Characteristic and Allowable Compressive Strengths of Dendrocalamus Sericeus Bamboo Culms with/without Node Using Artificial Neural Networks

Buachart, Chinnapat; Hansapinyo, Chayanon; Sukontasukkul, Piti; Zhang, Hexin; Sae-Long, Worathep; Chetchotisak, Panatchai; O'Brien, Timothy E.

Abstract

The strength of construction material is a crucial consideration in the process of structural design and construction. Conventional materials such as concrete or steel have been widely utilized due to their predictable material performance. However, a significant obstacle to the widespread use of bamboo in structural elements lies in the challenge of its standardization. Many previous research studies have explored bamboo’s load bearing capacity, but the information remains limited due to variations in species, size, age, physical properties, moisture content, and other factors, making it difficult to predict their load-bearing capacity. This study aims to propose Artificial Neural Network (ANN) models to predict ultimate compressive load and compressive strength of Dendrocalamus Sericeus bamboo culm. Additionally, for structural design purposes, the proposed ANN models were employed to determine the characteristic and allowable compressive strengths. As a first step, experimental data from compressive tests in the literature were used for training and developing the ANN model. To investigate the effect of the node on compressive loading capacities, the test data were separated into two datasets, “Node” samples and “Internode” samples. Through the training process, ANN models were finally proposed, and the R-square values for the prediction of ultimate compressive load and compressive strength from the proposed ANN models were significantly higher than those obtained from the linear regression analyses used in the literature. Subsequently, the characteristic and allowable compressive strengths were calculated and compared to the strengths obtained from the experiment data, revealing a difference of approximately only 8.0%. Overall, the ANN models presented in this study offer promising predictive ability for both ultimate compressive load and compressive strength of Dendrocalamus Sericeus bamboo culm, as well as for determining characteristic and allowable strengths. Hence, ANN models are suggested to be adopted as a tool for the design and construction of bamboo buildings.

Citation

Buachart, C., Hansapinyo, C., Sukontasukkul, P., Zhang, H., Sae-Long, W., Chetchotisak, P., & O'Brien, T. E. (2024). Characteristic and Allowable Compressive Strengths of Dendrocalamus Sericeus Bamboo Culms with/without Node Using Artificial Neural Networks. Case Studies in Construction Materials, 20, e02794. https://doi.org/10.1016/j.cscm.2023.e02794

• Journal Article Type: Article
• Acceptance Date: Dec 14, 2023
• Online Publication Date: Dec 15, 2023
• Publication Date: 2024-07
• Deposit Date: Dec 21, 2023
• Publicly Available Date: Dec 22, 2023
• Electronic ISSN: 2214-5095
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 20
• Pages: e02794
• DOI: https://doi.org/10.1016/j.cscm.2023.e02794
• Keywords: Compressive strength prediction, Dendrocalamus Sericeus, Indicative properties, Artificial neural network, Characteristic strength, Allowable strength
• Public URL: http://researchrepository.napier.ac.uk/Output/3436156