Open Access

Low-Parameter Critic-Based Multivariate WGAN Model for Clogging Detection in Drives

Artur Dawid Surówka

Artur Dawid Surówka

Corporate Technology Center, ABB Sp. z o.o. KrakówPoland
Orcid profile
Search for this author on
Sciendo|Google Scholar
Surówka, Artur Dawid
, 
Marcin Kosiba

Marcin Kosiba

Corporate Technology Center, ABB Sp. z o.o. KrakówPoland
Search for this author on
Sciendo|Google Scholar
Kosiba, Marcin
, 
Teemu Mikkelä

Teemu Mikkelä

Cadmatic OyKouvola, Finland
Search for this author on
Sciendo|Google Scholar
Mikkelä, Teemu
, 
Asko Kavala

Asko Kavala

Motion Services, ABB OyLappeenranta, Finland
Search for this author on
Sciendo|Google Scholar
Kavala, Asko
 and 
Marcin Firla

Marcin Firla

Corporate Technology Center, ABB Sp. z o.o. KrakówPoland
Search for this author on
Sciendo|Google Scholar
Firla, Marcin
  
May 17, 2025
Low-Parameter Critic-Based Multivariate WGAN Model for Clogging Detection in Drives's Cover Image
About this article
Previous Article
Next Article
Cite
Download Cover
Article Category: Special issue paper
Published Online: May 17, 2025
Page range: 125 - 139
Received: Feb 26, 2025
Accepted: Apr 17, 2025
DOI: https://doi.org/10.2478/pead-2025-0008
Keywords
© 2025 Artur Dawid Surówka et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

(a) Layout of the experimental bench; (b) graphical sketch of the setup; (c) localisation of the drive’s parts that were the focus of the study: heatsink, capacitor bank and fan with the airflow indicated and (d) localisation of PT100 temperature sensors inside the drive’s assembly: (1) heatsink temperature (outlet temperature), (2, 3, 4)—IGBT base (in the heatsink under IGBT) and (5)—heatsink temperature (inlet, fan side). DUT, device under test; IGBT, insulated gate bipolar transistor.
(a) Layout of the experimental bench; (b) graphical sketch of the setup; (c) localisation of the drive’s parts that were the focus of the study: heatsink, capacitor bank and fan with the airflow indicated and (d) localisation of PT100 temperature sensors inside the drive’s assembly: (1) heatsink temperature (outlet temperature), (2, 3, 4)—IGBT base (in the heatsink under IGBT) and (5)—heatsink temperature (inlet, fan side). DUT, device under test; IGBT, insulated gate bipolar transistor.

Figure 2.

Ambient-subtracted and scaled: (a) training (upon augmentation by 1D interpolation) and testing data involving (b) inlet, (c) outlet, (d) heatsink and (e) fan clogging scenarios.
Ambient-subtracted and scaled: (a) training (upon augmentation by 1D interpolation) and testing data involving (b) inlet, (c) outlet, (d) heatsink and (e) fan clogging scenarios.

Figure 3.

Model architecture and training scheme (the generator was consistent across all tested model architectures, and the critic, varied); the critic presented in this scheme has one filter only. OBAS, out of bounds anomaly scores.
Model architecture and training scheme (the generator was consistent across all tested model architectures, and the critic, varied); the critic presented in this scheme has one filter only. OBAS, out of bounds anomaly scores.

Figure 4.

(a) Training curve and (b) tSNE plot for the generated vs. real data for the M1 WGAN model.
(a) Training curve and (b) tSNE plot for the generated vs. real data for the M1 WGAN model.

Figure 5.

Values of critic-based OBAS for the VFD system affected by (a) heatsink; (b) outlet; (c) heatsink clogging and (d) fan blockage. The time periods during which the system operates at ambient temperatures of 25 C, 35 C and 45 C are shaded in green. Anomalous operations due to clogging are highlighted with magenta boxes. The letter ‘A’ indicates ambient temperature, while ‘C’ denotes the clogging/blockage level (50% vs. 75%). OBAS, out of bounds anomaly scores; VFD, variable frequency drive.
Values of critic-based OBAS for the VFD system affected by (a) heatsink; (b) outlet; (c) heatsink clogging and (d) fan blockage. The time periods during which the system operates at ambient temperatures of 25 C, 35 C and 45 C are shaded in green. Anomalous operations due to clogging are highlighted with magenta boxes. The letter ‘A’ indicates ambient temperature, while ‘C’ denotes the clogging/blockage level (50% vs. 75%). OBAS, out of bounds anomaly scores; VFD, variable frequency drive.

Figure 6.

Analysis of the minimal clogging/blockage level detectable in the analysed VFD under different ambient conditions: (a) 25 C, (b) 35 C, and (c) 45 C. The letter ‘C’ indicates the clogging/blockage level for which the data are presented. OBAS, out of bounds anomaly scores; VFD, variable frequency drive.
Analysis of the minimal clogging/blockage level detectable in the analysed VFD under different ambient conditions: (a) 25 C, (b) 35 C, and (c) 45 C. The letter ‘C’ indicates the clogging/blockage level for which the data are presented. OBAS, out of bounds anomaly scores; VFD, variable frequency drive.

Comparison of complexities of the critic models_

Architecture No. all parameters No. of trainable parameters Size in Kb (tflite)
M1 26 32 5.97
M4 173 197 6.46
M8 537 585 7.79

Outcomes of the performance assessment of the M1 model_

Type Phase ACC TPR FNR PPV F1
Inlet Start 0.78 0.79 0.21 0.86 0.83
Cooling 0.78 0.84 0.16 0.83 0.84
Active 0.57 0.36 0.64 0.91 0.51
Outlet Start 0.65 0.55 0.45 0.81 0.65
Cooling 0.67 0.67 0.32 0.80 0.73
Active 0.44 0.14 0.85 0.82 0.24
Heatsink Start 0.90 0.98 0.02 0.88 0.93
Cooling 0.88 1.00 0.00 0.84 0.91
Active 0.53 0.95 0.69 0.91 0.46
Fan Start 0.87 1.00 0.00 0.79 0.86
Cooling 0.84 1.00 0.00 0.76 0.86
Active 0.66 0.32 0.68 1.00 0.48
Language:
English
Publication timeframe:
1 times per year
Journal Subjects:
Computer Sciences, Artificial Intelligence, Engineering, Electrical Engineering, Electronics
Journal RSS Feed