Plastic Injection Moulding Process Research Articles

An integrated parameter optimization system for MIMO plastic injection molding using soft computing

This study proposes an integrated optimization system to find out the optimal parameter settings of multi-input multi-output (MIMO) plastic injection molding (PIM) process. The system is divided into two stages. In the first stage, the Taguchi method and analysis of variance (ANOVA) are employed to perform the experimental work, calculate the signal-to-noise (S/N) ratio, and determine the initial process parameters. The back-propagation neural network (BPNN) is employed to construct an S/N ratio predictor and a quality predictor. The S/N ratio predictor and genetic algorithms (GA) are integrated to search for the first optimal parameter combination. The purpose of this stage is to reduce the process variance. In the second stage, the quality predictor is combined with particle swarm optimization (PSO) to find the final optimal parameters. The quality characteristics, product length and warpage, are dedicated to finding the optimal process parameters. After the numerical analysis, the optimal parameters can meet the lowest variance and the product quality requirements simultaneously. Experimental results show that the proposed optimization system can not only satisfy the quality specification but also improve stability of the PIM process.

A process capability index for mixed binary-normal quality characteristics

While most of the methods developed for computing process capability indices (PCI) concentrate on cases with normally or continuous non-normally distributed quality characteristics, computing this measure for processes with mixed distributed data has not been investigated so far. In this paper, a new method is proposed for computing (PCI) for mixed binary-normal quality characteristics. In the proposed method, first a mixed binary-normal distribution is considered to be fitted on the available data. Having estimated the unknown parameters of the fitted distribution using maximum likelihood estimation and genetic algorithm, the proportion of the conforming items of the corresponding distribution is estimated by Monte Carlo simulation runs. Finally, the PCI is computed based on the relationship of PCI and proportion of conforming items. The performance of the proposed method is evaluated using simulation studies as well as a case study in a plastic injection moulding process.

Improvement of Injection Moulding Processes by Using Dual Energy Signatures

Minimising waste is the credo of all lean production systems. Process steps are therefore divided into value-adding and non value-adding ones. The best practice tool for this purpose is the value stream mapping method (VSM). It reveals waste in inventory and lead times. However, if it comes to improve value streams in terms of energy efficiency, then the manufacturing process itself has to be looked at dual, with regard to value-adding and non value-adding elements. This paper presents two methods of dualising the time and energy consumption in the plastic injection moulding process. Potentials for improving the process, from the viewpoints of energy and time, are highlighted. Based on the dual process analysis, improvement concepts are brought forward. The VSM can thus, while maintaining its inner logic, be extended to an energy value stream mapping method (EVSM).

Optimization of plastic injection molding process parameters for manufacturing a brake booster valve body

The plastic injection molding (PIM) process parameters have been investigated for manufacturing a brake booster valve body. The optimal PIM process parameters is determined with the application of computer-aided engineering integrating with the Taguchi method to improve the compressive property of the valve body. The parameters considered for optimization are the following: number of gates, gate size, molding temperature, resin temperature, switch over by volume filled, switch over by injection pressure, and curing time. An orthogonal array of L18 is created for the statistical design of experiments based on the Taguchi method. Then, Mold-Flow analyses are performed by using the designed process parameters based on the L18 orthogonal array. The signal-to-noise (S/N) ratio and the analysis of variance (ANOVA) are used to find the optimal PIM process parameters and to figure out the impact of the viscosity of resin, curing percentage, and compressive strength on a brake booster valve body. When compared with the average compression strength out of the 18 design experiments, the compression strength of the valve body produced using the optimal PIM process parameters showed a nearly 12% improvement.

Evaluation of Effect of Plastic Injection Molding Process Parameters on Shrinkage Based on Neural Network Simulation

The effects of process parameters, mold temperature (T mo), melt temperature (T me), cooling time (tc ), fill pressure (Pf ), packing pressure (Pp ), and packing time (tp ) on the shrinkage of injection molded polypropylene were investigated by utilizing a combination of the Artificial Neural Network (ANN) method and Moldflow software. An ANN model is developed to understand the relationship between plastic injection molding process parameters and shrinkage. The test results on the performance of the ANN model show that it can predict the shrinkage with reasonable accuracy. The simulation results show that the most important process parameter affecting shrinkage is Pp , followed by T me and T mo, with tc , Pf , and tp having the least effect. Shrinkage increases with the elevated T mo and tc . In contrast, the increases in Pp , Tme , tp , and Pf cause shrinkage to decrease. The strongest effect on the shrinkage is the amount of material forced into the mold, followed by the crystallinity and orientation of the material.

Prediction and Optimization of Dimensional Shrinkage Variations in Injection Molded Parts Using Forward and Reverse Mapping of Artificial Neural Networks

The most significant process parameters affecting dimensional shrinkage in transverse and longitudinal directions of molded parts in Plastic Injection Molding (PIM) process are injection velocity, mold temperature, melt temperature and packing pressure. In the present work, ANN model was developed for forward and reverse mapping prediction. In forward mapping PIM process parameters are expressed as the input parameters to predict dimensional shrinkage, whereas in reverse mapping, attempts were made to predict an appropriate set of process parameters required for arriving at the required dimensional shrinkage. The trained network with one thousand input-output data randomly generated from regression equations reported by earlier researchers resulted in minimum mean squared error. The performance of developed model was compared with experimental values for ten different test cases. The results show that ANN model with both forward and reverse mapping is capable of prediction with an error level of less than ten percent.

A Two-Stage Optimization System for the Plastic Injection Molding with Multiple Performance Characteristics

This study proposes a two-stage optimization system to generate the optimal process parameter settings of multi-quality characteristics in the plastic injection molding (PIM) products. In the first stage, Taguchi orthogonal array was employ to arrange the experimental work and to calculate the S/N ratio to determine the initial process parameter settings. Then, S/N ratio predictor and S/N quality predictor was constructed by employed the back-propagation neural network (BPNN). In addition, S/N ratio predictor was along with simulated annealing (SA) used to search for the first optimal parameter combination in order to reduce the PIM process variance. In the second stage, BPNN quality predictor and particle swarm optimization (PSO) was intended to find the optimal parameter settings for the best quality specification. Results from the experimental work show that the proposed two-stage optimization system can create the best process parameter settings which not only meet the quality specification, but also effectively reduce cost.

Optimization of Process Parameters using DOE, RSM, and GA in Plastic Injection Molding

In the past, plastic injection molding (PIM) product quality was usually measured by one single quality characteristic or by multiple quality characteristic with independent parameters one another. In this study, optimization of process parameters using design of experiment (DOE), response surface methodology (RSM), and genetic algorithm (GA) were proposed to generate the optimal process parameters settings of multiple-quality characteristics. In the first stage, significant PIM process parameters can be determined by DOE screening experiments. Then the optimal process parameter settings are obtained via computer aided engineering (CAE) simulation integrated with RSM and GA, which are taken as practically initial settings of process-related parameters. The experimental results show that the propose optimization model is very successful and can be used in industrial applications.

Optimization of Shrinkage in Plastic Injection Molding Process Using Statistical Methods and SA Algorithm

— Dimensional changes because of shrinkage is one of the most important problems in production of plastic part using injection molding. In this study, effect of injection molding parameters on the shrinkage in polypropylene (PP) and polystyrene (PS) has been investigated. The relationship between input and output of the process is investigated using regression analysis and ANOVA method. To do this, existing data is used. The selected input parameters are melting temperature, injection pressure, packing pressure and packing time. Effect of these parameters on the shrinkage of above mentioned materials is studied using mathematical modeling. For modeling the process, different types of regression equations including linear polynomial, Quadratic polynomial and logarithmic function, are used to interpolate experiment data. Next, using step backward elimination and 95% confidence level, insignificant parameters are eliminated from model. To check validity of the PP model, correlation coefficient of each model is calculated and the best model is selected. The same procedure is repeated for the PS model. Finally, optimum levels of the input parameters that minimize shrinkage, for both materials are determined. Simulated Annealing (SA) algorithm is applied on the developed mathematical models. The optimization results show that the proposed models and algorithm are effective in solving the mentioned problems.

Modeling of multi-connected porous passageway for mould cooling

Cooling channel design in the plastic injection moulding process is of paramount importance to the performance of the mould, influencing the quality of the parts being produced and productivity of the process. However, cooling channel design is usually limited to relatively simple configurations as well as conventional machining processes, such as straight-line drilling, and milling, etc. The cooling performance may not meet the expectations of the mould engineers. This paper proposes an alternative design method for a conformal cooling passageway with multi-connected porous characteristics based on the duality principle. The proposed method can provide a more uniform cooling performance between the mould plate and the conformal cooling passageway than the existing conformal cooling channel design. Injection mould defects like warpage or hot spots can be avoided. In this study, a 3D mould plate model was offset negatively and the location of the proposed multi-connected porous cooling passageway was identified. The negatively offset model was decomposed into a finite number of cubical cells via the sub-boundary spatial enumerated cell decomposition. Then a duality relationship between the primal and the dual graphs was developed. This provided the preliminary layout of the multi-connected porous passageway for the coolant flow in multiple directions. The cooling channel axis design of the multi-connected porous passageway, illustrated by the skeleton from the dual graph, was created. Following a Boolean difference operation, the proposed multi-connected porous cooling passageway inside the mould plate was able to be generated and fabricated with the aid of rapid tooling technologies. A real-life case study for the design of a multi-connected porous cooling passageway was implemented and examined. The effects of coolant flow and cooling performances, analyzed by computational fluid dynamics simulation, were validated.

Visibility-based conformal cooling channel generation for rapid tooling

In plastic injection moulding process, cooling channel design is an essential factor that affects the quality of the moulded parts and the productivity of the process. Non-uniform cooling or long cooling cycle time would result if a poorly designed cooling channel is adopted. Due to limitations of traditional machining processes, the cooling channel is usually formed from straight-line drilled holes and only simple shapes are allowed, regardless of the shape complexity of the part being moulded. With the advent of rapid tooling technology, cooling channels in complex shapes can now be possible. However, there are not many design methodologies for supporting this type of cooling channel. In this paper, a methodology called visibility-based cooling channel generation is proposed for automatic preliminary cooling channel design for rapid tooling. The cooling process between a mould surface and a cooling channel is considered analogous to whether they can be visible from each other. Without loss of generality, the mould surface is approximated by a polyhedral terrain and is normally offset. A number of point light sources together that can illuminate the whole polyhedral terrain are assigned to suitable terrain offset vertices. A cooling channel is then generated by connecting all the assigned light sources. When comparing the conventional verification and redesign methods by melt flow analysis, computer-aided design and, a better design of cooling channel for its mould surface results in a short time independent of the experience of mould engineer.

Optimization of Plastic Injection Molding Process Parameters for Thin-Wall Plastics Injection Molding

The effects of the process parameters on the warpge and shrinkage of parts in different thickness are analyzed by Taguchi optimization method. Taguchi optimization method was used for exploiting mold analysis based on three level factorial designs. Orthogonal arrays of Taguchi, the signal-to-noise (S/N) ratio, the analysis of variance (ANOVA) are utilized to find the optimal levels and the effect of process parameters on warpage. It can be concluded that Taguchi method is suitable to solve the quality problem of the injection-molded thermoplastic parts.

Support Vector Machines for Quality Monitoring in a Plastic Injection Molding Process

Support vector machines (SVMs) are receiving increased attention in different application domains for which neural networks (NNs) have had a prominent role. However, in quality monitoring little attention has been given to this more recent development encompassing a technique with foundations in statistic learning theory. In this paper, we compare C-SVM and /spl nu/-SVM classifiers with radial basis function (RBF) NNs in data sets corresponding to product faults in an industrial environment concerning a plastics injection molding machine. The goal is to monitor in-process data as a means of indicating product quality and to be able to respond quickly to unexpected process disturbances. Our approach based on SVMs exploits the first part of this goal. Model selection which amounts to search in hyperparameter space is performed for study of suitable condition monitoring. In the multiclass problem formulation presented, classification accuracy is reported for both strategies. Experimental results obtained thus far indicate improved generalization with the large margin classifier as well as better performance enhancing the strength and efficacy of the chosen model for the practical case study.

Optimisation of Plastic Injection Moulding Process with Soft Computing

The paper presents a hybrid strategy in a soft computing paradigm for the optimisation of the plastic injection moulding process. Various plastic injection molding process parameters, such as mold temperature, melt temperature, injection time and injection pressure are considered. The hybrid strategy combines numerical simulation software, a genetic algorithm and a multilayer neural network to optimise the process parameters. An approximate analysis model is developed using a Back-propagation neural network in order to avoid the expensive computation resulting from the numerical simulation software. According to the characteristic of the optimisation problem, a nonbinary genetic algorithm is applied to solve the optimisation model. The effectiveness of the improved strategy is shown by an example.

A knowledge-based engineering approach for cycle time estimation for plastic injection moulding process

The objective of this research is to develop an intelligent knowledge-based tool for the plastic industry. This research is divided into four phases: to collect all the required data for analysis with respect to functional, structural and manufacturing modules; to develop universal rules that control the plastic injection moulding process, based on the collected data, journals, books, manuals and personal interviews with targeted elements of the plastic industry; to represent the rules in a logical fashion, using knowledge-based programming techniques; and to develop a user-friendly interface that facilitates effective communication between the user and the software.

A multiple-criteria environmental impact assessment for the plastic injection molding process: a methodology

This paper proposes a multiple-criteria methodology for evaluating environmental impacts in the plastic injection molding process (PIMP) and incorporates the findings of an empirical study conducted in Hong Kong. The paper identifies and explains various indicators of environmental impact assessment and establishes a multiple-criteria rating matrix. It then elaborates on the implementation of a pilot program and discusses the relevance of the methodology inside and outside of the work environment. Results show that the methodology provides manufacturers with a feasible means to assess their environmental performance and perform benchmarking analysis. The methodology can also be modified and applied in different industry sectors.

Genetic Algorithm Application to a Scheduling Problem in the Plastic Injection Molding Process

Genetic Algorithm is applied to a scheduling problem in the plastic injection molding process. The problem is simplified by combinig the jobs with the same die. Total lateness to the due date is taken as an evaluation function and rather sufficient solution is obtained by GA. Moreover, a modified decoding procedure is proposed to optimize the second objective, without decreasing the original evaluation value. Simulation with real data in an industry shows an effectiveness of the proposed method.

Case Studies for Teaching Control Systems

Case studies can be used as an aid in teaching control systems to undergraduate students. A number of case studies, of differing styles, are described. Wherever possible the case studies make use of readily available software packages as analysis and design tools. A major case study considers the plastic injection moulding process, as one which involves many aspects of systems and control engineering viz. system dynamics, sequence control, man-machine systems and plant monitoring. It has been necessary to critically review the content of the control systems curriculum in the light of industrially relevant case study material.