A Novel Efficient Big Data Processing Scheme for Feature Extraction in Electrical Discharge Machining

Chao-Chun Chen, Min Hsiung Hung, Benny Suryajaya, Yu Chuan Lin, Haw Ching Yang, Hsien Cheng Huang, Fan-Tien Cheng

研究成果: Article

摘要

Electrical discharge machining (EDM) can machine hard conductive workpieces that are difficult to machine using traditional machining techniques. For monitoring the EDM process using virtual metrology (VM), probes with a very high sampling rate are needed to acquire the voltage and current signals of electrodes, thereby generating a huge amount of sensor data and raising a big data processing issue in extracting features from raw sensor data. This paper proposes a novel efficient big data processing scheme for feature extraction in EDM, called BEDPS, based on Spark and HDFS. A parallel gap-based wave detection mechanism using Spark is designed to efficiently detect effective machining waves from big machining raw data of EDM without the slow internode data communications in HDFS. A pre-loaded memory-based feature calculation mechanism is also developed to calculate the key features from machining-wave data in Spark in a parallel-processing manner. Testing results show that the proposed BEDPS is much more efficient in terms of total execution time in machining wave detection and feature calculation and more scalable in the data size that can be processed, compared to the existing system.

原文English
文章編號8605347
頁(從 - 到)910-917
頁數8
期刊IEEE Robotics and Automation Letters
4
發行號2
DOIs
出版狀態Published - 2019 四月 1

指紋

Electric discharge machining
Machining
Feature Extraction
Feature extraction
Electric sparks
Sensors
Big data
Sensor
Sampling
Data storage equipment
Data Communication
Electrodes
Monitoring
Parallel Processing
Metrology
Communication
Testing
Electric potential
Processing
Execution Time

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Biomedical Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

引用此文

Chen, Chao-Chun ; Hung, Min Hsiung ; Suryajaya, Benny ; Lin, Yu Chuan ; Yang, Haw Ching ; Huang, Hsien Cheng ; Cheng, Fan-Tien. / A Novel Efficient Big Data Processing Scheme for Feature Extraction in Electrical Discharge Machining. 於: IEEE Robotics and Automation Letters. 2019 ; 卷 4, 編號 2. 頁 910-917.
@article{3dce0f0d394342f08b81d88ea4b2c1d2,
title = "A Novel Efficient Big Data Processing Scheme for Feature Extraction in Electrical Discharge Machining",
abstract = "Electrical discharge machining (EDM) can machine hard conductive workpieces that are difficult to machine using traditional machining techniques. For monitoring the EDM process using virtual metrology (VM), probes with a very high sampling rate are needed to acquire the voltage and current signals of electrodes, thereby generating a huge amount of sensor data and raising a big data processing issue in extracting features from raw sensor data. This paper proposes a novel efficient big data processing scheme for feature extraction in EDM, called BEDPS, based on Spark and HDFS. A parallel gap-based wave detection mechanism using Spark is designed to efficiently detect effective machining waves from big machining raw data of EDM without the slow internode data communications in HDFS. A pre-loaded memory-based feature calculation mechanism is also developed to calculate the key features from machining-wave data in Spark in a parallel-processing manner. Testing results show that the proposed BEDPS is much more efficient in terms of total execution time in machining wave detection and feature calculation and more scalable in the data size that can be processed, compared to the existing system.",
author = "Chao-Chun Chen and Hung, {Min Hsiung} and Benny Suryajaya and Lin, {Yu Chuan} and Yang, {Haw Ching} and Huang, {Hsien Cheng} and Fan-Tien Cheng",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/LRA.2019.2891498",
language = "English",
volume = "4",
pages = "910--917",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

A Novel Efficient Big Data Processing Scheme for Feature Extraction in Electrical Discharge Machining. / Chen, Chao-Chun; Hung, Min Hsiung; Suryajaya, Benny; Lin, Yu Chuan; Yang, Haw Ching; Huang, Hsien Cheng; Cheng, Fan-Tien.

於: IEEE Robotics and Automation Letters, 卷 4, 編號 2, 8605347, 01.04.2019, p. 910-917.

研究成果: Article

TY - JOUR

T1 - A Novel Efficient Big Data Processing Scheme for Feature Extraction in Electrical Discharge Machining

AU - Chen, Chao-Chun

AU - Hung, Min Hsiung

AU - Suryajaya, Benny

AU - Lin, Yu Chuan

AU - Yang, Haw Ching

AU - Huang, Hsien Cheng

AU - Cheng, Fan-Tien

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Electrical discharge machining (EDM) can machine hard conductive workpieces that are difficult to machine using traditional machining techniques. For monitoring the EDM process using virtual metrology (VM), probes with a very high sampling rate are needed to acquire the voltage and current signals of electrodes, thereby generating a huge amount of sensor data and raising a big data processing issue in extracting features from raw sensor data. This paper proposes a novel efficient big data processing scheme for feature extraction in EDM, called BEDPS, based on Spark and HDFS. A parallel gap-based wave detection mechanism using Spark is designed to efficiently detect effective machining waves from big machining raw data of EDM without the slow internode data communications in HDFS. A pre-loaded memory-based feature calculation mechanism is also developed to calculate the key features from machining-wave data in Spark in a parallel-processing manner. Testing results show that the proposed BEDPS is much more efficient in terms of total execution time in machining wave detection and feature calculation and more scalable in the data size that can be processed, compared to the existing system.

AB - Electrical discharge machining (EDM) can machine hard conductive workpieces that are difficult to machine using traditional machining techniques. For monitoring the EDM process using virtual metrology (VM), probes with a very high sampling rate are needed to acquire the voltage and current signals of electrodes, thereby generating a huge amount of sensor data and raising a big data processing issue in extracting features from raw sensor data. This paper proposes a novel efficient big data processing scheme for feature extraction in EDM, called BEDPS, based on Spark and HDFS. A parallel gap-based wave detection mechanism using Spark is designed to efficiently detect effective machining waves from big machining raw data of EDM without the slow internode data communications in HDFS. A pre-loaded memory-based feature calculation mechanism is also developed to calculate the key features from machining-wave data in Spark in a parallel-processing manner. Testing results show that the proposed BEDPS is much more efficient in terms of total execution time in machining wave detection and feature calculation and more scalable in the data size that can be processed, compared to the existing system.

UR - http://www.scopus.com/inward/record.url?scp=85063310527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063310527&partnerID=8YFLogxK

U2 - 10.1109/LRA.2019.2891498

DO - 10.1109/LRA.2019.2891498

M3 - Article

AN - SCOPUS:85063310527

VL - 4

SP - 910

EP - 917

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 2

M1 - 8605347

ER -