# CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles’ Machine

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Materials and Methods

#### 2.1. Powertrain of an Electric Vehicl Jmghj

#### Electrolytic Capacitor

#### 2.2. Accelerated Aging Tests

#### Laboratory Setup

#### 2.3. Proposed Approach

_{0}) and the maximum (lb) and minimum (ub) values are set. Then, the degradation process of the electrolytic capacitor starts, and every 30 min the parameters are identified based on the non-invasive measurements of the converter. This is done until the accelerated aging test reaches a certain limit time. At the end of each iteration, the capacitance and ESR values are stored, while the initial, minimum and maximum values of the parameters are updated for the next identification. As mentioned in Section 2.2, the values of the capacitance and resistance are also measured using a specialized device to validate the accuracy of the parameter estimation method.

#### 2.3.1. Parameter Estimation Based on Nonlinear Least Squares Optimization

#### 2.3.2. Capacitance and ESR Forecasting Based on CNN-LSTM

## 3. Results

^{2}) since both assess the quality of the regression when compared to the actual values [38]. All models were programmed and trained using Python and it was carried out by means of a GeForce RTX 2080 Super GPU.

^{2}closer to 1 in the predictions made using the test dataset. The higher accuracy of the proposed method is also appreciated in Figure 12, where the model is capable of replicating the behavior of the electrolytic capacitor, even when it is tested with a set of data that was not used in the training process. The training time of the proposed method is longer than that of the LSTM approach, but lower than that of the CNN neural network. However, the time elapsed is relatively low considering that the proposed model consists of two hidden layers with different architecture.

## 4. Discussion

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Conflicts of Interest

## References

- Ma, S.; Cai, W.; Liu, W.; Shang, Z.; Liu, G. A lighted deep convolutional neural network based fault diagnosis of rotating machinery. Sensors
**2019**, 19, 2381. [Google Scholar] [CrossRef] [Green Version] - Martinez, D.; Henao, H.; Capolino, G.A. Overview of Condition Monitoring Systems for Power Distribution Grids. In Proceedings of the 2019 IEEE 12th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives, SDEMPED 2019, Toulouse, France, 27–30 August 2019; Institute of Electrical and Electronics Engineers Inc.: Buenos Aires, Argentina, 2019; pp. 160–166. [Google Scholar]
- Wei, Y.; Wu, D.; Terpenny, J. Robust Incipient Fault Detection of Complex Systems Using Data Fusion. IEEE Trans. Instrum. Meas.
**2020**, 69, 9526–9534. [Google Scholar] [CrossRef] - Martínez, J.; Riba, J.R.; Moreno-Eguilaz, M. State of health prediction of power connectors by analyzing the degradation trajectory of the electrical resistance. Electronics
**2021**, 10, 1409. [Google Scholar] [CrossRef] - Frosini, L. Monitoring and Diagnostics of Electrical Machines and Drives: A State of the Art. In Proceedings of the 2019 IEEE Workshop on Electrical Machines Design, Control and Diagnosis, WEMDCD 2019, Athens, Greece, 22–23 April 2019; Institute of Electrical and Electronics Engineers Inc.: Buenos Aires, Argentina, 2019; pp. 169–176. [Google Scholar]
- Gonzalez-Jimenez, D.; Del-Olmo, J.; Poza, J.; Garramiola, F.; Madina, P. Data-driven fault diagnosis for electric drives: A review. Sensors
**2021**, 21, 4024. [Google Scholar] [CrossRef] [PubMed] - Alam, M.K.; Khan, F.H. Reliability Analysis and Performance Degradation of a Boost Converter. IEEE Trans. Ind. Appl.
**2014**, 50, 3986–3994. [Google Scholar] [CrossRef] - Yang, S.; Bryant, A.; Mawby, P.; Xiang, D.; Ran, L.; Tavner, P. An industry-based survey of reliability in power electronic converters. IEEE Trans. Ind. Appl.
**2011**, 47, 1441–1451. [Google Scholar] [CrossRef] - Yang, S.; Xiang, D.; Bryant, A.; Mawby, P.; Ran, L.; Tavner, P. Condition monitoring for device reliability in power electronic converters: A review. IEEE Trans. Power Electron.
**2010**, 25, 2734–2752. [Google Scholar] [CrossRef] - Pecht, M.G.; Kang, M. Prognostics and Health Management of Electronics; Pecht, M.G., Kang, M., Eds.; John Wiley and Sons Ltd.: Chichester, UK, 2018; ISBN 9781119515326. [Google Scholar]
- Yuan, W.; Wang, T.; Diallo, D.; Delpha, C. A fault diagnosis strategy based on multilevel classification for a cascaded photovoltaic grid-connected inverter. Electronics
**2020**, 9, 429. [Google Scholar] [CrossRef] [Green Version] - Dang, H.L.; Kwak, S. Review of health monitoring techniques for capacitors used in power electronics converters. Sensors
**2020**, 20, 3740. [Google Scholar] [CrossRef] [PubMed] - Luchetta, A.; Manetti, S.; Piccirilli, M.C.; Reatti, A.; Corti, F.; Catelani, M.; Ciani, L.; Kazimierczuk, M.K. MLMVNNN for Parameter Fault Detection in PWM DC-DC Converters and Its Applications for Buck and Boost DC-DC Converters. IEEE Trans. Instrum. Meas.
**2019**, 68, 439–449. [Google Scholar] [CrossRef] - Cheng, Y.; Wu, J.; Zhu, H.; Or, S.W.; Shao, X. Remaining Useful Life Prognosis Based on Ensemble Long Short-Term Memory Neural Network. IEEE Trans. Instrum. Meas.
**2020**, 70, 3503912. [Google Scholar] [CrossRef] - Slade, P.G. Electrical Contacts: Principles and Applications, 2nd ed.; CRC Press: Boca Raton, FL, USA, 2017. [Google Scholar]
- Gómez-Pau, Á.; Riba, J.-R.; Moreno-Eguilaz, M. Time Series RUL Estimation of Medium Voltage Connectors to Ease Predictive Maintenance Plans. Appl. Sci.
**2020**, 10, 9041. [Google Scholar] [CrossRef] - Rojas-Dueñas, G.; Riba, J.-R.; Moreno-Eguilaz, M. Modeling of a DC-DC Bidirectional Converter used in Mild Hybrid Electric Vehicles from Measurements. Measurement
**2021**, 183, 109838. [Google Scholar] [CrossRef] - Rojas-Duenas, G.; Riba, J.-R.; Kahalerras, K.; Moreno-Eguilaz, M.; Kadechkar, A.; Gomez-Pau, A. Black-Box Modelling of a DC-DC Buck Converter Based on a Recurrent Neural Network. In Proceedings of the 2020 IEEE International Conference on Industrial Technology (ICIT), Buenos Aires, Argentina, 26–28 February 2020; Institute of Electrical and Electronics Engineers (IEEE): Buenos Aires, Argentina, 2020; pp. 456–461. [Google Scholar]
- Doucoure, B.; Agbossou, K.; Cardenas, A. Time series prediction using artificial wavelet neural network and multi-resolution analysis: Application to wind speed data. Renew. Energy
**2016**, 92, 202–211. [Google Scholar] [CrossRef] - Poon, J.; Jain, P.; Spanos, C.; Panda, S.K.; Sanders, S.R. Fault Prognosis for Power Electronics Systems Using Adaptive Parameter Identification. IEEE Trans. Ind. Appl.
**2017**, 53, 2862–2870. [Google Scholar] [CrossRef] - Riba, J.-R.; Gómez-Pau, Á.; Martínez, J.; Moreno-Eguilaz, M. On-Line Remaining Useful Life Estimation of Power Connectors Focused on Predictive Maintenance. Sensors
**2021**, 21, 3739. [Google Scholar] [CrossRef] - Ordóñez, C.; Sánchez Lasheras, F.; Roca-Pardiñas, J.; de Cos Juez, F.J. A hybrid ARIMA–SVM model for the study of the remaining useful life of aircraft engines. J. Comput. Appl. Math.
**2019**, 346, 184–191. [Google Scholar] [CrossRef] - Zhou, Y.; Huang, M. Lithium-ion batteries remaining useful life prediction based on a mixture of empirical mode decomposition and ARIMA model. Microelectron. Reliab.
**2016**, 65, 265–273. [Google Scholar] [CrossRef] - Kulkarni, C.; Biswas, G.; Saha, S.; Goebel, K. A Model-based Prognostics Methodology for Electrolytic Capacitors Based on Electrical Overstress Accelerated Aging. In Proceedings of the Annual Conference of the Prognostics and Health Management Society, Montreal, QC, Canada, 25–29 September 2011; Volume 3. [Google Scholar] [CrossRef]
- Kulkarni, C.S.; Biswas, G.; Koutsoukos, X. A Prognosis Case Study for Electrolytic Capacitor Degradation in DC-DC Converters. In Proceedings of the Annual Conference of the Prognostics and Health Management Society, San Diego, CA, USA, 27 September–1 October 2009. [Google Scholar]
- Al, M.; Van, J.; Gualous, H. DC/DC Converters for Electric Vehicles. Electr. Veh.-Model. Simul.
**2011**, 100, 466. [Google Scholar] [CrossRef] [Green Version] - Zhuang, W.; Li (Eben), S.; Zhang, X.; Kum, D.; Song, Z.; Yin, G.; Ju, F. A survey of powertrain configuration studies on hybrid electric vehicles. Appl. Energy
**2020**, 262, 114553. [Google Scholar] [CrossRef] - Perdigão, M.S.; Trovão, J.P.F.; Alonso, J.M.; Saraiva, E.S. Large-Signal Characterization of Power Inductors in EV Bidirectional DC-DC Converters Focused on Core Size Optimization. IEEE Trans. Ind. Electron.
**2015**, 62, 3042–3051. [Google Scholar] [CrossRef] - Celaya, J.R.; Kulkarni, C.; Biswas, G.; Goebel, K. Towards prognostics of electrolytic capacitors. Infotech Aerosp.
**2011**, 2011, 1519. [Google Scholar] [CrossRef] [Green Version] - Agarwal, N.; Ahmad, M.W.; Anand, S. Quasi-Online Technique for Health Monitoring of Capacitor in Single-Phase Solar Inverter. IEEE Trans. Power Electron.
**2018**, 33, 5283–5291. [Google Scholar] [CrossRef] - Kulkarni, C.; Biswas, G.; Koutsoukos, X.; Celaya, J.; Goebel, K. Integrated diagnostic/prognostic experimental setup for capacitor degradation and health monitoring. In Proceedings of the 2010 AUTOTESTCON, Orlando, FL, USA, 13–16 September 2010; pp. 351–357. [Google Scholar] [CrossRef] [Green Version]
- Rojas-Dueñas, G.; Riba, J.-R.; Moreno-Eguilaz, M. Non-Linear Least Squares Optimization for Parametric Identification of DC-DC Converters. IEEE Trans. Power Electron.
**2021**, 36, 654–661. [Google Scholar] [CrossRef] - Rojas-Dueñas, G.; Riba, J.R.; Moreno-Eguilaz, M. Parameter estimation of a single-phase boost pfc converter with emi filter based on an optimization algorithm. Electronics
**2021**, 10, 1231. [Google Scholar] [CrossRef] - He, F.; Zhou, J.; Feng, Z.K.; Liu, G.; Yang, Y. A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm. Appl. Energy
**2019**, 237, 103–116. [Google Scholar] [CrossRef] - Rawat, W.; Wang, Z. Deep convolutional neural networks for image classification: A comprehensive review. Neural Comput.
**2017**, 29, 2352–2449. [Google Scholar] [CrossRef] - Qin, D.; Yu, J.; Zou, G.; Yong, R.; Zhao, Q.; Zhang, B. A Novel Combined Prediction Scheme Based on CNN and LSTM for Urban PM2.5 Concentration. IEEE Access
**2019**, 7, 20050–20059. [Google Scholar] [CrossRef] - Yu, Y.; Si, X.; Hu, C.; Zhang, J. A review of recurrent neural networks: Lstm cells and network architectures. Neural Comput.
**2019**, 31, 1235–1270. [Google Scholar] [CrossRef] - Renaud, O.; Victoria-Feser, M.P. A robust coefficient of determination for regression. J. Stat. Plan. Inference
**2010**, 140, 1852–1862. [Google Scholar] [CrossRef] [Green Version]

**Figure 11.**Measured and estimated values during the accelerated aging test. (

**a**) Capacitance; (

**b**) ESR.

**Figure 12.**Prediction of the future values of (

**a**) Capacitance; (

**b**) Equivalent series resistance of the electrolytic capacitor.

**Figure 13.**Measured signals versus the estimated ones with the CNN-LSTM NN. (

**a**) Input voltage; (

**b**) Input current; (

**c**) Output voltage; (

**d**) Output voltage.

Parameter | Minimum | Maximum | Optimal |
---|---|---|---|

Kernel size | 1 | 15 | 4 |

LSTM neurons | 1 | 100 | 31 |

n | 20 | 100 | 56 |

m | 1 | 40 | 12 |

Method | Capacitance | ESR | Time Elapsed | ||
---|---|---|---|---|---|

RMSE | R^{2} | RMSE | R^{2} | ||

CNN-LSTM | 0.00042 | 0.995 | 0.0016 | 0.990 | 12.2 s |

NARX | 0.00080 | 0.825 | 0.0055 | 0.846 | 66 s |

LSTM | 0.00056 | 0.961 | 0.0035 | 0.944 | 8.03 s |

CNN | 0.00121 | 0.774 | 0.0094 | 0.790 | 12.8 s |

ARIMA | 0.00065 | 0.949 | 0.0032 | 0.951 | 4.7 s |

Kalman filter | 0.00071 | 0.938 | 0.0041 | 0.932 | 2.8 s |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Rojas-Dueñas, G.; Riba, J.-R.; Moreno-Eguilaz, M.
CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles’ Machine. *Sensors* **2021**, *21*, 7079.
https://doi.org/10.3390/s21217079

**AMA Style**

Rojas-Dueñas G, Riba J-R, Moreno-Eguilaz M.
CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles’ Machine. *Sensors*. 2021; 21(21):7079.
https://doi.org/10.3390/s21217079

**Chicago/Turabian Style**

Rojas-Dueñas, Gabriel, Jordi-Roger Riba, and Manuel Moreno-Eguilaz.
2021. "CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles’ Machine" *Sensors* 21, no. 21: 7079.
https://doi.org/10.3390/s21217079