A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Investigation of the effect of substituting conventional fine aggregate with PCB powder on concrete strength using artificial neural network
Cement concrete is a standard construction material because it can be shaped easily in the plastic state, and then, once it hardens, it can withstand enormous compressive forces. Aggregates make up about 70% of the total volume of concrete, providing not only bulk but also significant load-bearing capacity. Consequently, the aggregates' properties significantly impact the characteristics of concrete. This paper describes an experiment conducted to determine the viability of waste PCB powder as a partial replacement for fine aggregates. Waste electrical and electronic equipment is commonly referred to as "e-waste." The M30 blend was developed after experimenting with 5, 10, 15, 20, and 25% replacements. Additionally, admixtures such as metakaolin (MK) are added to strengthen the concrete. The primary objective of these experiments is to find ways to recycle as much PCB waste as possible into valuable raw materials while minimizing adverse environmental effects. According to this experiment's results, waste PCB powder as a substitute for fine aggregate (FA) led to the formation of lightweight concrete. Furthermore, the study aimed to determine how replacing fine aggregates with waste PCB powder affects concrete's compressive strength, split tensile strength, and flexural strength characteristics. This paper reports the mechanical properties tests conducted at each replacement level. The experimental data of PCB powder fine aggregate concrete has been verified using the ANN method. The neural network was educated in the same manner as experimental research designs. The ANN model’s predictions of mechanical properties were also accurate (R2 > 0.99), so it contributed there. The importance of hazardous waste recycling to the waste management sector in the construction industry was also established by this study. Thus, ANN methods have been proven reliable for response estimation and accurate parameter identification. In addition, the best parameters were determined using ANN techniques.
Investigation of the effect of substituting conventional fine aggregate with PCB powder on concrete strength using artificial neural network
Cement concrete is a standard construction material because it can be shaped easily in the plastic state, and then, once it hardens, it can withstand enormous compressive forces. Aggregates make up about 70% of the total volume of concrete, providing not only bulk but also significant load-bearing capacity. Consequently, the aggregates' properties significantly impact the characteristics of concrete. This paper describes an experiment conducted to determine the viability of waste PCB powder as a partial replacement for fine aggregates. Waste electrical and electronic equipment is commonly referred to as "e-waste." The M30 blend was developed after experimenting with 5, 10, 15, 20, and 25% replacements. Additionally, admixtures such as metakaolin (MK) are added to strengthen the concrete. The primary objective of these experiments is to find ways to recycle as much PCB waste as possible into valuable raw materials while minimizing adverse environmental effects. According to this experiment's results, waste PCB powder as a substitute for fine aggregate (FA) led to the formation of lightweight concrete. Furthermore, the study aimed to determine how replacing fine aggregates with waste PCB powder affects concrete's compressive strength, split tensile strength, and flexural strength characteristics. This paper reports the mechanical properties tests conducted at each replacement level. The experimental data of PCB powder fine aggregate concrete has been verified using the ANN method. The neural network was educated in the same manner as experimental research designs. The ANN model’s predictions of mechanical properties were also accurate (R2 > 0.99), so it contributed there. The importance of hazardous waste recycling to the waste management sector in the construction industry was also established by this study. Thus, ANN methods have been proven reliable for response estimation and accurate parameter identification. In addition, the best parameters were determined using ANN techniques.
Investigation of the effect of substituting conventional fine aggregate with PCB powder on concrete strength using artificial neural network
Asian J Civ Eng
Vishnupriyan, M. (author) / Annadurai, R. (author)
Asian Journal of Civil Engineering ; 24 ; 3155-3163
2023-12-01
9 pages
Article (Journal)
Electronic Resource
English
An investigation of the compressive strength of concrete by substituting fine aggregate with sawdust
| Springer Verlag | 2023
| British Library Online Contents | 1996
Effect of very fine aggregate on concrete strength
| British Library Online Contents | 1994
Effect of very fine aggregate on concrete strength
| Online Contents | 1994