Ratio Of Semiaxes Research Articles

Two orientation effects and large anisotropy of parameters in piezo-active 2–1–2 composites based on [0 1 1]-poled crystals

The results of a comparative study on piezo-active 2–1–2 composites with two ferroelectric components are discussed. The composite structure combines elements of 2–2 (laminar) and 1–3 (fibrous) connectivity patterns. The first component in each composite is domain-engineered [0 1 1]-poled single crystal with macroscopic mm2 symmetry and high piezoelectric activity. The second component is a poled ferroelectric ceramic that is represented by parallel rods in the shape of an elliptic cylinder with a large ratio of semi-axes at its base. The first orientation effect is appreciable due to rotations of the main crystallographic axes X and Y around Z || OX 3 by an angle α in each crystal layer. Rotation of the ceramic rod bases by an angle γ in a polymer medium leads to the second orientation effect in the 2–1–2 composite. The two orientation effects contribute to a large anisotropy of electromechanical coupling factors k3j∗ , energy-harvesting figures of merit (FOM) (Q3j∗)2 and modified FOM F3j∗σ for a stress-driven harvester. The large level of (Q32∗)2 , (Q33∗)2 , F32∗σ and F33∗σ (these parameters are of the order of 10−11–10−10 Pa−1) indicates that the studied composites are suitable for piezoelectric sensors, transducers and energy-harvesting systems. New m—α diagrams put forward in the present study show regions wherein the large anisotropy of the effective parameters ( |k33∗ / k3f∗|⩾5 , (Q33∗/Q3f∗ )2 ⩾10 and F33∗σ/F3f∗σ⩾10 , f = 1 and 2) is achieved when changing the volume fraction m of the single crystal and the rotation angle α. As a result, the leading role of the first orientation effect is emphasised.

Size, albedo, and rotational period of the Hayabusa2# target (98943) 2001 CC21

This study aims to determine the size, albedo, and rotational period of (98943) 2001 CC21, a target of the Hayabusa2 extended mission, using thermal data from the Spitzer Space telescope and ground-based observations. The Spitzer data were acquired with the Infrared Spectrograph in the 6-38 mu m range, reduced using the Spitzer pipeline, and modeled with the near-Earth asteroid thermal model to determine the asteroid size and albedo. The absolute magnitude and rotational period were determined thanks to new observations carried out at the 3.5m New Technology Telescope, the 1.2m Observatoire de Haute Provence, and the 0.7m Abastumani telescope. Three complete light curves were obtained in 2023 and 2024 at the last-mentioned telescope. We determine an absolute magnitude of H=18.94pm 0.05 and a rotational period of 5.02124pm 0.00001 hours, with a large light curve amplitude of sim 0.8 mag. at a phase angle of 22$^o$, indicating a very elongated shape with an estimated a/b semiaxis ratio geq 1.7, or a close-contact binary body. The emissivity of 2001 CC21 is consistent with that of silicates, and its albedo is 21.6pm 1.6 <!PCT!>. Finally, the spherical-equivalent diameter of 2001 CC21 is 465pm 15 m. The albedo value and emissivity determined here, coupled with results from polarimetry and spectroscopy from the literature, confirm that 2001 CC21 is an S-complex asteroid, and not an L-type one as was previously suggested. The size of 2001 CC21 is less than 500 m, which is smaller than its first size estimation (sim 700 m). These results are relevant in preparation of the observing strategy for 2001 CC21 of the Hayabusa2 extended mission.

Theory of electric field effect on the optical properties of elliptical quantum wire

In the approximation of the effective mass, the electric field effect on the optical properties of the elliptical quantum wire (EQW) was investigated. In an elliptic coordinate system, exact solutions of the Schrödinger equation for an electron in an EQW with hard walls are obtained. The electron energy spectrum consists of even and odd energies states, whose wave functions are expressed through even and odd Mathieu functions of the first kind. Using these solutions, an orthonormal basis was constructed. The influence of the electric field perpendicular to the quantum wire and parallel to the ellipse’s major axis on the energies and oscillator strength of quantum electron transitions was calculated using the matrix method. It is shown that the ellipticity of the quantum wire leads to the removal of the degeneracy of the energy spectrum of quasiparticles since the energies of even and odd electronic states depend differently on the ratio of the EQW semi-axes. The electron’s ground state is the even state, which is nondegenerate because there is no corresponding odd state. The electric field has a greater effect on energy states with a lower value of the magnetic quantum number. As the electric field strength increases, the energies of even and odd states shift to the region of lower energies.

Cluster halo shapes in CDM and SIDM models: unveiling the DM particle nature using a weak-lensing approach

ABSTRACT Self-interacting dark matter (SIDM) is an alternative to the standard collisionless cold dark matter model (CDM), allowing for interactions between the dark-matter particles through the introduction of a self-scattering cross-section. However, the observable effects between these two scenarios are hard to detect. In this work, we present a detailed analysis of an application of galaxy–galaxy lensing to measure with high precision the shapes of cluster haloes and how this approach can be used to obtain information regarding the nature of the dark-matter particle. Using two sets of simulated data, SIDM and CDM simulations, we compute stacked shear maps centred on several subsets of haloes with masses ≳1013.5 M⊙. From these maps, we obtain the quadrupole profiles related to the mean projected elongation of the particle distribution from which the shape parameters are derived. Accounting for a radial shape variation, this technique provides an enhancement of the observed differences between the simulated data sets. In particular, we obtain a higher slope of the power law for the shape-radial relation for the haloes identified in the SIDM simulation, which are rounder towards the centre. Also, as approaching to the mean virial radius, the projected semi-axis ratios converge to similar values than in the CDM simulation. Moreover, we account for the impact of the neighbouring mass, where more strongly elongated distributions are found for the haloes in the SIDM simulation, indicating that under dark matter self interaction, the large-scale structure imprints a more coherent accretion process.

Determination of the maximum mechanical stresses in the insulating material around a defect with a high dielectric permittivity in an electrostatic field

Introduction. All insulating macrohomogeneous solid materials change shape under the influence of an electric field. Problem. The presence of minor defects changes the distribution of an electric field and causes a significant concentration of mechanical stresses in a given section of the material, which, under certain circumstances, can cause partial or complete destruction of this material. Goal. The purpose of the work is to determine maximum mechanical stresses according to the von Mises criterion in insulating materials around defects with ionized air and water in an electrostatic field. Also, to analyze the influence of the following parameters on the indicated stresses: the location of the defect, the orientation angle of the semi-major axis of the defect cross-section, the ratio of semi-major and semi-minor axes, elastic and dielectric properties of the insulating material and the defect. Methodology. The study is based on the interrelated equations of electrostatics and structural mechanics for an isotropic piecewise homogeneous medium. The solution of these equations is obtained by the finite element method. Results. Graphs of dependences of maximum mechanical stresses on the ratio of semi-major and semi-minor axes of the ellipsoidal cross-section of the defect have been obtained. The minimum ratio of the greatest stresses in the insulating materials around the surface cracks and pores for ionized air has been 9.3 times for the maximum ratio of major and minor semi-axes of the cross-section of the defect considered in the work, which is 10. For a water defect, the similar ratio has been 2...5.6 times, increasing when the relative dielectric permittivity of the insulating material changes from 7 to 2. When Young’s modulus of the insulating material increases from 1 MPa to 100 GPa, the angles of the inclination of the linearized dependences of maximum mechanical stresses around bounded pores with ionized air (water) to the axis of the ratio of major and minor semi-axes of the defect cross-section have been increased by 35.9° (58.0°) and 18.6° (20.1°) at orientations of major semi-axes at angles of 0° and 45°, respectively. Originality. The numerical-field mathematical two-dimensional model has been developed for the first time, which consists of sequentially solved equations of electrostatics and structural mechanics, for the determination of the distribution of mechanical stresses in an insulating material with a liquid or gaseous defect. It has been established for the first time that the ratio of the elastic properties of the insulating material and the defect determines the angle of the inclination of the linearized dependence of the maximum mechanical stress to the axis of the ratio of major and minor semi-axes of the defect cross-section. Practical value. The types of defects that contribute to the aging of insulation materials under the combined action of an electric field and a stress field to the greatest extent have been established.

Multilayered Semi-Elliptical Arch Structures: A Damping Analysis

Arch structures are used in various load-bearing applications in up-to-date engineering. In some cases these structures are made of multilayered materials with elastic-plastic behaviour. In many applications, the arch structures are subjected to cyclic external loading. This circumstance necessitates developing analyses of damping energy. Such analyses can be very useful for evaluating the effects of a variety of factors and parameters on the damping energy. The present paper is concerned with analyzing of damping energy in a semi-elliptical multilayered arch structure under cyclic bending. The left foot of the arch is clamped. Besides, the arch right foot is restrained by a rotational spring. An approach for determining of the changes in curvature and the coordinates of neutral axis in the portions of the arch is developed. Then damping energy in the arch is derived by integrating the damping energy density in the layers and summation for the arch portions. A parametric investigation of effects of the strength of the rotational spring, ratio of the ellipse semi axes and loading on damping energy is carried-out.

Non uniform micromagnetic states in spheroidal magnetite nanoparticles

Non uniform micromagnetic configurations are calculated in spheroidal magnetite nanoparticles with different semiaxis ratios, a/b = 0.5 – 2.0, using Landau-Lifshitz-Gilbert equation. We take into account a complex, combined type of particle magnetic anisotropy, associated with the presence of both cubic magneto-crystalline anisotropy and shape anisotropy of spheroidal magnetite nanoparticle. It is shown that, depending on the particle aspect ratio, there are different types of vortex states, which compete in energy with the uniform magnetization. It is also found that the single-domain diameters of magnetite nanoparticles significantly depend on the orientation of the cubic easy anisotropy axes with respect to the symmetry axis of a spheroid. The calculated single-domain diameters of spheroidal nanoparticles are in satisfactory agreement with analytical estimates.

Wang tiles enable combinatorial design and robot-assisted manufacturing of modular mechanical metamaterials

In this paper, we introduce a novel design paradigm for modular architectured materials that allows for spatially nonuniform designs from a handful of building blocks, which can be robotically assembled for efficient and scalable production. The traditional, design-limiting periodicity in material design is overcome by utilizing Wang tiles to achieve compatibility among building blocks. We illustrate our approach with the design and manufacturing of an L-shaped domain inspired by a scissor-like soft gripper, whose internal module distribution was optimized to achieve an extreme tilt of a tip of the gripper’s jaw when the handle part was uniformly compressed. The geometry of individual modules was built on a 3 × 3 grid of elliptical holes with varying semi-axes ratios and alternating orientations. We optimized the distribution of the modules within the L-shaped domain using an enumeration approach combined with a factorial search strategy. To address the challenge of seamless interface connections in modular manufacturing, we produced the final designs by casting silicone rubber into modular molds automatically assembled by a robotic arm. The predicted performance was validated experimentally using a custom-built, open-hardware test rig, Thymos, supplemented with digital image correlation measurements. Our study demonstrates the potential for enhancing the mechanical performance of architectured materials by incorporating nonuniform modular designs and efficient robot-assisted manufacturing.

Simulation of a tubular cultivator rack of tillage machines under static and dynamic loads

Curved tubes of non-circular cross section are widely used in various fields of technology. The change in the planned operating modes of various technological processes is associated with the wear of the executing mechanisms, which is caused by unstable frequencies and amplitudes of oscillations. Thus, the issue of determining the oscillation parameters of these elements becomes more significant. The technique and results of tests for stresses, displacements and frequencies of natural oscillations of a tubular cultivator tine made in the form of a curved tube of various sections (mainly flat-oval with an inverse ratio of semiaxes) in the ANSYS software package are presented, the maximum allowable loads and the effect of a rigid tip on oscillation frequencies are determined.

Multi-scale characterization and in-plane crushing behavior of the elliptical anti-chiral honeycomb

Honeycombs with anti-chiral (AC) unit cells are found to have auxetic properties and enhanced energy absorption capacities than regular hexagonal honeycombs. To further improve the energy absorption capacity, by replacing the straight cell walls of the criss-cross anti-chiral (CAC) honeycomb with elliptical cell walls, a novel elliptical anti-chiral (EAC) honeycomb is proposed in this paper. The in-plane crushing response of the EAC honeycomb is investigated numerically under different impact velocities. The numerical modeling method in ABAQUS software is validated by the compression test data of 3D-printed EAC honeycomb specimens. Both experimental and numerical results reveal that the EAC honeycomb has a plateau stage and an enhancement stage in the stress–strain curve. The empirical formulas of critical impact velocity and plateau stress are further derived, which is in good agreement with the numerical simulation results. The parameter analysis further shows that the microstructural parameters have a great influence on the crushing strength of the EAC honeycomb. Under the same impact velocity, larger semi-axis length ratio results in larger plateau stress and densification strain, while smaller semi-axis length ratio means larger initial peak stress and plateau strain.

Magnetostatic interaction in oriented assembly of elongated nanoparticles

The elements of the magneto-dipole (MD) interaction matrix are calculated for a pair of oriented spheroidal magnetic nanoparticles with a semiaxis ratio a/b = 1.25, 1.5, 2.0 and 3.0 as functions of the distance between the particle centers. It is shown that the spherical approximation for the MD interaction matrix is already incorrect at aspect ratios a/b > 1.25, if the distance R between the particle centers is of the order of particle sizes. However, for moderate particle aspect ratios, a/b < 1.5, the first order correction to spherical approximation with respect to a small parameter (a2 – b2)/R2 is shown to be in a good agreement with numerical data. Using exact MD interaction matrix, the quasi-static hysteresis loops of dilute assemblies of oriented clusters of spheroidal nanoparticles with different filling densities are calculated, depending on the direction of the external magnetic field with respect to the particle orientation axis.

Deconvolution of ferromagnetic resonance spectrum of magnetic nanoparticle assembly using genetic algorithm

The ferromagnetic resonance (FMR) spectra of dilute random assemblies of magnetite nanoparticles with cubic magnetic anisotropy and various aspect ratios are calculated using the stochastic Landau–Lifshitz equation at a finite temperature, T = 300 K, taking into account the thermal fluctuations of the particle magnetic moments. Particles of non-spherical shape in the first approximation are described as elongated spheroids with a given semiaxes ratio a/b, where a and b are the long and transverse semiaxes of a spheroid, respectively. A representative database of FMR spectra is created for assemblies of randomly oriented spheroidal magnetite nanoparticles with various transverse diameters D = 5–25 nm, moderate aspect ratios a/b = 1.0–1.8, and magnetic damping constants κ = 0.1, 0.2. The basic FMR spectra of assemblies with D = 25 nm at different aspect ratios can be considered as representatives of assemblies of single-domain magnetite nanoparticles with transverse diameters D > 25 nm. The database is calculated at exciting frequency f = 4.9 GHz (S-band) to clarify the details of the FMR spectrum that depend on the particle magnetic anisotropy nature. The data obtained make it possible to analyze arbitrary combined FMR spectra constructed as weighted linear combinations of FMR spectra of the base assemblies. In addition, using a genetic algorithm, the corresponding inverse problem is solved. The latter consists in determining the volume fractions of the base assemblies in some arbitrary nanoparticle assembly, which is represented by its FMR spectrum.

Magnetostatic Interaction in Oriented Assembly of Elongated Nanoparticles

The elements of the magneto-dipole (MD) interaction matrix are calculated for a pair of oriented spheroidal magnetic nanoparticles with a semiaxes ratio a/b = 1.25, 1.5, 2.0 and 3.0 as a function of the distance between the particle centers. It is shown that the spherical approximation for MD interaction matrix is incorrect already at aspect ratios a/b > 1.25, if the distance R between the particle centers is of the order of particle sizes. However, for moderate particle aspect ratios, a/b < 1.5, the first order correction to spherical approximation with respect to a corresponding small parameter is shown to be in a good agreement with numerical data. Using exact MD interaction matrix, the quasi-static hysteresis loops of dilute assemblies of oriented clusters of spheroidal nanoparticles with different filling densities are calculated, depending on the direction of the external magnetic field with respect to the particle orientation axis.

Heating ability of elongated magnetic nanoparticles.

Low-frequency hysteresis loops and specific absorption rate (SAR) of various assemblies of elongated spheroidal magnetite nanoparticles have been calculated for a range of particle semiaxis ratios a/b = 1.0–3.0. The SAR of a dilute randomly oriented assembly of magnetite nanoparticles in an alternating magnetic field of moderate frequency, f = 300 kHz, and amplitude H0 = 100–200 Oe is shown to decrease significantly with an increase in the aspect ratio of nanoparticles. In addition, there is a narrowing and shift of the intervals of optimal particle diameters towards smaller particle sizes. However, the orientation of a dilute assembly of elongated nanoparticles in a magnetic field leads to an almost twofold increase in SAR at the same frequency and amplitude of the alternating magnetic field, the range of optimal particle diameters remaining unchanged. The effect of the magneto-dipole interaction on the SAR of a dilute assembly of oriented clusters of elongated magnetite nanoparticles has also been investigated depending on the volume fraction of nanoparticles in a cluster. It has been found that the SAR of the assembly of oriented clusters decreases by approximately an order of magnitude with an increase in the volume fraction of nanoparticles in a cluster in the range of 0.04–0.2.

Про демпфовані усталені резонансні коливання рідини в контейнері кругового перерізу для довільних періодичних непараметричних збурень

Nonlinear modal Narimanov-Moiseev—type equations are investigated to study resonant sloshing in a vertical cylindrical tank. The tank moves periodically in the space with the forcing frequency close to the lowest natural sloshing frequency. We show that the considered sloshing problem can to within the higher-order asymptotic terms be reduced to the case of orbital tank motions in the horizontal plane. Analytical solutions of the secular system which couples the dominant amplitudes of the steady-state sloshing are analytically solved. Effect of viscous damping is accounted. The results are compared with experimental measurements conducted by diverse authors for longitudinal and circular orbital tank excitations. A parametric analysis of the amplitude curves is done to clarify how the steady-state wave regimes and their stability change versus the forcing frequency and the semi-axes ratio of the elliptic orbit. The main result consists of confirming the experimental disappearance of the counter-directed swirling wave mode (relative to the elliptic orbit direction) when passaging to the circular orbit.

Modeling electrode-level crack and quantifying its effect on battery performance and impedance

Electrode-level cracks in a Li ion battery significantly impact its performance. We build a crack-containing electrochemical model to reveal the mechanism and quantify the effect of crack geometrical characteristics on specific energy, specific capacity and cell impedance. An elliptical-shaped crack is introduced into the electrode, which represents various configurations by changing the semi-axis ratio, crack angle and crack position. We show that lithium ion transport, electrochemical intercalation and the overall cell impedance are sensitive to the crack characteristics and electrotype absorption on crack surfaces. A longer crack more parallel to the current collector reduces the specific energy and specific capacity more significantly, especially when the current density is high. By contrast, a crack perpendicular to the current collector has little impact. The dependence on a series of crack orientation is quantified. The study of crack position shows that a crack closer to the separator has a stronger negative impact, dramatically reducing capacity. Electrochemical impedance spectroscopy simulations show that the crack shape factors such as semi-axis ratio, crack angle and electrolyte wetting ratio primarily affect the ohmic resistance. A longer crack more parallel to the current collector increases the ohmic resistance, while more crack wetting reduces the ohmic resistance. By contrast, crack position significantly affects the charge transfer resistance but with little impact on the ohmic resistance. A crack closer to the separator increases the charge transfer resistance. The effect of connected cracks into an open or closed ring shape is also considered, which can partially isolate active materials from the electrode depending on the size and orientation of the opening. This work provides a comprehensive and fundamental understanding of how various crack geometrical parameters affect the electrochemical behavior, which can assist in evaluating the significance of cracking, allow comparison with other degradation mechanisms to identify the limiting factor, and provide guidance on battery design and application strategy.

Parameter analysis and performance optimization for the vertical pipe intake-outlet of a pumped hydro energy storage station

Abstract The vertical pipe intake-outlet plays an important role in the pumped hydro energy storage (PHES), and its main parameters included the orifice height ratio (H∗), the diffuser short semi-axis ratio (a∗), the diffuser long semi-axis ratio (b∗) and the cover plate radius ratio (Rc∗). The aim of this study was to analyse effects of the parameters and obtain the optimal design. An integration method combining computational fluid dynamics (CFD), response surface methodology (RSM) and genetic algorithm was proposed. To evaluate grid independency, the grid converge index was introduced. Based on the validation for the baseline design (H∗ = 0.577, a∗ = 1.087, b∗ = 4.231 and Rc∗ = 1.635), a reliable CFD model was developed to obtain results of sample points. Then RSM models were constructed and assessed, and contribution and interactions of the parameters were analyzed. Finally, the optimal design (H∗ = 0.422, a∗ = 1.177, b∗ = 5.363 and Rc∗ = 2.115) was obtained. The CFD results show that the overall head loss coefficient, the inflow and the outflow velocity distribution coefficient are reduced by 4.687%, 11.765% and 38.596%, respectively. Especially, the negative velocity at the trashrack section in the pump mode is eliminated. The improvement demonstrates that the proposed method achieves significant superiority over the trial-and-error method traditionally adopted in the intake-outlet design.

Study of Ostwald-de Waele fluid flow in an elliptical annulus using the slot model and the CFD approach

Among consequences that can be induced by a non-uniform distribution of the stress and other causes during the drilling process is the elliptical shape of the well and consideration of this effect would improve the accuracy of the drilling fluid hydrodynamics prediction. In the present work, the elliptical shape of the annular space is simplified to apply the slot model taking into account the rotation of the inner cylinder. Moreover, the Slot model results are compared with the experimental data, as well as, with the CFD outcomes where a reasonable concordance is observed, especially for low ratios of the major and minor semi-axis. Also, the CFD results are validated with the experimental data from the flow loop setup. We concluded that the increase of the major and minor semi-axis ratio of the elliptical annulus results in a linear increase of the Ostwald-de Waele frictional pressure loss in the laminar regime for all considered rotation speeds of the inner cylinder. In addition, the increase of the eccentricity from 0 to 0.75 has a positive effect where the frictional pressure loss is decreased by almost 28% for all rotation speeds for the elliptical annulus ().

Resonant three-dimensional nonlinear sloshing in a square base basin. Part 5. Three-dimensional non-parametric tank forcing

Assuming an inviscid incompressible liquid (with irrotational flows) partly filling a square base tank, which performs a small-amplitude sway/surge/pitch/roll periodic motion whose frequency is close to the lowest natural sloshing frequency, a nine-dimensional Narimanov–Moiseev-type (modal) system of ordinary differential equations with respect to the hydrodynamic generalised coordinates was derived in the Part 1 (Faltinsen et al., J. Fluid Mech., vol. 487, 2003, pp. 1–42). Constructing and analysing asymptotic periodic solutions of the system made it possible to classify steady-state resonant sloshing and its stability for the harmonic reciprocating (longitudinal, diagonal and oblique) forcing. The results were supported by experimental observations and measurements. The present paper finalises the case studies by considering the three-dimensional non-parametric (combined sway, pitch, surge, roll and yaw, but no heave) cyclic tank motions. It becomes possible after establishing an asymptotic equivalence of the associated periodic solutions of the modal system to those for a suitable horizontal translatory elliptic forcing so that, as a consequence, resonant steady-state waves and their stability can be considered versus angular position, semi-axis ratio and direction (counter- or clockwise) of the equivalent orbits. The circular orbit causes stable swirling waves (co-directed with the orbit) but may also excite stable nearly standing waves. The orbit direction does not affect the response curves for wall-symmetric (canonic) and diagonal orbit positions. This is not true for the oblique-type elliptic forcing. When the semi-axis ratio changes from 0 to 1, the response curves exhibit astonishing metamorphoses significantly influencing the frequency ranges of stable nearly standing/swirling waves and ‘irregular’ sloshing. For the experimental input data by Ikeda et al. (J. Fluid Mech., vol. 700, 2012, pp. 304–328), the counter-directed swirling disappears as but the frequency range of irregular waves vanishes for .

DEEP LEARNING FOR MORPHOLOGICAL CLASSIFICATION OF GALAXIES FROM SDSS

We present the results of applying deep convolutional neural network to the images of redshift-limited ( z < 0 . 1) sample of ∼ 300000 galaxies from the SDSS DR9. We aimed to classify galaxies into the two classes: Elliptical and Spiral. To create the training sample, we used a set of ∼ 6000 galaxies from our previous work with visually inspected morphologi- cal types, and also added 80000 well-confirmed galaxies from Galaxy Zoo 2 dataset, that were also classified visually. With a given sample of ∼ 86000 galaxies, we used the deep neural network, namely Xception, to provide a classification of g-r-i composite images (25 arcsec in each axis in size) of galaxies. Keeping in the mind a relatively small training dataset, we provided the data augmentation (horizontal and vertical flips, random shifts on ± 10 pixels , and rotations within 180 degrees), that was randomly applied to the images during learning. The data augmentation is a key technique within our algorithm to display the variative nature of the observed galaxies, and avoid overfitting problem. We compared our classification result with the Support Vector Machine (SVM) classification performed on the SDSS photometric data (absolute magnitudes, colour indices, inverse concentration index, ratios of semiaxes, etc.), and proposed a method to learn the benefits from both approaches (Deep Learning and photometric classification). We show the common mistakes of both algorithms, and propose to stack these two approaches to block these mistakes, with a main goal to increase the overall classification quality of SDSS galaxies.