Fig 4 - uploaded by C.T. Kowalski
Content may be subject to copyright.
Source publication
This paper deals with the application of the Radial Basis Function (RBF) networks for the induction motor fault detection. The rotor faults are analysed and fault symptoms are described. Next the main stages of the design methodology of the RBF-based neural detectors are described. These networks are trained and tested using measurement data of the...
Similar publications
The manufacturing of lattice structures has been greatly facilitated thanks to the advances in additive manufacturing. Functionally graded lattice (FGL) structures, a major class of such structures, developed using topology optimization (TO) are known to have superior mechanical characteristics such as high stiffness to weight ratio. A new design m...
Citations
... RBF networks are also widely discussed in literature as a tool supporting, among others, rotor fault detection of the converter-fed induction motor [25], local dynamic integration of ensemble in prediction of time series [26], predicting the corrections of the Polish time scale UTC(PL) (Universal Coordinated Time) [27], accurate load forecasting in a power system [28]. Other research papers discuss using random forests to analyse distorted data of an electronic nose for recognising the gasoline bio-based additives [29], or in evaluating the impact of explanatory variables on the accuracy of prediction of daily inflow to the sewage treatment plant [30]. ...
... ANNs were used by [32] for yield modeling, by [33] for soil moisture modeling, and by [34] for rotor fault detection. ...
... The fact that a user performs the function of an expert in these systems is another disadvantage of these approaches, which results in lengthy analysis times and a lack of automation in the detection process. Artificial intelligence approaches, particularly artificial neural networks, are being employed to reduce the role of the expert in completely automated diagnostic systems [26,27]. ...
Broken rotor bars (BRBs) in induction motors (IMs) are a common kind of failure and one of the most difficult to detect since the induction motor continues to run properly in the absence of any evidence of a malfunction. There have been several approaches presented for identifying BRBs in IMs. However, in order to parameterize the current signal, they need tools with a high computational cost, making an online implementation of the appropriate monitoring system difficult. As a result, this paper proposes a novel AI-based approach to detect and classify BRBs faults in IMs using novel multi-class datasets from two three-phase, 400V induction motors; 2.2kW, two poles, 50 Hz, 24 stator slots and with 20,29 and 32 rotor bars numbers (M24Ns,(20,29,32)Nb), and 2.2kW, four poles, 60 Hz, 36 stator slots with 28 and 44 rotor bars numbers (M36Ns, (28,44)Nb) to help in the analysis of healthy and faulty IMs, as well as classification performance evaluation and benchmarking. The developed lightweight, intelligent, and autodetection system employs a self-configurable neural network model for BRBs in IM models. It provides four classification outputs: healthy, one-BRB, two-BRBs, and three-BRBs. The simulation results characterize the performance of the (M24Ns, (20,29,32) Nb) and (M36Ns, (28,44) Nb) IMs and the combined mode for both motors, demonstrating that the proposed approach is very effective in detecting and classifying BRBs, with a 99.8 % and a prediction time of 1.64 microseconds.
... The fact that a user performs the function of an expert in these systems is another disadvantage of these approaches, which results in lengthy analysis times and a lack of automation in the detection process. Artificial intelligence approaches, particularly artificial neural networks, are being employed to reduce the role of the expert in completely automated diagnostic systems [26,27]. ...
Broken rotor bars (BRBs) in induction motors (IMs) are a common kind of failure and one of the most difficult to detect since the induction motor continues to run properly in the absence of any evidence of a malfunction. There have been several approaches presented for identifying BRBs in IMs. However, in order to parameterize the current signal, they need tools with a high computational cost, making an online implementation of the appropriate monitoring system difficult. As a result, this paper proposes a novel AI-based approach to detect and classify BRBs faults in IMs using novel multi-class datasets from two three-phase, 400V induction motors; 2.2kW, 2 poles, 50 Hz, 24 stator slots and with 20,29 and 32 rotor bars numbers (M24Ns,(20,29,32)Nb ), and 2.2kW, 4 poles, 60 Hz, 36 stator slots with 28 and 44 rotor bars numbers (M36Ns, (28,44)Nb) to help in the analysis of healthy and faulty IMs, as well as classification performance evaluation and benchmarking. The developed lightweight, intelligent, and autodetection system employs a self-configurable neural network model for BRBs in IM models. It provides four classification outputs: healthy, one-BRB, two-BRBs, and three-BRBs. The simulation results characterize the performance of the (M24Ns, (20,29,32) Nb) and (M36Ns, (28,44) Nb) IMs and the combined mode for both motors, demonstrating that the proposed approach is very effective in detecting and classifying BRBs, with a 99.8 % and a prediction time of 1.64 microseconds.
... Radial basis function (RBF) networks are also widely discussed in the literature as a tool supporting, among others, rotor fault detection of the converter fed induction motor [13], local dynamic integration of ensemble in prediction of time series [14], predicting the corrections of the Polish time scale UTC(PL) (Universal Coordinated Time) [15], or accurate load forecasting in a power system [16]. However, solutions implementing the RBFN, Kohonen networks or MLP in ecodesign are scarce. ...
A new method of selection of materials at the design step is presented in this paper. The method takes into recyclability of materials. The authors compare the effectiveness of neural networks (a multilayer perceptron, radial basis function networks, and self-organizing feature map - SOFM networks) as modelling tools aiding the selection of compatible materials in ecodesign. The best artificial neural networks were used in an expert system. The input data for the selection of materials was start point to initiate the study. The input data, specified in cooperation with designers, include both technological and environmental parameters which guarantee the desired compatibility of materials. Next, models were developed using the selected neural networks. The models were assessed and implemented into an expert system. The authors show which models best fit their purpose and why. Models aiding the compatible materials selection help boost the recycling properties of designed products. Neural networks are a very good tool to support the selection of materials in the ecodesign. This has been proven in the article.
... Another limitation of these methods is the fact that the role of an expert in such systems is played by a man, which results in extended analysis time, as well as lack of automation of the detection process. To limit the role of the expert in the fully automated diagnostic systems, artificial intelligence methods are used, especially artificial neural networks [3][4][5][6][7]. ...
... • self-organizing Kohonen maps (SOM) [8,9], • radial basis function neural network (RBF) [7,10,11]. ...
In industrial drive systems, one of the widest group of machines are induction motors. During normal operation, these machines are exposed to various types of damages, resulting in high economic losses. Electrical circuits damages are more than half of all damages appearing in induction motors. In connection with the above, the task of early detection of machine defects becomes a priority in modern drive systems. The article presents the possibility of using deep neural networks to detect stator and rotor damages. The opportunity of detecting shorted turns and the broken rotor bars with the use of an axial flux signal is presented.
... Artificial intelligence techniques, and particularly artificial neural networks, are designed to evaluate the technical condition of a machine in accordance with the input information, which is most often the result of signal analysis. In the diagnostic systems, the most popular among the known neural structures are multi-layer perceptrons [8,9], radial basis function neural networks [10], self-organizing Kohonen maps [11,12] and wavelet neural networks [13]. These structures have a common feature, which is the need to provide initial processing of the diagnostic signals to identify the symptoms that constitute the input vector of a neural network. ...
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.
... In addition to the basic MLP and SOM structures discussed here, there is a great deal of interest in the literature on neural networks with radial basis functions (RBF) [17][18][19][20]. The main difference between MLP and RBF is the activation function used in the hidden layer. ...
This article presents the efficiency of using cascaded neural structures in the process of detecting damage to electrical circuits in a squirrel cage induction motor (IM) supplied from a frequency converter. The authors present the idea of a sequential connection of classic neural structures to increase the efficiency of damage classification and detection presented by individual neural structures, especially in the initial phase of single or multiple electrical failures. The easily measurable axial flux signal is used as a source of diagnostic information. The developed cascaded neural networks are implemented in the measurement and diagnostic software made in the LabVIEW environment. The results of the experimental research on a 1.5 kW IM supplied by an industrial frequency converter confirm the high efficiency of the use of the developed cascaded neural structures in the detection of incipient stator and rotor winding faults, namely inter-turn stator winding short circuits and broken rotor bars, as well as mixed failures in the entire range of changes of the load torque and supply voltage frequency
... Meanwhile, the trial-and-error method was used in the Qlearning system to gain the fuzzy rule base. In Part II: Fuzzy Parameter Adjustment, with the decreasing of temporal-difference (TD) error, the parameters of the membership function were updated through the fuzzy RBF neural network [24]. The Q value and the stateselection of Q-learning could be obtained to adjust the Figure 11: FNNQL strategy steps. ...
... And then, the new error eðk + 1Þ and the rate of the error ecðk + 1Þ can be derived based on Equations (12) and (13). The reward value vector r can be obtained based on Equation (24). And then, according to the Bellman optimality theory [26], the time difference error of TD (0) can be described as ...
This paper addresses the disturbance change control problem with an active deformation adjustment mechanism on a 5-meter deployable antenna panel. A fuzzy neural network Q-learning control (FNNQL) strategy is proposed in this paper for the disturbance change to improve the accuracy of the antenna panel. In the proposed method, the error of the model disturbance is reduced by introducing the fuzzy radial basis function (RBF) neural network into Q-learning, and the parameters of the fuzzy RBF neural network were optimized and adjusted by a Q-learning method. This allows the FNNQL controller to have a strong adaptability to deal with the disturbance change. Finally, the proposed method has been adopted in the middle plate of a 5-meter deployable antenna panel, and it was found that the method could successfully adapt the model disturbance change in the antenna panel. Results of the simulation also show that the whole control system meets the required accuracy requirements.
... Basic SA monitoring methods are based on the classic inference rules, where expert knowledge on the diagnosed object and its ability to perceive the characteristic features of the variables describing various states of system operation are crucial [21]. Modifications of these methods with additional units of analysis and assessment of fault symptoms based on the theory of artificial intelligence (neural networks-NN, fuzzy logic-FL, and neural-fuzzy networks-NFN) are becoming increasingly popular [24][25][26][27][28][29][30][31][32][33]. These systems produce better evaluation and accurate diagnosis possibilities of the inference system based on the characteristic properties of the measured signals [19]. ...
... A schematic diagram of these diagnostic methods is presented in Figure 1. Sensors 2019, 19 FOR PEER REVIEW 3 becoming increasingly popular [24][25][26][27][28][29][30][31][32][33]. These systems produce better evaluation and accurate diagnosis possibilities of the inference system based on the characteristic properties of the measured signals [19]. ...
This paper describes a Fault Tolerant Control structure for the Induction Motor (IM) drive. We analyzed the influence of current sensor faults on the properties of the vector-controlled IM drive system. As a control algorithm, the Direct Field Oriented Control structure was chosen. For the proper operation of this system and for other vector algorithms, information about the stator currents components is required. It is important to monitor and detect these sensor faults, especially in drives with an increased safety level. We discuss the possibility of the neural network application in detecting stator current sensor faults in the vector control algorithm. Simulation and experimental results for various drive conditions are presented.
