Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks
The Intelligent Fault Diagnosis of rotating machinery calls for a substantial amount of training data, posing challenges in acquiring such data for damaged industrial machinery. This paper presents a novel approach for generating synthetic data using a Generative Adversarial Network (GAN) with cycle...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/22/12458 |
| _version_ | 1797460236290752512 |
|---|---|
| author | Luigi Gianpio Di Maggio Eugenio Brusa Cristiana Delprete |
| author_facet | Luigi Gianpio Di Maggio Eugenio Brusa Cristiana Delprete |
| author_sort | Luigi Gianpio Di Maggio |
| collection | DOAJ |
| description | The Intelligent Fault Diagnosis of rotating machinery calls for a substantial amount of training data, posing challenges in acquiring such data for damaged industrial machinery. This paper presents a novel approach for generating synthetic data using a Generative Adversarial Network (GAN) with cycle consistency loss function known as cycleGAN. The proposed method aims to generate synthetic data that could effectively replace real experimental data. The generative model is trained to transform wavelet images of simulated vibrational signals into authentic data obtained from machinery with damaged bearings. The utilization of Maximum Mean Discrepancy (MMD) and Fréchet Inception Distance (FID) demonstrates a noteworthy resemblance between synthetic and real experimental data. Also, the generative model enables the synthesis of data that may have been entirely lacking from the experimental observation, indicating generative zero-shot learning capabilities. The efficacy of synthetic data in training diagnosis algorithms by means of Transfer Learning (TL) on Convolutional Neural Networks (CNNs) has been demonstrated to be comparable to that of real data. The study has been validated by means of the test rig for medium-sized industrial bearings accessible at the Politecnico di Torino. |
| first_indexed | 2024-03-09T17:02:15Z |
| format | Article |
| id | doaj.art-279dc01538ff42d2b4817a097e10b636 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T17:02:15Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-279dc01538ff42d2b4817a097e10b6362023-11-24T14:27:55ZengMDPI AGApplied Sciences2076-34172023-11-0113221245810.3390/app132212458Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial NetworksLuigi Gianpio Di Maggio0Eugenio Brusa1Cristiana Delprete2Dipartimento di Ingegneria Meccanica e Aerospaziale (DIMEAS), Politecnico di Torino, Corso Duca Degli Abruzzi 24, 10129 Torino, ItalyDipartimento di Ingegneria Meccanica e Aerospaziale (DIMEAS), Politecnico di Torino, Corso Duca Degli Abruzzi 24, 10129 Torino, ItalyDipartimento di Ingegneria Meccanica e Aerospaziale (DIMEAS), Politecnico di Torino, Corso Duca Degli Abruzzi 24, 10129 Torino, ItalyThe Intelligent Fault Diagnosis of rotating machinery calls for a substantial amount of training data, posing challenges in acquiring such data for damaged industrial machinery. This paper presents a novel approach for generating synthetic data using a Generative Adversarial Network (GAN) with cycle consistency loss function known as cycleGAN. The proposed method aims to generate synthetic data that could effectively replace real experimental data. The generative model is trained to transform wavelet images of simulated vibrational signals into authentic data obtained from machinery with damaged bearings. The utilization of Maximum Mean Discrepancy (MMD) and Fréchet Inception Distance (FID) demonstrates a noteworthy resemblance between synthetic and real experimental data. Also, the generative model enables the synthesis of data that may have been entirely lacking from the experimental observation, indicating generative zero-shot learning capabilities. The efficacy of synthetic data in training diagnosis algorithms by means of Transfer Learning (TL) on Convolutional Neural Networks (CNNs) has been demonstrated to be comparable to that of real data. The study has been validated by means of the test rig for medium-sized industrial bearings accessible at the Politecnico di Torino.https://www.mdpi.com/2076-3417/13/22/12458intelligent fault diagnosisgenerative adversarial networkscycleGANstransfer learningmachine fault diagnosisconvolutional neural networks |
| spellingShingle | Luigi Gianpio Di Maggio Eugenio Brusa Cristiana Delprete Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks Applied Sciences intelligent fault diagnosis generative adversarial networks cycleGANs transfer learning machine fault diagnosis convolutional neural networks |
| title | Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks |
| title_full | Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks |
| title_fullStr | Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks |
| title_full_unstemmed | Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks |
| title_short | Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks |
| title_sort | zero shot generative ai for rotating machinery fault diagnosis synthesizing highly realistic training data via cycle consistent adversarial networks |
| topic | intelligent fault diagnosis generative adversarial networks cycleGANs transfer learning machine fault diagnosis convolutional neural networks |
| url | https://www.mdpi.com/2076-3417/13/22/12458 |
| work_keys_str_mv | AT luigigianpiodimaggio zeroshotgenerativeaiforrotatingmachineryfaultdiagnosissynthesizinghighlyrealistictrainingdataviacycleconsistentadversarialnetworks AT eugeniobrusa zeroshotgenerativeaiforrotatingmachineryfaultdiagnosissynthesizinghighlyrealistictrainingdataviacycleconsistentadversarialnetworks AT cristianadelprete zeroshotgenerativeaiforrotatingmachineryfaultdiagnosissynthesizinghighlyrealistictrainingdataviacycleconsistentadversarialnetworks |