AN ARTIFICIAL NEURAL NETWORKS APPROACH TO STATOR CURRENT SENSOR FAULTS DETECTION FOR DTC-SVM STRUCTURE
Journal Title: Power Electronics and Drives - Year 2016, Vol 1, Issue 1
Abstract
Background: During last few years, fault-tolerant control systems (FTCS) [1] for electric motor drives became a very active research field for many research groups. The proper choice of the fault tolerant control algorithm and topology depends on the drive system requirements and used components. To ensure the proper work of complex systems, it is necessary to take account of diagnostic techniques, that within a reasonable period of time will allow to detect a failure and an appropriate response of the control structure [2, 8, 9]. Material and methods: The main goal of the paper is selection of the most appropriate neural net-work intended for the detection and identification of stator current sensor faults. Different network structures and learning algorithms were tested. Results: Detectors based on neural networks with various learning methods and structures were presented and tested during different drive conditions. Conducted tests and obtained results may be used in designing process of advanced detection algo-rithm for Fault Tolerant drives. Conclusions: It was proved that the lowest error values and quickest response of diagnostic unit were achieved for neural network with two hidden layers learnt by Leven-berg-Marquardt algorithm. Similar results were obtained for the same network but trained by Quasi-Newton method with the BFGS algorithm.
Authors and Affiliations
Kamil Klimkowski
Keywords
Related Articles
- EP ID EP175042
- DOI -
- Views 77
- Downloads 0
REVIEW OF SOLUTIONS USED IN HIGH SPEED INDUCTION MOTOR DRIVES OPERATING IN HOUSEHOLD APPLIANCES
The paper presents the high-speed induction motor drive as a alternative for household appliances. Short comparison was made between standard and high-speed motors. The solutions that use three-phase induction motors wer...
Model Predictive Control of 4-Leg 3-Level FCC Converter - Influence of Model Parameter Mismatch
This paper presents control method of 4-leg 3-level Flying Capacitor Converter (FCC) operating as Shunt Active Pow-er Filter (SAPF), based on Model Predictive Control with Finite number of Control States (FS-MPC). Curren...
MODIFIED SCHEME OF PREDICTIVE TORQUE CONTROL FOR THREE-PHASE FOUR-SWITCH INVERTER-FED MOTOR DRIVE WITH ADAPTIVE DC-LINK VOLTAGE IMBALANCE SUPPRESSION
These instructions The classical voltage space vector modulation techniques cannot be efficiently applied in four-switch three-phase voltage inverter-fed electrical drives due to a voltage offset in DC-link capacitors. T...
State Observer for Doubly-fed Induction Generator
In the paper a new state observer for doubly-fed generator has been proposed. In the new approach an extended mathematical model of the doubly fed generator is used to form equations of the introduced z type observer. St...
UNIVERSAL SPEED AND FLUX ESTIMATOR FOR INDUCTION MOTOR
In the paper the concept of the universal speed and flux estimator with additional parameters estimators is presented. Proposed solution is based on the MRAS type flux and speed estimator and is dedicated for automotive...