Prediction of the Remaining useful Life of the Rolling Element Bearings using Recurrent Neural Network
M.A
Bayati Nezhad
M.Sc., Mechanical Engineering Department, Shahid Rajaei University, Tehran, Iran
author
A
Mohammadi
Corresponding Author, Assistant Professor, Faculty of Mechanical Engineering Department, Shahid Rajaei
University, Tehran, Iran
author
A
Davood Abadi
PhD Student, Mechanical Engineering Department, Sharif University of Technology, Tehran, Iran
author
text
article
2020
eng
In this paper, the temperature feature was employed to trackdown the degradation trend of rolling element bearings. Theremaining useful life(RUL) of the rolling element bearingwas predicted by assuming root mean square growth (RMS)of the acceleration signal to exponential function form andextraction of two other features. Then, the performance ofthese features was investigated in the prediction using arecurrent neural network(RNN). The experimental data ofthe accelerated life test on the rolling element bearing havebeen extracted from the prognostic. Contrary to theprevious works, this paper considers the temperaturefeature instead of the time feature and also assuming theRMS of the acceleration signal to the exponential functionform and using a RNN which causes a new model moreapplicable than previous models.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_46440_63edfd27292e9757aa2e898efc7633df.pdf
dx.doi.org/10.30506/jmee.2020.46440
Uncertainty Analysis of Spray Injection Process in a Model Scale Liquid Fuel Micro-Motor
M
Nadjafi
Corresponding Author, Assistance Prof. of Aerospace Engineering, Aerospace Research Institute (Ministry of
Science, Research and Technology), Tehran, Iran
author
M.A
Farsi
Associate Professor of Aerospace Engineering, Aerospace Research Institute (Ministry of Science, Research
and Technology), Tehran, Iran
author
F
Ommi
Professor of Mechanical Engineering, Tarbiat Modares University (TMU), Tehran, Iran
author
text
article
2020
eng
Injection process and its parameters are the most importantfactors in the combustion process that depends on somefactors in operation. In this paper, initially, injectionparameters from viewpoint of macroscopic and microscopicin a manufactured model scale liquid fuel micro-motor thatare measured experimentally in Cold-Test and PhaseDoppler Analyzer (PDA) laboratories, are evaluated. Andthen, Uncertainty Analysis (UA) methodologies forexperimental uncertainty assessment are implemented todrive the respective block diagram. The sources ofuncertainty associated with the techniques are presented,and where such data were available, quantitative estimatesof their magnitude are given. Uncertainty analysis resultsthat are taken to spraying parameters show the highaccuracy of experimental test results. This framework is acomprehensive and complete technique that could beimplemented and executed over any set to analyzeuncertainty value, with difference that each set or case studyhas its respective parameters.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_46442_b51318c3d9cb5d0ba6bd45548acb8430.pdf
dx.doi.org/10.30506/jmee.2020.46442
An analytical study for nonlinear vibration analysis of two-directional functionally graded rectangular plate
Soheil
Hashemi
Faculty of Mechanical Engineering, K.N. Toosi University of Technology, Tehran, Iran
author
Ali Asghar
Jafari
K.N Toosi University
author
text
article
2020
eng
In this study, an analytical solution is presented for investigating the nonlinear vibration analysis of two-directional functionally graded rectangular plate for the first time. On the basis of first order shear deformation theory (FSDT) and Galerkin procedure, the equations of motion are developed. The nonlinear equation of motion is then solved analytically by modified Lindstedt-Poincare method. The volume fraction distribution is assumed to be symmetrical for characterizing the in-plane material inhomogeneity. Finally, the effects of some system parameters such as non-dimensional vibration amplitude, volume fraction indexes and aspect ratio on the nonlinear to linear frequency ratio are discussed in detail. To validate the analysis, the results of this paper are compared with the published data and good agreements are found.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_45000_21db9fa8ca2033617da5481f9418c6cf.pdf
dx.doi.org/10.30506/jmee.2020.112273.1193
Wind farm layout optimization using a Reynolds‐averaged Navier–Stokes model and a genetic algorithm
Abolfazl
Pourrajabian
Department of Energy, Materials and Energy Research Center (MERC), 14155-4777, Tehran, Iran
author
Reza
Ebrahimi
K.N Toosi University
author
Morteza
Rahmanpour
Faculty of Mechanical Engineering, Azarbaijan Shahid Madani University, Tabriz, Iran
author
Saeed
Rahgozar
Department of Energy, Materials and Energy Research Center (MERC), 14155-4777, Tehran, Iran
author
Maziar
Dehghan
Department of Energy, Materials and Energy Research Center (MERC), 14155-4777, Tehran, Iran
author
text
article
2020
eng
The placement of wind turbines in a wind farm can considerably affect the total output power. Using computational fluid dynamics and genetic algorithm, the optimal arrangement of turbines in a given wind farm was determined. A three-dimensional Reynolds-averaged Navier-Stokes simulation was conducted on a 660 kW three-bladed horizontal axis turbine. The airflow was assumed to be steady state and a pressure-based approach was adopted to solve the governing equations. Subsequently, an engineering expression for the wake evolution was developed and validated. By employing the characteristics of the wake propagation, the appropriate distances between the adjacent turbines were calculated. To find the optimal placement of the turbines, a purpose-built genetic algorithm was employed to minimize the objective function defined by the ratio of the wind farm cost to the output power. The results show that the final configuration is in line with the outcomes of the previous study. The sensitivity analysis of the genetic algorithm with respect to its parameters including the population size and the mutation rate was also performed to guarantee that the final layout is an optimal one.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_45001_202e35e8c0f32e0b227224e2548d0575.pdf
dx.doi.org/10.30506/jmee.2020.112337.1194
The Effect of Repeated Impact Loading on Reservoir Rock Properties
Marzieh
Naderan Tahan
Mechanical Engineering Department, Shahid Chamran University of Ahvaz, Iran
author
Khosro
Naderan Tahan
Mechanical Engineering Department, Shahid Chamran University of Ahvaz, Iran
author
Seyed Saied
Bahrainian
Mechanical Engineering Department, Shahid Chamran University of Ahvaz, Iran
author
text
article
2020
eng
The objective of this paper is to present the results of a research program launched to investigate the mechanism and amount of changes of reservoir rock properties due to pulse stress waves. These waves are induced in cylindrical samples by applying repeated impact loading along the sample axes in a falling weight testing apparatus. The samples are dry and free from any fluid and no confining pressure. After each step of loading, permeability, effective porosity, wave velocities are measured by standard methods and CT images are prepared. Results show that if the amplitude of dynamic stress exceeds the dynamic fracture strength and spall strength of the samples, micro fracture will emerge and permeability will increase significantly while the effective porosity decreases at first steps of loading but, recovers during the subsequent steps. Emerging and growth of new fractures are visible in CT images, too. Initial structure of samples, total energy consumption prior to complete breakage, and the strain rate of incident wave, affect the results.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_45003_e39226f11ae5f071e65bf5404ff19a25.pdf
dx.doi.org/10.30506/jmee.2020.115766.1204
Free and forced vibration behavior of cylinders made of two dimensional functionally graded materials using meshless method
Habib
Mirzaie
Department of Mechanical Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran
author
Seyed AliReza
Seyed Roknizadeh
Department of Mechanical Engineering, Ahvaz Branch, Islamic Azad University, Ahvaz, Iran
author
text
article
2020
eng
In this article, a meshless method is developed to analyze free and forced vibration behavior of axisymmetric cylinders made of two dimensional functionally graded materials (2D-FGMs). The meshless method is based on weak form of equations of motions using the Moving Least Square (MLS) approximations shape functions. The 2D-FGM cylinders are made of a mixture of a ceramic and a metal. The volume fraction of each component is assumed to be functionally varied along both radial and axial directions of cylinders. The effects of profile of material distributions, cylinder dimensions, boundary conditions and loading on the vibrational characteristics of the proposed 2D-FGM cylinders are investigated. The results of investigating the vibrations of the cylinders made of 2D-FGM confirmed that in the engineering design applications, the radial vibrations can be attenuated by adjusting the power coefficients along the radius and length of the cylinder.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_45004_2dcbdae5b9df02897dab8142027ec048.pdf
dx.doi.org/10.30506/jmee.2020.117657.1210
Robust sliding mode control of uncertain nonlinear ship autopilot system
Farzan
Rashidi
University of Hormozgan
author
Abbas
Harifi
University of Hormozgan
author
text
article
2020
eng
Designing of ship autopilot has been a challenging problem because of high nonlinearity of ship dynamics and various acting disturbances. Hence, In the last few years, many classical and intelligent algorithms are presented in the literature, for better control of ship autopilot. The main goal of the work is to design a proper and efficient controller for ship autopilot based on sliding mode control method. The major contribution of the paper is employing a nonlinear model as well as considering dynamic bounds of uncertainties for controller design. In order to reduce the chattering phenomenon, control scheme has been modified using integral switching variable. Simulation results in the rough wave condition show the success of method to overcome nonlinearity and disturbances, and high performance of the proposed controller comparing to similar research.
Iranian Journal of Mechanical Engineering Transactions of the ISME
Iranian Society of Mechanical Engineering
1605-9727
21
v.
2
no.
2020
https://jmee.isme.ir/article_45005_aa6c79f8edce097ee80323de007b22d4.pdf
dx.doi.org/10.30506/jmee.2020.118967.1220