Exploring the Impact of Pre-Mechanical Activation of Nickel Powder on the Structure of Deposited Metal: A Deep Neural Network Perspective
Abstract
:1. Introduction
2. Materials and Methods
- First Stage: The specified powder was subjected to MA followed by studying changes in bulk density and apparent particle size. X-ray spectroscopic microanalysis (XRMA) was also conducted. A total of 10 studies were performed at this stage.
- Second Stage: The influence of processed powders on the structure and properties of deposited metal was investigated by introducing powders into the molten metal of the welding pool. This stage included 15 studies.
- d—average particle size of the powder (µm),
- —mass of the powder (g) remaining on the sieve of size x (µm),
- M—total mass of the powder (g),
- —hole size on the sieve x (µm),
- —mass of the powder sieved through the last sieve of size z (g),
- —hole size on the last sieve z (µm).
3. Results
3.1. First Stage
3.2. Second Stage
3.3. GA-Based CNN Hyperparameter Optimization for Surface Analysis
- Filter Sizes: The convolutional layers use filters of varying sizes denoted as , where . For each filter size, the mathematical representation is given by:
- Number of Units in Dense Layers: The dense layers consist of units, where j varies depending on the layer. This is represented as:
- Optimizer: The choice of optimizer, O, is one of several available options such as Adam, SGD, or RMSprop. The optimizer affects the gradient descent updates as follows:
- Epochs: The number of epochs, E, used for training is varied. The training process iterates E times as follows:
- Batch Size: The batch size, B, determines how many samples are processed before updating the model weights:
4. Discussion
5. Conclusions
- Viability of Vibratory Mill for Mechanical Activation (MA): The study confirms that using a vibratory mill for MA of nickel powder is effective. Extending the processing duration is recommended to optimize results.
- Particle Deformation: Nickel powder particles exhibit significant deformation, with discoid particles observed at a processing time of 16 min. The best outcomes are achieved using a mill with a grinding media mix of 6 balls (20 mm diameter) and 8 balls (10 mm diameter). Processing also results in reduced bulk density of the powder.
- Impact on Weld Pool: Incorporating MA nickel powder into the weld pool shows minimal effects on the metal structure but leads to increased hardness. Further investigation is needed to explore the structural and property changes under conditions of greater damage and deformation.
- Optimization of Convolutional Neural Networks (CNNs): The study highlights the effectiveness of genetic algorithms (GAs) in optimizing CNNs for analyzing surfaces with and without MA, suggesting promising advancements in surface analysis techniques.
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Zhang, W.; Zhang, H.; Zhu, Y.; Huang, Z.; Zhang, Y.; Gan, T.; Hu, H.; Qin, Y. Construction of spontaneously polarized ceramic via synergistic mechanical activation–Biomimetic mineralization for activating air and water. J. Mater. Sci. Technol. 2023, 165, 132–142. [Google Scholar] [CrossRef]
- Pribytkov, G.A.; Baranovskiy, A.V.; Korzhova, V.V.; Krinitcyn, M.G. Mechanoactivated SHS in Ferrotitanium—Carbon Black Powder Mixtures. Int. J.-Self-Propagating-High-Temp. Synth. 2020, 29, 61–63. [Google Scholar] [CrossRef]
- Salvo, C.; Chicardi, E.; García-Garrido, C.; Jiménez, J.A.; Aguilar, C.; Usuba, J.; Mangalaraja, R.V. The influence of mechanical activation process on the microstructure and mechanical properties of bulk Ti2AlN MAX phase obtained by reactive hot pressing. Ceram. Int. 2019, 45, 17793–17799. [Google Scholar] [CrossRef]
- Gu, D.; Wamg, Z.; Shen, Y.; Li, Y. In-situ TiC particle reinforced Ti-Al matrix composites: Powder preparation by mechanical alloying and selective laser melting behavior. Appl. Surf. Sci. 2009, 255, 9230–9240. [Google Scholar] [CrossRef]
- Blednova, Z.M.; Rusinov, P.O.; Bezmogorychnaya, M.E. Influence of granulometric composition, energy state, and reactivity of the sprayed material on the formation of nanostructure of surface layers from shape memory effect materials (SMEM). Polythematic Online Sci. J. Kuban State Agrar. Univ. 2016, 484–498. [Google Scholar] [CrossRef]
- Shirokov, G.Y. Mechanochemistry: Theoretical Foundations; Ivanovo State University of Chemical Technology: Ivanovo, Russia, 2015; p. 214. [Google Scholar]
- Kobernik, N.V.; Chernyshov, G.G.; Gvozdev, P.P. Antifriction properties of coatings obtained by plasma surfacing of babbitt with carbon nanotubes. Weld. Diagn. 2013, 27–31. [Google Scholar]
- Linnik, A.A.; Pankratov, A.S.; Kobernik, N.V. Influence of Nanosized Tungsten Carbide Powders on the Structure and Properties of Weld Metal; Higher Educational Institutions: Tokyo, Japan, 2013; pp. 66–71. [Google Scholar]
- Sokolov, G.N.; Troshkov, A.S.; Lysak, V.I. Modification of the structure of deposited metal by nanodispersed tungsten carbides. Phys. Chem. Mater. Treat. 2009, 41–47. [Google Scholar]
- Boldyrev, A.M.; Gushchin, D.A.; Grebenchuk, I.V. Method for Producing Granulated Welding Flux Additives. 2016. [Google Scholar]
- Troshkov, A.S.; Sokolov, G.N.; Sychyova, S.S.; Lysak, V.I. Structure and Properties of Low-Carbon Metal Deposited under Ceramic Flux Containing Composite Microgranules Ni-Nanodispersed WC; Volgograd State Technical University: Volgograd, Russia, 2012; pp. 187–190. [Google Scholar]
- Linnik, A.A. Development of Technological Methods for Modifying Weld Metal with Nanoparticles Using Flux-Cored Wires in Flux-Cored Arc Welding: Specialty 05.02.10 Welding, Allied Processes, and Technologies. Ph.D. Thesis, Ivanovo State University of Chemical Technology, Ivanovo, Russia, 2017; p. 156. [Google Scholar]
- Filimonov, V.Y.; Prokof’ev, V.G. High-temperature synthesis in activated powder mixtures under conditions of linear heating: Ni–Al system. Combust. Flame 2021, 223, 88–97. [Google Scholar] [CrossRef]
- Nazemi, M.; Sheibani, S.; Rashchi, F.; Gonzalez-DelaCruz, V.M.; Caballero, A. Preparation of nanostructured nickel aluminate spinel powder from spent NiO/Al2O3 catalyst by mechano-chemical synthesis. Adv. Powder Technol. 2012, 23, 833–838. [Google Scholar] [CrossRef]
- Savić, S.M.; Mančić, L.; Vojisavljević, K.; Stojanović, G.; Branković, Z.; Aleksić, O.; Branković, G. Microstructural and electrical changes in nickel manganite powder induced by mechanical activation. Mater. Res. Bull. 2011, 46, 1065–1071. [Google Scholar] [CrossRef]
- Zhao, Z.; Wang, C.; Yang, L.; Cheng, Y.; Cai, Z.; Mehrizi, M.Z. Microstructure and properties of NiAl/TiC composite synthesized by spark plasma sintering of mechanically activated elemental powders. Ceram. Int. 2023, 49, 15710–15716. [Google Scholar] [CrossRef]
- Korkmaz, A.V.; Kayıran, H.F. Investigation of mechanical activation effect on high-volume natural pozzolanic cements. Open Chem. 2022, 20, 1029–1044. [Google Scholar] [CrossRef]
- Kochetov, N.; Kovalev, I. An X-ray diffraction study of mechanical activation-induced structural changes in Ni+Al mixtures containing nickel powders prepared by different techniques. Inorg. Mater. 2019, 55, 191–194. [Google Scholar] [CrossRef]
- Aleshin, N.; Grigor’ev, M.; Kobernik, N.; Mikheev, R.; Pankratov, A.; Samokhin, A.; Alekseev, N.; Sinaisky, M. Modification of weld metal with tungsten carbide and titanium nitride nanoparticles in twin submerged arc welding. High Energy Chem. 2018, 52, 440–445. [Google Scholar] [CrossRef]
- Kushchevskii, A.E.; Mozol’, T.F.; Pekarik, A.T.; Nichiporenko, O.S.; Medvedovskii, A.B. Properties of an atomized iron powder. Sov. Powder Metall. Met. Ceram. 1978, 17, 821–823. [Google Scholar] [CrossRef]
- Cheskis, K.I.; Bocharov, A.N. Properties of VKSt. 3kp oxygen-converter steel. Chem. Pet. Eng. 1967, 3, 49–51. [Google Scholar] [CrossRef]
- Zheng, W.; Dong, J.; Li, Y.; Wen, J.; Chang, C.; Li, B.; Li, Y. Preparation technology and microstructural changes of low-activity magnesium oxide based on salt lake bischofite. Powder Technol. 2024, 433, 119248. [Google Scholar] [CrossRef]
- Guo, Z.; Zhu, D.; Pan, J.; Yang, C.; Li, S.; Dong, T.; Tian, H.; Yan, X. Efficient and green treatment of ultrapure magnetite to prepare powder metallurgy iron powders. Powder Technol. 2021, 378, 19–28. [Google Scholar] [CrossRef]
- Guobin, W.; Qingfei, X.; Qiang, Z.; Xiangyang, L.; Saizhen, J.; Yingjie, P.; Chuangang, S. An innovatory approach for determining grinding media system to optimize fraction compositions of grinding products based on grinding dynamics principle. Powder Technol. 2024, 434, 119302. [Google Scholar] [CrossRef]
- Guo, W.; Gao, P.; Tang, Z.; Han, Y.; Meng, X. Effect of grinding media properties and stirrer tip speed on the grinding efficiency of a stirred mill. Powder Technol. 2021, 382, 556–565. [Google Scholar] [CrossRef]
- Shahzad, A.; Zadorozhnyy, V.Y.; Pavlov, M.; Zheleznyi, M.; Chirkov, A.; Zagrebin, D.; Semenov, D.; Khasenova, R.; Kaloshkin, S. Deposition of the Ti-Al coatings on different metallic substrates by mechanical alloying and subsequent laser treatment. J. Alloy Compd. 2018, 731, 1295–1302. [Google Scholar] [CrossRef]
- Hu, C.; Zuo, Y.; Chen, C.; Ong, S.P.; Luo, J. Genetic algorithm-guided deep learning of grain boundary diagrams: Addressing the challenge of five degrees of freedom. Mater. Today 2020, 38, 49–57. [Google Scholar] [CrossRef]
- Jeong, J.Y.; Hong, D.G.; Yim, C.H. Deep Learning to Predict Deterioration Region of Hot Ductility in High-Mn Steel by Using the Relationship between RA Behavior and Time-Temperature-Precipitation. Metals 2022, 12, 1689. [Google Scholar] [CrossRef]
- Thien, N.B.; Wakabayashi, Y.; Geng, Y.; Iwai, K.; Nishiura, T. Weighted Von Mises Distribution-based Loss Function for Real-time STFT Phase Reconstruction Using DNN. In Proceedings of the ISCA Interspeech 2023, Dublin, Ireland, 20–24 August 2023. [Google Scholar]
- Ha, V.P.; Dao, T.K.; Pham, N.Y.; Le, M.H. A variable-length chromosome genetic algorithm for time-based sensor network schedule optimization. Sensors 2021, 21, 3990. [Google Scholar] [CrossRef] [PubMed]
- Zhan, X.; Long, H.; Gou, F.; Duan, X.; Kong, G.; Wu, J. A convolutional neural network-based intelligent medical system with sensors for assistive diagnosis and decision-making in non-small cell lung cancer. Sensors 2021, 21, 7996. [Google Scholar] [CrossRef] [PubMed]
- Morales, C.G.; Yao, J.; Rane, T.; Edman, R.; Choset, H.; Dubrawski, A. Reslicing ultrasound images for data augmentation and vessel reconstruction. In Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK, 29 May–2 June 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 2710–2716. [Google Scholar]
- Kumar, T.; Mileo, A.; Brennan, R.; Bendechache, M. RSMDA: Random Slices Mixing Data Augmentation. Appl. Sci. 2023, 13, 1711. [Google Scholar] [CrossRef]
- Khalek, N.A.; Hamouda, W. DEAP Learning: A Data-Driven Approach to Unsupervised Cooperative Spectrum Sensing. In Proceedings of the GLOBECOM 2023-2023 IEEE Global Communications Conference, Kuala Lumpur, Malaysia, 4–8 December 2023; IEEE: Piscataway, NJ, USA, 2023; pp. 6389–6394. [Google Scholar]
- Zheng, W.; Doerr, B. Approximation Guarantees for the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). In IEEE Transactions on Evolutionary Computation; IEEE: Piscataway, NJ, USA, 2024. [Google Scholar]
- Wu, Z.; Ma, G. Automatic generation of BIM-based construction schedule: Combining an ontology constraint rule and a genetic algorithm. Eng. Constr. Archit. Manag. 2023, 30, 5253–5279. [Google Scholar] [CrossRef]
- Zollanvari, A. Deep Learning with Keras-TensorFlow. In Machine Learning with Python: Theory and Implementation; Springer: Berlin/Heidelberg, Germany, 2023; pp. 351–391. [Google Scholar]
- Kovaios, S.; Pappas, C.; Moralis-Pegios, M.; Tsakyridis, A.; Giamougiannis, G.; Kirtas, M.; Van Kerrebrouck, J.; Coudyzer, G.; Yin, X.; Passalis, N.; et al. Programmable Tanh-and ELU-based Photonic Neurons in Optics-Informed Neural Networks. J. Light. Technol. 2024, 42, 3652–3660. [Google Scholar] [CrossRef]
- Grigsby, E.; Lindsey, K.; Rolnick, D. Hidden symmetries of ReLU networks. In Proceedings of the International Conference on Machine Learning (PMLR), Honolulu, HI, USA, 23–29 July 2023; pp. 11734–11760. [Google Scholar]
- Ranjan, P.; Khan, P.; Kumar, S.; Das, S.K. log-Sigmoid Activation-Based Long Short-Term Memory for Time Series Data Classification. IEEE Trans. Artif. Intell. 2023, 5, 672–683. [Google Scholar] [CrossRef]
- Kaytan, M.; Aydilek, İ.B.; Yeroğlu, C. Gish: A novel activation function for image classification. Neural Comput. Appl. 2023, 35, 24259–24281. [Google Scholar] [CrossRef]
- Yang, F.; Huo, J.; Cheng, Z.; Chen, H.; Shi, Y. An Improved Mask R-CNN Micro-Crack Detection Model for the Surface of Metal Structural Parts. Sensors 2023, 24, 62. [Google Scholar] [CrossRef]
- Oyedeji, O.A.; Khan, S.; Erkoyuncu, J.A. Application of CNN for Multiple Phase Corrosion Identification and Region Detection. Appl. Soft Comput. 2024, 112008. [Google Scholar] [CrossRef]
- Elaiyarani, K.; Nigileeswari, B.; Rani, G.T.; Rajeswari, J.; Vignesh, S. Machine Learning Based Dent Damage Detection Using Image Processing Methods. In Proceedings of the 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE), Vellore, India, 22–23 February 2024; IEEE: Piscataway, NJ, USA, 2024; pp. 1–4. [Google Scholar]
- Abhilash, P.; Ahmed, A. Convolutional neural network–based classification for improving the surface quality of metal additive manufactured components. Int. J. Adv. Manuf. Technol. 2023, 126, 3873–3885. [Google Scholar] [CrossRef]
- Konovalenko, I.; Maruschak, P.; Brezinová, J.; Prentkovskis, O.; Brezina, J. Research of U-Net-based CNN architectures for metal surface defect detection. Machines 2022, 10, 327. [Google Scholar] [CrossRef]
- Tao, X.; Zhang, D.; Ma, W.; Liu, X.; Xu, D. Automatic metallic surface defect detection and recognition with convolutional neural networks. Appl. Sci. 2018, 8, 1575. [Google Scholar] [CrossRef]
- Aranda, R.M.; Astacio, R.; Urban, P.; Aranda, B.; Cuevas, F.G. Milling amorphous FeSiB ribbons with vibratory ball and disc mills. Powder Technol. 2024, 441, 119816. [Google Scholar] [CrossRef]
- Badar, N.; Yusoff, H.M.; Elong, K.; Kamarulzaman, N. Crystallite size reduction of Cr doped Al2O3 materials via optimized high-energy ball milling method. Adv. Powder Technol. 2023, 34, 104102. [Google Scholar] [CrossRef]
- Nesges, D.; Lang, T.; Birr, T.; Thommes, M.; Bartsch, J. Planetary roller melt granulation (PRMG)—A new continuous method for powder processing. Powder Technol. 2023, 427, 118728. [Google Scholar] [CrossRef]
- Das, S.; Robi, P. A novel refractory WMoVCrTa high-entropy alloy possessing fine combination of compressive stress-strain and high hardness properties. Adv. Powder Technol. 2020, 31, 4619–4631. [Google Scholar] [CrossRef]
- García-Triñanes, P.; Luding, S.; Shi, H. Tensile strength of cohesive powders. Adv. Powder Technol. 2019, 30, 2868–2880. [Google Scholar] [CrossRef]
- Ghadiri, M.; Kwan, C.C.; Ding, Y. Analysis of milling and the role of feed properties. Handb. Powder Technol. 2007, 12, 605–634. [Google Scholar]
- Loussaief, S.; Abdelkrim, A. Convolutional neural network hyper-parameters optimization based on genetic algorithms. Int. J. Adv. Comput. Sci. Appl. 2018, 9, 53643148. [Google Scholar] [CrossRef]
- Esmaeili, M.; Abbasi-Moghadam, D.; Sharifi, A.; Tariq, A.; Li, Q. Hyperspectral image band selection based on CNN embedded GA (CNNeGA). IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2023, 16, 1927–1950. [Google Scholar] [CrossRef]
- Pothuganti, S. Review on over-fitting and under-fitting problems in Machine Learning and solutions. Int. J. Adv. Res. Electr. Electron. Instrum. Eng 2018, 7, 3692–3695. [Google Scholar]
- Alarsan, F.I.; Younes, M. Best selection of generative adversarial networks hyper-parameters using genetic algorithm. SN Comput. Sci. 2021, 2, 283. [Google Scholar] [CrossRef]
- Itano, F.; de Sousa, M.A.d.A.; Del-Moral-Hernandez, E. Extending MLP ANN hyper-parameters Optimization by using Genetic Algorithm. In Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, 8–13 July 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–8. [Google Scholar]
Reference | Focus | Limitations |
---|---|---|
Kobernik et al., 2013 [7] | Application of MA for mechanical alloying of powders used in plasma powder deposition. | Limited to antifriction materials and does not explore nickel specifically. |
Sokolov et al., 2009 [9] | Incorporation of mechanically alloyed powders into coated electrodes and fluxes. | Broad application but lacks specific emphasis on pre-mechanical activation of nickel powder. |
Boldyrev et al., 2016 [10] | Methodology for integrating MA powders into electrodes and fluxes. | Does not detail the impact on microstructure and mechanical properties. |
Filimonov et al., 2021 [13] | Mathematical modeling of high-temperature synthesis in Ni + Al powder system. | Focuses on theoretical modeling and ignition criteria, not practical applications. |
Nazemi et al., 2012 [14] | Mechano-chemical synthesis of nanostructured nickel aluminate spinel powder. | Specific to nanostructured spinel, not broadly applicable to all nickel powders. |
Savic et al., 2011 [15] | Synthesis of nickel manganite powder and effects of mechanical activation. | Examines nickel manganite specifically, not general nickel powder. |
Zhao et al., 2023 [16] | Synthesis of NiAl/TiC0.95 composite via reactive spark plasma sintering of MA powders. | Focuses on specific composite material, not general use of MA nickel powders. |
Kormaz et al., 2022 [17] | Hybrid mechanical activation method in cement production to reduce energy consumption. | Application limited to cement production, not applicable to metal powders. |
, A | , V | , m/h | , m/min |
---|---|---|---|
200–210 | 37–38 | 16 | 2.2 |
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
Malashin, I.; Kobernik, N.; Pankratov, A.; Andriyanov, Y.; Aleksandrova, V.; Tynchenko, V.; Nelyub, V.; Borodulin, A.; Gantimurov, A.; Martysyuk, D.; et al. Exploring the Impact of Pre-Mechanical Activation of Nickel Powder on the Structure of Deposited Metal: A Deep Neural Network Perspective. Metals 2024, 14, 929. https://doi.org/10.3390/met14080929
Malashin I, Kobernik N, Pankratov A, Andriyanov Y, Aleksandrova V, Tynchenko V, Nelyub V, Borodulin A, Gantimurov A, Martysyuk D, et al. Exploring the Impact of Pre-Mechanical Activation of Nickel Powder on the Structure of Deposited Metal: A Deep Neural Network Perspective. Metals. 2024; 14(8):929. https://doi.org/10.3390/met14080929
Chicago/Turabian StyleMalashin, Ivan, Nikolay Kobernik, Alexandr Pankratov, Yuri Andriyanov, Vitalina Aleksandrova, Vadim Tynchenko, Vladimir Nelyub, Aleksei Borodulin, Andrei Gantimurov, Dmitry Martysyuk, and et al. 2024. "Exploring the Impact of Pre-Mechanical Activation of Nickel Powder on the Structure of Deposited Metal: A Deep Neural Network Perspective" Metals 14, no. 8: 929. https://doi.org/10.3390/met14080929