The first target of mining activities on the surface of the moon is to find and extract water from the
icy regolith on the moon. A test drilling unit was designed and fabricated under a NASA Early Stage
Innovation (ESI) grant. A high-frequency data acquisition system was used to record drilling
responses at 1000 Hz. Parameters like weight on bit (WOB), torque, rev/min, rate of penetration
(ROP), mechanical specific energy (MSE), field penetration index (FPI), and the uniaxial
compressive strength (UCS) were recorded for 40 boreholes in the analog samples made of regolith
simulant and specialised cement. Development of the AI system and machine learning (ML)
algorithms for analysis of data to evaluate strength and hence water content of icy regolith required
a large data set. In this case, the data set comprising of more than one billion data points recorded
while drilling into various analogue samples and cryogenic lunar formations to optimise power
consumption and make bit wear adjustment during drilling operations. The tests were also repeated
in the samples of icy regolith at various water content at -190C to verify the ability of the algorithms
to analyse the data and to estimate the strength of the frozen formation and hence water content.
The paper will discuss the objectives and methodologies used in the project and reviews the testing
program and the machine learning (ML) algorithms ability to identify various formations along the
exploration boreholes.