Low-Strain Impact Testing of Piles - AI Analysis

Low-strain integrity testing of foundation piles (ASTM D5882) is the most widespread quality assurance method for deep foundation. The equipment used is relatively low-cost, the pile head requires little preparation, and testing itself is very fast. Due to these properties, the method is especially suited to 100% testing of large piling sites with millions of piles annually tested around the world.  On the other hand, interpreting the method's test results is not always straightforward and must be performed by suitably experienced geotechnical engineers. In view of the large amounts of data collected, this task may be extremely time-consuming. However, recent developments in Artificial Intelligence (AI) and Machine Learning (ML) can help engineers streamline this process.  The AI model presented in this paper was trained on a database including hundreds of thousands of real pile test results individually analyzed by an experienced engineer and then validated using a representative set of test results provided by several testing laboratories. A metric for assessing the quality of the analysis is also proposed. So far, the outcome is encouraging and justifies further development.