Two Phases Anomaly Detection Based on Clustering and Visualization for Plastic Injection Molding Data

Lee, Seoyeong; Yun, Yongwan; Park, Seonggwan; Oh, Sujeong; Lee, Chaegyu; Jeong, Jongpil

doi:10.1016/j.procs.2022.03.067

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the authors in [20] employ an LSTM network to detect possible anomalies within the injection molding stage of the PET bottle production. This resembles this project, however the flow is reversed, as there the clustering step is not used to aid the anomaly detection phase, but rather to further cluster the detected anomaly data in order to improve the process.…”

Section: Anomaly Detectionmentioning

confidence: 99%

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Sorostinean,

Burghelea,

Gellert

2024

IEEE Access

View full text Add to dashboard Cite

This study addresses the need to develop a sustainable manufacturing process in industrial factories, as the industry desires to remain competitive while it is challenged to adopt eco-friendly practices. A Machine Learning-based software is proposed to deal with the environmental issues, aiming to facilitate the monitoring and analysis of industrial machinery, more exactly of CNC woodworking machines. The focus is on two aspects that determine the environmental impact: energy consumption and toxic emissions, which are used to determine the operating modes of the machines and to detect potential working anomalies. This software consists of a pipeline with two main components: the first one aims to categorize the operating modes of the used machines through time series clustering methods, such as Hidden Markov Models. The second component employs Hidden Markov Models again alongside deep learning based Autoencoders, in order to identify huge deviations within the environmental data. For evaluation, a dataset was collected as a time series from a CNC woodworking machine and then the preprocessed data was further analyzed using the implemented software. The experiments have shown that for anomaly detection in machine operating modes, the Hidden Markov Model outperforms the Autoencoder and state-of-the-art models in terms of efficiency and robustness.

show abstract

Section: Anomaly Detectionmentioning

confidence: 99%

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Sorostinean,

Burghelea,

Gellert

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Of the various plastic molding methods, injection molding is a prevalent method to apply. According to Lee et al (2022), injection molding is a method of making plastic products by injecting hot plastic melt through the cavity into the mold, the plastic melt follows the shape of the mold and undergoes cooling to become a finished product. This plastic injection process is carried out in three stages, namely charging, pressing, and holding with the help of piston pressure during these processes (Alonso-González, Felix, & Romero, 2022; Lee et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Application of PDCA Method in Improving the Quality of Valve Production

Putrawangsa

Caniago

Aprilio

2022

Eduvest

View full text Add to dashboard Cite

Plastic is one of the most widely used raw materials for a product. Human life cannot be separated from products or equipment made from plastic. Company X often has problems with the quality of the products produced, especially valve products as products that are produced every day. The corrective step used to assist Company X in improving the quality of valve products is the application of the PDCA method. PDCA method consists of the plan, do, check, and act stages. The proposed improvement design was carried out based on the results of data processing and obtained as many as 9 proposed improvements. In the do stage, implementation of the proposed improvements that have been designed is carried out, five proposed improvements can be implemented and the other four in the form of recommendations. Next is the check stage, which is the process of collecting data again on the results of the implementation of the proposed improvement. Based on the results of the check stage, a standardization process was carried out at the act stage to improve the performance of the proposed improvement and the quality of the valve product. Standardization is done by changing or improving the proposed improvements that have been implemented. Research has succeeded in reducing the number of defective valve products with the proportion of defects that were previously 1.16% to 0.57%.

show abstract

An experimental study on the application of reinforcement learning in injection molding in the spirit of Industry 4.0

Párizs,

Török

2024

Applied Soft Computing

View full text Add to dashboard Cite

Two Phases Anomaly Detection Based on Clustering and Visualization for Plastic Injection Molding Data

Cited by 4 publications

References 12 publications

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Anomaly Detection in Smart Industrial Machinery Through Hidden Markov Models and Autoencoders

Application of PDCA Method in Improving the Quality of Valve Production

An experimental study on the application of reinforcement learning in injection molding in the spirit of Industry 4.0

Contact Info

Product

Resources

About