An intelligent approach to predict the drilling penetration rate using acoustic emission technique (AET)

Mehrbod Khoshouei ¹, Raheb Bagherpour ², Mohammad Hossein Jalalian ¹

⁰Department of Mining Engineering, Isfahan University of Technology, Isfahan, 8415683111, Iran.

Scientific Reports +

|

October 28, 2025

View abstract on PubMed

Summary

Geotechnical drilling performance can be predicted using vibroacoustic signals and artificial intelligence (AI). Machine learning models accurately forecast penetration rates, enhancing efficiency and sustainability in excavation projects.

Area Of Science

Geotechnical Engineering
Artificial Intelligence
Signal Processing

Background

Optimization is crucial in geotechnical engineering due to energy constraints and cost demands.
Drilling efficiency is vital for mining and tunneling, necessitating intelligent performance strategies.
Monitoring While Drilling (MWD) and Acoustic Emission Technique (AET) offer real-time data acquisition and analysis.

Purpose Of The Study

To predict drilling penetration rate (PR) by analyzing vibroacoustic signals and drilling parameters.
To evaluate the effectiveness of Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Regression (SVR) models for PR prediction.
To demonstrate the integration of vibroacoustic monitoring with AI for enhanced drilling performance.

Main Methods

Collected and analyzed vibroacoustic signals and drilling parameters.
Developed and compared three machine learning models: ANN, RF, and SVR.
Assessed model performance using metrics such as R-squared, MAPE, and RMSE.

Main Results

All models demonstrated reliable predictive accuracy for penetration rate.
Random Forest (RF) achieved the highest R-squared value (0.816) and lowest MAPE (31.54%).
Support Vector Regression (SVR) showed comparable performance with R-squared of 0.808 and MAPE of 29.52%.

Conclusions

Integrating vibroacoustic monitoring with AI-driven models is feasible for accurate PR prediction.
This approach supports real-time decision-making and improves drilling efficiency.
The findings promote sustainable practices in underground and surface excavation projects.

Keywords:

Acoustic emission technique (AET) Artificial intelligence (AI) Monitoring while drilling (MWD) Penetration rate