This research work is aimed to carryout experimental investigation on copper slag incorporated self-compacting (SCC) concrete; here, copper slag is used as a replacement to fine aggregate in the range of 0–100%. The self-compacting concrete is manufactured with powder matrix incorporating cement, flyash, metakaolin, and silicafume. The powder matrix is decided based on the objective of flow properties and strength properties. The fresh concrete properties of various mixes were studied and collected. Then, the concrete is casted as cubes and cylinders and tested for its strength behavior. The flow properties of copper slag-replaced mix were within stipulated guideline values by EFNARC, and early age strength attainment gets affected by the replacement of copper slag. The collected experimental results were designed to a data set categorizing as input and target. This data set is then used as a parameter in feed forward artificial neural network (ANN) and a predictive model is developed. This predictive model is then compared with the existing experimental values and tested for its performance. The results show that ANN provides a reliable predictive model for both flow and strength properties.

中文翻译：

---

基于人工神经网络的掺铜渣自密实混凝土试验研究与预测

本研究旨在对掺铜渣的自密实（SCC）混凝土进行试验研究；在这里，铜渣用作 0-100% 范围内的细骨料的替代品。自密实混凝土采用粉末基体制造，掺入水泥、粉煤灰、偏高岭土和硅灰。粉末基体是根据流动性能和强度性能的目标来确定的。研究和收集了各种混合料的新拌混凝土性能。然后，将混凝土浇铸成立方体和圆柱体，并测试其强度性能。铜渣替代混合物的流动性能在 EFNARC 规定的指导值范围内，早期强度获得受到铜渣替代的影响。收集的实验结果被设计成一个数据集，分类为输入和目标。然后将该数据集用作前馈人工神经网络 (ANN) 中的参数，并开发预测模型。然后将该预测模型与现有的实验值进行比较并测试其性能。结果表明，ANN 为流动和强度特性提供了可靠的预测模型。