Amir Tabatabaei

A traveling-wave fault location technique for three-terminal lines based on wavelet analysis and Recurrent Neural Network using GPS timing

One of the most important features of smart distribution networks is handling fault situations in an efficient way. This paper describes a fault location algorithm for three-terminal transmission lines based on wavelet transform and Artificial Neural Network (ANN). Because of small size data base, Recurrent Neural Network (RNN) was utilized and for the purpose of synchronized time tagging, the Global Positioning System (GPS) with the highly-accurate timing capabilities is used. All the possible fault types are generated using the ATP-EMTP and results are discussed. Extensive simulation studies indicate that proposed network estimate fault location in different conditions with average error percentage less than 0.15% though practical limitations.

Rapid and Precise GLONASS GDOP Approximation using Neural Networks

Russian global navigation satellite system (GLONASS) provides civilian and military users three-dimensional position determination and navigation services as same as US global positioning system. Geometric dilution of precision (GDOP) provides a simple interpretation of positioning precision. Usual method for GLONASS GDOP calculation is matrix inversion. However this process imposes a huge calculation load on receiver, especially when large number of visible satellites exists. To overcome this problem, artificial neural network is used. Different configurations and training methods are simulated on a data base obtained by a GLONASS receiver. Then navigation precision and execution times are explored and compared. Results show that recurrent neural network has 0.00024 RMS error, which is the best against other focused tools including feed forward back propagation and radial basis function neural network with usual training and with genetic algorithm adopted weights and biases.

Evaluating different types of artificial neural network structures for performance prediction of compact heat exchanger

In the present work, the performance of an air-to-refrigerant laminated type evaporator is predicted using a genetic algorithm (GA)-integrated feed-forward neural network (FFNN) and recurrent neural network (RNN). The obtained results are compared with the results of the FFNN with back-propagation learning algorithm, as the most recommended algorithm in the literature. The considered evaporator consists of single-phase and two-phase regions in the refrigerant side which makes the ANN-based methods so suitable for its modeling. To train the mentioned neural networks, the steady-state experimental data of the evaporator performance include capacity, outlet refrigerant pressure and temperature and outlet air dry- and wet-bulb temperatures is collected with varying input parameters. The results show a good agreement with experimental data, and it is observed that RNN-based method has the best average root-mean-square error (1.169 against 5.017, 4.791 and 2.286 for FFNN, GA-trained FFNN and numerical modeling, respectively). In fact, using GA to optimize FFNN structure makes better results than conventional FFNN, but the RNN method provides the best results because of using suitable intelligent configuration. Also, in contrary to numerical method, it is much faster and calculation processing load is lower. Therefore, RNN is proposed as a substitute for FFNN and the GA-trained FFNN. Finally, a sensitivity analysis determined the inlet refrigerant pressure as the most important parameter in predicting the evaporator capacity.

A Fast GLONASS FDMA Acquisition Algorithm Using Multi-Satellite Search Strategy

Integration of US global positioning system with other existing global navigation satellite system such as recently-augmented Russian Global Navigation Satellite System (GLONASS) suffers calculation time cost in software platforms. Acquisition stage as the first part of a software receiver is a challenging part for increasing the speed. In this paper, a rapid GLONASS acquisition algorithm is proposed using multi-satellite search strategy. The proposed algorithm divides satellites in multi-groups and generates a local replica for them. Analyzing of the received signal and this replica correlation will show whether this group has in-view satellites or not. Simulations on real data base created using an AAA GLONASS receiver prove the positive effect of this algorithm in speeding up the receiver acquisition to about 2.32 with least misdetection probability.

Vectorized and federated software receivers combining GLONASS and GPS

In traditional federated receiver, all the tracking channels work independently, and there is no interaction among them. However, in vectorized receiver, stronger channels aid others in their tracking. Such architecture makes a receiver to be of interest for positioning in urban canyons and harsh environments. On the other hand, the combination of GPS and GLONASS as the only augmented global constellations is utilized to increase the availability of the receivers which is defined as the percentage of the epochs with enough number of tracked satellites for solving the positioning equation. We report about the software implementation of a GPS-combined-GLONASS Vectorized Receiver (GGVR) and performance assessment of this architecture in signal attenuation and blocking incidents. We also compare the GGVR performance with a GPS-combined-GLONASS Federated Receiver (GGFR). Experimental tests in different case studies are included. The results show that in the static blocking situation, the GGVR can reacquire the signal immediately after the momentary outage while the GGFR must return to acquisition stage. For two dynamic case studies, one in a suburban road and one in an urban canyon, the position results on the road are the same, but in an urban environment, the GGFR has only 88% availability in contrast to 100% availability of the GGVR.

Performance analysis of GLONASS integration with GPS vectorised receiver in urban canyon positioning

Urban-canyon positioning encounters many problems such as successive attenuation and even blocking of the signals. Vectorised receiver is a solution in which stronger signals aid weak and blocked ones to be tracked and reacquired. On the other hand, limited accessibility to the sky makes trouble in the performance of navigation filter. As the result, integration of satellite-based positioning systems is suggested to increase the number of visible satellites in the receiver view. In this paper, the architecture of an implemented GPS-combined-GLONASS Vectorised Receiver (GGVR) in a software platform is explored and its advantages rather than a GPS-only Vectorised Receiver (GVR) are demonstrated analytically. Experimental tests in different static and dynamic scenarios are also included. The results show that in the urban-canyon trajectory where the GVR has only 80% availability, the GGVR positioning solution is 100% available in the whole movement duration.