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

End Point Prediction: Gran Plot01:07

End Point Prediction: Gran Plot

787
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
787

You might also read

Related Articles

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

Sort by
Same author

Microplastic sedimentary records in a shallow lake of North China: Identifiable responses to hydrological and socio-economic drivers.

Water research·2026
Same author

Metabolic division of labor drives synergistic production of biomass, lipid and α-tocopherol in Euglena gracilis-Chlorella pyrenoidosa co-cultures.

Bioresource technology·2026
Same author

Unraveling microbial signatures in the comorbidity of autoimmune diseases and depression.

BMC microbiology·2026
Same author

Caffeic acid-grafted high-amylose maize starch for self-stabilizing emulsion gels: efficient encapsulation and protection of pterostilbene.

Food chemistry·2026
Same author

A high-amylose maize starch hydrogel mask for stabilized encapsulation of thyme essential oil with Higuchi-controlled release.

International journal of biological macromolecules·2026
Same author

Identification of soybean variety based on spectral data and RGB image fusion combined with deep learning method.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Related Experiment Video

Updated: Oct 30, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

632

Spark Analysis Based on the CNN-GRU Model for WEDM Process.

Changhong Liu1,2, Xingxin Yang3, Shaohu Peng3

  • 1School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou 510006, China.

Micromachines
|July 2, 2021
PubMed
Summary

This study introduces a novel spark image-based approach for predicting discharge status in wire electrical discharge machining (WEDM). The method utilizes deep learning to analyze spark image features, offering improved accuracy over traditional pulse waveform analysis.

Keywords:
convolution neural network (CNN)deep learninggated recurrent unit (GRU)spark analysiswire electrical discharge machining (WEDM)

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

590
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

728

Related Experiment Videos

Last Updated: Oct 30, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

632
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

590
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

728

Area of Science:

  • Manufacturing Engineering
  • Materials Science
  • Artificial Intelligence

Background:

  • Wire electrical discharge machining (WEDM) is crucial for precision part fabrication, typically analyzed via pulse characteristics.
  • Existing research on spark image-based analysis for WEDM discharge status prediction is limited.
  • Traditional methods correlating pulse waveforms with machining status may not always be accurate.

Purpose of the Study:

  • To propose and validate a novel spark image-based approach for predicting WEDM discharge status.
  • To explore the relationship between spark image features and discharge status.
  • To develop a robust deep learning model for accurate discharge status prediction.

Main Methods:

  • A synchronous high-speed image and waveform acquisition system was employed.
  • Spark image features (area, energy, energy density, distribution) were extracted and analyzed.
  • A deep learning model combining Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) was developed.
  • A quantitative labeling method for machining states was introduced to enhance model stability.

Main Results:

  • Experimental results revealed that traditional assumptions about pulse waveforms and machining status are not universally true.
  • The proposed CNN-GRU model effectively predicted discharge status using a time series of extracted spark image features.
  • The quantitative labeling method improved the overall stability and predictive performance of the model.
  • The spark image-based approach demonstrated superior prediction results compared to a standalone GRU model.

Conclusions:

  • Spark image analysis offers a viable and potentially more accurate alternative to traditional pulse waveform analysis in WEDM.
  • The developed deep learning model (CNN-GRU) with quantitative labeling provides a stable and effective method for real-time discharge status prediction.
  • This approach enhances the understanding and control of the WEDM process, leading to improved manufacturing outcomes.