Performance evaluation of slag-based concrete at elevated temperatures by a novel machine learning approach

Toufigh, Vahab; Palizi, Soheil

doi:10.1016/j.conbuildmat.2022.129357

Cited by 19 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the convergence speed of modified DE is less than the two other algorithms. In this regard, other studies that used this algorithm reported that the DE speed of convergence is usually less than similar meta-heuristic algorithms due to the probability assigned to each response in each step of iteration [38], which is novel among these types of algorithms. Through the modification in this study, the convergence speed was increased, and the latter-mentioned privilege was maintained simultaneously.…”

Section: Example Twomentioning

confidence: 99%

“…Dolphin echolocation (DE) by Kaveh and Farhoudi [32], grey wolf optimizer (GWO) by Mirjalili et al [33], and whale optimization algorithms (WOA) by Mirjalili and Lewis [34] are three nature-based meta-heuristic algorithms, which have been previously employed to solve complex engineering problems [35][36][37][38]. The similarity of these algorithms is that they consist of a group of search agents that randomly explore the search area.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Tuned Mass Damper Parameters Design by Means of Meta-Heuristic Optimization Algorithms

Alkasassbeh¹,

Yasin²,

Almasaeid³

2023

cea

View full text Add to dashboard Cite

Tuned mass dampers (TMDs) as vibration-mitigating devices are widely used in structures to reduce their displacement response under dynamic forces. Through a novel dolphin echolocation (DE) algorithm, this paper provides optimum tuning of TMD parameters. Developing some features of this algorithm results in a faster convergence to the optimum solution. Besides, grey wolf and whale optimization algorithms (GWO and WOA), as two other nature-based meta-heuristic algorithms, are employed in this problem. The modified DE illustrates a more optimum design of TMD's parameters rather than GWO and WOA. The code has been verified by a sample structure from the literature and then applied to a high-rise forty-story structure under strong ground motions. The numerical results reveal that the optimum TMD is viable in attenuating the structural responses, including relative displacements and absolute accelerations under different earthquake excitations. For instance, in the high-rise structure, the modified DE, GWO, and WOA reduce the maximum displacements up to 45%, 43%, and 38%, respectively. Moreover, the algorithms, specifically the modified DE, propose more cost-effective designs in comparison with previous studies in the literature by introducing smaller TMD parameters.

show abstract

Section: Example Twomentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Tuned Mass Damper Parameters Design by Means of Meta-Heuristic Optimization Algorithms

Alkasassbeh¹,

Yasin²,

Almasaeid³

2023

cea

View full text Add to dashboard Cite

show abstract

“…Dissimilarities of concretes containing SCMs subjected to elevated temperatures were related to various sources of these materials. The performance of GGBFS-based concretes and their behavior at elevated temperatures was also evaluated by a machine learning methodology [ 59 ]. The temperature was not the most influential factor but rather the GGBFS/water and GGBFS/superplasticizer ratios.…”

Section: Fire Resistance Of Opc Concretes With Supplementary Cementit...mentioning

confidence: 99%

Eco-Concrete in High Temperatures

Sundin¹,

Hedlund²,

Ćwirzeń³

2023

Materials

View full text Add to dashboard Cite

Concrete technology is becoming more and more sustainable and ecological following more extensive and focused research. The usage of industrial waste and by-products, such as steel ground granulated blast-furnace slag (GGBFS), mine tailing, fly ash, and recycled fibers, is a very important step toward a good transition of concrete into a “green” future and significant improvement in waste management in the world. However, there are also several known durability-related problems with some types of eco-concretes, including exposure to fire. The general mechanism occurring in fire and high-temperature scenarios is broadly known. There are many variables that weightily influence the performance of this material. This literature review has gathered information and results regarding more sustainable and fire-resistant binders, fire-resistant aggregates, and testing methods. Mixes that utilize industrial waste as a total or partial cement replacement have been consistently achieving favorable and frequently superior outcomes when compared to conventional ordinary Portland cement (OPC)-based mixes, especially at a temperature exposure up to 400 °C. However, the primary emphasis is placed on examining the impact of the matrix components, with less attention given to other factors such as sample treatment during and following exposure to high temperatures. Furthermore, there is a shortage of established standards that could be utilized in small-scale testing.

show abstract

“…Prediction model studies have been carried out with machine learning in many different areas including the hydraulic conductivity of sandy floors, liquefaction of fine-grained ground, geopolymers of construction demolition waste, cement-based materials of carbon nanotubes, post-fire compressive strength of slag-based concrete, a nominal cutting capacity of a reinforced concrete wall, slope stability, axial loadbearing capacity of concrete-filled steel pipes, shear strength of reinforced concrete beams with and without striation, construction cost, shear strength of the ground, location after blasting operations, vibrations and migration mode of reinforced concrete curtain walls, building mechanics, building materials, construction management, etc. in the field of civil engineering [6][7][8][9][10][11][12][13][14][15][16][17][18]. Machine learning algorithms have a wide range of applications that can be applied to classification and regressiontype problems.…”

Section: Introductionmentioning

confidence: 99%

Prediction of Damping Capacity Demand in Seismic Base Isolators via Machine Learning

Ocak,

Işıkdağ,

Bekdaş

et al. 2024

CMES

View full text Add to dashboard Cite

Base isolators used in buildings provide both a good acceleration reduction and structural vibration control structures. The base isolators may lose their damping capacity over time due to environmental or dynamic effects. This deterioration of them requires the determination of the maintenance and repair needs and is important for the long-term isolator life. In this study, an artificial intelligence prediction model has been developed to determine the damage and maintenance-repair requirements of isolators as a result of environmental effects and dynamic factors over time. With the developed model, the required damping capacity of the isolator structure was estimated and compared with the previously placed isolator capacity, and the decrease in the damping property was tried to be determined. For this purpose, a data set was created by collecting the behavior of structures with single degrees of freedom (SDOF), different stiffness, damping ratio and natural period isolated from the foundation under far fault earthquakes. The data is divided into 5 different damping classes varying between 10% and 50%. Machine learning model was trained in damping classes with the data on the structure's response to random seismic vibrations. As a result of the isolator behavior under randomly selected earthquakes, the recorded motion and structural acceleration of the structure against any seismic vibration were examined, and the decrease in the damping capacity was estimated on a class basis. The performance loss of the isolators, which are separated according to their damping properties, has been tried to be determined, and the reductions in the amounts to be taken into account have been determined by class. In the developed prediction model, using various supervised machine learning classification algorithms, the classification algorithm providing the highest precision for the model has been decided. When the results are examined, it has been determined that the damping of the isolator structure with the machine learning method is predicted successfully at a level exceeding 96%, and it is an effective method in deciding whether there is a decrease in the damping capacity.

show abstract

Performance evaluation of slag-based concrete at elevated temperatures by a novel machine learning approach

Cited by 19 publications

References 32 publications

Tuned Mass Damper Parameters Design by Means of Meta-Heuristic Optimization Algorithms

Tuned Mass Damper Parameters Design by Means of Meta-Heuristic Optimization Algorithms

Eco-Concrete in High Temperatures

Prediction of Damping Capacity Demand in Seismic Base Isolators via Machine Learning

Contact Info

Product

Resources

About