# US 10,871,468 B2 · Non-contact material inspection

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,871,468 B2
- Document ID: US10871468B2
- Status: Granted
- Kind: B2
- Application number: 16/293,468
- Filed: 2019-03-05
- Published: 2020-05-07
- Granted: 2020-12-22
- Earliest claimed: 2018-11-05
- Assignees: Tata Consultancy Services Limited
- Applicants: Tata Consultancy Services Limited
- Inventors: Rajat Kumar Das; Arijit Sinharay; Smriti Rani; Andrew Gigie; Tapas Chakravarty
- Web page: https://patentgrep.com/patent/US10871468B2

## CPC

- G01N 27/72: by investigating magnetic variables
- G01S 7/417: {involving the use of neural networks}
- G01N 22/00: Investigating or analysing materials by the use of microwaves or radio waves, i.e. electromagnetic waves with a wavelength of one millimetre or more (G01N3/00 - G01N17/00, G01N24/00 take precedence)
- G01S 7/35: Details of non-pulse systems
- G01S 13/04: Systems determining presence of a target (based on relative movement of target G01S13/56)
- G01S 13/06: Systems determining position data of a target
- G01S 13/32: using transmission of continuous waves, whether amplitude-, frequency-, or phase-modulated, or unmodulated
- G01S 13/88: Radar or analogous systems specially adapted for specific applications (electromagnetic prospecting or detecting of objects, e.g. near-field detection, G01V3/00)
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES

## Abstract

This disclosure relates to non-contact inspection of material for identifying and estimate composition of a material under inspection. Traditionally, material inspection is an invasive process involving contact based approaches. A radar-based approach requires placement of the radar at a specific location, which is a challenge since amplitude of the reflected signal, depends on the distance from the material under inspection. The present disclosure addresses this technical problem by providing a Continuous Wave radar-based approach that is based on absolute slope at extrema points on the reflected signal from the material under inspection.

## Claims

### Claim 1

A processor implemented method comprising the steps of:
computing, by a controller unit, 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;
identifying, by the controller unit, maxima points and minima points from the extrema points by performing a second order derivative thereon;
computing, by the controller unit, 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;
generating, by the controller unit, 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;
training, a machine learning based classifier model, using the generated first feature set; and
classifying a material under inspection based on absolute slope computed using any two consecutive extrema points using the trained classifier model.

### Claim 2 (depends on 1)

The processor implemented method of claim 1, wherein the baseband signal B(t) is obtained by mixing the reflected signal with a local oscillator signal T(t) and passing a resultant signal through a low pass filter.

### Claim 3 (depends on 1)

The processor implemented method of claim 1, wherein the maxima points are the extrema points for which the second derivative is negative and slope of the baseband signal is at first positive and then goes through zero to become negative; and the minima points are the extrema points for which the second derivative is positive and the slope of the baseband signal is at first negative and then goes through zero to become positive.

### Claim 4 (depends on 1)

The processor implemented method of claim 1, wherein the step of generating a first feature set is followed by:
generating, by the controller unit, a second feature set comprising the first feature set and composition of each sample material in the sample set;
training, a regression model, using the generated second feature set; and
estimating composition of the material under inspection based on absolute slope computed using any two consecutive extrema points using the trained regression model.

### Claim 5

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.

### Claim 6

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.

### Claim 7 (depends on 6)

The system of claim 6, wherein the baseband signal B(t) is obtained by mixing the reflected signal with a local oscillator signal T(t) and passing a resultant signal through a low pass filter.

### Claim 8 (depends on 6)

The system of claim 6, wherein the maxima points are the extrema points for which the second derivative is negative and slope of the baseband signal is at first positive and then goes through zero to become negative; and the minima points are the extrema points for which the second derivative is positive and the slope of the baseband signal is at first negative and then goes through zero to become positive.