Prediction of Concrete Compressive Strength Based on ISSA-BPNN-AdaBoost

Ping Li, Zichen Zhang, Jiming Gu · 2024

Read Prediction of Concrete Compressive Strength Based on ISSA-BPNN-AdaBoost by Ping Li, Zichen Zhang, Jiming Gu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11642094.txt.

Description

Ping Li, Zichen Zhang, and Jiming Gu stack learning methods to predict the strength of concrete without crushing test blocks, in a 2024 paper. Lab crushing is slow and costly, yet builders must know a mix's strength before they pour. Machine learning can guess strength from the recipe, if the guess is sharp enough.

Their stack starts with an improved sparrow search, a nature-inspired optimizer tuned with chaos maps and adaptive jumps, which first proves itself on ten test problems. The search then tunes a neural network, and a boosting method trains many such networks and blends their votes. On two data sets the stack beat rival stacks and single models at guessing compressive strength. The result supports blended learning as the strong path for this task.

Catalog record

CREATORPing Li, Zichen Zhang, Jiming Gu
YEAR2024
COLLECTIONPAPERS
FORMATTXT
FILE SIZE53 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11642094

Browse the full library · About the Tower of Babel