Prediction of Compression Ratio of I.C. Engine Selective Assembly Using Adaptive-Neuro Fuzzy Inference System
Tóm tắt
Selective assembly is a technique that improves the quality of product assemblies made from low-quality parts. Prior to assembly, parts are sorted and grouped by size. However, even if parts are within tolerance limits, variations in size due to geometrical dimensions and tolerance can have a significant impact on the final output. Despite significant research on selected assembly modeling to reduce the need for extra parts and minimize tolerance differences, the resulting assemblies still fail to meet required standards. This study examines how the adaptive neuro-fuzzy inference method (ANFIS) can predict accurate compression ratios for the random selection of assembly components from bins. To gather data, real measurements were taken of engine assembly parts. This experimental data was used to build the ANFIS model, which correlated assembly part sizes with compression ratio. The study involved measuring the sizes of assembly parts, which were then used to train and test an ANFIS model. The accuracy of the ANFIS predictions was assessed by comparing the model’s results to actual values. The ANFIS model demonstrated a maximum correlation coefficient (R) of 0.9900–0.9999 and an accuracy of 95.3594% in predicting compression ratio. Root mean square errors (RMSE) were also low, and the mean relative errors (MRE) ranged from 0.055 to 8.396% (RMSE). The results showed that the ANFIS model was able to accurately predict engine compression ratio during the assembly process. The findings suggest that the ANFIS approach can be a useful tool in reducing the workload required for engine assembly by accurately predicting compression ratio.
Tài liệu tham khảo
M. Hallmann, B. Schleich, S. Wartzack, Int. J. Adv. Manuf. Technol. 107, 4859 (2020). https://doi.org/10.1007/s00170-020-05254-5
A. R. Aderiani, K. Wärmefjord, R. Söderberg, J. Manufact. Sci. Eng. 140, 071015 (2018). https://doi.org/10.1115/1.4039767.
S. M. Kannan, G. Raja Pandian, Int. J. Precis. Eng. Manuf. 21, 1217 (2020). https://doi.org/10.1007/s12541-019-00287-7.
R. Weill, Robot. Comput. Integr. Manuf. 4, 41 (1988). https://doi.org/10.1016/0736-5845(88)90058-0
Y. Zhang, Z. Li, J. Gao, J. Hong, F. Villecco, Y. Li, Math. Probl. Eng. 2012, 1 (2012). https://doi.org/10.1155/2012/513958
D. Vignesh Kumar, D. Ravindran, N. Lenin, M. Siva Kumar, Proc. Inst. Mech. Eng. C: J. Mech. Eng. Sci. 233, 18 (2019). https://doi.org/10.1177/0954406218756439.
M.N. Islam, Int. J. Adv. Manuf. Technol. 42, 910 (2009). https://doi.org/10.1007/s00170-008-1649-4
A.K. Jeevanantham, S.V. Chaitanya, A. Rajeshkannan, Int. J. Precis. Eng. Manuf. 20, 1801 (2019). https://doi.org/10.1007/s12541-019-00194-x
A. Lu, J.-F. Fei, Proc. Inst. Mech. Eng. B: J. Eng. Manuf. 229, 508 (2015). https://doi.org/10.1177/0954405414530896
C. Sinanoğlu, H. Rıza Börklü, Assem. Autom. 25, 38 (2005). https://doi.org/10.1108/01445150510578996.
J.-S. R. Jang, IEEE Trans. Syst., Man, Cybern. 23, 665 (1993). https://doi.org/10.1109/21.256541.
H. Metin Ertunc and M. Hosoz, Int. J. Refrigeration 31, 1426 (2008). https://doi.org/10.1016/j.ijrefrig.2008.03.007.
A.N. Bhatt, N. Shrivastava, Arch. Computat. Methods Eng. 29, 897 (2022). https://doi.org/10.1007/s11831-021-09596-5
A. Hasiloglu, M. Yilmaz, O. Comakli, İ Ekmekci, Int. J. Therm. Sci. 43, 1075 (2004). https://doi.org/10.1016/j.ijthermalsci.2004.01.010
H. Esen, M. Inalli, A. Sengur, M. Esen, Energy Build.40, 1074 (2008). https://doi.org/10.1016/j.enbuild.2007.10.002
H. Esen, M. Inalli, A. Sengur, M. Esen, Int. J. Refrig 31, 65 (2008). https://doi.org/10.1016/j.ijrefrig.2007.06.007
M.K. Das, N. Kishor, Expert Syst. Appl. 36, 1142 (2009). https://doi.org/10.1016/j.eswa.2007.10.044
A.Ş Şahin, Renew. Energy 36, 2747 (2011). https://doi.org/10.1016/j.renene.2011.03.009
R.B. Ruben, P. Asokan, S. Vinodh, Int. J. Sustain. Eng. 10, 158 (2017). https://doi.org/10.1080/19397038.2017.1286409
U. Çaydaş, A. Hasçalık, S. Ekici, Expert Syst. Appl. 36, 6135 (2009). https://doi.org/10.1016/j.eswa.2008.07.019
S. M. More, J. Kakati, S. Pal, U. K. Saha, J. Comput. Inform. Sci. Eng. 22, 050801 (2022).https://doi.org/10.1115/1.4053920
A.Chakraborty, S. Roy, R. Banerjee, Heat Mass Transfer 54, 2725 (2018).https://doi.org/10.1007/s00231-018-2312-8
A.Yasar, B. S. Kul, and M. Ciniviz, J. Energy Resources Technol. 144, 122305 (2022). https://doi.org/10.1115/1.4054699
M. Hosoz, H. M. Ertunc, and H. Bulgurcu, Expert Syst. Applications, S0957417411007524 (2011). https://doi.org/10.1016/j.eswa.2011.04.225