Non-contact material inspection

A non-contact material inspection apparatus comprising:

• a Continuous Wave (CW) radar configured to slide towards or away from a material under inspection;
• a motor configured to move the CW radar towards or away from the material under inspection;
• a controller unit comprising:
• one or more data storage devices configured to store instructions;
• and
• one or more hardware processors operatively coupled to the one or more data storage devices, wherein the one or more hardware processors are configured by the instructions to:
• control the movement of the CW radar, via the motor;
• compute extrema points within an empirically determined length of a reflected signal, the reflected signal being a signal reflected off a sample material in a sample set in response to a transmitted signal from the CW radar, wherein the empirically determined length of the reflected signal is 2.5λ, wherein λ represents wavelength of the reflected signal, and wherein the step of computing extrema points comprises:
• moving the CW radar in steps of λ/10 within the 2.5λ from a starting point being at a distance of at least 6λ, from the sample material;
• measuring a baseband signal B(t) corresponding to the reflected signal at each λ/10 distance;
• performing a first order derivative of the measured baseband signal B(t);
• and
• identifying points where the first order derivative is zero as the extrema points;
• identify maxima points and minima points from the extrema points by performing a second order derivative thereon;
• compute absolute slope of each line between a maxima point and a consecutive minima point from the identified maxima points and minima points based on associated amplitude and distance of the CW radar from the corresponding sample material;
• generate a first feature set comprising average of slopes computed for a plurality of iterations of the steps of computing the extrema points, identifying the maxima points and the minima points thereof and computing the absolute slope of each line, corresponding to each sample material from the sample set;
• train a machine learning based classifier model using the generated first feature set;
• generate a second feature set comprising the first feature set and composition of each sample material in the sample set;
• and
• train a regression model using the generated second feature set;
• the classifier model configured to classify the material under inspection based absolute slope computed using any two consecutive extrema points;
• and
• the regression model configured to estimate composition of the material under inspection based on absolute slope computed using any two consecutive extrema points.

A system comprising:

• one or more data storage devices operatively coupled to one or more hardware processors and configured to store instructions configured for execution by the one or more hardware processors to:
• compute extrema points within an empirically determined length of a reflected signal, the reflected signal being a signal reflected off a sample material in a sample set in response to a transmitted signal from a Continuous Wave (CW) radar, wherein the empirically determined length of the reflected signal is 2.5λ, wherein λ represents wavelength of the reflected signal, and wherein the step of computing extrema points comprises:
• moving the CW radar in steps of λ/10 within the 2.5λ from a starting point being at a distance of at least 6λ, from the sample material;
• measuring a baseband signal B(t) corresponding to the reflected signal at each λ/10 distance;
• performing a first order derivative of the measured baseband signal B(t);
• and
• identifying points where the first order derivative is zero as the extrema points;
• identify maxima points and minima points from the extrema points by performing a second order derivative thereon;
• compute absolute slope of each line between a maxima point and a consecutive minima point from the identified maxima points and minima points based on associated amplitude and distance of the CW radar from the corresponding sample material;
• generate a first feature set comprising average of slopes computed for a plurality of iterations of the steps of computing the extrema points, identifying the maxima points and the minima points thereof and computing the absolute slope of each line, corresponding to each sample material from the sample set;
• train a machine learning based classifier model using the generated first feature set;
• generate a second feature set comprising the first feature set and composition of each sample material in the sample set;
• and
• train a regression model using the generated second feature set.