J. Mater. Sci. Technol. ›› 2020, Vol. 53: 41-52.DOI: 10.1016/j.jmst.2020.01.069
• Research Article • Previous Articles Next Articles
Wei Hua,b, Zhongwei Maa, Shude Jia,b,*(), Qi Songa,b,*(), Mingfei Chenb, Wenhui Jiangb,c
Received:
2019-12-09
Revised:
2020-01-03
Accepted:
2020-01-28
Published:
2020-09-15
Online:
2020-09-21
Contact:
Shude Ji,Qi Song
Wei Hu, Zhongwei Ma, Shude Ji, Qi Song, Mingfei Chen, Wenhui Jiang. Improving the mechanical property of dissimilar Al/Mg hybrid friction stir welding joint by PIO-ANN[J]. J. Mater. Sci. Technol., 2020, 53: 41-52.
No. | Ultrasonic power (W) | Welding speed (mm/min) | Rotational velocity (rpm) | UST (MPa) | Data source |
---|---|---|---|---|---|
1 | 0 | 30 | 900 | 81 | This study |
2 | 0 | 30 | 1000 | 77 | [ |
3 | 0 | 30 | 1100 | 53 | This study |
4 | 0 | 40 | 900 | 109 | This study |
5 | 0 | 40 | 1000 | 126 | This study |
6 | 0 | 40 | 1200 | 66 | [ |
7 | 0 | 50 | 900 | 122 | This study |
8 | 0 | 50 | 1000 | 134 | This study |
9 | 0 | 50 | 1100 | 119 | This study |
10 | 0 | 60 | 900 | 147 | This study |
11 | 0 | 60 | 1000 | 137 | [ |
12 | 0 | 60 | 1100 | 117 | This study |
13 | 0 | 70 | 1000 | 118 | This study |
14 | 0 | 70 | 1100 | 110 | This study |
15 | 0 | 80 | 1100 | 79 | This study |
16 | 600 | 30 | 1000 | 94 | This study |
17 | 600 | 60 | 1000 | 131 | This study |
18 | 600 | 80 | 1000 | 58 | [ |
19 | 1000 | 30 | 1000 | 115 | [ |
20 | 1000 | 60 | 1000 | 133 | This study |
21 | 1000 | 80 | 1000 | 87 | [ |
22 | 1400 | 30 | 1000 | 113 | This study |
23 | 1400 | 60 | 1000 | 152 | [ |
24 | 1400 | 80 | 1000 | 134 | [ |
25 | 1800 | 30 | 1000 | 92 | This study |
26 | 1800 | 60 | 1000 | 120 | This study |
27 | 1800 | 80 | 1000 | 80 | [ |
Table 1 Training and testing data samples for PIO-ANN.
No. | Ultrasonic power (W) | Welding speed (mm/min) | Rotational velocity (rpm) | UST (MPa) | Data source |
---|---|---|---|---|---|
1 | 0 | 30 | 900 | 81 | This study |
2 | 0 | 30 | 1000 | 77 | [ |
3 | 0 | 30 | 1100 | 53 | This study |
4 | 0 | 40 | 900 | 109 | This study |
5 | 0 | 40 | 1000 | 126 | This study |
6 | 0 | 40 | 1200 | 66 | [ |
7 | 0 | 50 | 900 | 122 | This study |
8 | 0 | 50 | 1000 | 134 | This study |
9 | 0 | 50 | 1100 | 119 | This study |
10 | 0 | 60 | 900 | 147 | This study |
11 | 0 | 60 | 1000 | 137 | [ |
12 | 0 | 60 | 1100 | 117 | This study |
13 | 0 | 70 | 1000 | 118 | This study |
14 | 0 | 70 | 1100 | 110 | This study |
15 | 0 | 80 | 1100 | 79 | This study |
16 | 600 | 30 | 1000 | 94 | This study |
17 | 600 | 60 | 1000 | 131 | This study |
18 | 600 | 80 | 1000 | 58 | [ |
19 | 1000 | 30 | 1000 | 115 | [ |
20 | 1000 | 60 | 1000 | 133 | This study |
21 | 1000 | 80 | 1000 | 87 | [ |
22 | 1400 | 30 | 1000 | 113 | This study |
23 | 1400 | 60 | 1000 | 152 | [ |
24 | 1400 | 80 | 1000 | 134 | [ |
25 | 1800 | 30 | 1000 | 92 | This study |
26 | 1800 | 60 | 1000 | 120 | This study |
27 | 1800 | 80 | 1000 | 80 | [ |
Number of neurons in HL | Coef?cient of transfer functions | Learning rate | Maximum number of iterations | |
---|---|---|---|---|
For HL | For OL | |||
5 | 1 | 1 | 0.01 | 200 |
Table 2 Basic sets for PIO-ANN optimization.
Number of neurons in HL | Coef?cient of transfer functions | Learning rate | Maximum number of iterations | |
---|---|---|---|---|
For HL | For OL | |||
5 | 1 | 1 | 0.01 | 200 |
Weight from IL to HL | Threshold of HL | Weight from HL to OL | Threshold of OL | |||
---|---|---|---|---|---|---|
Neurons in HL | Ultrasonic power | Welding speed | Rotational velocity | |||
1 | -1.1821 | 1.8069 | -3.8399 | 3.8629 | 0.5677 | |
2 | -0.5422 | -9.1515 | 3.5741 | 3.5336 | 0.1663 | |
3 | 1.0517 | -1.3441 | -0.3198 | -2.0775 | 0.0617 | 0.7107 |
4 | 0.0861 | 1.2462 | 2.7584 | 0.4734 | -0.3746 | |
5 | 0.3675 | 4.436 | 1.3536 | 3.9955 | 0.7852 |
Table 3 PIO-ANN structure with the most accurate prediction.
Weight from IL to HL | Threshold of HL | Weight from HL to OL | Threshold of OL | |||
---|---|---|---|---|---|---|
Neurons in HL | Ultrasonic power | Welding speed | Rotational velocity | |||
1 | -1.1821 | 1.8069 | -3.8399 | 3.8629 | 0.5677 | |
2 | -0.5422 | -9.1515 | 3.5741 | 3.5336 | 0.1663 | |
3 | 1.0517 | -1.3441 | -0.3198 | -2.0775 | 0.0617 | 0.7107 |
4 | 0.0861 | 1.2462 | 2.7584 | 0.4734 | -0.3746 | |
5 | 0.3675 | 4.436 | 1.3536 | 3.9955 | 0.7852 |
Fig. 5. Training and prediction results of PIO-ANN: (a) mean squared errors, (b) comparisons between the predicted and verified results and (c) evolutionary curve.
Ultrasonic power (W) | Welding speed (mm/min) | Rotational velocity (rpm) | Predicted tensile strength (MPa) | Actual tensile strength (MPa) | Deviation |
---|---|---|---|---|---|
1426 | 63 | 997 | 165 | 161 | 2.5% |
Table 4 Optimization results based on PIO optimization.
Ultrasonic power (W) | Welding speed (mm/min) | Rotational velocity (rpm) | Predicted tensile strength (MPa) | Actual tensile strength (MPa) | Deviation |
---|---|---|---|---|---|
1426 | 63 | 997 | 165 | 161 | 2.5% |
Position | Al (at.%) | Mg (at.%) |
---|---|---|
1 | 98.41 | 1.59 |
2 | 3.98 | 96.02 |
3 | 65.73 | 34.27 |
4 | 53.46 | 46.54 |
5 | 46.06 | 53.94 |
6 | 41.69 | 58.31 |
Table 5 EDS spot scanning results.
Position | Al (at.%) | Mg (at.%) |
---|---|---|
1 | 98.41 | 1.59 |
2 | 3.98 | 96.02 |
3 | 65.73 | 34.27 |
4 | 53.46 | 46.54 |
5 | 46.06 | 53.94 |
6 | 41.69 | 58.31 |
Fig. 12. (a) Macro morphology of fracture surface; (b) enlarged view of local region marked in Fig. 12(a); enlarged view of local region marked in Fig. 12(b): (c) region A, (d) region B, (e) region C and (f) region D.
[1] | Z. Ma, Y. Jin, S. Ji, X. Meng, L. Ma, Q. Li, J. Mater. Sci. Technol. 35 (2019) 94-99. |
[2] | B. He, L. Cui, D.P. Wang, H.J. Li, C.X. Liu, Acta Metall. Sin. (Engl. Lett.) 33 (2019) 135-146. |
[3] | Y. Chen, S. Chen, L. Li, Int. J. Adv. Manuf. Technol 44 (2009) 265-272. |
[4] | Y.B. Zhong, C.S. Wu, G.K. Padhy, J. Mater, Process. Technol. 239 (2017) 273-283. |
[5] | G.K. Padhy, C.S. Wu, S. Gao, Mater. Des. 116 (2017) 207-218. |
[6] | X.C. Liu, C.S. Wu, Mater. Des. 90 (2016) 350-358. |
[7] |
Z. Xu, Z. Li, J. Li, Z. Ma, J. Yan, Ultrason. Sonochem. 46 (2018) 79-88.
DOI URL PMID |
[8] | W.F. Xu, X.K. Wu, J. Ma, H.J. Lu, Y.X. Luo, J. Mater. Res. Technol. 8 (2019) 6029-6040. |
[9] |
Y. Huang, J. Wang, L. Wan, X. Meng, H. Liu, H. Li, Mater. Lett. 185 (2016) 181-184.
DOI URL |
[10] | Y. Huang, X. Meng, Y. Xie, J. Li, L. Wan, Compos. Part A-Appl. Sci. Manuf. 112 (2018) 328-336. |
[11] | Y. Huang, X. Meng, Y. Xie, L. Wan, Z. Lv, J. Cao, J. Feng, Compos. Part A-Appl. Sci. Manuf. 105 (2018) 235-257. |
[12] | S.D. Ji, X.C. Meng, J.G. Liu, L.G. Zhang, S.S. Gao, Mater. Des. 62 (2014) 113-117. |
[13] | X.Q. Lv, C.S. Wu, G.K. Padhy, Mater. Lett. 203 (2017) 81-84. |
[14] | S. Ji, X. Meng, Z. Liu, R. Huang, Z. Li, Mater. Lett. 201 (2017) 173-176. |
[15] | Z. Liu, S. Ji, X. Meng, J. Mater, Eng. Perform. 27 (2018) 1404-1413. |
[16] | Z. Liu, X. Meng, S. Ji, Z. Li, L. Wang, J. Manuf. Process. 31 (2018) 552-559. |
[17] | W.K. Kim, B.C. Goo, S.T. Won, Mater. Manuf. Process. 25 (2010) 637-643. |
[18] | M. Koilraj, V. Sundareswaran, S. Vijayan, S.R. Koteswara Rao, Mater. Des. 42 (2012) 1-7. |
[19] |
K.Y. Benyounis, A.G. Olabi, Adv. Eng. Softw. 39 (2008) 483-496.
DOI URL |
[20] | H. Darzi Naghibi, M. Shakeri, M. Hosseinzadeh, Trans. Ind. Inst. Metals 69 (2016) 891-900. |
[21] | N. Zhou, J. Zhang, J. Feng, S. Liu, J. Comput. 7 (2012) 1887-1894. |
[22] | J. Kennedy, R. Eberhart, ICNN’95: Int. Conf. Neural Networks, Vol. 4, 1995, pp. 1942-1948. |
[23] |
D. Karaboga, B. Basturk, J. Glob. Optim. 39 (2007) 459-471.
DOI URL |
[24] | E. Atashpaz-Gargari, C. Lucas, 2007 IEEE Congr. Evol. Comput. CEC 2007,2007, pp. 4661-4667. |
[25] | Y. Shi, Emerg. Res. Swarm Intell. Algorithm Optim, IGI Global, Hershey, PA, USA, 2015, pp. 1-35. |
[26] | H. Duan, P. Qiao, Int. J. Intell. Comput. Cybern. 7 (2014) 24-37. |
[27] | S. Ji, S. Niu, J. Liu, J. Mater, Sci. Technol. 35 (2019) 1712-1718. |
[28] | Z. Liu, S. Ji, X. Meng, Int. J. Adv. Manuf. Technol. 97 (2018) 4127-4136. |
[29] | S. Ji, R. Huang, X. Meng, L. Zhang, Y. Huang, J. Mater, Eng. Perform. 26 (2017) 2359-2367. |
[30] | X. Meng, Y. Jin, S. Ji, D. Yan, J. Mater. Sci. Technol 34 (2018) 1817-1822. |
[31] | K. Anand, B. Kumar Barik, K. Tamilmannan, P. Sathiya, Eng. Sci. Technol. Int. J. 18 (2015) 394-407. |
[32] | K. Kamal Babu, K. Panneerselvam, P. Sathiya, A. Noorul Haq, S. Sundarrajan, P. Mastanaiah, C.V. Srinivasa Murthy, Int. J. Adv. Manuf. Technol. 94 (2018) 3117-3129. |
[33] | H. Darzi Naghibi, M. Shakeri, M. Hosseinzadeh, Trans. Ind. Inst. Met. 69 (2016) 891-900. |
[34] | Z. Li, Y. Yue, S. Ji, P. Chai, Z. Zhou, Mater. Des. 90 (2016) 238-247. |
[35] | Z. Zhou, Y. Yue, S. Ji, Z. Li, L. Zhang, Int. J. Adv. Manuf. Technol. 88 (2017) 2135-2141. |
[36] | Y.S. Sato, S.H.C. Park, M. Michiuchi, H. Kokawa, Scr. Mater. 50 (2004) 1233-1236. |
[37] | T. Yuan, S. Kou, Z. Luo, Acta Mater 106 (2016) 144-154. |
[38] | P. Dong, D. Sun, H. Li, Mater. Sci. Eng. A 576 (2013) 29-35. |
[39] | W.F. Xu, Y.X. Luo, M.W. Fu, Mater. Charact. 138 (2018) 48-55. |
[40] | Z.H. Zhang, W.Y. Li, Y. Feng, J.L. Li, Y.J. Chao, Acta Mater 92 (2015) 117-125. |
[41] | Z. Zhang, X. Yang, J. Manuf. Syst. 33 (2017) 987-990. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||