Search for: [Keywords = "XGBoost"]

Search results

Number of results: 3

items per page: 25 50 75

Sort by:

of 1

Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring

Ida Barkiah Yuslena Sari

International Journal of Electronics and Telecommunications | 2023 | vol. 69 | No 3 | 571-577 | DOI: 10.24425/ijet.2023.146509

Keywords HOG XGBoost classification feature extraction concrete crack monitoring

Download PDF Download RIS Download Bibtex

Abstract

This study proposes a method that combines Histogram of Oriented Gradients (HOG) feature extraction and Extreme Gradient Boosting (XGBoost) classification to resolve the challenges of concrete crack monitoring. The purpose of the study is to address the common issue of overfitting in machine learning models. The research uses a dataset of 40,000 images of concrete cracks and HOG feature extraction to identify relevant patterns. Classification is performed using the ensemble method XGBoost, with a focus on optimizing its hyperparameters. This study evaluates the efficacy of XGBoost in comparison to other ensemble methods, such as Random Forest and AdaBoost. XGBoost outperforms the other algorithms in terms of accuracy, precision, recall, and F1-score, as demonstrated by the results. The proposed method obtains an accuracy of 96.95% with optimized hyperparameters, a recall of 96.10%, a precision of 97.90%, and an F1-score of 97%. By optimizing the number of trees hyperparameter, 1200 trees yield the greatest performance. The results demonstrate the efficacy of HOG-based feature extraction and XGBoost for accurate and dependable classification of concrete fractures, overcoming the overfitting issues that are typically encountered in such tasks.

Go to article

Authors and Affiliations

Ida Barkiah

Yuslena Sari

Department of Civil Engineering, Universitas Lambung, Mangkurat, Indonesia
Department of Information Technology, Universitas Lambung Mangkurat, Indonesia

The Use of the XGBoost and Kriging Methods in the Prediction of the Microstructure of CGI Cast Iron

Łukasz Sztangret Izabela Olejarczyk-Wożeńska Krzysztof Regulski Grzegorz Gumienny Barbara Mrzygłód

Archives of Foundry Engineering | 2023 | vol. 23 | No 4 | 22-33 | DOI: 10.24425/afe.2023.146671

Keywords compacted graphite iron Machine Learning artificial neural networks kriging XGBoost

Download PDF Download RIS Download Bibtex

Abstract

Compacted Graphite Iron (CGI), is a unique casting material characterized by its graphite form and extensive matrix contact surface. This type of cast iron has a tendency towards direct ferritization and possesses a complex set of intriguing properties. The use of data mining methods in modern foundry material development facilitates the achievement of improved product quality parameters. When designing a new product, it is always necessary to have a comprehensive understanding of the influence of alloying elements on the microstructure and consequently on the properties of the analyzed material. Empirical studies allow for a qualitative assessment of the above-mentioned relationships, but it is the use of intelligent computational techniques that allows for the construction of an approximate model of the microstructure and, consequently, precise predictions. The formulated prognostic model supports technological decisions during the casting design phase and is considered as the first step in the selection of the appropriate material type.

Go to article

Bibliography

[1] König, M. (2010). Literature review of microstructure formation in compacted graphite iron. International Journal of Cast Metals Research. 23(3), 185-192. https://doi.org/10.1179/136404609X12535244328378.
[2] Dawson, S. & Hang, F. (2009). Compacted graphite iron-a material solution for modern diesel engine cylinder blocks and heads. China Foundry. 6(3), 241-246.
[3] Chen, Y., Pang, J. C., Li, S. X., Zou, C. L. & Zhang, Z. F. (2022). Damage mechanism and fatigue strength prediction of compacted graphite iron with different microstructures. International Journal of Fatigue. 164, 107126, 1-14. https://doi.org/10.1016/j.ijfatigue.2022.107126.
[4] Sandoval, J., Ali, A., Kwon, P., Stephenson, D. & Guo, Y. (2023). Wear reduction mechanisms in modulated turning of compacted graphite iron with coated carbide tool. Tribology International. 178, 108062, 1-13. https://doi.org/10.1016/j.triboint.2022.108062.
[5] Hosadyna-Kondracka, M., Major-Gabryś, K., Warmuzek, M. & Brůna, M. (2022). Quality assessment of castings manufactured in the technology of moulding sand with furfuryl-resole resin modified with PCL additive. Archives of Metallurgy and Materials. 67(2), 753-758. https://doi.org/10.24425/amm.2022.137814.
[6] Mrzygłód, B., Łukaszek-Sołek, A., Olejarczyk-Wożeńska, I. & Pasierbiewicz, K. (2022). Modelling of plastic flow behaviour of metals in the hot deformation process using artificial intelligence methods. Archives of Foundry Engineering. 22(3), 41-52. DOI: 10.24425/afe.2022.140235.
[7] Palkanoglou, E.N., Baxevanakis, K.P. & Silberschmidt, V.V. (2022). Thermal debonding of inclusions in compacted graphite iron: Effect of matrix phases. Engineering Failure Analysis. 139, 106476, 1-13. https://doi.org/10.1016/j.engfailanal.2022.106476.
[8] Patel, M., Dave, K. (2022). An insight of compacted graphite iron (CGI) characteristics and its production: a review. Recent Advances in Manufacturing Processes and Systems: Select Proceedings of RAM 2021, 131-148.
[9] Górny, M., Lelito, J., Kawalec, M. & Sikora, G. (2015). Influence of structure on the thermophisical properties of thin walled castings. Archives of Foundry Engineering. 15(2), 23-26.
[10] Górny, M., Kawalec, M., Witek, G. & Rejek, A. (2019). The influence of wall thickness and mould temperature on structure and properties of thin wall ductile iron castings. Archives of Foundry Engineering. 19(2), 55-59. DOI: 10.24425/afe.2019.127116.
[11] Saka, S.O., Seidu, S.O., Akinwekomi, A.D. & Oyetunji, A. (2021). Alloying elements variant on the development of antimony modified compacted graphite iron using rotary furnace. Annals of the Faculty of Engineering Hunedoara. 19(2), 13-22.
[12] Soiński, M.S., Jakubus, A., Borowiecki, B. & Mierzwa, P. (2021). Initial assessment of graphite precipitates in vermicular cast iron in the as-cast state and after thermal treatments. Archives of Foundry Engineering. 21(4), 131-136.
[13] Domeij, B., Elfsberg, J. & Diószegi, A. (2023). Evolution of dendritic austenite in parallel with eutectic in compacted graphite iron under three cooling conditions. Metallurgical and Materials Transactions B. 1-16.
[14] Ren, Z., Jiang, H., Long, S. & Zou, Z. (2023). On the mechanical properties and thermal conductivity of compacted graphite cast iron with different pearlite contents. Journal of Materials Engineering and Performance. 1-9. https://doi.org/10.1007/s11665-023-07823-7.
[15] Gumienny, G., Kacprzyk, B., Mrzygłód, B. & Regulski, K., (2022). Data-driven model selection for compacted graphite iron microstructure prediction. Coatings. 12(11), 1676, 1-18. DOI: 10.3390/coatings12111676.
[16] Mrzygłód, B., Gumienny, G., Wilk-Kołodziejczyk, D. & Regulski, K., (2019). Application of selected artificial intelligence methods in a system predicting the microstructure of compacted graphite iron. Journal of Materials Engineering and Performance. 28, 3894-3904. DOI: 10.1007/s11665-019-03932-4.
[17] Wilk-Kołodziejczyk, D., Regulski, K., Gumienny, G. & Kacprzyk, B. (2018). Data mining tools in identifying the components of the microstructure of compacted graphite iron based on the content of alloying elements. International Journal of Advanced Manufacturing Technology. 95(9-12), 3127-3139. DOI 10.1007/s00170-017-1430-7.
[18] Wilk-Kołodziejczyk, D., Kacprzyk, B., Gumienny, G., Regulski, K., Rojek, G. & Mrzygłód, B., (2017). Approximation of ausferrite content in the compacted graphite iron with the use of combined techniques of data mining, Archives of Foundry Engineering. 17(3), 117-122. DOI 10.1515/afe-2017-0102.
[19] Kusiak, J., Sztangret, Ł. & Pietrzyk, M. (2015). Effective strategies of metamodelling of industrial metallurgical processes. Advances in Engineering Software. 89, 90-97. DOI: 10.1016/j.advengsoft.2015.02.002.
[20] Sacks, J., Welch, W.J., Mitchel, T. & Wynn, H.P., (1989) Design and analysis of computer experiments. Stat Sci. 4, 409-435. DOI: 10.1214/ss/1177012413.
[21] Fragassa, C. (2022) Investigating the material properties of nodular cast iron from a data mining perspective. Metals. 12(9), 1493, 1-26. DOI: 10.3390/met12091493.
[22] Huang, W., Lyu, Y., Du, M., Gao, S-D., Xu, R-J., Xia, Q-K. & Zhangzhou, J. (2022). Estimating ferric iron content in clinopy-roxene using machine learning models. American Mineralogist. 107, 1886-1900. DOI: 10.2138/am-2022-8189.
[23] Sika, R., Szajewski, D., Hajkowski, J. & Popielarski, P. (2019). Application of instance-based learning for cast iron casting defects prediction. Management and Production Engineering Review. 10(4), 101-107. DOI: 10.24425/mper.2019.131450.
[24] Chen, S. & Kaufmann, T. (2022). Development of data-driven machine learning models for the prediction of casting surface defects. Metals. 12(1), 1-15. DOI: 10.3390/met12010001
[25] Alrfou, K., Kordijazi, A., Rohatgi, P. & Zhao, T. (2022). Synergy of unsupervised and supervised machine learning methods for the segmentation of the graphite particles in the microstructure of ductile iron. Materials Today Communications. 30. 103174. DOI: 10.1016/j.mtcomm.2022.103174.
[26] Vantadori, S., Ronchei, C., Scorza, D., Zanichelli, A. & Luciano, R. (2022). Effect of the porosity on the fatigue strength of metals. Fatigue & Fracture of Engineering Materials & Structures. 45(9), 2734-2747. https://doi.org/10.1111/ffe.13783.
[27] Dučić, N., Jovičić, A., Manasijević, S., Radiša, R., Ćojbašić, Z. & Savković, B. (2020). Application of machine learning in the control of metal melting production process. Applied Sciences. 10(17), 6048, 1-15. DOI: 10.3390/app10176048
[28] Kihlberg, E., Norman, V., Skoglund, P., Schmidt, P. & Moverare, J. (2021). On the correlation between microstructural pa-rameters and the thermo-mechanical fatigue performance of cast iron. International Journal of Fatigue. 145, 106112, 1-10. DOI: 10.1016/j.ijfatigue.2020.106112.
[29] Hernando, J.C., Elfsberg, J., Ghassemali, E., Dahle, A.K. & Diószegi, A. (2020). The role of primary austenite morphology in hypoeutectic compacted graphite iron alloys. International of Metalcasting. 14, 745-754. DOI: 10.1007/s40962-020-00410-9.
[30] Regordosa, A., de la Torre, U., Loizaga, A., Sertucha, J. & Lacaze, J. (2020). Microstructure Changes During Solidification of Cast Irons: Effect of Chemical Composition and Inoculation on Competitive Spheroidal and Compacted Graphite Growth. International of Metalcasting. 14, 681-688. DOI: 10.1007/s40962-019-00389-y.
[31] Ribeiro B.C.M., Rocha F.M., Andrade B.M., Lopes W., Corrêa E.C.S., (2020). Influence of different concentrations of silicon, copper and tin in the microstructure and in the mechanical properties of compacted graphite iron, Materials Research. 23(2), e2019-0678, 1-10. DOI: 10.1590/1980-5373-MR-2019-0678.
[32] Tan, P.-N., Steinbach, M. & Kumar, V. (2005). Introduction to Data Mining. Boston: Pearson Addison-Wesley.
[33] Rokach, L. & Maimon, O. (2005). Top-down induction of decision trees classifiers-a survey. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews). 35(4), 476-487.
[34] Barros, R.C., de Carvalho, A. & Freitas, A.A. (2015). Automatic Design of Decision-Tree Induction Algorithms, Springer International Publishing.
[35] Regulski, K., Wilk-Kołodziejczyk, D. & Gumienny, G. (2016). Comparative analysis of the properties of the Nodular Cast Iron with Carbides and the Austempered Ductile Iron with use of the machine learning and the support vector machine. The In-ternational Journal of Advanced Manufacturing Technology. 87(1), 1077-1093. DOI: 10.1007/s00170-016-8510-y.
[36] Rui, G., Zhiqian, Z., Tao, W., Guangheng, L., Jingyi, Z. & Dianrong, G., (2020) Degradation state recognition of piston pump based on ICEEMDAN and XGBoost, Applied Sciences. 10(18), 6593, 1-17. DOI:10.3390/app10186593

Go to article

Authors and Affiliations

Łukasz Sztangret

e-mail:

ORCID:

Izabela Olejarczyk-Wożeńska

e-mail:

ORCID:

Krzysztof Regulski

e-mail:

ORCID:

Grzegorz Gumienny

e-mail:

ORCID:

Barbara Mrzygłód

e-mail:

ORCID:

AGH University of Science and Technology, Poland
Lodz University of Technology, Poland

Ensemble of feature extraction methods to improve the structural damage classification in a wind turbine foundation

Jersson X. Leon-Medina Núria Parés Maribel Anaya Diego A. Tibaduiza Francesc Pozo

Bulletin of the Polish Academy of Sciences Technical Sciences | 2023 | 71 | 3 | e144606 | DOI: 10.24425/bpasts.2023.144606

Keywords structural health monitoring wind turbine foundation damage classification machine learning feature extraction XGBoost

Download PDF Download RIS Download Bibtex

Abstract

The condition monitoring of offshore wind power plants is an important topic that remains open. This monitoring aims to lower the maintenance cost of these plants. One of the main components of the wind power plant is the wind turbine foundation. This study describes a data-driven structural damage classification methodology applied in a wind turbine foundation. A vibration response was captured in the structure using an accelerometer network. After arranging the obtained data, a feature vector of 58 008 features was obtained. An ensemble approach of feature extraction methods was applied to obtain a new set of features. Principal Component Analysis (PCA) and Laplacian eigenmaps were used as dimensionality reduction methods, each one separately. The union of these new features is used to create a reduced feature matrix. The reduced feature matrix is used as input to train an Extreme Gradient Boosting (XGBoost) machine learning-based classification model. Four different damage scenarios were applied in the structure. Therefore, considering the healthy structure, there were 5 classes in total that were correctly classified. Five-fold cross validation is used to obtain a final classification accuracy. As a result, 100% of classification accuracy was obtained after applying the developed damage classification methodology in a wind-turbine offshore jacket-type foundation benchmark structure.

Go to article

Authors and Affiliations

Jersson X. Leon-Medina

1 2

e-mail:

ORCID:

Núria Parés

e-mail:

ORCID:

Maribel Anaya

e-mail:

ORCID:

Diego A. Tibaduiza

e-mail:

ORCID:

Francesc Pozo

1 5

e-mail:

ORCID:

Control, Data, and Artificial Intelligence (CoDAlab), Department of Mathematics, Escola d’Enginyeria de Barcelona Est (EEBE),Campus Diagonal-Besòs (CDB), Universitat Politècnica de Catalunya (UPC), Eduard Maristany 16, 08019 Barcelona, Spain
Programa de Ingeniería Mecatrónica, Universidad de San Buenaventura, Carrera 8H #172-20, Bogota, Colombia
Laboratori de Càlcul Numèric (LaCàN), Department of Mathematics, Escola d’Enginyeria de Barcelona Est (EEBE), Campus Diagonal-Besòs
Departamento de Ingeniería Eléctrica y Electrónica, Universidad Nacional de Colombia, Cra 45 No. 26-85, Bogotá 111321, Colombia
Institute of Mathematics (IMTech), Universitat Politècnica de Catalunya (UPC), Pau Gargallo 14, 08028 Barcelona, Spain

Search results

Filters

Search results

Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring

Abstract

Authors and Affiliations

The Use of the XGBoost and Kriging Methods in the Prediction of the Microstructure of CGI Cast Iron

Abstract

Bibliography

Authors and Affiliations

Ensemble of feature extraction methods to improve the structural damage classification in a wind turbine foundation

Abstract

Authors and Affiliations