Scholarlink

<p>Pervious concrete is proven to environmentally benefit urban pavement construction. Optimizing compaction energy evidently reduces uncertainty in mass production of pervious concrete with uniform characteristics. Distribution of compaction energy in wet mix and rearrangement of binder-coated aggregate particles are affected by size and shape of aggregates. This study analyses the impact of aggregate size and shape on porosity and compressive strength prediction based on mix-design parameters. Aggregate-to-cement ratio (3, 4 and 5), compaction (0, 30 and 60 blows from standard proctor rammer), aggregate sizes (5–12&#xa0;mm, 12–18&#xa0;mm and 18–25&#xa0;mm) and aggregate shape (0, 200 and 1000 revolutions of milling in Los-Angeles-Abrasion-Value instrument) were used to cast a total number of 486 samples. Porosity was computed from constituent ratios (T.Poro) and apparent weight (M.Poro) methods. Compressive strength (Com.S) of the samples were recorded using universal-testing-machine (UTM). Relationship between M.Poro and T.Poro was significantly affected by shape of aggregate and not by size. Boosted-Forest machine learning algorithm had an accuracy of prediction (R<sup>2</sup>) above 0.8 for all models of T.Poro, M.Poro and Com.S for each class of aggregate shape. A generic boosted-forest model with AC ratio, compaction, aggregate size and aggregate shape as independent parameters had enhanced accuracy (R<sup>2</sup>) of 0.95, 0.96 and 0.93 for T.Poro, M.Poro and Com.S, respectively. High accuracy and details of contribution of independent parameters on the predictions make Boosted-Forest more suitable for prediction of performance of pervious concrete in the design phase of applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Boosted Forest Model for Aggregate Size and Shape Impact on Porosity and Compressive Strength of Pervious Concrete

  • 期刊论文

  • 发表日期：

    2025年7月18日

查看全文
  • Daniel Niruban Subramaniam,
  • Pratheeba Jeyananthan,
  • Navaratnarajah Sathiparan

摘要

Pervious concrete is proven to environmentally benefit urban pavement construction. Optimizing compaction energy evidently reduces uncertainty in mass production of pervious concrete with uniform characteristics. Distribution of compaction energy in wet mix and rearrangement of binder-coated aggregate particles are affected by size and shape of aggregates. This study analyses the impact of aggregate size and shape on porosity and compressive strength prediction based on mix-design parameters. Aggregate-to-cement ratio (3, 4 and 5), compaction (0, 30 and 60 blows from standard proctor rammer), aggregate sizes (5–12 mm, 12–18 mm and 18–25 mm) and aggregate shape (0, 200 and 1000 revolutions of milling in Los-Angeles-Abrasion-Value instrument) were used to cast a total number of 486 samples. Porosity was computed from constituent ratios (T.Poro) and apparent weight (M.Poro) methods. Compressive strength (Com.S) of the samples were recorded using universal-testing-machine (UTM). Relationship between M.Poro and T.Poro was significantly affected by shape of aggregate and not by size. Boosted-Forest machine learning algorithm had an accuracy of prediction (R2) above 0.8 for all models of T.Poro, M.Poro and Com.S for each class of aggregate shape. A generic boosted-forest model with AC ratio, compaction, aggregate size and aggregate shape as independent parameters had enhanced accuracy (R2) of 0.95, 0.96 and 0.93 for T.Poro, M.Poro and Com.S, respectively. High accuracy and details of contribution of independent parameters on the predictions make Boosted-Forest more suitable for prediction of performance of pervious concrete in the design phase of applications.