In this paper, we present an analysis of important aspects that arise during the development of neural network applications. Our aim is to determine if the choice of library can impact the system’s overall performance, either during training or design, and to extract a set of criteria that could be used to highlight the advantages and disadvantages of each library under consideration. To do so, we first extracted the previously mentioned aspects by comparing two of the most popular neural network libraries—PyTorch and TensorFlow—and then we performed an analysis on the obtained results, with the intent of determining if our initial hypothesis was correct. In the end, the results of the analysis are gathered, and an overall picture of what tasks are better suited for what library is presented.
Recorded information about transmission system faults or disturbances is essential for determining the performance of system components and to analyze the nature and cause of a disturbance in energetics. The systems for disturbance recording perform the monitoring and analysis of different events specific to energetic systems. The root-mean-square (RMS) values and phase shifts of voltages and currents are widely used in post-failure analysis and for monitoring the characteristic parameters of electric lines. This paper deals with the Fourier method adequate for measurement of RMS values and phase shifts in energetic systems. Experimental results obtained using a system for disturbance recording in power stations of energetic system are also presented.
This work presents some considerations on a control method for a three-phase asynchronous motor and a time-frequency analysis of the proposed system. The control method uses the delta modulation principle to generate the command signals for a full bridge power inverter that drives three phase asynchronous motor. The time-frequency analysis can bring more new information that could be used to develop new control strategies. The operation principle and the analysis and simulation results are also presented to compare the performances of this control method versus a direct feed from mains.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.