Abstract
Magnetic refrigeration (MR) combines many unique features such as low cost, high efficiency and environmental friendliness which make it preferred to the conventional gas compression system of refrigeration. MR employs manganite-based material due to its high magnetocaloric effect as well as tunable Curie temperature (\({T}_{\mathrm{C}}\)). For effective utilization of this technology, \({T}_{\mathrm{C}}\) of manganite refrigerant needs to be tuned to ambient room temperature. In order to relieve experimental stress involved and consequently save valuable time and resources, support vector regression (SVR) computational intelligence technique is proposed using manual search (MS-SVR) and a novel gravitational search algorithm (GSA-SVR) for its hyper-parameter optimization. The developed GSA-SVR model shows better performance than MS-SVR model with performance improvement of 86.03% on the basis of root mean square error (RMSE) and 0.07% on the basis of correlation coefficient (CC) on the training dataset while 11.48% of RMSE improvement and 2.48% of CC improvement were recorded for the testing dataset. The outstanding results presented in this work suggest the potential of the proposed models in promoting room temperature MR through quick estimation of the effect of dopants on \({T}_{\mathrm{C}}\) so as to obtain manganite that works well around the room temperature without loss of precision.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Aghemenloh E, Yusuf S, Idiodi JOA (2013) Surface energy calculation of hcp metals using the analytical equivalent crystal theory. Mater Chem Phys 138(2–3):529–534
Akande KO, Owolabi TO, Olatunji SO (2015) Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization. J Nat Gas Sci Eng 22:515–522
Basak D, Pal S, Partababis DC (2007) Support vector regression. Neural Inf Process Lett Rev 11(10):203–224
Beigvand SD, Abdi H, La Scala M (2016) Combined heat and power economic dispatch problem using gravitational search algorithm. Electr Power Syst Res 133(2016):160–172
Bettaibi A, M’nassri R, Selmi A, Rahmouni H, Chniba-boudjada N (2015) Effect of chromium concentration on the structural, magnetic and electrical properties of praseodymium-calcium manganite. J Alloys Compd 650:268–276
Cai CZ, Wang GL, Wen YF, Pei JF, Zhu XJ, Zhuang WP (2010) Superconducting transition temperature \(T_{\rm c}\) estimation for superconductors of the doped \(\text{ MgB }_{2}\) system using topological index via support vector regression. J Supercond Nov Magn 23(5):745–748
Cai CZ, Xiao TT, Tang JL, Huang SJ (2013) Analysis of process parameters in the laser deposition of \(\text{ YBa }_{2}\text{ Cu }_{3}\text{ O }_{7}\) superconducting films by using SVR. Physica C Supercond 493:100–103
Cheikhrouhou A (2015) Structural, magnetic and magnetocaloric properties of K-doped \(\text{ Pr }_{0.8}\text{ Na }_{0.2-x}\text{ K }_{x}\text{ MnO }_{3}\) manganites. J Alloys Compd 650:676–683
Cui Y, Dy JG, Alexander B, Jiang SB (2008) Fluoroscopic gating without implanted fiducial markers for lung cancer radiotherapy based on support vector machines. Phys Med Biol 53(16):N315–N327
Ghodhbane S, Tka E, Dhahri J, Hlil EK (2014) A large magnetic entropy change near room temperature. J Alloys Compd 600:172–177
Gutierrez J, Bermejo FJ, Veglio N, Barandiaran JM, Romano P, Mondelli C, Gonzalez MA, Murani AP (2006) Structural correlations in \(\text{ La }_{0.7}\text{ Pb }_{0.3}\,(\text{ Mn }_{1-x}\text{ Fe }_{x})\text{ O }_{3}\) manganites as probed by small-angle and polarized neutron diffraction. J Phys Condens Matter 18(43):9951–9966
Han X, Chang X, Quan L, Xiong X, Li J, Zhang Z, Liu Y (2014) Feature subset selection by gravitational search algorithm optimization. Inf Sci 281:128–146
Ju FY, Hong WC (2013) Application of seasonal SVR with chaotic gravitational search algorithm in electricity forecasting. Appl Math Model 37(23):9643–9651
Kossi SEL, Ghodhbane S, Dhahri J, Hlil EK (2015) The impact of disorder on magnetocaloric properties in Ti-doped manganites of \(\text{ La }_{0.7}\text{ Sr }_{0.25}\text{ Na }_{0.05}\text{ Mn }_{(1-x)}\text{ Ti }_{x}\text{ O }_{3}\,(0 \le x \le 0.2)\). J Magn Magn Mater 395:134–142
Mahjoub S, Baazaoui M, M’nassri R, Rahmouni H, Boudjada NC, Oumezzine M (2014a) Effect of iron substitution on the structural, magnetic and magnetocaloric properties of \(\text{ Pr }_{0.6}\text{ Ca }_{0.1}\text{ Sr }_{0.3}\text{ Mn }_{1-x}\text{ Fe }_{x}\text{ O }_{3}\,(0\leqslant x \leqslant 0.075)\) manganites. J Alloys Compd 608:191–196
Mahjoub S, Baazaoui M, Rafik M, Rahmouni H, Chniba N, Neel I, Cedex G (2014b) Effect of iron substitution on the structural, magnetic and manganites. J Alloys Compd 608:191–196
Majid A, Khan A, Javed G, Mirza AM (2010) Lattice constant prediction of cubic and monoclinic perovskites using neural networks and support vector regression. Comput Mater Sci 50(2):363–372
Mleiki A, Othmani S, Cheikhrouhou-Koubaa W, Koubaa M, Cheikhrouhou A, Hlil EK (2015) Effect of praseodymium doping on the structural, magnetic and magnetocaloric properties of \(\text{ Sm }_{0.55-x}\text{ Pr }_{x}\text{ Sr }_{0.45}\text{ MnO }_{3}\) manganites. J Alloys Compd 645:559–565
Mn B, Fe À (2014) Effect of Fe-doping on structural, magnetic and magnetocaloric properties. Ceram Int 40(10):16041–16050
Niu P, Liu C, Li P (2015) Optimized support vector regression model by improved gravitational search algorithm for flatness pattern recognition. Neural Comput Appl 2015:1167–1177
Owolabi TO, Akande KO, Olatunji SO (2015a) Estimation of superconducting transition temperature \(T_{\rm C}\) for superconductors of the doped \(\text{ MgB }_{2}\) system from the crystal lattice parameters using support vector regression. J Supercond Nov Magn 28(1):75–81
Owolabi TO, Akande KO, Sunday OO (2015b) Modeling of average surface energy estimator using computational intelligence technique. Multidiscip Model Mater Struct 11(2):284–296
Owolabi TO, Akande KO, Olatunji SO (2015c) Development and validation of surface energies estimator (SEE) using computational intelligence technique. Comput Mater Sci 101:143–151
Owolabi TO, Akande KO, Olatunji SO (2015d) Estimation of surface energies of hexagonal close packed metals using computational intelligence technique. Appl Soft Comput 31:360–368
Owolabi TO, Akande KO, Olatunji SO (2015e) Estimation of surface energies of transition metal carbides using machine learning approach. Int J Mater Sci Eng 3(2):104–119
Owolabi TO, Akande KO, Olatunji SO (2016a) Computational intelligence method of estimating solid–liquid interfacial energy of materials at their melting temperatures. J Intell Fuzzy Syst 31(1):519–527
Owolabi TO, Akande KO, Olatunji SO (2016b) Application of computational intelligence technique for estimating superconducting transition temperature of YBCO superconductors. Appl Soft Comput 43:143–149
Phan MH, Yu SC (2007) Review of the magnetocaloric effect in manganite materials. J Magn Magn Mater 308(2):325–340
Rashedi E, Nezamabadi-pour H, Saryazdi S (2009) GSA: a gravitational search algorithm. Inf Sci 179(13):2232–2248
Rezaei M, Nezamabadi-pour H (2015) Using gravitational search algorithm in prototype generation for nearest neighbor classification. Neurocomputing 157(2015):256–263
Selmi A, M’nassri R, Cheikhrouhou-Koubaa W, Boudjada NC, Cheikhrouhou A (2015a) Influence of transition metal doping (Fe Co, Ni and Cr) on magnetic and magnetocaloric properties of \(\text{ Pr }_{0.7}\text{ Ca }_{0.3}\text{ MnO }_{3}\) manganites. Ceram Int 41(8):10177–10184
Selmi A, M’nassri R, Cheikhrouhou-Koubaa W, Boudjada NC, Cheikhrouhou A (2015b) Effects of partial Mn-substitution on magnetic and magnetocaloric properties in \(\text{ Pr }_{0.7}\text{ Ca }_{0.3}\text{ Mn }_{0.95}\text{ X }_{0.05}\text{ O }_{3}\) (Cr, Ni, Co and Fe) manganites. J Alloys Compd 619:627–633
Selmi A, M’nassri R, Cheikhrouhou-Koubaa W, Boudjada NC, Cheikhrouhou A (2015c) The effect of Co doping on the magnetic and magnetocaloric properties of \(\text{ Pr }_{0.7}\text{ Ca }_{0.3}\text{ Mn }_{1-x}\text{ Co }_{x}\text{ O }_{3}\) manganites. Ceram Int 41(6):7723–7728
Selmi A, M’nassri R, Boudjada NC, Cheikhrouhou A (2015d) The effect of Co doping on the magnetic and magnetocaloric properties. Ceram Int 41(6):7723–7728
Vapnik V (1995) The nature of statistical learning theory. Springer, New York
Varvescu A, Deac IG (2015) Critical magnetic behavior and large magnetocaloric effect in \(\text{ Pr }_{0.67}\text{ Ba }_{0.33}\text{ MnO }_{3}\) perovskite manganite. Phys B Condens Matter 470–471:96–101
Wang Z, Jiang J (2013) Magnetic entropy change in perovskite manganites \(\text{ La }_{0.7}\text{ A }_{0.3}\text{ MnO }_{3}\) transition. Solid State Sci 18:36–41
Xiang J, Han X, Duan F, Qiang Y, Xiong X, Lan Y, Chai H (2015) A novel hybrid system for feature selection based on an improved gravitational search algorithm and k-NN method. Appl Soft Comput 31(2015):293–307
Acknowledgements
The support received from University of Dammam is acknowledged.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
This article does not contain any studies with animals performed by any of the authors.
Informed consent
This article does not contain studies with human participants.
Additional information
Communicated by V. Loia.
Rights and permissions
About this article
Cite this article
Owolabi, T.O., Akande, K.O., Olatunji, S.O. et al. Modeling of Curie temperature of manganite for magnetic refrigeration application using manual search and hybrid gravitational-based support vector regression. Soft Comput 22, 3023–3032 (2018). https://doi.org/10.1007/s00500-017-2554-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-017-2554-2