Abstract: Laser and synthetic profilometry of positive displacement motors (PDM) and ML methods, systems, and computer medium storing instructions for predicting PDM attribute(s). Laser profilometric scans (LPS) and mechanical stator minor ID (SMID) measurements from a plurality of locations in the stator are used for training a stator profilometric ML (SPML) model to learn stator profiles. The SPML model is deployed on input SMID measurements to generate synthetic stator dimension data (SSDD). LPS are preprocessed for feature alignment and statistical profilometric data are extracted for use in training the SPML model, and/or for training a PDM motor performance ML (MPML) model to learn PDM performance. The MPML training dataset may also include the learned stator profiles from the SPML model. The MPML model is deployed, on either input LPS or SSDD generated by the SPML model from input SMID measurements, to generate PDM performance data.

Abstract: Laser and synthetic profilometry of positive displacement motors (PDM) and ML methods, systems, and computer medium storing instructions for predicting PDM attribute(s). Laser profilometric scans (LPS) and mechanical stator minor ID (SMID) measurements from a plurality of locations in the stator are used for training a stator profilometric ML (SPML) model to learn stator profiles. The SPML model is deployed on input SMID measurements to generate synthetic stator dimension data (SSDD). LPS are preprocessed for feature alignment and statistical profilometric data are extracted for use in training the SPML model, and/or for training a PDM motor performance ML (MPML) model to learn PDM performance. The MPML training dataset may also include the learned stator profiles from the SPML model. The MPML model is deployed, on either input LPS or SSDD generated by the SPML model from input SMID measurements, to generate PDM performance data.