File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3390/mi12060702
- Scopus: eid_2-s2.0-85108869173
- PMID: 34208519
- WOS: WOS:000666523800001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Spark Analysis Based on the CNN-GRU Model for WEDM Process
Title | Spark Analysis Based on the CNN-GRU Model for WEDM Process |
---|---|
Authors | |
Keywords | wire electrical discharge machining (WEDM) deep learning spark analysis convolution neural network (CNN) gated recurrent unit (GRU) |
Issue Date | 2021 |
Publisher | MDPI AG. The Journal's web site is located at http://www.mdpi.com/journal/micromachines |
Citation | Micromachines, 2021, v. 12 n. 6, p. article no. 702 How to Cite? |
Abstract | Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in manufacturing industry, is a nontraditional machining method using discharge energy which is transformed into thermal energy to efficiently remove materials. A great amount of research has been conducted based on pulse characteristics. However, the spark image-based approach has little research reported. This paper proposes a discharge spark image-based approach. A model is introduced to predict the discharge status using spark image features through a synchronous high-speed image and waveform acquisition system. First, the relationship between the spark image features (e.g., area, energy, energy density, distribution, etc.) and discharge status is explored by a set of experiments). Traditional methods have claimed that pulse waveform of “short” status is related to the status of non-machining while through our research, it is concluded that this is not always true by conducting experiments based on the spark images. Second, a deep learning model based on Convolution neural network (CNN) and Gated recurrent unit (GRU) is proposed to predict the discharge status. A time series of spark image features extracted by CNN form a 3D feature space is used to predict the discharge status through GRU. Moreover, a quantitative labeling method of machining state is proposed to improve the stability of the model. Due the effective features and the quantitative labeling method, the proposed approach achieves better predict result comparing with the single GRU model. |
Persistent Identifier | http://hdl.handle.net/10722/300785 |
ISSN | 2021 Impact Factor: 3.523 2020 SCImago Journal Rankings: 0.575 |
PubMed Central ID | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, C | - |
dc.contributor.author | Yang, X | - |
dc.contributor.author | Peng, S | - |
dc.contributor.author | Zhang, Y | - |
dc.contributor.author | Peng, L | - |
dc.contributor.author | Zhong, RY | - |
dc.date.accessioned | 2021-07-06T03:10:13Z | - |
dc.date.available | 2021-07-06T03:10:13Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Micromachines, 2021, v. 12 n. 6, p. article no. 702 | - |
dc.identifier.issn | 2072-666X | - |
dc.identifier.uri | http://hdl.handle.net/10722/300785 | - |
dc.description.abstract | Wire electrical discharge machining (WEDM), widely used to fabricate micro and precision parts in manufacturing industry, is a nontraditional machining method using discharge energy which is transformed into thermal energy to efficiently remove materials. A great amount of research has been conducted based on pulse characteristics. However, the spark image-based approach has little research reported. This paper proposes a discharge spark image-based approach. A model is introduced to predict the discharge status using spark image features through a synchronous high-speed image and waveform acquisition system. First, the relationship between the spark image features (e.g., area, energy, energy density, distribution, etc.) and discharge status is explored by a set of experiments). Traditional methods have claimed that pulse waveform of “short” status is related to the status of non-machining while through our research, it is concluded that this is not always true by conducting experiments based on the spark images. Second, a deep learning model based on Convolution neural network (CNN) and Gated recurrent unit (GRU) is proposed to predict the discharge status. A time series of spark image features extracted by CNN form a 3D feature space is used to predict the discharge status through GRU. Moreover, a quantitative labeling method of machining state is proposed to improve the stability of the model. Due the effective features and the quantitative labeling method, the proposed approach achieves better predict result comparing with the single GRU model. | - |
dc.language | eng | - |
dc.publisher | MDPI AG. The Journal's web site is located at http://www.mdpi.com/journal/micromachines | - |
dc.relation.ispartof | Micromachines | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | wire electrical discharge machining (WEDM) | - |
dc.subject | deep learning | - |
dc.subject | spark analysis | - |
dc.subject | convolution neural network (CNN) | - |
dc.subject | gated recurrent unit (GRU) | - |
dc.title | Spark Analysis Based on the CNN-GRU Model for WEDM Process | - |
dc.type | Article | - |
dc.identifier.email | Zhong, RY: zhongzry@hku.hk | - |
dc.identifier.authority | Zhong, RY=rp02116 | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.3390/mi12060702 | - |
dc.identifier.pmid | 34208519 | - |
dc.identifier.pmcid | PMC8235280 | - |
dc.identifier.scopus | eid_2-s2.0-85108869173 | - |
dc.identifier.hkuros | 323105 | - |
dc.identifier.volume | 12 | - |
dc.identifier.issue | 6 | - |
dc.identifier.spage | article no. 702 | - |
dc.identifier.epage | article no. 702 | - |
dc.identifier.isi | WOS:000666523800001 | - |
dc.publisher.place | Switzerland | - |