One of the most important issues that power companies face when trying to reduce time and cost maintenance is condition monitoring. In electricity market worldwide, a significant amount of electrical energy is produced by synchronous machines. One type of these machines is brushless synchronous generators in which the rectifier bridge is mounted on rotating shafts. Since bridge terminals are not accessible in this type of generators, it is difficult to detect the possible faults on the rectifier bridge. Therefore, in this paper, a method is proposed to facilitate the rectifier fault detection. The proposed method is then evaluated by applying two conventional kinds of faults on rectifier bridges including one diode open-circuit and two diode open-circuit (one phase open-circuit of the armature winding in the auxiliary generator in experimental set). To extract suitable features for fault detection, the wavelet transform has been used on recorded audio signals. For classifying faulty and healthy states, K-Nearest Neighbours (KNN) supervised classification method was used. The results show a good accuracy of the proposed method.
This article presents combined approach to analog electronic circuits testing by means of evolutionary methods (genetic algorithms) and using some aspects of information theory utilisation and wavelet transformation. Purpose is to find optimal excitation signal, which maximises probability of fault detection and location. This paper focuses on most difficult case where very few (usually only input and output) nodes of integrated circuit under test are available.
Wind turbines are nowadays one of the most promising energy sources. Every year, the amount of energy produced from the wind grows steadily. Investors demand turbine manufacturers to produce bigger, more efficient and robust units. These requirements resulted in fast development of condition-monitoring methods. However, significant sizes and varying operational conditions can make diagnostics of the wind turbines very challenging. The paper shows the case study of a wind turbine that had suffered a serious rolling element bearing (REB) fault. The authors compare several methods for early detection of symptoms of the failure. The paper compares standard methods based on spectral analysis and a number of novel methods based on narrowband envelope analysis, kurtosis and cyclostationarity approach. The very important problem of proper configuration of the methods is addressed as well. It is well known that every method requires setting of several parameters. In the industrial practice, configuration should be as standard and simple as possible. The paper discusses configuration parameters of investigated methods and their sensitivity to configuration uncertainties
Minimum Entropy Deconvolution (MED) has been recently introduced to the machine condition monitoring field to enhance fault detection in rolling element bearings and gears. MED proved to be an excellent aid to the extraction of these impulses and diagnosing their origin, i.e. the defective component of the bearing. In this paper, MED is revisited and re-introduced with further insights into its application to fault detection and diagnosis in rolling element bearings. The MED parameter selection as well as its combination with pre-whitening is discussed. Two main cases are presented to illustrate the benefits of the MED technique. The first one was taken from a fan bladed test rig. The second case was taken from a wind turbine with an inner race fault. The usage of the MED technique has shown a strong enhancement for both fault detection and diagnosis. The paper contributes to the knowledge of fault detection of rolling element bearings through providing an insight into the usage of MED in rolling element bearings diagnostic. This provides a guide for the user to select optimum parameters for the MED filter and illustrates these on new interesting cases both from a lab environment and an actual case.
This paper focuses on testing the monitoring system of the Direct Current motor. This system gives the possibility of diagnosing various types of failures by means of analysis of acoustic signals. The applied method is based on a study of acoustic signals generated by the DC motor. A study plan of the DC motor’s acoustic signal was proposed. Studies were conducted for a faultless DC motor and Direct Current motor with 3 shorted rotor coils. Coiflet wavelet transform and K-Nnearest neighbor classifier with Euclidean distance were used to identify the incipient fault. This approach keeps the motor operating in acceptable condition for a long time and is also inexpensive.
The paper presents a methodology for parametric fault clustering in analog electronic circuits with the use of a self-organizing artificial neural network. The method proposed here allows fast and efficient circuit diagnosis on the basis of time and/or frequency response which may lead to higher production yield. A self-organizing map (SOM) has been applied in order to cluster all circuit states into possible separate groups. So, it works as a feature selector and classifier. SOM can be fed by raw data (data comes from the time or frequency response) or some pre-processing is done at first. The author proposes conversion of a circuit response with the use of e.g. gradient and differentiation. The main goal of the SOM is to distribute all single faults on a two-dimensional map without state overlapping. The method is aimed for the development stage because the tolerances of elements are not taken into account, however single but parametric faults are considered. Efficiency analyses of fault clustering have been made on several examples e.g. a Sallen-Key BPF and an ECG amplifier. Testing procedure is performed in time and frequency domains for the Sallen-Key BPF with limited number of test points i.e. it is assumed that only input and output pins are available. A similar procedure has been applied to a real ECG amplifier in the frequency domain. Results prove a high efficiency in acceptable time which makes the method very convenient (easy and quick) as a first test in the development stage.
This article discusses a system of recognition of acoustic signals of loaded synchronous motor. This software can recognize various types of incipient failures by means of analysis of the acoustic signals. Proposed approach uses the acoustic signals generated by loaded synchronous motor. A plan of study of the acoustic signals of loaded synchronous motor is proposed. Studies include following states: healthy loaded synchronous motor, loaded synchronous motor with shorted stator coil, loaded synchronous motor with shorted stator coil and broken coil, loaded synchronous motor with shorted stator coil and two broken coils. The methods such as FFT, method of selection of amplitudes of frequencies (MSAF-5), Linear Support Vector Machine were used to identify specific state of the motor. The proposed approach can keep high recognition rate and reduce the maintenance cost of synchronous motors.
The paper focuses on the problem of robust fault detection using analytical methods and soft computing. Taking into account the model-based approach to Fault Detection and Isolation (FDI), possible applications of analytical models, and first of all observers with unknown inputs, are considered. The main objective is to show how to employ the bounded-error approach to determine the uncertainty of soft computing models (neural networks and neuro-fuzzy networks). It is shown that based on soft computing models uncertainty defined as a confidence range for the model output, adaptive thresholds can be described. The paper contains a numerical example that illustrates the effectiveness of the proposed approach for increasing the reliability of fault detection. A comprehensive simulation study regarding the DAMADICS benchmark problem is performed in the final part.
Together with the dynamic development of modern computer systems, the possibilities of applying refined methods of nonparametric estimation to control engineering tasks have grown just as fast. This broad and complex theme is presented in this paper for the case of estimation of density of a random variable distribution. Nonparametric methods allow here the useful characterization of probability distributions without arbitrary assumptions regarding their membership to a fixed class. Following an illustratory description of the fundamental procedures used to this end, results will be generalized and synthetically presented of research on the application of kernel estimators, dominant here, in problems of Bayes parameter estimation with asymmetrical polynomial loss function, as well as for fault detection in dynamical systems as objects of automatic control, in the scope of detection, diagnosis and prognosis of malfunctions. To this aim the basics of data analysis and exploration tasks - recognition of outliers, clustering and classification - solved using uniform mathematical apparatus based on the kernel estimators methodology were also investigated