Recognition of Monochrome Thermal Images of Synchronous Motor with the Application of Binarization and Nearest Mean Classifier

Abstract

This article discusses the recognition method of imminent failure conditions of synchronous motor. The proposed approach is based on a study of thermal images of the motor. Studies were carried out for four conditions of motor with the application of binarization and nearest mean classifier with Manhattan distance. Pattern creation process used 40 monochrome thermal images. Identification process was carried out for 160 monochrome thermal images. The experiments show that the method can be useful for protection of synchronous motor. Moreover, this method can be used to diagnose equipments in steelworks and other industrial plants.Keywords: Diagnostics, Recognition, Thermal images, Synchronous motor, nearest mean classifier Artykuł omawia metodę rozpoznawania stanów przedawaryjnych silnika synchronicznego. Proponowane podejście jest oparte na badaniu obrazów termowizyjnych silnika. Przeprowadzono badania dla czterech stanów silnika z zastosowaniem binaryzacji i klasyfikatora najbliższej średniej z metryką Manhattan. Proces tworzenia wzorców do rozpoznawania został przeprowadzony dla 40 monochromatycznych obrazów termowizyjnych. W procesie identyfikacji użyto 160 monochromatycznych obrazów termowizyjnych. Eksperymenty pokazują, że metoda może być przydatna do ochrony silników synchronicznych. Ponadto metoda może być stosowana do diagnozowania urządzeń w hutach i innych zakładach przemysłowych.

Theoretical and Experimental Research of Error of Method of Thermocouple with Controlled Profile of Temperature Field

“…To find the temperature T , for which the combined maximum permissible error of MTC and the thermocouple of the first zone Apparently, as it is defined in point 10 of the above mentioned instruction, the value of MET ∆ is calculated according to (9) as the difference, and the terms of (9) are calculated in point 9, also as the differences. In addition, it is clear that changes in temperatures GT T ∆ and PT T ∆ will be small.…”

“…However, technological progress is challenging for existing measuring methods and expands the need for measurements in new conditions [3]- [6]. At the same time, requirements for accuracy of measurements are increasing in industry and areas, where temperature has been measured for a long time [1], [2], [7]- [9].…”

Recognition of acoustic signals of induction motor using FFT, SMOFS-10 and LSVM

“…They also develop early fault detection methods [1,5,6,[10][11][12][13][14][15]. Especially non-invasive methods are developed such as: acoustic, vibrations, thermal, magnetic [3,14,19,27,28,29,35,36,38].…”

“…These motors have low maintenance and low price. To reduce maintenance costs scientists analyze mechanical properties of materials [18,20,25,30].They also develop early fault detection methods [1,5,6,[10][11][12][13][14][15]. Especially non-invasive methods are developed such as : acoustic, vibrations, thermal, magnetic [3, 14, 19, 27, 28, 29, 35, 36, 38].…”

Designing an accurate system for temperature measurements

“…The expansion of the sphere of temperature measurements [3,4,[18][19][20], the increase in the requirements for their quality [17,21] and the need for non-stationary measurements [15,18,19] imposes additional requirements on sensors [1,4,22], equipment [23,24] and methods of signal processing [20,21].…”