Identification of the State of Electrical Appliances with the Use of a Pulse Signal Generator

Abstract

The paper presents the novel HF-GEN method for determining the characteristics of Electrical Appliance (EA) operating in the end-user environment. The method includes a measurement system that uses a pulse signal generator to improve the quality of EA identification. Its structure and the principles of operation are presented. A method for determining the characteristics of the current signals’ transients using the cross-correlation is described. Its result is the appliance signature with a set of features characterizing its state of operation. The quality of the obtained signature is evaluated in the standard classification task with the aim of identifying the particular appliance’s state based on the analysis of features by three independent algorithms. Experimental results for 15 EAs categories show the usefulness of the proposed approach.

Application of the Time-Domain Signal Analysis for Electrical Appliances Identification in the Non-Intrusive Load Monitoring

“…The highest accuracy (ratio of the correctly identified events) was 98.80%, which was achieved for f s = 250 kHz and 23rd order median filter. Detailed results are presented using the confusion matrix, where the main diagonal represents the correct classifications (True Positive-TP) and the other values represent misclassifications [22,46]. Figures 9 and 10 show confusion matrices for particular events in the optimal combination of the filter's length and sampling frequency (switching devices on and off, respectively).…”

“…Even when STFT (Short-Time Fourier Transform) is applied, information about the time instant of the sample's value changes is lost (only frequency components remain). Partly, this problem can be solved by using the Wavelet Transform (WT), which uses a variablewidth analysis window [21,22]. The NILM methods using WT are vulnerable to changes in the background signal [22].…”

“…Partly, this problem can be solved by using the Wavelet Transform (WT), which uses a variablewidth analysis window [21,22]. The NILM methods using WT are vulnerable to changes in the background signal [22]. In the MF group, to which the method described in this paper belongs to, the typical features are current harmonic components [23][24][25], which are often calculated using FFT for the window of a couple of milliseconds duration.…”

Potential and Opportunities of Use of Postindustrial Buildings and Territories for Urban Development: Case Studies of the Historical Area in Lviv (Ukraine)

“…"The order of urban renewal" was presented as a set of aesthetic preferences, expertise, state policy, and local government [8][9][10]. Recent discoveries and inventions such as new construction materials, artificial intelligence [11][12][13], concepts of the internet of things, and smart cities [11,[14][15][16] are rapidly changing the architecture and operating principles of cities [17]. That is why relevant and effective strategies for preserving their historical heritage are needed.…”

International Journal of Electronics and Telecommunications

“…Described DMA interface is a building block of a DAQ card. In our previous works, two general purpose DAQ cards were used for testing of methods applied in the IRTM NIALM system [2][3]. A new FPGA-based DAQ hardware will provide more flexibility and improve the system.…”