Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Measuring Acceleration Due to Gravity01:12

Measuring Acceleration Due to Gravity

638
Consider a coffee mug hanging on a hook in a pantry. If the mug gets knocked, it oscillates back and forth like a pendulum until the oscillations die out.
A simple pendulum can be described as a point mass and a string. Meanwhile, a physical pendulum is any object whose oscillations are similar to a simple pendulum, but cannot be modeled as a point mass on a string because its mass is distributed over a larger area. The behavior of a physical pendulum can be modeled using the principles of...
638

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Optimal Scheduling in General Multi-Queue System by Combining Simulation and Neural Network Techniques.

Sensors (Basel, Switzerland)·2023
Same author

Combination of Sensor Data and Health Monitoring for Early Detection of Subclinical Ketosis in Dairy Cows.

Sensors (Basel, Switzerland)·2020
See all related articles

Related Experiment Video

Updated: Aug 30, 2025

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

8.9K

On the Problem of State Recognition in Injection Molding Based on Accelerometer Data Sets.

Julian Brunthaler1, Patryk Grabski1, Valentin Sturm2

  • 1AISEMO GmbH, 4675 Weibern, Austria.

Sensors (Basel, Switzerland)
|August 26, 2022
PubMed
Summary
This summary is machine-generated.

Smart machine learning models using 3D-accelerometer data can automatically identify injection molding production and downtime. This monitoring system shows promise for optimizing industrial processes.

Keywords:
accelerometer sensorconvolutional neural networkinjection moldingmachine-learning algorithmstate recognition

More Related Videos

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars
05:32

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

Published on: August 4, 2018

12.7K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

Related Experiment Videos

Last Updated: Aug 30, 2025

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

Published on: April 13, 2016

8.9K
A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars
05:32

A Soft Tooling Process Chain for Injection Molding of a 3D Component with Micro Pillars

Published on: August 4, 2018

12.7K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.2K

Area of Science:

  • Industrial Engineering
  • Machine Learning
  • Sensor Technology

Background:

  • Smart technologies are increasingly integrated into industrial processes.
  • Continuous monitoring of manufacturing, like injection molding, is crucial for identifying operational and downtime periods.
  • Accurate state recognition is essential for process optimization and efficiency.

Purpose of the Study:

  • To develop and evaluate supervised machine learning algorithms for automatic recognition of production and downtime periods in injection molding.
  • To utilize data from a 3D-accelerometer sensor for training and verifying these algorithms.
  • To establish the efficacy of accelerometer data-based machine learning models in distinguishing key steps of an injection molding cycle.

Main Methods:

  • Development of two supervised machine learning algorithms: one using descriptive statistics features and another employing a convolutional neural network.
  • Implementation of a 3D-accelerometer sensor to collect datasets for algorithm training and validation.
  • Application of ANOVA tests to compare the statistical differences between the developed algorithms.

Main Results:

  • The developed machine learning models achieved a balanced accuracy of approximately 72-92% in recognizing producing and non-producing periods.
  • Accelerometer data proved effective for distinguishing key phases within an injection molding cycle.
  • While ANOVA tests showed no significant statistical differences between comparative algorithms, the neural network exhibited higher accuracy metric variances.

Conclusions:

  • Accelerometer data combined with machine learning offers a viable solution for automated monitoring of injection molding processes.
  • The developed system has significant potential for improving the efficiency and understanding of industrial manufacturing.
  • Further research may refine the neural network approach to reduce variance and enhance overall performance.