An Experimental Investigation of the Application of Artificial Neural Network Techniques to Predict the Cyclic Polarization Curves of AL-6XN Alloy with Sensitization
2
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Artificial neural network techniques show an excellent ability to predict the data (output) for various com plex characteristics (input). It is primarily specialized to solve nonlinear relationship problems. This studyis an experimental investigation that applies artificial neural network techniques and an experimentaldesign to predict the cyclic polarization curves of the super-austenitic stainless steel AL-6XN alloy withsensitization. A cyclic polarization test was conducted in a 3.5% NaCl solution based on an experimentaldesign matrix with various factors (degree of sensitization, temperature, pH) and their levels, and a total of36 cyclic polarization data were acquired. The 36 cyclic polarization patterns were used as training data forthe artificial neural network model. As a result, the supervised learning algorithms with back-propagationshowed high learning and prediction performances. The model showed an excellent training performance(R2=0.998) and a considerable prediction performance (R2=0.812) for the conditions that were not includedin the training data.
Abstract
Artificial neural network techniques show an excellent ability to predict the data (output) for various com plex characteristics (input). It is primarily specialized to solve nonlinear relationship problems. This studyis an experimental investigation that applies artificial neural network techniques and an experimentaldesign to predict the cyclic polarization curves of the super-austenitic stainless steel AL-6XN alloy withsensitization. A cyclic polarization test was conducted in a 3.5% NaCl solution based on an experimentaldesign matrix with various factors (degree of sensitization, temperature, pH) and their levels, and a total of36 cyclic polarization data were acquired. The 36 cyclic polarization patterns were used as training data forthe artificial neural network model. As a result, the supervised learning algorithms with back-propagationshowed high learning and prediction performances. The model showed an excellent training performance(R2=0.998) and a considerable prediction performance (R2=0.812) for the conditions that were not includedin the training data.
참고문헌 (11)
- Z. Cui, "Passivation behavior and surface chemistry of 2507 super duplex stainless steel in artificial seawater:Influence of dissolved oxygen and pH", Corrosion Science, 150, pp.218~ (2019)[DOI]
- R. T. Loto, "Effect of elevated temperature variations on the corrosion resistance of S31603 and SS2562 austenitic stainless steels in chloride-sulphate environments", Journal of Materials Research and Technology, 8, pp.5415~ (2019)[DOI]
- 장형민, "304L 스테인리스강의 열처리에 따른 입계부식민감도 연구", CORROSION SCIENCE AND TECHNOLOGY, 19(1), pp.37~42 (2020), 한국부식방식학회[DOI]
- Z. G. Song, "Precipitated phases of superaustenitic stainless steel 654SMO", Journal of Iron and Steel Research International, 24, pp.743~ (2017)[DOI]
- Q. Hu, "Modeling the corrosion behavior of Ni-Cr-Mo-V high strength steel in the simulated deep sea environments using design of experiment and artificial neural network", Journal ofMaterials Science & Technology, 35, pp.168~ (2019)[DOI]
- C. L. C. Roxas, "An artificial neural network model for the corrosion current density of steel in mortar mixed with seawater", International Journal of GEOMATE, 16, pp.79~ (2019)[DOI]
- M. T. Hagan, "Training feedforward networks with the Marquardt algorithm", IEEE Transactions on Neural Networks, 5, pp.989~ (1994)[DOI]
- C. I. Rocabruno-Valdés, "Corrosion rate prediction for metals in biodiesel using artificial neural networks", Renewable Energy, 140, pp.592~ (2019)[DOI]
- Guangming Jiang, "Predicting concrete corrosion of sewers using artificial neural network", Water Research, 92, pp.52~60 (2016), Elsevier BV[DOI]
- Jiapeng Sun, "Optimization of concrete hollow brick using hybrid genetic algorithm combining with artificial neural networks", International Journal of Heat and Mass Transfer, 53(23-24), pp.5509~5518 (2010), Elsevier BV[DOI]
- Gerson Lachtermacher, "Back propagation in time-series forecasting", Journal of Forecasting, 14(4), pp.381~393 (1995), Wiley[DOI]