An application of machine learning approach to fault detection of a synchronous machine

Ferreira, Jose Gregorio; Warzecha, Adam

doi:10.1109/isem.2017.7993548

Cited by 12 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jose Gregorio et al [7] have proposed a Sparse Discriminate Analysis scheme that used for both feature reduction and classification. Sparse Discriminate Analysis is used for identifying discriminate features.…”

Section: Feature Selectionmentioning

confidence: 99%

Data Fault Detection Using Minimum Redundancy Maximum Relevance in Combination with Support Vector

priya

Muthurajkumar

2022

Preprint

View full text Add to dashboard Cite

Wireless Sensor Network (WSN) refers to a network of devices that can communicate the informa- tion gathered from a monitored field through wireless links. WSNs measures environmental conditions like temperature, sound, pollution levels, humidity, wind, etc. WSN’s data fault detection is a challenging problem due to presence of sensors in unpredictable areas. The data fault detection has to be precise and accurate, so that it can be used for weather prediction, disease prediction etc. In recent years, Machine Learning plays a vital role in accurate fault Detection. To make the detection process accurate it is mandatory to reduce the number of input features to the Support Vector Machine (SVM). Minimum Redundancy Maximum Relevance (MRMR) which is an efficient feature selection algorithm is proposed in this work. The feature set is used to train the Support Vector Machine (SVM) to detect data faults. The data fault detection accuracy is calculated which shows the accuracy of 92.9% for smaller test data and accuracy of 97.2% for larger test data.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

Data Fault Detection Using Minimum Redundancy Maximum Relevance in Combination with Support Vector

priya

Muthurajkumar

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…These methods can reduce the memory computation while remaining high classification accuracy. It shows advantages comparing to linear models [38][39][40][41]. There are several different machine learning algorithms for classification problems.…”

Section: Machine Learning Algorithmsmentioning

confidence: 99%

Experimental Setup for Online Fault Diagnosis of Induction Machines via Promising IoT and Machine Learning: Towards Industry 4.0 Empowerment

et al. 2021

View full text Add to dashboard Cite

In recent years, the internet of things (IoT) represents the main core of Industry 4.0 for cyberphysic systems (CPS) in order to improve the industrial environment. Accordingly, the application of IoT and CPS has been expanded in applied electrical systems and machines. However, cybersecurity represents the main challenge of the implementation of IoT against cyber-attacks. In this regard, this paper proposes a new IoT architecture based on utilizing machine learning techniques to suppress cyber-attacks for providing reliable and secure online monitoring for the induction motor status. In particular, advanced machine learning techniques are utilized here to detect cyber-attacks and motor status with high accuracy. The proposed infrastructure validates the motor status via communication channels and the internet connection with economical cost and less effort on connecting various networks. For this purpose, the CONTACT Element platform for IoT is adopted to visualize the processed data based on machine learning techniques through a graphical dashboard. Once the cyber-attacks signal has been detected, the proposed IoT platform based on machine learning will be visualized automatically as fake data on the dashboard of the IoT platform. Different experimental scenarios with data acquisition are carried out to emphasize the performance of the suggested IoT topology. The results confirm that the proposed IoT architecture based on the machine learning technique can effectively visualize all faults of the motor status as well as the cyber-attacks on the networks. Moreover, all faults of the motor status and the fake data, due to the cyber-attacks, are successfully recognized and visualized on the dashboard of the proposed IoT platform with high accuracy and more clarified visualization, thereby contributing to enhancing the decision-making about the motor status. Furthermore, the introduced IoT architecture with Random Forest algorithm provides an effective detection for the faults on motor due to the vibration under industrial conditions with excellent accuracy of 99.03% that is significantly greater than the other machine learning algorithms. Besides, the proposed IoT has low latency to recognize the motor faults and cyber-attacks to present them in the main dashboard of the IoT platform.

show abstract

“…The Goertzel algorithm is used for the calculation, due to the increased efficiency for individual frequencies compared to the N-point Discrete Fourier Transformation [16].…”

Section: Frequency Analysismentioning

confidence: 99%

Fault Tolerant Control by Asymmetric Operation of Double Three-Phase PMSMs with Inter-Turn Faults

Foitzik

Doppelbauer

2020

2020 International Conference on Electrical Machines (ICEM)

View full text Add to dashboard Cite

Inter-turn faults are most likely the initial stator winding fault in variable speed drive systems with Voltage Source Inverters. The machine must stay within its thermal requirements locally at the fault to prevent its propagation. In this paper, we present a fault tolerant control scheme for a double three-phase Permanent Magnet Synchronous Machine which minimizes the propagation of the fault by adapting the operating points of both systems independently. We estimate the generated heat by the inter-turn fault with a machine learning regression. If the estimated heat of the faulty system is greater than a definite value, the operating point of this system is adapted until the estimated heat is below the limit. The healthy system is used to compensate the torque reduction of the faulty system. We validated the concept of the control scheme with a Finite Element Analysis simulation. The presented double threephase machine can compensate 13.9 W at nominal torque, which is an improvement of 74% compared to the equivalent single three-phase machine with the same heat limitation strategy. This heat reduction equals a temperature reduction of 111.2 K at fault locally.

show abstract

An application of machine learning approach to fault detection of a synchronous machine

Cited by 12 publications

References 13 publications

Data Fault Detection Using Minimum Redundancy Maximum Relevance in Combination with Support Vector

Data Fault Detection Using Minimum Redundancy Maximum Relevance in Combination with Support Vector

Experimental Setup for Online Fault Diagnosis of Induction Machines via Promising IoT and Machine Learning: Towards Industry 4.0 Empowerment

Fault Tolerant Control by Asymmetric Operation of Double Three-Phase PMSMs with Inter-Turn Faults

Contact Info

Product

Resources

About