scholarly journals Transfer Learning Applied to Characteristic Prediction of Injection Molded Products

Polymers ◽  
2021 ◽  
Vol 13 (22) ◽  
pp. 3874
Author(s):  
Yan-Mao Huang ◽  
Wen-Ren Jong ◽  
Shia-Chung Chen
Keyword(s):  
Neural Network ◽  
Injection Molding ◽  
Transfer Learning ◽  
Analysis Data ◽  
Mold Temperature ◽  
Training Data ◽  
Injection Molding Process ◽  
Backpropagation Neural Network ◽  
Molding Process ◽  
Injection Speed

This study addresses some issues regarding the problems of applying CAE to the injection molding production process where quite complex factors inhibit its effective utilization. In this study, an artificial neural network, namely a backpropagation neural network (BPNN), is utilized to render results predictions for the injection molding process. By inputting the plastic temperature, mold temperature, injection speed, holding pressure, and holding time in the molding parameters, these five results are more accurately predicted: EOF pressure, maximum cooling time, warpage along the Z-axis, shrinkage along the X-axis, and shrinkage along the Y-axis. This study first uses CAE analysis data as training data and reduces the error value to less than 5% through the Taguchi method and the random shuffle method, which we introduce herein, and then successfully transfers the network, which CAE data analysis has predicted to the actual machine for verification with the use of transfer learning. This study uses a backpropagation neural network (BPNN) to train a dedicated prediction network using different, large amounts of data for training the network, which has proved fast and can predict results accurately using our optimized model.

scholarly journals A Review on Machine Learning Models in Injection Molding Machines

2022 ◽  
Vol 2022 ◽  
pp. 1-28
Author(s):  
Senthil Kumaran Selvaraj ◽  
Aditya Raj ◽  
R. Rishikesh Mahadevan ◽  
Utkarsh Chadha ◽  
Velmurugan Paramasivam
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Injection Molding ◽  
Performance Criteria ◽  
Machine Learning Techniques ◽  
Injection Molding Process ◽  
Molding Process ◽  
Injection Speed ◽  
Detection Techniques ◽  
And Performance

One of the most suitable methods for the mass production of complicated shapes is injection molding due to its superior production rate and quality. The key to producing higher quality products in injection molding is proper injection speed, pressure, and mold design. Conventional methods relying on the operator’s expertise and defect detection techniques are ineffective in reducing defects. Hence, there is a need for more close control over these operating parameters using various machine learning techniques. Neural networks have considerable applications in the injection molding process consisting of optimization, prediction, identification, classification, controlling, modeling, and monitoring, particularly in manufacturing. In recent research, many critical issues in applying machine learning and neural network in injection molding in practical have been addressed. Some problems include data division, collection, and preprocessing steps, such as considering the inputs, networks, and outputs, algorithms used, models utilized for testing and training, and performance criteria set during validation and verification. This review briefly explains working on machine learning and artificial neural network and optimizing injection molding in industries.

Optimization and Design for Parameter in Injection Molding Technology of Cell Shell of Polypropylene

2011 ◽  
Vol 189-193 ◽  
pp. 537-540
Author(s):  
Jia Min Zhang ◽  
Ming Yi Zhu ◽  
Zhao Xun Lian ◽  
Rong Zhu
Keyword(s):  
Injection Molding ◽  
Injection Pressure ◽  
Mold Temperature ◽  
Injection Molding Process ◽  
Technological Parameters ◽  
Molding Process ◽  
Melt Temperature ◽  
Injection Speed ◽  
Technical Parameters ◽  
High Degree

The use of L27 (35) orthogonal to the battery shell injection molding process is optimized. The main factors of technical parameters were determined mould temperature, melt temperature, the speed of injection, injection pressure, cooling time.On the basis of actual production, to determine the factors values of different process parameters.Combination of scrapped products in key (reduction and a high degree of tolerance deflated) tests were selected in the process parameters within the scope of the assessment. Various factors impact on the product of the total height followed by cooling time, mold temperature, melt temperature, injection pressure, injection speed from strong to weak .The best products technological parameters were determined.Good results were obtained for production.

scholarly journals Effects of Injection Molding Process Parameters on the Chemical Foaming Behavior of Polypropylene and Polystyrene

Polymers ◽  
2021 ◽  
Vol 13 (14) ◽  
pp. 2331
Author(s):  
Chen-Yuan Chung ◽  
Shyh-Shin Hwang ◽  
Shia-Chung Chen ◽  
Ming-Chien Lai
Keyword(s):  
Injection Molding ◽  
Process Parameters ◽  
Mold Temperature ◽  
Expansion Ratio ◽  
Injection Molding Process ◽  
Molding Process ◽  
Melt Temperature ◽  
Foaming Agent ◽  
Experimental Database ◽  
Injection Speed

In the present study, semi-crystalline polypropylene (PP) and amorphous polystyrene (PS) were adopted as matrix materials. After the exothermic foaming agent azodicarbonamide was added, injection molding was implemented to create samples. The mold flow analysis program Moldex3D was then applied to verify the short-shot results. Three process parameters were adopted, namely injection speed, melt temperature, and mold temperature; three levels were set for each factor in the one-factor-at-a-time experimental design. The macroscopic effects of the factors on the weight, specific weight, and expansion ratios of the samples were investigated to determine foaming efficiency, and their microscopic effects on cell density and diameter were examined using a scanning electron microscope. The process parameters for the exothermic foaming agent were optimized accordingly. Finally, the expansion ratios of the two matrix materials in the optimal process parameter settings were compared. After the experimental database was created, the foaming module of the chemical blowing agents was established by Moldex3D Company. The results indicated that semi-crystalline materials foamed less due to their crystallinity. PP exhibits the highest expansion ratio at low injection speed, a high melt temperature, and a low mold temperature, whereas PS exhibits the highest expansion ratio at high injection speed, a moderate melt temperature, and a low mold temperature.

scholarly journals The Study of Optimal Molding of a LED Lens with Grey Relational Analysis and Molding Simulation

2019 ◽  
Vol 63 (4) ◽  
pp. 278-294 ◽  
Author(s):  
Min-Wen Wang ◽  
Fatahul Arifin ◽  
Van-Hanh Vu
Keyword(s):  
Injection Molding ◽  
Mold Temperature ◽  
Injection Molding Process ◽  
Molding Process ◽  
Melt Temperature ◽  
Injection Speed ◽  
Relational Analysis ◽  
Total Displacement ◽  
Packing Pressure ◽  
Grey Relational

Injection molding technology is known as the most widely used method in mass production of plastic products. To meet the quality requirements, a lot of methods were applied in optimization of injection molding process parameter. In this study the optimization based on Taguchi orthogonal array and Grey relational analysis (GRA) is used to optimize the injection molding process parameters on a LED lens. The four process parameters are: packing pressure, injection speed, melt temperature and mold temperature. The multi-response quality characteristics are total displacement, volumetric shrinkage, and thermal residual stress. The optimal molding parameters are packing pressure (90 MPa), injection speed (300 mm/sec), melt temperature (270 °C) and mold temperature (90 °C). The luminous uniformity of the LED is 92.61 % and the viewing angle of the LED is 124.76°. Among the four factors, packing pressure plays the key role in reducing total displacement, volumetric shrinkage, and thermal residual stress.

scholarly journals Towards Optimization of μ-Injection Molding Process for a New V-shaped Geometrical Component Using X-Ray CT-Based Quality Characterization

2019 ◽  
Vol 3 (1) ◽  
pp. 13
Author(s):  
Jitendra Rathore ◽  
Giovanni Lucchetta ◽  
Simone Carmignato
Keyword(s):  
Injection Molding ◽  
Process Parameters ◽  
Functional Performance ◽  
Quality Criteria ◽  
Mold Temperature ◽  
Process Window ◽  
Injection Molding Process ◽  
Molding Process ◽  
Melt Temperature ◽  
Injection Speed

The influence of micro-injection molding process parameters on a molded component’s quality is very prominent. Depending on the functional performance of the part, the desired quality is defined by several criteria which may include dimensional tolerances, shrinkage/warpage, fiber characteristics, and internal defects. A correlation of process parameters with the defined quality attributes needs to be investigated for a new geometrical component. In this work, a micro-component with a new V-shaped geometry is chosen, as this type of geometry finds potential applications in the medical industry. The parts are manufactured with polyoxymethylene resin with a full-factorial design of experimental plan with investigating parameters of mold temperature, melt temperature, injection speed, and packing pressure. The number of internal pores and amount of volumetric shrinkage are identified as the critical quality criteria and the effect of the process parameters is studied with respect to those criteria. The measurement results indicated that the presence of pores is inevitable within the chosen process window; however, the amount can be minimized with careful selection of process settings. Moreover, the statistical analyses demonstrated the significance levels of the process parameters.

scholarly journals Study on External Gas-Assisted Mold Temperature Control with the Assistance of a Flow Focusing Device in the Injection Molding Process

Materials ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 965 ◽  
Author(s):  
Nguyen Truong Giang ◽  
Pham Son Minh ◽  
Tran Anh Son ◽  
Tran Minh The Uyen ◽  
Thanh-Hai Nguyen ◽  
...  
Keyword(s):  
Injection Molding ◽  
Temperature Control ◽  
Mold Temperature ◽  
Injection Molding Process ◽  
Melt Flow ◽  
Flow Focusing ◽  
Molding Process ◽  
Heating Efficiency ◽  
Flow Length ◽  
Insert Plate

In the injection molding field, the flow of plastic material is one of the most important issues, especially regarding the ability of melted plastic to fill the thin walls of products. To improve the melt flow length, a high mold temperature was applied with pre-heating of the cavity surface. In this paper, we present our research on the injection molding process with pre-heating by external gas-assisted mold temperature control. After this, we observed an improvement in the melt flow length into thin-walled products due to the high mold temperature during the filling step. In addition, to develop the heating efficiency, a flow focusing device (FFD) was applied and verified. The simulations and experiments were carried out within an air temperature of 400 °C and heating time of 20 s to investigate a flow focusing device to assist with external gas-assisted mold temperature control (Ex-GMTC), with the application of various FFD types for the temperature distribution of the insert plate. The heating process was applied for a simple insert model with dimensions of 50 mm × 50 mm × 2 mm, in order to verify the influence of the FFD geometry on the heating result. After that, Ex-GMTC with the assistance of FFD was carried out for a mold-reading process, and the FFD influence was estimated by the mold heating result and the improvement of the melt flow length using acrylonitrile butadiene styrene (ABS). The results show that the air sprue gap (h) significantly affects the temperature of the insert and an air sprue gap of 3 mm gives the best heating rate, with the highest temperature being 321.2 °C. Likewise, the actual results show that the height of the flow focusing device (V) also influences the temperature of the insert plate and that a 5 mm high FFD gives the best results with a maximum temperature of 332.3 °C. Moreover, the heating efficiency when using FFD is always higher than without FFD. After examining the effect of FFD, its application was considered, in order to improve the melt flow length in injection molding, which increased from 38.6 to 170 mm, while the balance of the melt filling was also clearly improved.

scholarly journals Induced network-based transfer learning in injection molding for process modelling and optimization with artificial neural networks

2021 ◽  
Vol 112 (11-12) ◽  
pp. 3501-3513
Author(s):  
Yannik Lockner ◽  
Christian Hopmann
Keyword(s):  
Injection Molding ◽  
Transfer Learning ◽  
Injection Molding Process ◽  
Process Data ◽  
Molding Process ◽  
Melt Temperature ◽  
Processing Industry ◽  
Source Models ◽  
Plastics Processing ◽  
Artificial Neural

AbstractThe necessity of an abundance of training data commonly hinders the broad use of machine learning in the plastics processing industry. Induced network-based transfer learning is used to reduce the necessary amount of injection molding process data for the training of an artificial neural network in order to conduct a data-driven machine parameter optimization for injection molding processes. As base learners, source models for the injection molding process of 59 different parts are fitted to process data. A different process for another part is chosen as the target process on which transfer learning is applied. The models learn the relationship between 6 machine setting parameters and the part weight as quality parameter. The considered machine parameters are the injection flow rate, holding pressure time, holding pressure, cooling time, melt temperature, and cavity wall temperature. For the right source domain, only 4 sample points of the new process need to be generated to train a model of the injection molding process with a degree of determination R2 of 0.9 or and higher. Significant differences in the transferability of the source models can be seen between different part geometries: The source models of injection molding processes for similar parts to the part of the target process achieve the best results. The transfer learning technique has the potential to raise the relevance of AI methods for process optimization in the plastics processing industry significantly.

scholarly journals Prediction of the maximum flow length of a thin injection molded part

2020 ◽  
Vol 40 (9) ◽  
pp. 783-795
Author(s):  
Sara Liparoti ◽  
Vito Speranza ◽  
Annarita De Meo ◽  
Felice De Santis ◽  
Roberto Pantani
Keyword(s):  
Injection Molding ◽  
Maximum Flow ◽  
Mold Temperature ◽  
Complete Characterization ◽  
Rheological Parameters ◽  
Injection Molding Process ◽  
Spiral Flow ◽  
Molding Process ◽  
Molded Part ◽  
Flow Length

AbstractOne of the most significant issues, when thin parts have to be obtained by injection molding (i.e. in micro-injection molding), is the determination of the conditions of pressure, mold temperature, and injection temperature to adopt to completely fill the cavity. Obviously, modern computational methods allow the simulation of the injection molding process for any material and any cavity geometry. However, this simulation requires a complete characterization of the material for what concerns the rheological and thermal parameters, and also a suitable criterion for solidification. These parameters are not always easily reachable. A simple test aimed at obtaining the required parameters is then highly advantageous. The so-called spiral flow test, consisting of measuring the length reached by a polymer in a long cavity under different molding conditions, is a method of this kind. In this work, with reference to an isotactic polypropylene, some spiral flow tests obtained with different mold temperatures and injection pressures are analyzed with a twofold goal: on one side, to obtain from a few simple tests the basic rheological parameters of the material; on the other side, to suggest a method for a quick prediction of the final flow length.

Sign in / Sign up

Export Citation Format

Share Document