Fault Detection in Soft-started Induction Motors using Convolutional Neural Network Enhanced by Data Augmentation Techniques

Pasqualotto, Dario; Navarro-Navarro, Angela; Zigliotto, M.; Antonino-Daviu, Jose A.; Biot-Monterde, Vicente

doi:10.1109/iecon48115.2021.9589439

Cited by 7 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With regards to the accuracy of the methodologies, some of the works in Table 9 achieved a rate of 100% [ 22 , 23 , 49 ], but all of them were focused on DOL starting, and they were analyzing current signals. On the other hand, those works focused on soft-started induction motors and achieved, in both cases, an overall accuracy of 94.40%, analyzing the stray-flux [ 27 ] and the combination of stray-flux and current [ 28 ]. Both of them relied on the STFT as the time–frequency analysis tool, which displays noisy time–frequency maps when soft starters are used, making it more difficult to identify the typical patterns related to broken bars.…”

Section: Resultsmentioning

confidence: 99%

“…Thus, it is important to obtain new methods that could lead to automatically identifying the presence of these faults, before a catastrophic failure occurs, when soft starters are used. In this regard, in [ 27 ], the authors proposed the use of a CNN, applied to the stray-flux signals, as a method to detect the presence and the severity of bar breakages in induction motors driven by soft starters. The accuracy rate achieved in this work was 94.40%.…”

Section: Introductionmentioning

confidence: 99%

“…In this regard, Data Augmentation Techniques (DAT) have been proven to be a reliable way to enhance the data base used in CNN. In [ 18 , 27 ] it was stated that the use of Data Augmentation Techniques is a reliable method to deal with the scarcity of samples, providing a good dataset to use in a CNN. In particular, adding Gaussian noise to a signal is one of the DAT that is commonly employed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic Classification of Rotor Faults in Soft-Started Induction Motors, Based on Persistence Spectrum and Convolutional Neural Network Applied to Stray-Flux Signals

Biot-Monterde

Navarro-Navarro

Zamudio-Ramírez

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Due to their robustness, versatility and performance, induction motors (IMs) have been widely used in many industrial applications. Despite their characteristics, these machines are not immune to failures. In this sense, breakage of the rotor bars (BRB) is a common fault, which is mainly related to the high currents flowing along those bars during start-up. In order to reduce the stresses that could lead to the appearance of these faults, the use of soft starters is becoming usual. However, these devices introduce additional components in the current and flux signals, affecting the evolution of the fault-related patterns and so making the fault diagnosis process more difficult. This paper proposes a new method to automatically classify the rotor health state in IMs driven by soft starters. The proposed method relies on obtaining the Persistence Spectrum (PS) of the start-up stray-flux signals. To obtain a proper dataset, Data Augmentation Techniques (DAT) are applied, adding Gaussian noise to the original signals. Then, these PS images are used to train a Convolutional Neural Network (CNN), in order to automatically classify the rotor health state, depending on the severity of the fault, namely: healthy motor, one broken bar and two broken bars. This method has been validated by means of a test bench consisting of a 1.1 kW IM driven by four different soft starters coupled to a DC motor. The results confirm the reliability of the proposed method, obtaining a classification rate of 100.00% when analyzing each model separately and 99.89% when all the models are analyzed at a time.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Classification of Rotor Faults in Soft-Started Induction Motors, Based on Persistence Spectrum and Convolutional Neural Network Applied to Stray-Flux Signals

Biot-Monterde

Navarro-Navarro

Zamudio-Ramírez

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…A similar approach, but for working with soft start systems, can be applied at the next stages of the study. Along with control algorithms for soft starters of IMs based on an ANN [32][33][34][35], artificial intelligence systems [36], observers [37] and fuzzy control [38] are also used.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the Control System for a Soft Starter of an Induction Motor Based on a Multi-Zone AC Voltage Converter

Kosykh¹,

Udovichenko²,

Lopatkin³

et al. 2022

Preprint

View full text Add to dashboard Cite

The development trends of the modern world of power electronics dictate the requirements for the use of AC voltage converters as soft starters for induction motors. A direct connection of the motors to the mains voltage negatively affects both the motor itself and the mains system as a whole due to high starting currents values, which entail, as a rule, more frequent accidents and shorter the drive system service life. The paper presents a study of the control system of a multi-zone AC voltage regulator. The use of capacitive voltage dividers will also compensate for the consumed reactive power. The article analyzes the features of modern soft starters, describes the circuit design, presents a mathematical calculation by the method of algebraization of differential equations, a performed simulation modeling in Matlab/Simulink, and also an assembled experimental stand for further research. Particular attention is paid to the definition of the multizonality concept of the proposed converter and the analysis of the control method. The developed algorithm of the double-loop automatic control system will minimize the influence of induction motors on the mains voltage, and thus improve electromagnetic compatibility.

show abstract

Data augmentation in predictive maintenance applicable to hydrogen combustion engines: a review

Schwarz,

Rahal,

Sahelices

et al. 2024

Artif Intell Rev

View full text Add to dashboard Cite

Machine-learning-based predictive maintenance models, i.e. models that predict breakdowns of machines based on condition information, have a high potential to minimize maintenance costs in industrial applications by determining the best possible time to perform maintenance. Modern machines have sensors that can collect all relevant data of the operating condition and for legacy machines which are still widely used in the industry, retrofit sensors are readily, easily and inexpensively available. With the help of this data it is possible to train such a predictive maintenance model. The main problem is that most data is obtained from normal operating conditions, whereas only limited data are from failures. This leads to highly unbalanced data sets, which makes it very difficult, if not impossible, to train a predictive maintenance model that can detect faults reliably and timely. Another issue is the lack of available real data due to privacy concerns. To address these problems, a suitable data generation strategy is needed. In this work, a literature review is conducted to identify a solution approach for a suitable data augmentation strategy that can be applied to our specific use case of hydrogen combustion engines in the automotive field. This literature review shows that, among the different state-of-the-art proposals, the most promising for the generation of reliable synthetic data are the ones based on generative models. The analysis of the different metrics used in the state of the art allows to identify the most suitable ones to evaluate the quality of generated signals. Finally, an open problem in research in this area is identified and it is the need to validate the plausibility of the data generated. The generation of results in this area will contribute decisively to the development of predictive maintenance models.

show abstract

Fault Detection in Soft-started Induction Motors using Convolutional Neural Network Enhanced by Data Augmentation Techniques

Cited by 7 publications

References 14 publications

Automatic Classification of Rotor Faults in Soft-Started Induction Motors, Based on Persistence Spectrum and Convolutional Neural Network Applied to Stray-Flux Signals

Automatic Classification of Rotor Faults in Soft-Started Induction Motors, Based on Persistence Spectrum and Convolutional Neural Network Applied to Stray-Flux Signals

Analysis of the Control System for a Soft Starter of an Induction Motor Based on a Multi-Zone AC Voltage Converter

Data augmentation in predictive maintenance applicable to hydrogen combustion engines: a review

Contact Info

Product

Resources

About