Hybrid Optimization Assisted Deep Convolutional Neural Network for Hardening Prediction in Steel
Journal of King Saud University: Science
Hardness is a property that prevents forced scraping or surface penetration of material surfaces against deformation. Indeed, some methods in the tradition of forecasting the mechanical properties of the steel used to recommend a new hardening forecast using a profound learning model. More particularly, an Optimized Deep Convolutional Neural Network (DCNN) framework is used that makes the prediction more accurate and precise. The input given to the model is the chemical composition of steel
... sition of steel along with the distance from the quenched end, which directly predicts the hardening of steel as the model already knows of it. Moreover, to make the prediction more accurate, this paper aims to make a fine-tuning of Convolutional layers in DCNN. This paper suggests a new hybrid algorithm for optimal tuned, which is then hybridized Sea Lion Optimization (SLNO), Dragonfly Algorithm (DA), and Sea Lion insisted on Dragon Fly Modification (SL-DU). This is an optimal tuning. Finally, the performance of the proposed work is compared and validated over other state-of-the-art models for error measures. Finally, the performance of the adopted system was evaluated compared with other traditional systems and the results were achieved. According to the analysis, the MAE of the pattern used for distance 1.5 was 77.16%, 9.84%, 12.71%, and 23.36% better than regression, MVR, ANN, and CNN. 2. At first, the inputs used to train the model are certain chemical composition of steel along with the distance from the quenched end, by which the hardening of steel could be directly predicted while testing. 3. Also, to make the prediction more precise, the work is extended to make a fine-tuning of Convolutional layers in DCNN, for which the SL-DU is exploited. 4. The efficiency of the device implemented is eventually measured against other cutting-edge systems and the results are achieved. The arrangement of the paper is given as Section II analyses the review. Section III portrays the materials and methods and section IV portrays the framework of the proposed harden ability prediction. Further, section V illustrates the optimal tuning of the Convolutional layer by the proposed hybrid algorithm. Section VI portrays the results and the paper is concluded by section VII. I. LITERATURE REVIEW A. Related works ASSs were analyzed to the fundamental mechanisms and microstructure characteristics of plastic deformation. Also, the constitutive equations were adopted in this work for evaluating the grain size effect, dislocation network, solute clusters, and dislocation loops, and so on. It was revealed that irradiation hardening was attained systematically without any adaptable constraints. Finally, the findings of the analysis have shown that the introduced plan is superior to other schemes as regards hardness prediction.