Prevention of the Fracture Problem Occurring in Automotive Alternator Heatsink Blocks Using Artificial Intelligence
Abstract
:1. Introduction
2. The Proposed Approach
2.1. Data Measurement from Bench Test
2.2. Verification of Results with Simulation
2.3. Other Design and Simulation Studies
3. Optimization of Alternator Heatsink
3.1. Design of the Experiment
3.2. Surrogate Modeling
3.3. Optimization
4. Conclusions
- In rotating machines used in vehicles, each component within the machine is subjected to excitation at different frequencies, both from the machine itself and from the effects of the vehicle. This situation, frequently encountered in vibration tests of components, leads to breakage, cracking and separation, necessitating product redesign and resolution of the resonance-related problems. The required redesign and simulation studies result in significant time losses and high costs. Developing artificial intelligence models that can predict the natural frequency of similar components can be used as an important time-saving and cost-reduction method in addressing recurrent resonance-related breakage and cracking problems.
- ANN and MATLAB Simulink regression models provided accurate approximations compared to the finite element analysis, while significantly reducing computation time and effort.
- Six of the methods used for the alternator heatsink optimization problem, except PSO, gave the same value and were found to be suitable for the alternator heatsink optimization problem.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Karthik, C.A.; Kalita, P.; Cui, X.; Peng, X. Thermal management for prevention of failures of lithium ion battery packs in electric vehicles: A review and critical future aspects. Energy Storage 2020, 2, e137. [Google Scholar] [CrossRef]
- Wu, Y.; Li, N.; Liu, Y.; Tang, L.; Cao, W. Research on parameter estimation methods of fatigue life distribution model of automotive chassis parts. Adv. Mech. Eng. 2022, 14, 168781322211177. [Google Scholar] [CrossRef]
- An, Z.; Jia, L.; Ding, Y.; Dang, C.; Li, X. A review on lithium-ion power battery thermal management technologies and thermal safety. J. Therm. Sci. 2017, 26, 391–412. [Google Scholar] [CrossRef]
- Tarı, İ.; Yalcin, F.S. CFD Analyses of a Notebook Computer Thermal Management System and a Proposed Passive Cooling Alternative. IEEE Trans. Compon. Packag. Technol. 2010, 33, 443–452. [Google Scholar] [CrossRef]
- Golahmar, A.; Niordson, C.F.; Martínez-Pañeda, E. A phase field model for high-cycle fatigue: Total-life analysis. Int. J. Fatigue 2023, 170, 107558. [Google Scholar] [CrossRef]
- Nikitin, I.; Nikitin, A.; Wang, C. Calculation of fatigue fracture in structural elements using a multimode damage model. In Proceedings of the XXII International Conference on Computational Mechanics and Modern Applied Software Systems (CMMASS 2021), Alushta, Crimea, 4–13 September 2021; EDP Sciences: Ulis, France, 2022; Volume 362, p. 01018. [Google Scholar] [CrossRef]
- Wang, D.; Han, C.; Wang, L.; Li, X.; Cai, E.; Zhang, P. Surface roughness prediction of large shaft grinding via attentional CNN-LSTM fusing multiple process signals. Int. J. Adv. Manuf. Technol. 2023, 126, 4925–4936. [Google Scholar] [CrossRef]
- Kong, Y.; Abdullah, S.; Schramm, D.; Omar, M.Z.; Haris, S.M.; Brückmann, T.; Kracht, F.E. Characterizing Spring Durability for Automotive Ride Using Artificial Neural Network Analysis. Int. J. Eng. Technol. (UAE) 2018, 7, 47. [Google Scholar] [CrossRef]
- Krejsa, M.; Brožovský, J.; Lehner, P.; Seitl, S.; Kala, Z.; Krejsa, V. Probabilistic fatigue analysis of existing steel structure. In Proceedings of the 4th International Scientific Conference Structural and Physical Aspects of Construction Engineering (SPACE 2019), Strbske Pleso, Slovakia, 13–15 November 2019; EDP Sciences: Ulis, France, 2020; Volume 310, p. 00012. [Google Scholar] [CrossRef]
- Topaloğlu, A.; Kaya, N.; Öztürk, F. Predictions of the design decisions for vehicle alloy wheel rims using neural network. Proc. Inst. Mech. Eng. Part D J. Automob. Eng. 2023, 237, 2913–2927. [Google Scholar] [CrossRef]
- Huang, C.; Zhao, Y.; Jin, G. Finite Element Modeling and Vibration Analysis of Sprag Clutch-Flexible Rotor System. Res. Sq. 2020. [Google Scholar] [CrossRef]
- Kreitzer, S.; Obermeyer, J.; Mistry, R. The Effects of Structural and Localized Resonances on Induction Motor Performance. IEEE Trans. Ind. Appl. 2008, 44, 1367–1375. [Google Scholar] [CrossRef]
- Castillo-Villar, K.K.; Herbert-Acero, J.F. A Metaheuristic-Based Approach for the Capacitated Supply Chain Network Design Problem Including Imperfect Quality and Rework. IEEE Comput. Intell. Mag. 2014, 9, 31–45. [Google Scholar] [CrossRef]
- Agarwal, A.; Chandra, A.; Shalivahan, S.; Singh, R.K. Grey wolf optimizer: A new strategy to invert geophysical data sets. Geophys. Prospect. 2018, 66, 1215–1226. [Google Scholar] [CrossRef]
- Küçükoglu, I.; Öztürk, N. A differential evolution approach for the vehicle routing problem with backhauls and time windows. J. Adv. Transp. 2014, 48, 942–956. [Google Scholar] [CrossRef]
- Ene, S.; Küçükoglu, I.; Aksoy, A.; Öztürk, N. A hybrid metaheuristic algorithm for the green vehicle routing problem with a heterogeneous fleet. Int. J. Veh. Des. 2016, 71, 75–102. [Google Scholar] [CrossRef]
- Küçükoglu, I.; Öztürk, N. Two-stage optimization method for material flow and allocation management in cross-docking networks. Int. J. Prod. Res. 2017, 55, 410–429. [Google Scholar] [CrossRef]
- Dallagnol, V.A.F.; Berg, J.V.D.; Mous, L. Portfolio management using value at risk: A comparison between genetic algorithms and particle swarm optimization. Int. J. Intell. Syst. 2009, 24, 766–792. [Google Scholar] [CrossRef]
- Wu, D.; Wang, S.; Liu, Q.; Abualigah, L.; Jia, H. An Improved Teaching-Learning-Based Optimization Algorithm with Reinforcement Learning Strategy for Solving Optimization Problems. Comput. Intell. Neurosci. 2022, 2022, 1535957. [Google Scholar] [CrossRef]
- Kankar, P.K.; Sharma, S.C.; Harsha, S.P. Fault diagnosis of ball bearings using machine learning methods. Expert Syst. Appl. 2011, 38, 1876–1886. [Google Scholar] [CrossRef]
- Gopinath, S.; Sathiyasekar, K.; Padmanaban, S.; Chokkalingam, B. Insulation condition assessment of high-voltage rotating machines using hybrid techniques. IET Gener. Transm. Distrib. 2019, 13, 171–180. [Google Scholar] [CrossRef]
- Bıçakçı, S.; Çoramık, M.; Güneş, H.; Çıtak, H.; Ege, Y. A New Artificial Neural Network-Based Failure Determination System for Electric Motors. Arab. J. Sci. Eng. 2022, 47, 835–847. [Google Scholar] [CrossRef]
- Çallı, M.; Albak, E.İ.; Öztürk, F. Prediction and optimization of the design and process parameters of a hybrid DED product using artificial intelligence. Appl. Sci. 2022, 12, 5027. [Google Scholar] [CrossRef]
- Albak, E.İ.; Solmaz, E.; Kaya, N.; Öztürk, F. Impact attenuator conceptual design using lightweight materials and meta-modeling technique. Mater. Test. 2019, 61, 621–626. [Google Scholar] [CrossRef]
- Abdel-Basset, M.; Mohamed, R.; Jasser, M.B.; Hezam, I.M.; Mohamed, A.W. Developments on metaheuristic-based optimization for numerical and engineering optimization problems: Analysis, design, validation, and applications. Alex. Eng. J. 2023, 78, 175–212. [Google Scholar] [CrossRef]
- Abualigah, L.; Diabat, A.; Mirjalili, S.; Abd Elaziz, M.; Gandomi, A.H. The arithmetic optimization algorithm. Comput. Methods Appl. Mech. Eng. 2021, 376, 113609. [Google Scholar] [CrossRef]
- Abualigah, L.; Yousri, D.; Abd Elaziz, M.; Ewees, A.A.; Al-qaness, M.A.; Gandomi, A.H. Aquila Optimizer: A novel meta-heuristic optimization Algorithm. Comput. Ind. Eng. 2021, 157, 107250. [Google Scholar] [CrossRef]
- Abdollahzadeh, B.; Gharehchopogh, F.S.; Mirjalili, S. African vultures optimization algorithm: A new nature-inspired metaheuristic algorithm for global optimization problems. Comput. Ind. Eng. 2021, 158, 107408. [Google Scholar] [CrossRef]
- Faramarzi, A.; Heidarinejad, M.; Stephens, B.; Mirjalili, S. Equilibrium optimizer: A novel optimization algorithm. Knowl.-Based Syst. 2020, 191, 105190. [Google Scholar] [CrossRef]
- Holland, J.H. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence; MIT Press: Cambridge, MA, USA, 1992. [Google Scholar]
- Kennedy, J.; Eberhart, R. Particle swarm optimization. In Proceedings of the ICNN’95 International Conference on Neural Networks, Perth, WA, Australia, 27 November–1 December 1995; IEEE: Piscataway, NJ, USA, 1995; Volume 4, pp. 1942–1948. [Google Scholar]
- ANSYS 2019 R2. Available online: https://www.ansys.com/ (accessed on 26 June 2024).
- Staudemeyer, R.C.; Morris, E.R. Understanding LSTM—A tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv 2019, arXiv:1909.09586. [Google Scholar]
- Almási, A.-D.; Woźniak, S.; Cristea, V.; Leblebici, Y.; Engbersen, T. Review of advances in neural networks: Neural design technology stack. Neurocomputing 2016, 174, 31–41. [Google Scholar] [CrossRef]
- MATLAB R2024a. Available online: https://www.mathworks.com/products/matlab.html (accessed on 17 June 2024).
- Shu, C.; Zhao, S.; Hou, S. Crashworthiness analysis of two-layered corrugated sandwich panels under crushing loading. Thin Walled Struct. 2018, 133, 42–51. [Google Scholar] [CrossRef]
Mode | Frequency [Hz] | Amplitude [g] | Type |
---|---|---|---|
1 | 202.93 | 27.311 | Structural Mode |
2 | 321.05 | 13.539 | Local Mode |
3 | 383.28 | 25.356 | Structural Mode |
4 | 447.80 | 11.989 | Local Mode |
5 | 496.17 | 9.681 | Local Mode (B+) |
No. | B+ Section Thickness [mm] | Bolt Hole Thickness [mm] | B+ Cable Weight [gr] | Heatsink Natural Frequency [Hz] | No. | B+ Section Thickness [mm] | Bolt Hole Thickness [mm] | B+ Cable Weight [gr] | Heatsink Natural Frequency [Hz] |
---|---|---|---|---|---|---|---|---|---|
1 | 3.1798 | 3.5748 | 48.976 | 640.86 | 31 | 3.4210 | 3.5510 | 61.954 | 583.73 |
2 | 3.3804 | 3.0856 | 44.893 | 621.36 | 32 | 3.2184 | 3.4011 | 49.840 | 625.07 |
3 | 2.7048 | 3.9377 | 68.170 | 578.10 | 33 | 3.2862 | 3.1431 | 44.326 | 632.38 |
4 | 2.5697 | 3.3517 | 41.209 | 664.23 | 34 | 3.0219 | 3.5098 | 65.422 | 565.29 |
5 | 2.6675 | 3.2548 | 55.300 | 577.60 | 35 | 3.2326 | 3.4558 | 62.302 | 574.99 |
6 | 2.8129 | 3.1811 | 56.647 | 564.65 | 36 | 2.7844 | 3.6066 | 47.941 | 644.17 |
7 | 2.7494 | 3.3276 | 57.223 | 580.72 | 37 | 2.6466 | 3.8574 | 46.756 | 664.94 |
8 | 3.4012 | 3.2454 | 65.815 | 545.80 | 38 | 2.7802 | 3.7363 | 50.230 | 645.86 |
9 | 2.5317 | 3.7219 | 40.249 | 697.15 | 39 | 3.0458 | 3.9056 | 64.972 | 590.18 |
10 | 3.0568 | 3.1196 | 63.787 | 535.06 | 40 | 3.3260 | 3.0674 | 64.126 | 533.36 |
11 | 2.5889 | 3.2956 | 53.392 | 590.51 | 41 | 2.7533 | 3.2229 | 54.412 | 582.08 |
12 | 3.3419 | 3.3045 | 58.888 | 576.01 | 42 | 2.9204 | 3.4932 | 54.571 | 604.01 |
13 | 2.5951 | 3.9318 | 46.375 | 677.06 | 43 | 3.3713 | 3.9784 | 48.550 | 677.80 |
14 | 2.9979 | 3.4259 | 53.977 | 602.48 | 44 | 3.1056 | 3.8284 | 59.272 | 612.14 |
15 | 3.4948 | 3.8043 | 59.755 | 610.23 | 45 | 3.4827 | 3.4781 | 63.406 | 575.81 |
16 | 2.8454 | 3.6593 | 69.727 | 554.45 | 46 | 2.6116 | 3.3681 | 51.163 | 610.99 |
17 | 2.5234 | 3.8154 | 51.544 | 634.16 | 47 | 3.3016 | 3.1069 | 51.841 | 587.27 |
18 | 2.6310 | 3.1689 | 42.709 | 629.23 | 48 | 3.1135 | 3.7762 | 52.330 | 642.21 |
19 | 2.8815 | 3.9981 | 40.834 | 720.18 | 49 | 2.7242 | 3.5420 | 48.073 | 638.60 |
20 | 2.8016 | 3.8778 | 56.161 | 625.90 | 50 | 2.9763 | 3.2048 | 57.577 | 566.34 |
21 | 2.6870 | 3.0525 | 62.767 | 529.76 | 51 | 2.9012 | 3.4180 | 66.520 | 549.22 |
22 | 3.4293 | 3.5310 | 58.402 | 601.96 | 52 | 3.0678 | 3.1983 | 66.901 | 532.96 |
23 | 3.1401 | 3.3298 | 50.749 | 613.34 | 53 | 3.2482 | 3.7905 | 60.694 | 601.47 |
24 | 3.4558 | 3.6951 | 68.665 | 570.91 | 54 | 2.5602 | 3.3796 | 47.185 | 627.39 |
25 | 2.9634 | 3.2727 | 52.807 | 593.34 | 55 | 3.2809 | 3.9665 | 58.036 | 627.93 |
26 | 3.4399 | 3.6155 | 69.466 | 563.45 | 56 | 3.3443 | 3.0176 | 43.609 | 619.43 |
27 | 2.5118 | 3.6444 | 41.941 | 682.56 | 57 | 2.8286 | 3.8737 | 42.952 | 695.60 |
28 | 3.0847 | 3.6273 | 46.000 | 664.67 | 58 | 2.9512 | 3.6803 | 45.445 | 673.16 |
29 | 3.2510 | 3.4471 | 61.279 | 578.43 | 59 | 3.0083 | 3.5933 | 43.954 | 670.27 |
30 | 2.7024 | 3.0456 | 67.402 | 515.26 | 60 | 3.1460 | 3.7070 | 55.522 | 617.59 |
1-Fold | 2-Fold | 3-Fold | 4-Fold | 5-Fold | |
---|---|---|---|---|---|
Train | 0.9991 | 0.9991 | 0.9993 | 0.9988 | 0.9989 |
Test | 0.9982 | 0.9977 | 0.9951 | 0.9993 | 0.9994 |
All | 0.9990 | 0.9990 | 0.9990 | 0.9989 | 0.9990 |
Algorithm | Best Value | Mean Value | Worst Value | Standard Deviation | Total CPU Time |
---|---|---|---|---|---|
AOA | 728.902224 | 728.901906 | 728.900627 | 4.20 × 10−4 | 00:43:19 |
Aquila | 728.902226 | 728.902211 | 728.902135 | 2.14 × 10−5 | 01:24:46 |
AVOA | 728.902226 | 728.902226 | 728.902226 | 0.00 × 100 | 00:43:26 |
EO | 728.902226 | 728.902226 | 728.902226 | 0.00 × 100 | 00:43:35 |
GA | 728.902226 | 728.902225 | 728.902225 | 2.87 × 10−7 | 00:43:33 |
PSO | 728.467356 | 728.467356 | 728.467356 | 1.17 × 10−13 | 00:47:01 |
Algorithm | TD1 | TD2 | TD3 | FEA | Optimum | % Error | LM Simulink Model | % Error |
---|---|---|---|---|---|---|---|---|
AOA | 3.273 | 4 | 40 | 735.71 | 728.902 | −0.93% | 734.71 | −0.14% |
Aquila | 3.275 | 4 | 40 | 732.63 | 728.902 | −0.51% | 734.52 | 0.26% |
AVOA | 3.275 | 4 | 40 | 732.63 | 728.902 | −0.51% | 734.52 | 0.26% |
EO | 3.275 | 4 | 40 | 732.63 | 728.902 | −0.51% | 734.52 | 0.26% |
GA | 3.275 | 4 | 40 | 732.63 | 728.902 | −0.51% | 734.52 | 0.26% |
PSO | 3.500 | 4 | 40 | 740.65 | 728.467 | −1.64% | 738.3 | −0.32% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Kökden, D.; Egi, A.; Bulut, E.; Albak, E.İ.; Korkmaz, İ.; Öztürk, F. Prevention of the Fracture Problem Occurring in Automotive Alternator Heatsink Blocks Using Artificial Intelligence. Appl. Sci. 2024, 14, 11758. https://doi.org/10.3390/app142411758
Kökden D, Egi A, Bulut E, Albak Eİ, Korkmaz İ, Öztürk F. Prevention of the Fracture Problem Occurring in Automotive Alternator Heatsink Blocks Using Artificial Intelligence. Applied Sciences. 2024; 14(24):11758. https://doi.org/10.3390/app142411758
Chicago/Turabian StyleKökden, Dinçer, Adem Egi, Emre Bulut, Emre İsa Albak, İbrahim Korkmaz, and Ferruh Öztürk. 2024. "Prevention of the Fracture Problem Occurring in Automotive Alternator Heatsink Blocks Using Artificial Intelligence" Applied Sciences 14, no. 24: 11758. https://doi.org/10.3390/app142411758
APA StyleKökden, D., Egi, A., Bulut, E., Albak, E. İ., Korkmaz, İ., & Öztürk, F. (2024). Prevention of the Fracture Problem Occurring in Automotive Alternator Heatsink Blocks Using Artificial Intelligence. Applied Sciences, 14(24), 11758. https://doi.org/10.3390/app142411758