Online Prediction of Molded Part Quality in the Injection Molding Process Using High-Resolution Time Series

Optimization and parameter adjustment of an injection molding (IM) process depend largely on a good modelling and prediction of industrial process, which has been received considerable attention in recent years. However, IM process is a typical multivariate production process with multiple product quality indices. It poses a great challenge for multi-output quality prediction problem to select key process variables as input with good interpretability. This study proposes a multivariate quality prediction method for IM process using copula entropy (CE) and multi-output support vector regression (MSVR). First, copula entropy is employed to characterize the association relationships between each process variable and the set of quality indices, thus key process variables can be selected by ranking CE. Then, the quantitative relationship between key process variables and quality indices is established by MSVR. Finally, the proposed method is tested by the experiment on a real IM process dataset. This study will provide an important reference for modelling and prediction of IM process and other multi-output problems.

Today, around 30% of manufactured plastic goods rely on injection moulding. The cooling time can represent more than 70% of the injection cycle. In this process, heat transfer during the cooling step has a great influence both on the quality of the final parts that are produced, and on the moulding cycle time. Models based on a full 3D finite element method renders unpractical the use of optimization of the design and placement of the cooling channel in injection moulds. We have extended the use of boundary element method (BEM) to this process. We introduce in this paper a practical methodology to optimize both the position and the shape of the cooling channels in injection moulding processes. We couple the direct computation with an optimization algorithm such as SQP (Sequential Quadratic Programming). First, we propose an implementation of the model reduction in the BEM solver. This technique permits to reduce considerably the computing time during the linear system resolution (unsteady case). Secondly, we couple it with an optimization algorithm to evaluate its potentiality. For example, we can minimize the maximal temperature on the cavity surface subject to a temperature uniformity constraint. Thirdly, we present encouraging computational results on plastic parts that show that our optimization methodology is viable.

Improvements in part quality and cost reduction are the primary objectives of CAE use in the injection molding industry. Engineers use advanced injection molding simulation software to analyze and verify their part designs. Traditionally, engineers have had to rerun simulations to verify the effects of changes in gate locations. For complex models, simulations are very time consuming. To reduce the design cycle time, a Design Optimization Module is developed by C-MOLD. One of the functions of this new software module is to automatically select optimal gate locations. This innovative technology is the result of close R&D collaboration between C-MOLD and LG-PRC in Korea. An overview of gate location optimization technology is presented in this paper, and several examples are also presented as illustration.

For many years, injection molding is adopted as the most suitable manufacturing process in the production of complex plastic components. It is very difficult to boost the product's quality stability to attain a higher forming speed and higher automation in the injection moulding process because the process often disrupted by numerous inevitable deviations. The settings for different process parameters and machine parameters have quite a major influence on the overall product quality and its performance of the injection moulding process, which shows the final product quality as output responses. Identifying the perfect process parameter settings so that numerous responses may be optimized at almost the same time is becoming a significant research challenge these days. Smart manufacturing is at the heart of the new industrial revolution, and it will continue to be the primary means of transforming and upgrading the manufacturing industry in the upcoming decades. Melt temperature, the temperature of mould, injection pressure, and velocity of molten polymer while injection, injection time, pressure of molten polymer while holding into the mold cavity, holding time of molten polymer, and cooling time are the variety of input process parameters.  While mechanical characteristics, flaws such as warpage, volumetric or dimensional shrinkage, sink mark on outer surface, residual stress, and surface finish/roughness are examples of responses. To study and optimize the molding process, researchers have used a wide range of methods. Mathematical modeling, simulation, design of experiments, Taguchi methodology, analysis of variance - ANOVA, response surface methodology - RSM, evolutionary algorithm (EA), artificial neural networks - ANN, genetic algorithms - GA, fuzzy logic, particle swarm optimization - PSO, are examples of these techniques. This paper presents a review of the numerous strategies that used till date for optimizing the key injection moulding parameters, as well as their benefits and challenges. In the review, it is discovered that a perfect injection molding process, which takes care of overall quality control is still being researched upon. The process parameters involved in injection molding, required response, and the methodologies used for optimization of overall injection molding process are discussed throughout this paper.

The effect of EVI time series density on crop classification accuracy

Data-based process monitoring in injection molding plays an important role in compensating disturbances in the process and the associated impairment of part quality. Selecting appropriate features for a successful online quality prediction based on machine learning methods is crucial. Time series such as the injection pressure and injection flow curve are particularly suitable for this purpose. Predicting quality as early as possible during a cycle has many advantages. In this paper it is shown how the recording length of the time series affects the prediction performance when using machine learning algorithms. For this purpose, two successful molding quality prediction algorithms (k Nearest Neighbors and Ridge Regression) are trained with time series of different lengths on extensive data sets. Their prediction performances for part weight and a geometric dimension are evaluated. The evaluations show that recording time series until the end of a cycle is not necessary to obtain good prediction results. These findings indicate that early reliable quality prediction is possible within a cycle, which speeds up prediction, allows timely part handling at the end of the cycle and provides the basis for automated corrective interventions within the same cycle.

Existing clustering algorithms are weak in extracting peak intervals for clustering time series data. In this paper, we propose a new clustering algorithm named Peak Interval Extraction Strategy based Hierarchical Clustering method (PIES_HC) for clustering time series data. The proposed PIES_HC algorithm can effectively exploit inherent peak interval information of a time series data set to enhance clustering performance. The main contributions of our work include the design of a strategy to extract peak intervals of time series data and the development of a new similarity measure method based on peak intervals. With a synthetic data set and three real-life data sets, our experimental results confirm that the proposed PIES_HC algorithm outperforms time series clustering algorithms based on Euclidean Distance and Dynamic Time Warping in terms of Accuracy.

The simulation solutions of different plastic injection molding processes are as multifaceted as the field of injection molding itself. In this study, the simulation of a special injection molding process, which generates partially foamed integral components, was parameterized and performed. This partial and physical foaming is realized by a defined volume expansion of the mold cavity. Using the injection molding simulation software Moldex 3D, this so-called Pull and Foam process was digitally reconstructed and simulated. Since the Pull and Foam process is a special injection molding technique for producing foamed components, the validity of the simulation results was analyzed and evaluated. With the use of Moldex 3D, varied settings such as different bubble growth models and mesh topologies were set, parameterized, and then analyzed, to provide differentiated numerical calculation solutions. Actual manufactured components represent the experimental part of this study and are produced for reference. Different evaluation methods were used to quantify morphological quantities such as porosities, local densities, and cell distributions. These methods are based on two-dimensional and three-dimensional imaging techniques such as optical microscopy and X-ray microtomography (µ-CT). Thus, this structural characterization of the manufactured samples serves as the validation basis for the calculated results of the simulations. According to the illustrated results, the adequate selection of bubble growth models and especially mesh topologies must be considered for valid simulation of specific core-back techniques, such as the Pull and Foam injection molding process.

In injection moulding processes, the measurement of the temperature distribution is very important for the validation of models used for simulative part design due to the high influence on shrinkage and warpage of the moulded part, but is also very challenging to measure. During the injection moulding process high mould pressures occur and the cavity is not easily accessible. Therefore, contact sensors cannot be used since they induce shear stress into the melt, which changes the flow behaviour of the melt and thus the temperature field. In this work, we present a method for the contactless determination of the temperature distribution of a moulded part during injection moulding using ultrasound tomography. With time-of-flight ultrasound measurements from different directions it is possible to reconstruct the distribution of ultrasound velocity in the cross-section of a moulded part. With this distribution, the temperature field can be calculated using additional material characteristic properties. Based on this concept, an injection mould was designed, that allows performing ultrasound tomography with 20 ultrasound transducers radially arranged around a cylindrical shaped cavity. This allows the temperature determination under real process conditions with a spatial resolution of 3.5 mm2. A highly parallelised measurement device allows recording of several complete datasets before no more signals can be detected due to shrinkage of the moulded part. During several injections moulding-cycles all sensor positions were able to detect noticeable signals. Due to internal signal processing of the measurement device, it is not yet possible to calculate arrival times of the ultrasound signal but amplitude-scans show the general feasibility of ultrasound tomography during injection moulding..

Injection moulding is one of the most important manufacturing processes for mass production of complex plastic parts. The quality of injection moulded parts depends not only on the material, shape, and function of the part design, but also on how the material is processed during moulding. Traditional design approaches based on intuition, prior experience, and trial-and-error methodology have been becoming less efficient and effective. With advances in numerical modelling and computer simulation techniques, there have been tremendous efforts made to develop computer simulation tools to facilitate injection moulding design and process set-up. This paper reviews the history of research and development in the filling simulation of injection moulding. The existing models are classified into three categories: one-dimensional models, 2.5D models, and three-dimensional models. The basic features and relative key techniques about these models have been discussed. The techniques of tacking the moving flow front have also been presented. It is then followed by conclusions and discussions of these mentioned models.

The aim of this study is to improve the quality of micro-structured parts manufactured by Micro Sacrificial Plastic Mold Inserted Metal Powder Injection Molding (μ-SPiMIM) process using LIGA. The defects in plastic injection molding such as weld-line and short filling, which developed around micro pillar structures of plastic molds, were evaluated with a laser microscope observation. The effects of molding conditions on the quality in micro injection molding of micro plastic parts were discussed. The effects of molding conditions in metal powder injection molding were also investigated.

Todays, there are various of optimisation methods that have been studied by many researchers in order to find the appropriate combination of processing parameters setting in the injection moulding process. From the previous literatures, the optimisation works have been proven will improve the moulded part quality. In this study, the application of optimisation work to improve warpage of front panel housing has been explored. By selecting cooling time, coolant temperature, packing pressure and melt temperature as the variable parameters, design of experiment (DOE) have been constructed by using the rotatable central composite design (CCD) approach. Response Surface Methodology (RSM) was performed in order to define the optimal processing parameters setting which will optimise the warpage condition. Based on the results, melt temperature is the most significant factor contribute to the warpage condition and warpage have optimised by 47.1% after optimisation. The findings show that the application of optimisation work offers the best quality of moulded part produced.

When hybrid moulds are used for the production of injection moulds, mostly the mould designer and/or plastic processor ignore the implementation of multiple mould materials and its effect on the polymer processing and material characteristics. This effect of mould material selection for injection moulds is underestimated. When one selects a mould material with poor or good thermal behaviour, it results in slower or faster cooling down of the polymer with positive or negative influence on the rheology of the injected polymer. To analyse the effect of mould material on the rheology of polymers, a hybrid micro injection mould of a spiral flow part was designed in which the flow length has been analysed for several injection moulding parameters and mould materials. Both mould and polymer analyses resulted in a better understanding of the rheology during the injection moulding process of hybrid moulds. It also resulted in a better understanding of the needed mould design strategy for multiple material moulds related to rheology, specially for micro injection moulding. Conventionally, micro moulds use techniques such as inductive heating to optimise the rheology. The research has proven that appropriate mould material selection can eliminate the need of mould heating during the injection process.

Slope deformation prediction is crucial for early warning of slope failure, which can prevent property damage and save human life. Existing predictive models focus on predicting the displacement of a single monitoring point based on time series data, without considering spatial correlations among monitoring points, which makes it difficult to reveal the displacement changes in the entire monitoring system and ignores the potential threats from nonselected points. To address the above problem, this paper presents a novel deep learning method for predicting the slope deformation, by considering the spatial correlations between all points in the entire displacement monitoring system. The essential idea behind the proposed method is to predict the slope deformation based on the global information (i.e., the correlated displacements of all points in the entire monitoring system), rather than based on the local information (i.e., the displacements of a specified single point in the monitoring system). In the proposed method, (1) a weighted adjacency matrix is built to interpret the spatial correlations between all points, (2) a feature matrix is assembled to store the time-series displacements of all points, and (3) one of the state-of-the-art deep learning models, i.e., T-GCN, is developed to process the above graph-structured data consisting of two matrices. The effectiveness of the proposed method is verified by performing predictions based on a real dataset. The proposed method can be applied to predict time-dependency information in other similar geohazard scenarios, based on time-series data collected from multiple monitoring points.

The application of Taguchi method to reduce warpage in an injection moulding process is studied. The objective of this paper is to analyze the effect of injection moulding parameters, i.e., injection time, packing time, melt temperature and mould temperature, on the warpage defect in dumbbell plastics part. Optical comparator horizontal type was used to measure the difference of warpage value on each part. L9 orthogonal array with 3 replications was done with 27 totals of specimens. The result collected was optimized using Taguchi method and percentage of contribution was calculated using analysis of variance (ANOVA). According to the analysis, it is found that the significant factors affected warpage are injection time (32.01%), packing time (29.73%), mould temperature (24.39%) and melt temperature (13.87%). The optimum parameters for minimizing the warpage were injection time (1s), packing time (5s), melt temperature (270 °C) and the mould temperature (21 °C). By using Taguchi method and ANOVA analysis, optimum parameters and the percentage of contribution of parameters can be obtained. Thus, it shows that design of experiment method is the good quality tools to get the best quality for production.