Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network

Liu, Xiangqun; Zhang, Hongyue; Liu, Jun; Yang, Jing

doi:10.1109/41.873210

Cited by 142 publications

(18 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the model (29)- (32) has a direct relation to the motor physical parameters, the true relation between them is nonlinear. There are many nonlinear factors in the motor, e.g., the nonlinearity of the magnetization characteristic of the material, the effect of material reaction, the effect caused by an eddy current in the magnet, residual magnetism, the commutator characteristic, mechanical frictions (Xiang-Qun and Zhang, 2000). These factors are not shown in the model (29)- (32).…”

Section: Methodsmentioning

confidence: 99%

Local stability conditions for discrete-time cascade locally recurrent neural networks

Patan¹

2010

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

The paper deals with a specific kind of discrete-time recurrent neural network designed with dynamic neuron models. Dynamics are reproduced within each single neuron, hence the network considered is a locally recurrent globally feedforward. A crucial problem with neural networks of the dynamic type is stability as well as stabilization in learning problems. The paper formulates local stability conditions for the analysed class of neural networks using Lyapunov's first method. Moreover, a stabilization problem is defined and solved as a constrained optimization task. In order to tackle this problem, a gradient projection method is adopted. The efficiency and usefulness of the proposed approach are justified by using a number of experiments.

show abstract

Section: Methodsmentioning

confidence: 99%

Local stability conditions for discrete-time cascade locally recurrent neural networks

Patan¹

2010

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

show abstract

“…Therefore, there is a need to detect and isolate faults as early as possible. Recently, a great deal of attention has been paid to electrical motor fault diagnosis (Nandi et al, 2005;Li et al, 2004;Moseler and Isermann, 2000;Xiang-Qun and Zhang, 2000;Fuessel and Isermann, 2000). In general, the elaborated solutions can be splitted into three categories: signal analysis methods, knowledge based methods and model based approaches (Xiang-Qun and Zhang, 2000;Korbicz et al, 2004).…”

Section: Neural Network Based Fault Diagnosis Of a DC Motormentioning

confidence: 99%

Towards Robustness in Neural Network Based Fault Diagnosis

Patan¹,

Witczak²,

Korbicz³

2008

International Journal of Applied Mathematics and Computer Science

View full text Add to dashboard Cite

Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as neural networks become more and more popular in industrial applications of fault diagnosis. Taking into account the two crucial aspects, i.e., the nonlinear behaviour of the system being diagnosed as well as the robustness of a fault diagnosis scheme with respect to modelling uncertainty, two different neural network based schemes are described and carefully discussed. The final part of the paper presents an illustrative example regarding the modelling and fault diagnosis of a DC motor, which shows the performance of the proposed strategy.

show abstract

“…[3] In the automotive industry the reason why there is a growing need for the development of the procedures for fault detection and diagnosis, in order to increase reliability and the availability of the electric motors part's of the automobile with the purpose of reducing the maintenance costs for the car. [4], [5] Also, an early detection and diagnosis can help avoid car's system breakdown and material damage, [6], [7] II. VIBRATION AND CURRENT ELECTRICAL EQUIPMENT DIAGNOSTICS Basically, vibration is oscillating motion of a particle or body about a fixed reference point.…”

Section: Introductionmentioning

confidence: 99%

Study of DC motor diagnosis based on the vibration spectrum and current analysis

Iorgulescu

Beloiu

2012

2012 International Conference on Applied and Theoretical Electricity (ICATE)

View full text Add to dashboard Cite

In this paper fault detection of permanent magnet dc motor is described. In past, Current Signature Analysis (CSA) has become an established tool for online fault analysis of AC induction motors. Presently, very little research has been performed using current signature analysis on DC motors. This paper is a brief introduction to fault diagnosis of DC motors using vibration and current signature analysis. In order to do the diagnostics there are analyzed vibration from the piezoelectric accelerometer. The accelerometer is mounted on the frame's motor. Also, for the current measurement it's used ampere sensor. Initially the measurements were realized by using "healthy" DC motor. Then we made successive measurements for the same type of motor with provoked faults. The many faults of DC motors are regarding collectors motor, the commutator short circuit and displaced permanent magnet out of poles in polar axe. We observe significant vibration and also current spectrum differences between "healthy" motors and faulty electrical motor. The spectral analysis of current and vibration provides a method to detect DC motors faults. Using these methods, diagnostic of commutator short circuit and displaced permanent magnet out of poles in polar axe, would be detected even if the motor operated unload.

show abstract

Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network

Cited by 142 publications

References 10 publications

Local stability conditions for discrete-time cascade locally recurrent neural networks

Local stability conditions for discrete-time cascade locally recurrent neural networks

Towards Robustness in Neural Network Based Fault Diagnosis

Study of DC motor diagnosis based on the vibration spectrum and current analysis

Contact Info

Product

Resources

About