Real-time parameter optimization based on neural network for smart injection molding

Lee, H; Liau, Yee Yeng; Ryu, Kwang Ryel

doi:10.1088/1757-899x/324/1/012076

Cited by 12 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although public health emergency management has been paid much attention, the research in this area is still in its infancy and initial stage. Especially in the "top down" emergency response system, how to highlight the role and function of primary medical units is a problem that we are waiting to study at present, especially the remote public health emergency management of the Internet of things is also in the exploratory stage [27][28][29]. is paper will focus on the current situation and focus on analyzing the low delay emergency management system of remote public medical care based on the Internet of things, which has a strong convincing and promoting role in improving the relevant mechanism.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Remote Public Medical Emergency Management System with Low Delay Based on Internet of Things

Feng

Zhong-yu

2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Due to the limitation of economic geography condition, the existing health resources distribution is uneven, the emergence of remote medical disciplines perfectly solved this difficult problem, using computer and network communication network on audio video information transmissions, querying, display, storage, and backup and realizing the network of outpatient service, remote consultation, health advice, and other functions. Telemedicine enables the limited available medical resources to be shared and fully utilized and also enables many economically underdeveloped provinces to enjoy a higher level of medical sharing services. Public health emergency management system on the overall design of the low latency according to system function will be based on the Internet of things. The remote public health emergency management system is divided into three subsystems low latency modules, basic subsystems of platform, application platform, and specific application subsystems, and designs the structure of the various modules. The implementation process is given. In the realization of the system, this paper describes in detail how to realize the functions of the public medical low delay emergency management system, and, in the end, the realization process of the system is reasonably summarized. The application of Internet of things technology in regional emergency rescue can realize the identification and real-time positioning of material personnel, the collection and transmission of the wounded’s physiological information, real-time information transmission, and interaction based on mobile handheld devices, as well as the integration of emergency rescue resources, information integration, and command decision-making, so as to assist rescue operations and improve rescue efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimization of Remote Public Medical Emergency Management System with Low Delay Based on Internet of Things

Feng

Zhong-yu

2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…Many more researchers proposed ANN-based models of the injection molding process for a subsequent optimization of the product warpage [17][18][19][20][21][22], mechanical properties [23][24][25], or even a combination of several quality parameters together in a single model [26][27][28]. Each of the above described research works refer to an explicitly generated database, introducing an iterative data generation process and therefore costs into the optimization.…”

Section: Artificial Neural Network In Injection Moldingmentioning

confidence: 99%

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

Lockner

Hopmann

2021

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The 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.

show abstract

“…Dado que esto es foco de interés, se han planteado a lo largo del tiempo diferentes soluciones para controlar estas variables. Resumiendo los resultados de estas implementaciones podemos ver que en (Zhang, S., Dubay, R., & Charest, M., 2014), (Tan, Y. S., Ng, Y. T., & Low, J. S. C., 2017), (Vrabič, R., Kozjek, D., & Butala, P., 2017), (Hu, F., He, Z., Zhao, X., & Zhang, S., 2017), (Siller, H. R., Romero, D., Rabelo, R. J., & Vazquez, E., 2018), (Ogorodnyk, O., & Martinsen, K., 2018), (Lucchetta, G., Masato, D., & Sorgato, M., 2018), (Ageyeva, T., Horváth, S., & Kovács, J. G., 2019), (Park, H. S., Phuong, D. X., & Kumar, S., 2019, (Lee, H., Liau, Y., & Ryu, K., 2018) y (Charest, M., Finn, R., & Dubay, R., 2018) se utiliza tecnología de sensores de temperatura y presiones en las cavidades de los moldes; cada una de las implementaciones ha tomado diferentes medidas en acondicionar las herramientas y las máquinas para poder recopilar los datos, mientras que en los casos donde se ha realizado integración de tecnología, se ha buscado que esta sea la adecuada para obtener los resultados deseados, sobre todo en (Ageyeva, T., Horváth, S., & Kovács, J. G., 2019) donde se proponen diferentes maneras de obtener los datos del comportamiento de plástico por medio de tecnologías diversas.…”

Section: Datos Medidas Y Casos De Aplicaciónunclassified

Aplicación del internet industrial de las cosas(ioT)en líneas de manufactura por proceso de moldeo por inyección de plástico.

Lugo

Ibarra-Esquer

Bernal

2021

recibe

View full text Add to dashboard Cite

Las revoluciones industriales han impulsado el desarrollo tecnológico, social y económico. Una de las industrias que se ha beneficiado por los avances tecnológicos es la de moldeo por inyección de plástico, que recientemente ha incorporado tecnologías de la industria 4.0. A partir de esto, el presente documento tiene como objetivo posicionarnos en el contexto de la industria de moldeo por inyección de plástico y el progreso de la industria 4.0 aplicada a sus procesos. Esta industria conlleva un proceso complejo controlado, que requiere el uso de herramientas estadísticas que muestren el comportamiento y resultados del proceso. Los datos se suelen recopilar de forma manual, con fallas u omisiones que generan problemas en diversas áreas. Se plantea entonces utilizar tecnologías de industria 4.0 para aumentar la eficiencia, descifrar tendencias y optimizar recursos y procesos, partiendo de la noción que el uso de estas tecnologías facilita la toma de decisiones acertadas en base a datos extraídos de producción, mejorando el análisis de las causas raíz de la problemática. Por medio de una revisión sistemática de literatura se encuentran casos exitosos de implementación, conceptos en el campo del Internet Industrial de las Cosas y la relación entre la industria de moldeo por inyección y la industria 4.0, con resultados utilizables como referencia para el planteamiento de nuevos proyectos y soluciones por parte de la comunidad interesada en la industria de moldeo por inyección de plástico.

show abstract

Real-time parameter optimization based on neural network for smart injection molding

Cited by 12 publications

References 8 publications

Optimization of Remote Public Medical Emergency Management System with Low Delay Based on Internet of Things

Optimization of Remote Public Medical Emergency Management System with Low Delay Based on Internet of Things

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

Aplicación del internet industrial de las cosas(ioT)en líneas de manufactura por proceso de moldeo por inyección de plástico.

Contact Info

Product

Resources

About