Research Article
Applicability of Artificial Neural Networks to Predict Mechanical and Permeability Properties of Volcanic Scoria-Based Concrete
Table 5
Weight matrix and weights between input and hidden layers (W1) and between hidden and output layers (W2) for the ANN1 model.
| Neuron | W1 | W2 | Input | Output | Time (day) | Cement content (kg) | VS content (kg) | Water content (kg) | SP |
| 1 | −2.105944022 | 1.075228351 | 1.255199036 | 0.438755839 | −0.030683697 | 1.279718465 | 2 | 0.144053427 | −0.972020695 | 0.742996724 | 1.753640631 | −1.340918263 | −1.208902522 | 3 | 1.732934016 | 0.61985474 | −1.155641212 | −1.283690471 | 3.243864115 | 0.460723363 | 4 | 0.903445767 | 0.372764295 | 1.572839487 | −0.87906307 | 1.904073089 | 0.705296001 | 5 | 0.938501968 | −1.091473696 | −2.116933639 | −0.459056052 | 1.573936415 | 1.53887134 | 6 | 0.344253977 | −0.597794971 | 0.779210827 | 1.235683476 | 2.059459437 | 0.961634634 | 7 | −1.024890536 | −1.466697926 | −1.591821924 | −1.081779779 | 1.829483202 | 0.698867474 | 8 | −0.064928174 | −1.591852569 | 1.716382139 | 1.62579402 | −2.437814145 | −0.331804241 | 9 | −1.498209432 | 0.875620108 | −0.423664145 | −1.895854904 | 2.039710262 | 0.545700344 | 10 | −0.233072918 | −1.362387421 | 1.333842112 | −1.465558 | 1.098041189 | −0.562090401 | 11 | −0.936088182 | 2.726784678 | −1.120598625 | −2.150579249 | −0.530783246 | 0.108067552 | 12 | −11.888422 | 0.182734218 | 0.268691589 | 0.167278196 | 0.141190095 | −4.372180414 | 13 | −0.214986128 | −1.611586142 | 1.972556139 | −1.4704395 | 1.201024837 | −0.399869245 | 14 | 1.564288124 | 0.63694431 | 1.050612614 | −0.532653652 | 0.778724302 | 0.192780767 | 15 | 0.430315807 | −0.418860675 | 0.04929488 | −0.345348435 | −1.723849754 | 2.899735928 | 16 | −0.007106844 | −1.904352783 | −1.119167674 | 1.319502798 | 0.223633621 | 2.309346307 |
|
|