic algorithm is a method for solving optimization problems that is based on natural selection and a process that drives biological evolution. The genetic algorithm repeatedly modifies a population of individual solutions. At each step, the genetic algorithm selects individuals at random from the current population to be parents and uses them to produce the children for the next generation. Over successive generations, the population "evolves" toward an optimal solution (Matlab help). To solve the above optimization problem GA is coupled with the neural network. It should be mentioned the direct link between the simulation software and GA required a long time before optimum process parameters were identified. An initial population is generated at random, and the fitness function based on the neural network model is used to calculate the fitness for all initial individuals. Then, selection, crossover and mutation are used to reproduce a new generation. The process is repeated until the maximum generation number or population 52

5 Journal of Optimization in Industrial Engineering 13 (2013) convergence occurs. Based on the above algorithm, the optimization program for the injection molding process has been developed using MATLAB. In this study the population size is 20 and value of Elite count is considered 2. The number of individuals with the best fitness values in the current generation who are guaranteed to survive to the next generation are called Elite children. The value of crossover fraction is 0.8. The Crossover fraction specifies the fraction of each population, other than elite children that are made up of crossover children. Figure 5 shows the best fitness achieved after 51 generations. Table 4 shows the optimized process parameters. Fig. 5. Evolution of generations for injection molding process optimization Table 4 Optimized process parameters Packing pressure (MPa) 10 Packing time (s) 16/457 Melt temperature (C) 233/ Experimental Test and Results Comparison Mold wall temperature(c) 23/154 The optimized process parameters should be tested by experimental fabrication to evaluate efficiency of the proposed method. The experimental fabrication is performed by Krauss Maffei 150 C2 injection machine. The moveable half of mold is shown in Fig. 6. Table 5 shows the comparison between results of the Moldflow simulation, neural network and experimental fabrication using optimal process parameters setting. The results of experimental fabrication were in good agreement with Moldflow and neural network results that reveal accuracy of Moldflow simulation and neural network. The part weight is close to desirable weight and the process cycle time is reduced from 35.5 to 32 second. Fig. 6. Moveable half of mold Table 5 Comparison between FE simulation, ANN r and experimental fabrication results Moldflow simulation ANN pridiction Experimental fabrication 4. Conclusions Maximum injection pressure(mpa) Part weight(g) Process cycle time(s) The purpose of this research was to obtain the process parameters that ensure the accurate part weight, less process cycle time, and injection pressure. The research results indicate that the proposed approach can effectively help engineers determine optimal process parameters setting and achieve competitive advantages of product quality and costs. The efficiency of the method depends on the selection of appropriate process parameters, process parameter ranges and accuracy of Moldflow simulations and neural network predictions. In this study, the process parameters were determined within constraints of machine tools and mold steel. Thus, some parameters could not be considered as the parameters for optimizing the injection process. Because of the fixed mold constraint, the gate location and coolant point could not change their locations. For future study, the researcher should perform the experiments using this methodology before producing new products and its mold. 53

6 Mohammad Saleh Meiabadi et al./ Optimization of Plastic Injection References [1] Bharti, P.K. and Khan., M. I. (2010). Recent methods for optimization of plastic injection molding process a retrospective and literature review. International Journal of Engineering Science and Technology, 2(9), [2] Changyu, S., Lixia., W. and Qian, L. (2007).Optimization of injection molding process parameters using combination of artificial neural network and genetic algorithm method. Journal of Materials Processing Technology, 183, [3] Chavanatnusorn., P. (2009). Determination of the optimal processing conditions in plastic injection molding using computer-aided engineering, artificial neural network model, and genetic algorithm. M.sc thesis. kasetsart university. [4] Chen, W.C., Fu, G.L., Tai, P.H. and Deng, W.J. (2009). Process parameter optimization for MIMO plastic injection molding via soft computing. Expert Systems with Applications, 36, [5] Chen, W.C., Wang, M.W., Fu, G.L. and Chen, C.T. (2008). Optimization of plastic injection molding process via taguchi's Parameter Design Method, BPNN, AND DFP. Proceeding of Seventh International Conference on Machine Learning and Cybernetics. Kunming July, [6] Hamedi, M. and Bisepar, M. (2006). Application of a Hybrid of Artificial Intelligence for Optimization Part Dimensional Contradictions in Plastic Injection Process.14 th Annual Mechanical Engineering Conference. [7] Kurtaran, H., Ozcelik, B. and Erzulumla, T. (2005). Warpage optimization of a bus ceiling lamp base using neural network model and genetic algorithm. Journal Materials Processing Technology, 169, [8] [9] Ozcelik, B., Erzulumla, T. (2006). Comparison of the warpage optimization in the plastic injection molding using ANOVA, neural network model genetic algorithm. Journal Materials Processing Technology, 171, [10] Spina, R. (2006). Optimization of injection molded parts by using ANN-PSO approach. Journal of Achievement in Materials and Manufacturing Engineering, 15,

### Verification Experiment on Cooling and Deformation Effects of Automatically Designed Cooling Channels for Block Laminated Molds

International Journal of Engineering and Advanced Technology (IJEAT ISSN: 2249 8958 Volume-4 Issue-5 June 2015 Verification Experiment on Cooling and Deformation Effects of Automatically Designed Cooling

### SOLUTIONS FOR MOLD DESIGNERS

SOLUTIONS FOR MOLD DESIGNERS White Paper Abstract For CAE analysis tools to be truly useful, they must provide practical information that drives design decisions. Moldflow Plastics Advisers (MPA ) solutions

### A Statistical Experimental Study on Shrinkage of Injection-Molded Part

A Statistical Experimental Study on Shrinkage of Injection-Molded Part S.Rajalingam 1, Awang Bono 2 and Jumat bin Sulaiman 3 Abstract Plastic injection molding is an important process to produce plastic

### Effect of Differences Core and Cavity Temperature on Injection Molded Part and Reducing the Warpage by Taguchi Method

International Journal of Engineering & Technology IJET-IJENS Vol:10 No:06 125 Effect of Differences Core and Cavity Temperature on Injection Molded Part and Reducing the Warpage by Taguchi Method Z. Shayfull*

### Measurement of warpage of injection moulded Plastic components using image processing

Measurement of warpage of injection moulded Plastic components using image processing S.Selvaraj 1, P.Venkataramaiah 2 Research Scholar, Dept of Mechanical Engineering, Sri Venkateswara University College

### Using Injection Molding Process for Manufacturing a HDPE Mini Wheel

J. Eng. Technol. Educ. (2013) 10(4): 450-466 December 2013 Using Injection Molding Process for Manufacturing a HDPE Mini Wheel Thi Truc-Ngan Huynh* Department of Mechanical Engineering, National Kaohsiung

### WARPAGE PREDICTION IN PLASTIC INJECTION MOLDED PART USING ARTIFICIAL NEURAL NETWORK *

IJST, Transactions of Mechanical Engineering, Vol. 37, No. M2, pp 149-160 Printed in The Islamic Republic of Iran, 2013 Shiraz University WARPAGE PREDICTION IN PLASTIC INJECTION MOLDED PART USING ARTIFICIAL

### Finite Element Thermal Analysis of Conformal Cooling Channels in Injection Moulding

5 th Australasian Congress on Applied Mechanics, ACAM 2007 10-12 December 2007, Brisbane, Australia Finite Element Thermal Analysis of Conformal Cooling Channels in Injection Moulding A.B.M. Saifullah

### Optimum Design of Worm Gears with Multiple Computer Aided Techniques

Copyright c 2008 ICCES ICCES, vol.6, no.4, pp.221-227 Optimum Design of Worm Gears with Multiple Computer Aided Techniques Daizhong Su 1 and Wenjie Peng 2 Summary Finite element analysis (FEA) has proved

### CHAPTER 2 INJECTION MOULDING PROCESS

CHAPTER 2 INJECTION MOULDING PROCESS Injection moulding is the most widely used polymeric fabrication process. It evolved from metal die casting, however, unlike molten metals, polymer melts have a high

### THREE-DIMENSIONAL INSERT MOLDING SIMULATION IN INJECTION MOLDING

THREE-DIMENSIONAL INSERT MOLDING SIMULATION IN INJECTION MOLDING Rong-Yeu Chang* National Tsing-Hua University, HsinChu, Taiwan 30043, ROC Yi-Hui Peng, David C.Hsu and Wen-Hsien Yang CoreTech System Co.,Ltd.,

### Investigation of process parameters for an Injection molding component for warpage and Shrinkage

Investigation of process parameters for an Injection molding component for warpage and Shrinkage Mohammad Aashiq M 1, Arun A.P 1, Parthiban M 2 1 PGD IN TOOL & DIE DESIGN ENGINEERING-PSG IAS 2 ASST.PROFESSOR

### INJECTION MOLDING COOLING TIME REDUCTION AND THERMAL STRESS ANALYSIS

INJECTION MOLDING COOLING TIME REDUCTION AND THERMAL STRESS ANALYSIS Tom Kimerling University of Massachusetts, Amherst MIE 605 Finite Element Analysis Spring 2002 ABSTRACT A FEA transient thermal structural

### An Optimization of Shrinkage in Injection Molding Parts by Using Taguchi Method

An Optimization of Shrinkage in Injection Molding Parts by Using Taguchi Method H. Radhwan *,a, M. T. Mustaffa b, A. F. Annuar c, H. Azmi d, M. Z. Zakaria e and A. N. M. Khalil f School of Manufacturing

### STRUCTURAL ANALYSIS OF FIBER- FILLED PLASTICS

STRUCTURAL ANALYSIS OF FIBER- FILLED PLASTICS WITH MOULDING PROCESS INDUCED ANISOTROPY Abstract P. Satheesh Kumar 1, S. Srikari 2, N. S. Mahesh 3, S. Reddy 4 1 Student, M. Sc. [Engg.], 2 Professor, 3 Professor

### A Binary Model on the Basis of Imperialist Competitive Algorithm in Order to Solve the Problem of Knapsack 1-0

212 International Conference on System Engineering and Modeling (ICSEM 212) IPCSIT vol. 34 (212) (212) IACSIT Press, Singapore A Binary Model on the Basis of Imperialist Competitive Algorithm in Order

### 3D Printed Injection Molding Tool ("PIMT") Guide. Objet Ltd.

3D Printed Injection Molding Tool ("PIMT") Guide Objet Ltd. 2 Injection molding is a high speed, automated and versatile process that can produce high precision complex three dimensional parts from a fraction

### Integrative Optimization of injection-molded plastic parts. Multidisciplinary Shape Optimization including process induced properties

Integrative Optimization of injection-molded plastic parts Multidisciplinary Shape Optimization including process induced properties Summary: Andreas Wüst, Torsten Hensel, Dirk Jansen BASF SE E-KTE/ES

### Evaluation of Filling Conditions in Injection Moulding by Integrating Numerical Simulations

Middle-East Journal of Scientific Research 12 (12): 1608-1614, 2012 ISSN 1990-9233 IDOSI Publications, 2012 DOI: 10.5829/idosi.mejsr.2012.12.12.2 Evaluation of Filling Conditions in Injection Moulding

### Open Access Research on Application of Neural Network in Computer Network Security Evaluation. Shujuan Jin *

Send Orders for Reprints to reprints@benthamscience.ae 766 The Open Electrical & Electronic Engineering Journal, 2014, 8, 766-771 Open Access Research on Application of Neural Network in Computer Network

### Minimization of sink mark defects in injection molding process Taguchi approach

MultiCraft International Journal of Engineering, Science and Technology Vol. 2, No. 2, 2010, pp. 13-22 INTERNATIONAL JOURNAL OF ENGINEERING, SCIENCE AND TECHNOLOGY www.ijest-ng.com 2010 MultiCraft Limited.

### AN OVERVIEW OF GAS ASSIST

GAS ASSIST INJECTION MOLDING AN OVERVIEW OF GAS ASSIST April 2010 www.bauerptg.com GAS ASSIST INJECTION MOLDING TECHNOLOGY It is a fact that packing force must be applied and maintained to an injection

### MIT 2.810 Manufacturing Processes and Systems. Homework 6 Solutions. Casting. October 15, 2015. Figure 1: Casting defects

MIT 2.810 Manufacturing Processes and Systems Casting October 15, 2015 Problem 1. Casting defects. (a) Figure 1 shows various defects and discontinuities in cast products. Review each one and offer solutions

### A Hybrid Tabu Search Method for Assembly Line Balancing

Proceedings of the 7th WSEAS International Conference on Simulation, Modelling and Optimization, Beijing, China, September 15-17, 2007 443 A Hybrid Tabu Search Method for Assembly Line Balancing SUPAPORN

### Influence of material data on injection moulding simulation Application examples Ass.Prof. Dr. Thomas Lucyshyn

TRAINING IN THE FIELD OF POLYMER MATERIALS / PLASTICS Influence of material data on injection moulding simulation Application examples Ass.Prof. Dr. Thomas Lucyshyn 24 th April 2014 Otto Gloeckel-Straße

### ARTIFICIAL INTELLIGENCE METHODS IN EARLY MANUFACTURING TIME ESTIMATION

1 ARTIFICIAL INTELLIGENCE METHODS IN EARLY MANUFACTURING TIME ESTIMATION B. Mikó PhD, Z-Form Tool Manufacturing and Application Ltd H-1082. Budapest, Asztalos S. u 4. Tel: (1) 477 1016, e-mail: miko@manuf.bme.hu

### DESIGN OF PLASTIC INJECTION MOLD FOR AN AIR VENT BEZEL THROUGH FLOW ANALYSIS (CAE) FOR DESIGN ENHANCEMENT

DESIGN OF PLASTIC INJECTION MOLD FOR AN AIR VENT BEZEL THROUGH FLOW ANALYSIS (CAE) FOR DESIGN ENHANCEMENT Jitendra Dilip Ganeshkar 1, R.B.Patil 2 1 ME CAD CAM Pursuing, Department of mechanical engineering,

### A Survey on Methods used for Optimization of Injection Molding

A Survey on Methods used for Optimization of Injection Molding Aditya Shirish Joshi 1, Rahul Radhesham Jayaswal 2 1 Department of Mechanical Engineering ISB&M Scool of Technology Pune, India 2 Department

### Understanding Plastics Engineering Calculations

Natti S. Rao Nick R. Schott Understanding Plastics Engineering Calculations Hands-on Examples and Case Studies Sample Pages from Chapters 4 and 6 ISBNs 978--56990-509-8-56990-509-6 HANSER Hanser Publishers,

### Analecta Vol. 8, No. 2 ISSN 2064-7964

EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

### Part and tooling design. Eastman Tritan copolyester

Part and tooling design Eastman Tritan copolyester Part and tooling design Process Part design Tooling design High cavitation considerations Process Process Project development flow chart Concept OEM generates

### Development of a new model for predicting EDM properties of Cu-TaC compact electrodes based on artificial neural network method

Australian Journal of Basic and Applied Sciences, 6(13): 192-199, 2012 ISSN 1991-8178 Development of a new model for predicting EDM properties of Cu-TaC compact electrodes based on artificial neural network

### Prediction Model for Crude Oil Price Using Artificial Neural Networks

Applied Mathematical Sciences, Vol. 8, 2014, no. 80, 3953-3965 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ams.2014.43193 Prediction Model for Crude Oil Price Using Artificial Neural Networks

MuCell Injection Molding: Unique Process Solutions for Light Weighting Plastic Parts MuCell Injection Molding Brent Strawbridge, Vice President Sales Lightweighting Custom enewsletter AGENDA Technology

### Predictive time series analysis of stock prices using neural network classifier

Predictive time series analysis of stock prices using neural network classifier Abhinav Pathak, National Institute of Technology, Karnataka, Surathkal, India abhi.pat93@gmail.com Abstract The work pertains

### Analysis and Optimization of Investment Castings to Reduce Defects and Increase Yield

Analysis and Optimization of Investment Castings to Reduce Defects and Increase Yield Arunkumar P 1, Anand.S.Deshpande 2, Sangam Gunjati 3 1 Associate Professor, Mechanical Engineering, KLS Gogte Institute

### Numerical Analysis of Independent Wire Strand Core (IWSC) Wire Rope

Numerical Analysis of Independent Wire Strand Core (IWSC) Wire Rope Rakesh Sidharthan 1 Gnanavel B K 2 Assistant professor Mechanical, Department Professor, Mechanical Department, Gojan engineering college,

### Web Service Monitoring Scheduler based on evaluated QoS in Dynamic Environment

Quest Journals Journal of Software Engineering and Simulation Volume 2 ~ Issue 3 (2014) pp: 01-08 ISSN(Online) :2321-3795 ISSN (Print):2321-3809 www.questjournals.org Research Paper Web Service Monitoring

### Neural Network and Genetic Algorithm Based Trading Systems. Donn S. Fishbein, MD, PhD Neuroquant.com

Neural Network and Genetic Algorithm Based Trading Systems Donn S. Fishbein, MD, PhD Neuroquant.com Consider the challenge of constructing a financial market trading system using commonly available technical

### R. Urval 1, S. Lee* 1, S. V. Atre 1, S.-J. Park 2 and R. M. German 2. Introduction

Optimisation of process conditions in powder injection moulding of microsystem components using a robust design method: part I. primary design parameters R. Urval 1, S. Lee* 1, S. V. Atre 1, S.-J. Park

International Journal of Computer Trends and Technology- volume4issue2-2013 ABSTRACT: Neural Network Design in Cloud Computing B.Rajkumar #1,T.Gopikiran #2,S.Satyanarayana *3 #1,#2Department of Computer

### Proposal and Analysis of Stock Trading System Using Genetic Algorithm and Stock Back Test System

Proposal and Analysis of Stock Trading System Using Genetic Algorithm and Stock Back Test System Abstract: In recent years, many brokerage firms and hedge funds use a trading system based on financial

### Wireless Sensor Networks Coverage Optimization based on Improved AFSA Algorithm

, pp. 99-108 http://dx.doi.org/10.1457/ijfgcn.015.8.1.11 Wireless Sensor Networks Coverage Optimization based on Improved AFSA Algorithm Wang DaWei and Wang Changliang Zhejiang Industry Polytechnic College

### Performance Optimization of I-4 I 4 Gasoline Engine with Variable Valve Timing Using WAVE/iSIGHT

Performance Optimization of I-4 I 4 Gasoline Engine with Variable Valve Timing Using WAVE/iSIGHT Sean Li, DaimlerChrysler (sl60@dcx dcx.com) Charles Yuan, Engineous Software, Inc (yuan@engineous.com) Background!

### Material Testing Report SN 6641 ISOFIL HK 30 TXH0 NAT01

Material Testing Report SN 6641 ISOFIL HK 30 TXH0 NAT01 Lot# 2103304 Prepared for: SIRMAX SPA Via dell artigianato 42 Cittadella Italy Prepared by: Autodesk Moldflow Plastics Labs 2353 N. Triphammer Rd.

### A New Approach For Estimating Software Effort Using RBFN Network

IJCSNS International Journal of Computer Science and Network Security, VOL.8 No.7, July 008 37 A New Approach For Estimating Software Using RBFN Network Ch. Satyananda Reddy, P. Sankara Rao, KVSVN Raju,

### Keywords: Image complexity, PSNR, Levenberg-Marquardt, Multi-layer neural network.

Global Journal of Computer Science and Technology Volume 11 Issue 3 Version 1.0 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc. (USA) Online ISSN: 0975-4172

### Using Artificial Intelligence and Machine Learning Techniques. Some Preliminary Ideas. Presentation to CWiPP 1/8/2013 ICOSS Mark Tomlinson

Using Artificial Intelligence and Machine Learning Techniques. Some Preliminary Ideas. Presentation to CWiPP 1/8/2013 ICOSS Mark Tomlinson Artificial Intelligence Models Very experimental, but timely?

### Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network

Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network Qian Wu, Yahui Wang, Long Zhang and Li Shen Abstract Building electrical system fault diagnosis is the

### Solid shape molding is not desired in injection molding due to following reasons.

PLASTICS PART DESIGN and MOULDABILITY Injection molding is popular manufacturing method because of its high-speed production capability. Performance of plastics part is limited by its properties which

### Numerical Research on Distributed Genetic Algorithm with Redundant

Numerical Research on Distributed Genetic Algorithm with Redundant Binary Number 1 Sayori Seto, 2 Akinori Kanasugi 1,2 Graduate School of Engineering, Tokyo Denki University, Japan 10kme41@ms.dendai.ac.jp,

### A Service Revenue-oriented Task Scheduling Model of Cloud Computing

Journal of Information & Computational Science 10:10 (2013) 3153 3161 July 1, 2013 Available at http://www.joics.com A Service Revenue-oriented Task Scheduling Model of Cloud Computing Jianguang Deng a,b,,

### Model-based Parameter Optimization of an Engine Control Unit using Genetic Algorithms

Symposium on Automotive/Avionics Avionics Systems Engineering (SAASE) 2009, UC San Diego Model-based Parameter Optimization of an Engine Control Unit using Genetic Algorithms Dipl.-Inform. Malte Lochau

### CHAPTER 5 PREDICTIVE MODELING STUDIES TO DETERMINE THE CONVEYING VELOCITY OF PARTS ON VIBRATORY FEEDER

93 CHAPTER 5 PREDICTIVE MODELING STUDIES TO DETERMINE THE CONVEYING VELOCITY OF PARTS ON VIBRATORY FEEDER 5.1 INTRODUCTION The development of an active trap based feeder for handling brakeliners was discussed

### Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57. Application of Intelligent System for Water Treatment Plant Operation.

Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57 Application of Intelligent System for Water Treatment Plant Operation *A Mirsepassi Dept. of Environmental Health Engineering, School of Public

### Power Prediction Analysis using Artificial Neural Network in MS Excel

Power Prediction Analysis using Artificial Neural Network in MS Excel NURHASHINMAH MAHAMAD, MUHAMAD KAMAL B. MOHAMMED AMIN Electronic System Engineering Department Malaysia Japan International Institute

Plastics made perfect Validation and optimization of plastic parts Innovative plastic resins and functional plastic part designs are on the rise in almost every industry. Plastics and fiber-filled composites

### A Parallel Processor for Distributed Genetic Algorithm with Redundant Binary Number

A Parallel Processor for Distributed Genetic Algorithm with Redundant Binary Number 1 Tomohiro KAMIMURA, 2 Akinori KANASUGI 1 Department of Electronics, Tokyo Denki University, 07ee055@ms.dendai.ac.jp

### RESEARCH PROJECT. High Pressure Die Casting Defects and Simulation Process by Computer Added Engineering (CAE)

RESEARCH PROJECT High Pressure Die Casting Defects and Simulation Process by Computer Added Engineering (CAE) ME8109 CASTING AND SOLIDIFICATION OF MATERIALS Presented by: Irshad Ali (Student # 500482510)

### THE PSEUDO SINGLE ROW RADIATOR DESIGN

International Journal of Mechanical Engineering and Technology (IJMET) Volume 7, Issue 1, Jan-Feb 2016, pp. 146-153, Article ID: IJMET_07_01_015 Available online at http://www.iaeme.com/ijmet/issues.asp?jtype=ijmet&vtype=7&itype=1

### Injection molding equipment

Injection Molding Process Injection molding equipment Classification of injection molding machines 1. The injection molding machine processing ability style clamping force(kn) theoretical injection volume(cm3)

### Application of Neural Network in User Authentication for Smart Home System

Application of Neural Network in User Authentication for Smart Home System A. Joseph, D.B.L. Bong, D.A.A. Mat Abstract Security has been an important issue and concern in the smart home systems. Smart

### Design and Analysis of Vapour Absorbing Machine

Vol. 3, Issue. 4, Jul - Aug. 2013 pp-2161-2165 ISSN: 2249-6645 Design and Analysis of Vapour Absorbing Machine Prashant Tile 1, S. S.Barve 2 12 Department 100 of Mechanical Engineering, VJTI, Mumbai, India

### SOLIDWORKS SOLIDWORKS Plastics. Dassault Systèmes SolidWorks Corporation 175 Wyman Street Waltham, MA U.S.A.

SOLIDWORKS 2015 SOLIDWORKS Plastics Dassault Systèmes SolidWorks Corporation 175 Wyman Street Waltham, MA 02451 U.S.A. 1995-2014, Dassault Systèmes SolidWorks Corporation, a Dassault Systèmes S.A. company,

### Exhaust pipe FSI simulation to evaluate optimum gasketed joint (flange) design

Exhaust pipe FSI simulation to evaluate optimum gasketed joint (flange) design Prashant Mahiras, Yogesh Jaju Dana India Technical Centre, Pune, India Keywords: Fluid Structure Interaction (FSI), Co-Simulation,

### A Robust Method for Solving Transcendental Equations

www.ijcsi.org 413 A Robust Method for Solving Transcendental Equations Md. Golam Moazzam, Amita Chakraborty and Md. Al-Amin Bhuiyan Department of Computer Science and Engineering, Jahangirnagar University,

### COMPUTATIONAL ENGINEERING OF FINITE ELEMENT MODELLING FOR AUTOMOTIVE APPLICATION USING ABAQUS

International Journal of Advanced Research in Engineering and Technology (IJARET) Volume 7, Issue 2, March-April 2016, pp. 30 52, Article ID: IJARET_07_02_004 Available online at http://www.iaeme.com/ijaret/issues.asp?jtype=ijaret&vtype=7&itype=2

### The Influence of EDM Parameters in Finishing Stage on Material Removal Rate of Hot Work Steel Using Artificial Neural Network

2012, TextRoad Publication SSN 2090-30 Journal of Basic and pplied Scientific Research www.textroad.com The nfluence of EDM Parameters in Finishing Stage on Material Remoal Rate of Hot Work Steel Using

### International Journal of Advanced Research in Computer Science and Software Engineering

Volume 4, Issue 2, February 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com A Novel Approach

### SOLIDWORKS CAD Software Training Catalog COURSES FOCUS ON FUNDAMENTAL SKILLS AND CONCEPTS KEY TO INSURING SUCCESS

SOLIDWORKS CAD Software Training Catalog COURSES FOCUS ON FUNDAMENTAL SKILLS AND CONCEPTS KEY TO INSURING SUCCESS SOLIDWORKS CAD Software Course Index Course Number Course Title Course Length 100 SOLIDWORKS

### Effect of Using Neural Networks in GA-Based School Timetabling

Effect of Using Neural Networks in GA-Based School Timetabling JANIS ZUTERS Department of Computer Science University of Latvia Raina bulv. 19, Riga, LV-1050 LATVIA janis.zuters@lu.lv Abstract: - The school

### Genetic Algorithms and Sudoku

Genetic Algorithms and Sudoku Dr. John M. Weiss Department of Mathematics and Computer Science South Dakota School of Mines and Technology (SDSM&T) Rapid City, SD 57701-3995 john.weiss@sdsmt.edu MICS 2009

### Gas-Assist Injection Molding: An Innovative Medical Technology

COVER STORY >> MOLDING Gas-Assist Injection Molding: An Innovative Medical Technology In certain medical device applications, gas-assist molding can provide solutions that conventional injection molding

### Email: mod_modaber@yahoo.com. 2Azerbaijan Shahid Madani University. This paper is extracted from the M.Sc. Thesis

Introduce an Optimal Pricing Strategy Using the Parameter of "Contingency Analysis" Neplan Software in the Power Market Case Study (Azerbaijan Electricity Network) ABSTRACT Jalil Modabe 1, Navid Taghizadegan

### MASTER DEGREE PROJECT

MASTER DEGREE PROJECT Finite Element Analysis of a Washing Machine Cylinder Thesis in Applied Mechanics one year Master Degree Program Performed : Spring term, 2010 Level Author Supervisor s Examiner :

### Sensitivity Analysis based on Artificial Neural Networks for Evaluating Economical Plans

, July 6-8, 20, London, U.K. Sensitivity Analysis based on Artificial Neural Networks for Evaluating Economical Plans Fraydoon Rahnamy Roodposti, Reza Ehtesham Rasi Abstract the present article offers

### Genetic algorithms for changing environments

Genetic algorithms for changing environments John J. Grefenstette Navy Center for Applied Research in Artificial Intelligence, Naval Research Laboratory, Washington, DC 375, USA gref@aic.nrl.navy.mil Abstract

### Fundamentals of Design for Plastic Injection Molding. Kelly Bramble

Fundamentals of Design for Plastic Injection Molding Kelly Bramble 1 Fundamentals of Design for Plastic Injection Molding Copyright, Engineers Edge, LLC www.engineersedge.com All rights reserved. No part

### D A T A M I N I N G C L A S S I F I C A T I O N

D A T A M I N I N G C L A S S I F I C A T I O N FABRICIO VOZNIKA LEO NARDO VIA NA INTRODUCTION Nowadays there is huge amount of data being collected and stored in databases everywhere across the globe.

### PROCESS OF COOLING INJECTION MOULD AND QUALITY OF INJECTION PARTS

1. LUBOŠ BĚHÁLEK, 2. JOZEF DOBRÁNSKY PROCESS OF COOLING INJECTION MOULD AND QUALITY OF INJECTION PARTS Abstract: Injection mould cooling to an important way influences both technology and economy of production

### Price Prediction of Share Market using Artificial Neural Network (ANN)

Prediction of Share Market using Artificial Neural Network (ANN) Zabir Haider Khan Department of CSE, SUST, Sylhet, Bangladesh Tasnim Sharmin Alin Department of CSE, SUST, Sylhet, Bangladesh Md. Akter

### Automatic Algorithm Design by Neural Network and Indicators in Iran Stock Transactions

Journal of Novel Applied Sciences Available online at www.jnasci.org 2015 JNAS Journal-2015-4-4/501-507 ISSN 2322-5149 2015 JNAS Automatic Algorithm Design by Neural Network and Indicators in Iran Stock

### Autodesk Simulation Moldflow. Plastics made perfect.

Plastics made perfect. Plastic injection molding simulation of a concept consumer printer. Designed in Inventor software. Simulated in software. Rendered in 3ds Max software. Validation and Optimization

### Numerical simulation of the utility glass press-andblow

Numerical simulation of the utility glass press-andblow process Introduction STEKLÝ, J., MATOUŠEK, I. Glass melt press-and-blow process is a typical two stage technology allowing automatized production

### A Guide to Thermoform Processing of Polypropylene. Introduction

A Guide to Thermoform Processing of Polypropylene Introduction Thermoforming is the process of heating plastic sheet to a pliable state and forming it into shape. Thermoforming offers processing advantages

### OPTIMIZATION OF VENTILATION SYSTEMS IN OFFICE ENVIRONMENT, PART II: RESULTS AND DISCUSSIONS

OPTIMIZATION OF VENTILATION SYSTEMS IN OFFICE ENVIRONMENT, PART II: RESULTS AND DISCUSSIONS Liang Zhou, and Fariborz Haghighat Department of Building, Civil and Environmental Engineering Concordia University,

### ISSN: 2319-5967 ISO 9001:2008 Certified International Journal of Engineering Science and Innovative Technology (IJESIT) Volume 2, Issue 3, May 2013

Transistor Level Fault Finding in VLSI Circuits using Genetic Algorithm Lalit A. Patel, Sarman K. Hadia CSPIT, CHARUSAT, Changa., CSPIT, CHARUSAT, Changa Abstract This paper presents, genetic based algorithm

### Fully Coupled Automated Meshing with Adaptive Mesh Refinement Technology: CONVERGE CFD. New Trends in CFD II

Flame Front for a Spark Ignited Engine Using Adaptive Mesh Refinement (AMR) to Resolve Turbulent Flame Thickness New Trends in CFD II Fully Coupled Automated Meshing with Adaptive Mesh Refinement Technology:

### A Systematic Approach to Diagnosing Mold Filling and Part Quality Variations

VOL. 3 NO. 2 A Systematic Approach to Diagnosing Mold Filling and Part Quality Variations www.beaumontinc.com A Systematic Approach to Diagnosing Mold Filling and Part Quality Variations Applying Fundamental

### POLITECNICO DI TORINO. Engineering Faculty Master s Degree in Aerospace Engineering. Final Thesis

POLITECNICO DI TORINO Engineering Faculty Master s Degree in Aerospace Engineering Final Thesis DETECTION AND ANALYSIS OF BARELY VISIBLE IMPACT DAMAGE AND ITS PROGRESSION ON A COMPOSITE OVERWRAPPED PRESSURE

### ECONOMIC GENERATION AND SCHEDULING OF POWER BY GENETIC ALGORITHM

ECONOMIC GENERATION AND SCHEDULING OF POWER BY GENETIC ALGORITHM RAHUL GARG, 2 A.K.SHARMA READER, DEPARTMENT OF ELECTRICAL ENGINEERING, SBCET, JAIPUR (RAJ.) 2 ASSOCIATE PROF, DEPARTMENT OF ELECTRICAL ENGINEERING,

### Flow characteristics of microchannel melts during injection molding of microstructure medical components

Available online www.jocpr.com Journal of Chemical and Pharmaceutical Research, 2014, 6(5):112-117 Research Article ISSN : 0975-7384 CODEN(USA) : JCPRC5 Flow characteristics of microchannel melts during

### PLAANN as a Classification Tool for Customer Intelligence in Banking

PLAANN as a Classification Tool for Customer Intelligence in Banking EUNITE World Competition in domain of Intelligent Technologies The Research Report Ireneusz Czarnowski and Piotr Jedrzejowicz Department

### Online Tuning of Artificial Neural Networks for Induction Motor Control

Online Tuning of Artificial Neural Networks for Induction Motor Control A THESIS Submitted by RAMA KRISHNA MAYIRI (M060156EE) In partial fulfillment of the requirements for the award of the Degree of MASTER

### Leran Wang and Tom Kazmierski {lw04r,tjk}@ecs.soton.ac.uk

BMAS 2005 VHDL-AMS based genetic optimization of a fuzzy logic controller for automotive active suspension systems Leran Wang and Tom Kazmierski {lw04r,tjk}@ecs.soton.ac.uk Outline Introduction and system

### NTC Project: S01-PH10 (formerly I01-P10) 1 Forecasting Women s Apparel Sales Using Mathematical Modeling

1 Forecasting Women s Apparel Sales Using Mathematical Modeling Celia Frank* 1, Balaji Vemulapalli 1, Les M. Sztandera 2, Amar Raheja 3 1 School of Textiles and Materials Technology 2 Computer Information

### ANN Based Fault Classifier and Fault Locator for Double Circuit Transmission Line

International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-4, Special Issue-2, April 2016 E-ISSN: 2347-2693 ANN Based Fault Classifier and Fault Locator for Double Circuit