A Study on Condition Monitoring and Diagnosis of Injection Molding Process Using Probabilistic Neural Network Method

2014 ◽  
Author(s):  
Dae Seong Baek ◽  
Chengjun Li ◽  
Jung Soo Nam ◽  
Cho Rok Na ◽  
Myungho Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Injection Molding ◽  
Injection Molding Process ◽  
Cavity Pressure ◽  
Molding Process ◽  
Nozzle Pressure ◽  
Screw Position ◽  
Diagnosis Model ◽  
Condition Diagnosis ◽  
Pressure Nozzle

The objective of this research is the development of condition diagnosis model for injection molding process based on wavelet packet decomposition (WPD), feature extraction from cavity pressure, nozzle pressure and screw position signals and probability neural network (PNN) method. The node energies from the WPD of cavity and nozzle pressure signals are identified. In addition, five (5), seven (7) and two (2) critical features are extracted from the cavity pressure, nozzle pressure and screw position signals via the new feature extraction algorithm. The node energies and critical features are input to the PNN based condition diagnosis model for the injection modeling process. A series of injection modeling experiments are conducted and their results are used to validate the model. It is demonstrated that the proposed model is applicable to diagnose the injection molding process conditions. In particular, it is also shown that the utilization of cavity pressure and screw position signals in the model can result in higher diagnosis accuracy from the case studies.

In-Mold Monitoring of Temperature and Cavity Pressure During the Injection Molding Process

2014 ◽  
Author(s):  
Catalin Fetecau ◽  
Felicia Stan ◽  
Laurentiu I. Sandu
Keyword(s):  
Injection Molding ◽  
Pressure Sensors ◽  
Temperature Sensors ◽  
Injection Molding Process ◽  
Cavity Pressure ◽  
Molding Process ◽  
Shear Rates ◽  
Wide Range ◽  
Simulation Results ◽  
Two Temperature

This paper focuses on the in-mold monitoring of temperature and cavity pressure. The melt contact temperature and the cavity pressure along the flow path were directly measured using two pressure sensors and two temperature sensors fitted into the cavity of a spiral mold. Three melt temperatures and dies of different heights (1.0, 1.5 and 2 mm) were used to achieve a wide range of practically relevant shear rates. In order to analyze the extent to which the numerical simulation can predict the behavior of the molten polymer during the injection molding process, molding experiments were simulated using the Moldflow software and the simulation results were compared with the experimental data under the same injection molding conditions.

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.

scholarly journals Study of an Online Monitoring Adaptive System for an Injection Molding Process Based on a Nozzle Pressure Curve

Polymers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 555
Author(s):  
Jia-Chen Fan-Jiang ◽  
Chi-Wei Su ◽  
Guan-Yan Liou ◽  
Sheng-Jye Hwang ◽  
Huei-Huang Lee ◽  
...  
Keyword(s):  
Control System ◽  
Injection Molding ◽  
Peak Pressure ◽  
Viscosity Index ◽  
Injection Molding Process ◽  
Pressure Curve ◽  
Molding Process ◽  
Injection Speed ◽  
Nozzle Pressure ◽  
Product Weight

Injection molding is a popular process for the mass production of polymer products, but due to the characteristics of the injection process, there are many factors that will affect the product quality during the long fabrication processes. In this study, an adaptive adjustment system was developed by C++ programming to adjust the V/P switchover point and injection speed during the injection molding process in order to minimize the variation of the product weight. Based on a series of preliminary experiments, it was found that the viscosity index and peak pressure had a strong correlation with the weight of the injection-molded parts. Therefore, the viscosity index and peak pressure are used to guide the adjustment in the presented control system, and only one nozzle pressure sensor is used in the system. The results of the preliminary experiments indicate that the reduction of the packing time and setting enough clamping force can decrease the variation of the injected weight without turning on the adaptive control system; meanwhile, the master pressure curve obtained from the preliminary experiment was used as the control target of the system. With this system, the variation of the product weight and coefficient of variation (CV) of the product weight can be decreased to 0.21 and 0.05%, respectively.

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.

Sign in / Sign up

Export Citation Format

Share Document