scholarly journals A New Artificial Neural Network Based Failure Determination System For Electric Motors

2021 ◽  
Author(s):  
Sabri Bicakci ◽  
Mustafa Coramik ◽  
Huseyin Gunes ◽  
Hakan Citak ◽  
Yavuz Ege
Keyword(s):  
Single Phase ◽  
Frequency Component ◽  
Vibration Sensor ◽  
Sequential Minimal Optimization ◽  
Training Stage ◽  
Nonlinear Relation ◽  
Determination System ◽  
Rotor Bearings ◽  
Accuracy Degree

Abstract A new measurement system was developed for determination of failures and defining the level of failure that may occur in bearings and rotor bearings or in foot of motor in single phase capacitor start motor. In system, the vibratory operation of the motor is provided by connecting different screws on the motor’s rotor mounted flywheel or by gradually removing the nut bolts of motor foot. The VB3 vibration sensor outputs were recorded to the computer. The changing characteristics of sensor output for each experiment had more than one frequency component; therefore, FFT was performed for determining such components. It was observed that the frequency and amplitude values of first 5 harmonics could be used for determining the presence, type and level of failure but there was a nonlinear relation between each other. 2 different ANN customized separately were developed for determining the type and rate of the failure of motor. 80%, 10% and 10% of available data were reserved for training, testing and verification respectively and the ANN was trained. Accuracy degree for the ANN in the estimations following the training stage was calculated as R = 0.97-0.98. Furthermore, the results of ANN was compared with the results obtained using Sequential Minimal Optimization (SMO), Naive Bayes (NB) and J48 algorithms; and it was determined that the accuracy degree of ANN was higher.

scholarly journals Single-phase determination of calcium and magnesium in biodiesel using smartphone-based digital images

Fuel ◽  
2022 ◽  
Vol 307 ◽  
pp. 121837
Author(s):  
Samara Soares ◽  
Gabriel M. Fernandes ◽  
Liz M.B. Moraes ◽  
Alex D. Batista ◽  
Fábio R.P. Rocha
Keyword(s):  
Single Phase ◽  
Digital Images ◽  
Phase Determination ◽  
Calcium And Magnesium

In-line single-phase extraction for direct determination of total iron in oils using CdTe quantum dots and a flow-batch system

2015 ◽  
Vol 7 (18) ◽  
pp. 7707-7714 ◽  
Author(s):  
Marcelo B. Lima ◽  
Stéfani Iury E. Andrade ◽  
Inakã S. Barreto ◽  
Mário César U. Araújo
Keyword(s):  
Quantum Dots ◽  
Single Phase ◽  
Direct Determination ◽  
Total Iron ◽  
Cdte Quantum Dots ◽  
Phase Extraction ◽  
Batch System ◽  
System P ◽  
Novel Method

In this work, a novel method for direct determination of total iron in viscous samples is presented.

scholarly journals IMPLEMENTATION OF SIMPLE ADDITIVE WEIGHTING METHOD IN THE DETERMINATION SYSTEM OF THESIS SUPERVISOR

2021 ◽  
Vol 23 (2) ◽  
pp. 133-141
Author(s):  
Renny Puspita Sari ◽  
Ferdy Febriyanto ◽  
Ibnur Rusi
Keyword(s):  
Higher Education ◽  
Information Systems ◽  
Higher Education Institutions ◽  
Natural Sciences ◽  
Weighting Method ◽  
Weight Value ◽  
Determination System ◽  
Simple Additive Weighting

Majors are part of higher education institutions that a very important role determining the thesis student supervisor . At the Department of Information Systems, Faculty of Mathematics and Natural Sciences (MIPA) the determination of the thesis supervisor is carried out through a lecturer meeting based on its title in accordance with the competence of the lecturer who will guide, regardless of the number of lecturers' workload or the number of students being supervised. The results of the decision of the meeting to determine the supervisors will be announced to students after the meeting is held. This flow inefficient and may lead to ineffective determination of the supervisor . The final result of the system shows that the Simple Additive Weighting (SAW) method can be applied to determine the weight value of each attribute so as to produce a ranking of each alternative lecture who will be selected as a student supervisor for the thesis according to the result of computerized and accurate calculations.

New Method of Modeling Infrared Spectra of Non-Cubic Single-Phase Polycrystalline Materials with Random Orientation

2002 ◽  
Vol 56 (9) ◽  
pp. 1194-1205 ◽  
Author(s):  
Thomas G. Mayerhöfer
Keyword(s):  
Single Phase ◽  
Common Factor ◽  
Dispersion Analysis ◽  
Polycrystalline Materials ◽  
Implicit Assumption ◽  
Resolution Limit ◽  
Random Orientation ◽  
New Approach ◽  
Arithmetic Average

A new approach has been used to model optical properties of noncubic single-phase polycrystalline materials with random orientation and crystallites small compared to the resolution limit of light. This method has been applied to fresnoite (Ba2TiSi2O8) and proved to provide widely adequate results to effective medium approximation (EMA) and an excellent correspondence between simulated and measured spectra. In contrast to EMA, the new theory predicts that the deviation between damping constants of polycrystalline and single crystal fresnoite can be adjusted by one common factor for all damping constants. Based on EMA and the new model, much smaller damping constants have been determined for polycrystalline fresnoite compared to conventional dispersion analysis; the latter is able to provide a relevant dielectric function, but seems to be of little reliability concerning the determination of meaningful oscillator parameters due to the implicit assumption of an arithmetic average of the principal dielectric functions. This approximation, which can be derived in a similar form from EMA and is of widespread use, is shown to be inferior to an approximation based on the arithmetic average of the principal refractive indices.

Sign in / Sign up

Export Citation Format

Share Document