In this article results of diagnostic investigations of separately excited DC motor were presented. In diagnostics were applied a Fourier analysis method based on the fast Fourier transform (FFT) and a recognition method using Bayes classifier. In training process a set of the most important frequencies has been determined for which differences of corresponding signals in two states are the largest. Three categories of signals have been recognized in identification process: faultless state, state of the rotor broken one coil and state of the rotor shorted three coils
An early fault diagnostic method of Direct Current motors was presented in this article. The proposed method used acoustic signals of a motor. A method of feature extraction called MSAF-RATIO30-EXPANDED (method of selection of amplitudes of frequencies – ratio 30% of maximum of amplitude – expanded) was presented and implemented. An analysis of proposed method was carried out for early fault states of a real DC motor. Four following states of the DC motor were measured and analyzed: the healthy DC motor, DC motor with 3 shorted rotor coils, DC motor with 6 shorted rotor coils, DC motor with a broken coil. Measured states were caused by natural degradation of the DC motor. The obtained results of analysis were good. The presented early fault diagnostic method can be used for protection of DC motors.
Acoustic signal is more and more frequently used to diagnose machines operated in industrial conditions where installation of sensors is hindered. Impact of background noise seems to be the major problem as part of analysis of such signal. In most cases of industrial environments, background level is high; thus, it prevents against concluding as per standard methods that have been used in diagnostic testing. This study specifies the problem related to diagnosing machines operated under variable loads. Synchronous methods are used for diagnosing these types of machines, those include synchronisation of diagnostic signal with revolutions of the diagnosed machine. For the purpose of this study an acoustic signal was used as the diagnostic signal. Application of the synchronous method (order analysis) enables eliminating an impact of background noise derived from other sources. This study specifies application of acoustic signal to diagnose planetary gear in laboratory testing rig in order to discover damages at early stage of degradation. This method was compared with the method basing on measurement of vibrations.
This paper describes a fault-tolerant controller (FTC) of induction motor (IM) with inter-turn short circuit in stator phase winding. The fault-tolerant controller is based on the indirect rotor field oriented control (IRFOC) and an observer to estimate the motor states, the amount of turns involved in short circuit and the current in the short circuit. The proposed fault controller switches between the control of the two components of measured stator current in the synchronously rotating reference frame and the control of the two components of estimated current in the case of faulty condition when the estimated current in the short circuit is not destructive of motor winding. This technique is used to eliminate the speed and the rotor flux harmonics and to assure the decoupling between the rotor flux and torque controls. The results of the simulation for controlling the speed and rotor flux of the IM demonstrate the applicability of the proposed FTC.
The paper puts forward a method of designing and creating a complete computer system for monitoring and diagnosis of business and industrial facilities, as well as for control purposes. The proposed solution represents a computer-network system being a practical tool for communication, control and management of modern plants and enterprises. The applied concept of communication, based on the Service Oriented Architecture (SOA), makes a new attempt to solve certain performance problems met when using a (previously developed) Networked Object Monitor (NOM). The principal idea of increasing the performance of NOM lies in employing a common data bus, refereed to as a Diagnostic Service Bus (DSB), in the NOM monitor. The paper also describes a preliminary concept of a network description language (SMOL), which is designed to describe the functions, mechanisms, and network devices and to be a basis for simulation and verification of the NOMmonitor function.
In this paper deep neural networks are proposed to diagnose inter-turn short-circuits of induction motor stator windings operating under the Direct Field Oriented Control method. A convolutional neural network (CNN), trained with a Stochastic Gradient Descent with Momentum method is used. This kind of deep-trained neural network allows to significantly accelerate the diagnostic process compared to the traditional methods based on the Fast Fourier Transform as well as it does not require stationary operating conditions. To assess the effectiveness of the applied CNN-based detectors, the tests were carried out for variable load conditions and different values of the supply voltage frequency. Experimental results of the proposed induction motor fault detection system are presented and discussed.