In-Mold Sensors for Injection Molding: On the Way to Industry 4.0

Ageyeva, Tatyana; Horvath, Szabolcs; Kovács, József

doi:10.3390/s19163551

Cited by 81 publications

(44 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although there is a partial convergence of signals generated in the processing machine and the injection mold, the data obtained from the forming cavity are more informative and may be of greater importance [45]. Placing the sensors system for monitoring conditions in a real mold cavity gives the possibility of complete verification of analyses using the finite elements method (FEM) tools for assumed processing conditions [46].…”

Section: Entry In the Literature Listmentioning

confidence: 99%

The Microcellular Structure of Injection Molded Thick-Walled Parts as Observed by In-Line Monitoring

2020

View full text Add to dashboard Cite

The aim of the study was to detect the influence of nitrogen pressure on the rheological properties and structure of PA66 GF30 thick-walled parts, produced by means of microcellular injection molding (MIM), using the MuCell® technology. The process was monitored in-line with pressure and temperature sensors assembled in the original injection mold. The measured data was subsequently used to evaluate rheological properties inside an 8.4 mm depth mold cavity. The analysis of the microcellular structure was related to the monitored in-line pressure and temperature changes during the injection process cycle. A four-times reduction of the maximum filling pressure in the mold cavity for MIM was found. At the same time, the holding pressure was taken over by expanding cells. The gradient effect of the cells distribution and the fiber arrangement in the flow direction were observed. A slight influence of nitrogen pressure on the cells size was found. Cells with a diameter lower than 20 µm dominate in the analyzed cases. An effect of reduction of the average cells size in the function of distance to the gate was observed. The creation of structure gradient and changes of cells dimensions were evaluated by SEM images and confirmed with the micro CT analysis.

show abstract

Section: Entry In the Literature Listmentioning

confidence: 99%

The Microcellular Structure of Injection Molded Thick-Walled Parts as Observed by In-Line Monitoring

2020

View full text Add to dashboard Cite

show abstract

“…Most of these parameters can be acquired from the IMM sensors installed by its manufacturer, however, some require additional sensors in the molds, as for example, the mold temperature and pressure data. This data is suggested as one of the essential indicators of production of the high quality parts, as it reflects the evolution of the polymer conditions inside the mold, and is used and investigated by both industry and academia (Zhao et al, 2014;Kurt et al, 2009;Kurt et al, 2010;Ageyeva, Horváth & Kovács, 2019). There are a number of sensors available on the market for installation in molds (piezoelectric/piezoresistive, strain gage, surface mounted thermocouples, ultrasonic sensors, optical sensors, etc.).…”

Section: Injection Molding Processmentioning

confidence: 99%

“…There are a number of sensors available on the market for installation in molds (piezoelectric/piezoresistive, strain gage, surface mounted thermocouples, ultrasonic sensors, optical sensors, etc.). Some of them have operating temperatures that do not allow insertion into the mold cavity and touching the molten material (indirect, contact-free measurement), while others are able to operate in these extreme conditions (direct measurement) (Ageyeva, Horváth & Kovács, 2019).…”

Section: Injection Molding Processmentioning

confidence: 99%

Towards a general application programming interface (API) for injection molding machines

Ogorodnyk

Larsen

Lyngstad

et al. 2020

PeerJ Computer Science

View full text Add to dashboard Cite

Injection molding is a complicated process, and the final part quality depends on many machine and process parameters settings. To increase controllability of the injection molding process, acquisition of the process data is necessary. This paper describes the architecture and development of a prototype of an open application programming interface (API) for injection molding machines (IMMs), which has the potential to be used with different IMMs to log and set the necessary process parameter values. At the moment, the API includes an implementation of EMI data exchange protocol and can be used with ENGEL IMMs with CC300 and RC300 controllers. Data collection of up to 97 machine and process parameters (the number might vary depending on the type of machine at hand), obtained from sensors installed in the machine by the manufacturer is allowed. The API also includes a module for the acquisition of data from additional 3d party sensors. Industrial Raspberry Pi (RevPi) was used to perform analog-to-digital signal conversion and make sensors data accessible via the API prototype. The logging of parameters from the machine and from sensors is synchronized and the sampling frequency can be adjusted if necessary. The system can provide soft real-time communication.

show abstract

“…With the trend of intelligent manufacturing, the accuracy and automation of injection molding can further be improved through artificial intelligence (AI) [ 15 ], cyber-physical systems [ 16 ], Internet of Things [ 17 ] and data mining [ 18 ]. AI is a method that combines domain, statistical and computer science knowledge by simulating human intelligence.…”

Section: Introductionmentioning

confidence: 99%

Quality Prediction for Injection Molding by Using a Multilayer Perceptron Neural Network

Ke¹,

Huang²

2020

Polymers

View full text Add to dashboard Cite

Injection molding has been widely used in the mass production of high-precision products. The finished products obtained through injection molding must have a high quality. Machine parameters do not accurately reflect the molding conditions of the polymer melt; thus, the use of machine parameters leads to erroneous quality judgments. Moreover, the cost of mass inspections of finished products has led to strict restrictions on comprehensive quality testing. Therefore, an automatic quality inspection that provides effective and accurate quality judgment for each injection-molded part is required. This study proposes a multilayer perceptron (MLP) neural network model combined with quality indices for performing fast and automatic prediction of the geometry of finished products. The pressure curves detected by the in-mold pressure sensor, which reflect the flow state of the melt, changes in various indicators and molding quality, were considered in this study. Furthermore, the quality indices extracted from pressure curves with a strong correlation with the part quality were input into the MLP model for learning and prediction. The results indicate that the training and testing of the first-stage holding pressure index, pressure integral index, residual pressure drop index and peak pressure index with respect to the geometric widths were accurate (accuracy rate exceeded 92%), which demonstrates the feasibility of the proposed method.

show abstract

In-Mold Sensors for Injection Molding: On the Way to Industry 4.0

Cited by 81 publications

References 82 publications

The Microcellular Structure of Injection Molded Thick-Walled Parts as Observed by In-Line Monitoring

The Microcellular Structure of Injection Molded Thick-Walled Parts as Observed by In-Line Monitoring

Towards a general application programming interface (API) for injection molding machines

Quality Prediction for Injection Molding by Using a Multilayer Perceptron Neural Network

Contact Info

Product

Resources

About