Application of ANN Model Based on Information Optimization in Quantitative Analysis of Soil Compactness Tested by Instant Vibration

摘要

Along with the rapid development of road enterprise, the traditional testing method of soil compactness could not adapt to currently situation. So the method for measuring the soil compactness by instant hammering is put forward. By analysis of test data, some feature parameters reflecting the characteristics of the signal are extracted. To determine the soil compactness quantitatively, the model of artificial neural network based on hidden information maximization is built. The correctness and reliability are then validated and discussed. Result shows that it quite agree with the tested result by ring-knife method. This provides a new non-destructive, reliable and fast testing method for determining soil compactness in engineering practice.