Spark Analysis Based on the CNN-GRU Model for WEDM Process
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 conducte...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-06-01
|
Series: | Micromachines |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-666X/12/6/702 |
id |
doaj-043269f8c48640469e90160ff93989de |
---|---|
record_format |
Article |
spelling |
doaj-043269f8c48640469e90160ff93989de2021-07-01T00:18:42ZengMDPI AGMicromachines2072-666X2021-06-011270270210.3390/mi12060702Spark Analysis Based on the CNN-GRU Model for WEDM ProcessChanghong Liu0Xingxin Yang1Shaohu Peng2Yongjun Zhang3Lingxi Peng4Ray Y. Zhong5School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electromechanical Engineering, Guangdong University of Technology, Guangzhou 510006, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou 510006, ChinaDepartment of Industrial and Manufacturing Systems Engineering, The University of Hong Kong, Hong Kong 999077, ChinaWire 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.https://www.mdpi.com/2072-666X/12/6/702wire electrical discharge machining (WEDM)deep learningspark analysisconvolution neural network (CNN)gated recurrent unit (GRU) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Changhong Liu Xingxin Yang Shaohu Peng Yongjun Zhang Lingxi Peng Ray Y. Zhong |
spellingShingle |
Changhong Liu Xingxin Yang Shaohu Peng Yongjun Zhang Lingxi Peng Ray Y. Zhong Spark Analysis Based on the CNN-GRU Model for WEDM Process Micromachines wire electrical discharge machining (WEDM) deep learning spark analysis convolution neural network (CNN) gated recurrent unit (GRU) |
author_facet |
Changhong Liu Xingxin Yang Shaohu Peng Yongjun Zhang Lingxi Peng Ray Y. Zhong |
author_sort |
Changhong Liu |
title |
Spark Analysis Based on the CNN-GRU Model for WEDM Process |
title_short |
Spark Analysis Based on the CNN-GRU Model for WEDM Process |
title_full |
Spark Analysis Based on the CNN-GRU Model for WEDM Process |
title_fullStr |
Spark Analysis Based on the CNN-GRU Model for WEDM Process |
title_full_unstemmed |
Spark Analysis Based on the CNN-GRU Model for WEDM Process |
title_sort |
spark analysis based on the cnn-gru model for wedm process |
publisher |
MDPI AG |
series |
Micromachines |
issn |
2072-666X |
publishDate |
2021-06-01 |
description |
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. |
topic |
wire electrical discharge machining (WEDM) deep learning spark analysis convolution neural network (CNN) gated recurrent unit (GRU) |
url |
https://www.mdpi.com/2072-666X/12/6/702 |
work_keys_str_mv |
AT changhongliu sparkanalysisbasedonthecnngrumodelforwedmprocess AT xingxinyang sparkanalysisbasedonthecnngrumodelforwedmprocess AT shaohupeng sparkanalysisbasedonthecnngrumodelforwedmprocess AT yongjunzhang sparkanalysisbasedonthecnngrumodelforwedmprocess AT lingxipeng sparkanalysisbasedonthecnngrumodelforwedmprocess AT rayyzhong sparkanalysisbasedonthecnngrumodelforwedmprocess |
_version_ |
1721348929970241536 |