Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms

Polymers, Journal Year: 2021, Volume and Issue: 13(19), P. 3389 - 3389

Published: Oct. 2, 2021

The innovation of geopolymer concrete (GPC) plays a vital role not only in reducing the environmental threat but also as an exceptional material for sustainable development. application supervised machine learning (ML) algorithms to forecast mechanical properties has significant developing innovative environment field civil engineering. This study was based on use artificial neural network (ANN), boosting, and AdaBoost ML approaches, python coding predict compressive strength (CS) high calcium fly-ash-based GPC. performance comparison both employed techniques terms prediction reveals that ensemble AdaBoost, boosting were more effective than individual technique (ANN). indicates highest value R2 equals 0.96, gives 0.93, while ANN model less accurate, indicating coefficient determination 0.87. lesser values errors, MAE, MSE, RMSE give 1.69 MPa, 4.16 2.04 respectively, accuracy algorithm. However, statistical check errors (MAE, RMSE) k-fold cross-validation method confirms precision technique. In addition, sensitivity analysis introduced evaluate contribution level input parameters towards CS better can be achieved by incorporating other such bagging, gradient boosting.

Language: Английский

---

Electrical efficiency of the photovoltaic/thermal collectors cooled by nanofluids: Machine learning simulation and optimization by evolutionary algorithm

Energy Reports, Journal Year: 2021, Volume and Issue: 8, P. 24 - 36

Published: Dec. 10, 2021

Photovoltaic/thermal (PV/T) are high-tech devices to transform solar radiation into electrical and thermal energies. Nano-coolants recently considered enhance the efficiency of PV/T systems. There is no accurate model predict/optimize systems' cooled by nano-coolants. Therefore, this research employs machine-learning approaches simulate system performance water-based nanofluids. The best topology artificial neural networks, least-squares support vector regression, adaptive neuro-fuzzy inference systems (ANFIS) found trial-and-error statistical analyses. ANFIS as method for simulation system. This approach predicted 200 experimental datasets with absolute average relative deviation (AARD) 13.6%, mean squared error (MSE) 2.548, R2=0.9534. Furthermore, predicts a new external database containing 63 samples AARD=15.21%. optimization stage confirms that 30 lit/hr water-silica nano-coolant (3wt%, 12.5 nm) at intensity 788.285 W/m2 condition maximizes efficiency. In optimum condition, enhancement in 27.7%. Finally, fabricated has been utilized generating several pure predictions have never published before.

Language: Английский

---

Application of machine learning methods for estimating and comparing the sulfur dioxide absorption capacity of a variety of deep eutectic solvents

Journal of Cleaner Production, Journal Year: 2022, Volume and Issue: 363, P. 132465 - 132465

Published: June 3, 2022

Language: Английский

---

A roadmap towards energy‐efficient data fusion methods in the Internet of Things

Concurrency and Computation Practice and Experience, Journal Year: 2022, Volume and Issue: 34(15)

Published: March 30, 2022

Abstract Nowadays, with the rapid progress of Internet‐based and distributed systems such as cloud computing, peer‐to‐peer networking, Internet Things (IoT), significant improvements in almost every engineering commercial field have been made. On basis IoT, smart cities are formed utilizing intelligent information processing, universal connectivity, ubiquitous sensing, real‐time monitoring. Energy conservation is one issues current IoT development due to poor battery endurance objects. Over last years, cities' explosive growth, a huge range studies regarding energy efficiency done. The diversity sparse data multi‐sourcing utilized developing scenarios. In order use efficiently these improve services, fusion plays an important role. It saves network resources, improves transmission efficiency, extracts useful from raw data. To best our knowledge, there still lack comprehensive systematic study about surveying analyzing available energy‐efficient techniques IoT. Thus, this article aims address gap using method.

Language: Английский

---

Application of Neural Network and Time-Domain Feature Extraction Techniques for Determining Volumetric Percentages and the Type of Two Phase Flow Regimes Independent of Scale Layer Thickness

Applied Sciences, Journal Year: 2022, Volume and Issue: 12(3), P. 1336 - 1336

Published: Jan. 27, 2022

One of the factors that significantly affects efficiency oil and gas industry equipment is scales formed in pipelines. In this innovative, non-invasive system, inclusion a dual-energy gamma source two sodium iodide detectors was investigated with help artificial intelligence to determine flow pattern volume percentage two-phase by considering thickness scale tested pipeline. proposed structure, consisting barium-133 cesium-137 isotopes emit photons, one detector recorded transmitted photons second scattered photons. After simulating mentioned structure using Monte Carlo N-Particle (MCNP) code, time characteristics named 4th order moment, kurtosis skewness were extracted from data both transmission (TD) scattering (SD). These considered as inputs multilayer perceptron (MLP) neural network. Two networks able percentages high accuracy, well classify all regimes correctly, trained.

Language: Английский

---

Single‐objective service composition methods in cloud manufacturing systems: Recent techniques, classification, and future trends

Concurrency and Computation Practice and Experience, Journal Year: 2021, Volume and Issue: 34(5)

Published: Nov. 3, 2021

Abstract In recent years, cloud manufacturing (CMfg) has been developed as an intelligent system, in which geographically distributed resources are available services the platform. Choosing and integrating single into a combined service to fulfill client's requests requires higher emphasis. However, by increasing customers' trend utilize CMfg, providers encouraged publish with various functional non‐functional characteristics. Thus, composition optimal selection become one of most challenging topics CMfg. Hence, inclusive review current studies on this NP‐hard issue is extremely desirable. This article first, selects field single‐objective CMfg classifies surveys them comprehensively terms QoS parameters, energy consumption, user constraint, so forth. aims provide useful roadmap for future researchers who intended explore novel work field. The search articles was conducted November 2020.

Language: Английский

---

ANN based predictive mimicker for mechanical and rheological properties of eco-friendly geopolymer concrete

Case Studies in Construction Materials, Journal Year: 2022, Volume and Issue: 17, P. e01536 - e01536

Published: Oct. 7, 2022

Due to an increase in global warming, the construction industry, like rest of world is turning towards sustainable solutions. The industry major contributor warming primarily due use cement. Geopolymer eco-friendly material that utilizes zero cement for its production. However, issue limits commercial implementation complex mix design, which not as straightforward conventional concrete. As geopolymer contains more elements than concrete, design process challenging. Alongside there are no defined guidelines designing makes task it quite time-consuming, uneconomical, and iterative. objective this research develop a machine learning model can predict mechanical rheological properties An Artificial Neural Network-based was developed, takes input mix's constituents predicts both result. MAE (Mean square error) compressive strength, elastic modulus, flexural slump value training set were 2.53, 0.72, 0.121, 8.9, respectively, while testing 4.32, 1.5, 0.65, 19.7. These performance results seem excellent be used prediction. This paper will help effective concrete with limited experimentation.

Language: Английский

---

ANN-based predictive mimicker for the constitutive model of engineered cementitious composites (ECC)

Construction and Building Materials, Journal Year: 2024, Volume and Issue: 420, P. 135530 - 135530

Published: Feb. 29, 2024

Language: Английский

---

Edge Computing for Real-Time Decision Making in Autonomous Driving: Review of Challenges, Solutions, and Future Trends

International Journal of Advanced Computer Science and Applications, Journal Year: 2024, Volume and Issue: 15(7)

Published: Jan. 1, 2024

In the coming half-century, autonomous vehicles will share roads alongside manually operated automobiles, leading to ongoing interactions between two categories of vehicles. The advancement driving systems has raised importance real-time decision-making abilities. Edge computing plays a crucial role in satisfying this requirement by bringing computation and data processing closer source, reducing delay, enhancing overall efficiency This paper explores core principles edge computing, emphasizing its capability handle close origin. study focuses on issues network reliability, safety, scalability, resource management. It offers insights into strategies technology that effectively these challenges. Case studies demonstrate practical implementations highlight real-world benefits processes for Furthermore, outlines upcoming trends examines emerging technologies such as artificial intelligence, 5G connectivity, innovative architectures.

Language: Английский

---

Adaptive Computational Solutions to Energy Efficiency in Cloud Computing Environment Using VM Consolidation

Archives of Computational Methods in Engineering, Journal Year: 2022, Volume and Issue: 30(3), P. 1789 - 1818

Published: Nov. 27, 2022

Language: Английский

---