Control and Modeling Parameters for Heat Diagnostics of Power Electri-Cal Equipment Failure

Akinshyn

2021

MEC

Self Cite

The article notes the growing popularity of digital programmable technology in diagnostic monitoring systems of electromechanical equipment (EME) for various purposes due to the ability to monitor the technical condition of operating devices in real time. The main reasons that restrain the use of DMS with artificial neural networks in the municipal sphere are considered. It has been noted the directions of improvement of popular means of thermal parameters monitoring and hardware solutions to increase the initial data validity used in the possible EMO fault identification. The purpose of this work was to study and develop components for the formation of initial information, including artificial neurons, which make it possible to increase the reliability of possible fault identification accompanied by heating of individual parts of the operated electromechanical equipment. Based on the adopted algorithm for approximating the initial data arrays, the priority of using the logistic function for modeling the rate of temperature change in the EME was justified. It have been proposed the electronic model structure of an artificial neuron (AN) and an algorithm for generating information output signal, depending on the rate of change of a controlled parameter at a technological object. It have been presented the electronic modeling results in the Simulink environment and the physical implementation of the AN electronic model, which confirmed the suitability of the proposed device in the diagnostic thermal expert of the EME technical condition during its operation in real time. Electronic experiments with AN made it possible to obtain a calibration characteristic for a practical assessment of the tendency for the development of non-standardized thermal events that may cause possible faults in certain parts of the equipment. It have been considered possible options for using AN in local thermal diagnostic tools for the analysis and assessment of events indicating the feasibility of performing unscheduled maintenance or preceding possible and unknown electromechanical equipment faults. It has been presented the results of experiments and simulation of thermal processes, confirming the expandability of the functional diagnostic devices properties with neural network systems, which popularity is constantly growing.

Section: постановка проблемиunclassified

Section: виклад основного матеріалу 1 вибір методу апроксимації швидкості зміни температуриunclassified

Synthesis of Thermal Diagnostic Expert Components With an Artificial Neuron

Akinshyn

2021

MEC

Self Cite

“…Теплова діагностика електричних машин, що раніше отримала популярність [2], продовжує розвиватися, тому що для її застосування істотно розширився асортимент термічних датчиків, особливо, безконтактного виконання з електронними засобами дистанційної передачі виміряних величин в реальному часі [3]. Комплекти з оригінальними пристроями перетворення температури приходять на зміну стаціонарним і мобільним установкам, застосовуваним при виконанні планових і щоденних технічних оглядів (ЩТО) транспортних засобів, електрообладнання ліфтів, ескалаторів тощо.…”

Section: постановка проблемиunclassified

“…При повторно-короткочасних режимах експлуатації ЕМО найбільш ефективними засобами контролю температури є пристрої з термодатчиками самого різного виконання [1,3,6]. Особливе місце у всьому асортименті пристроїв займають засоби дистанційного контролю, що встановлюються безпосередньо або поблизу компонентів, що нагріваються, вихід з ладу яких відбувається з відомою ймовірністю: підшипники (51%), обмотки статора (15,8%) і ротора (4,7%), з'єднувальні вали, муфти (2,4%), зовнішні пристрої (15,6%), та ін., що становлять сукупність ЕМО [3,7].…”

Section: аналіз останніх досліджень і публікаційunclassified

“…Для ідентифікації процесів генерації тепла окремими блоками, вузлами тощо з можливими несправностями в них знаходять застосування системи діагностичного контролю (СДК) на основі інтелектуальних електронних систем і штучних нейронних мереж (ШНС) прямого поширення − персептрона [8,9] виду [3] ( )…”

Section: аналіз останніх досліджень і публікаційunclassified

See 1 more Smart Citation

Increasing the Efficiency of Thermal Diagnostic Control of Electric Motors

Kovalik

2020

MEC

Self Cite

The article considers the cause of electromechanical equipment heating (EMЕ) during its operation. It has been reflected the well-known malfunctions of electric motors, that lead to overheating and failure of their individual components. Based on the analysis of existing methods of thermal diagnostics, It has been considered the trends in the creation of devices for monitoring thermal processes and it has been noted the reasons that restrain the use of technical diagnostics tools for thermal faults during the operation of EME. The purpose of this work was to increase the efficiency of the formation of initial information messages. Using the experimental data in the implementation of the EME working cycles, value of the thermal process velocity accompanying the variable technological modes with the bipolar behavior of the output ordinate were determined. Compared to the heating temperature, the rate of value change with a more noticeable contrast reflected the thermal events in the EME, thus determining the priority of this parameter to increase the efficiency of the measuring device. It has been considered methods of forming an array of initial data using a remote transducer sensor to control the heating temperature of equipment with a modulator. It has been proposed algorithms for the electronic formation of an array of initial values and their sorting according to the “principle of flotation”, when a select variables, belonging to the heating processes or cooling of equipment, is provided. A way and an algorithm for determining the rate of temperature change based on current data using a D-shaper are considered. Experimental studies of the electronic components of the diagnostic device with the D-shaper of the initial data array elements confirmed their physical implementation possibility by hardware and software. The results of data arrays formation, taking into account digital sequences in int format with an error of ± 1 Hz, in contrast to the most controlled parameter – float with an error of ± 0.08 ° C, did not change the properties of information messages, but made it possible to reduce the requirements for a microcalculator or a computing device. The results, obtained using the proposed technical solution, confirmed the possibility of increasing the efficiency of thermal and diagnostic control, contributing to a more accurate identification of possible electric motor malfunctions in the EME. The work presents illustrations confirming the suitability of mathematical descriptions and algorithms for processing the initial data for their practical application in electronic measuring instruments for monitoring and diagnosing malfunctions based on thermal events. Keywords: artificial neural network, remote control, modeling, parameter converter, modulator, transport, traction motor, identification, programming.

Local Means of Thermal Diagnostic Control of Electrical Equipment Functionality

Коваленко

et al. 2021

MEC

Self Cite

Attention is drawn to the lack in many municipal transport models of off-line testing engineering tools of on-board parameters and assessment of electromechanical equipment in real time. These development restraints are caused by stagnation of engineering decisions that can be eliminated with the help of the unlimited possibilities of modern microelectronics. It has been considered an example of thermal control of electrical equipment during its operations. The popularity of the thermal method of equipment control is confirmed by its application not only in transport, but also in electromechanical devices. It has been considered methods of using several thermal transducers for collecting data and forming matrices characterizing a certain class of breakdowns. The most important matrix is the initial one, which refers to the serviceable equipment at the beginning of equipment operations. Due to increased reliability of data, it is advisable to develop effective methods for selective selection of initial values. The paper drew attention to the possibility of solving such problems by software with the implementation of comparison methods, sorting options, etc. The peculiarity of algorithms development for such auxiliary operations is due to the possibility of creating data arrays for the practical identification of possible failures, both in individual parts of the equipment and in the set of components as a whole. It has been presented the results of the binary representation of intermediate and final information messages, which greatly simplify the implementation of diagnostic examination tools. Modeling in the Matlab environment confirmed acceptability of proposed engineering decisions adapted for their implementation by means of processors with RISC-architecture. Despite the fact that binary methods of breakdowns technical appraisal will always differ much more inaccuracy than those made on the basis of direct measurements, proposed autonomous local binary experts in onboard versions of their implementation in transport are less labor-intensive, do not require maintenance, are economical and may turn out to be good helpers to prevent possible equipment failures when operating vehicles on passenger service lines.