Claims:WE CLAIM:
1. A method for automated estimation of coal rank and phase fraction of a coal sample, the method comprising:
capturing, by an estimation system, a predefined number of images of the coal sample using one or more standard reflectance values;
generating, by the estimation system, a reflectance histogram for each of the predefined number of images by dividing grey values of the images with corresponding one or more standard reflectance values;
generating, by the estimation system, a cumulative histogram by aggregating the reflectance histogram of each of the predefined number of images;
segmenting, by the estimation system, the cumulative histogram into a plurality of segments based on one or more inflection points, wherein each segment of the plurality of segments represents a maceral type of the coal sample; and
estimating, by the estimation system, the coal rank and the phase fraction of the coal sample by calculating histogram values in the plurality of segments.

2. The method as claimed in claim 1, wherein generating the reflectance histogram comprises:
binarizing each of the predefined number of images for segmenting maceral coal region from a background region; and
converting a plurality of phase pixel values corresponding to the maceral coal region into reflectance values for generating the reflectance histogram.

3. The method as claimed in claim 1, wherein the reflectance histogram represents a distribution of reflectance values of each class of macerals within the maceral coal region.

4. The method as claimed in claim 1, wherein generating the cumulative histogram comprises:
smoothening the reflectance histogram by determining a mean and standard deviation of reflectance values using a sliding window of predefined length.

5. The method as claimed in claim 4 further comprises estimating a maximum likelihood of the mean and standard deviation to optimally fit the smoothened reflectance histogram data to a Gaussian distribution.

6. The method as claimed in claim 1, wherein segmenting the cumulative histogram comprises:
normalizing the cumulative histogram;
computing a first-order derivative of the normalized cumulative histogram;
determining an end point of a leading flat portion and a start point of a trailing flat portion of the cumulative histogram based on the first-order derivative; and
designating the end point and the start point as the one or more inflection points for the cumulative histogram.

7. The method as claimed in claim 1, wherein:
for a high-rank coal sample, the coal rank and the phase fraction are estimated using a Gaussian fit on histogram values in the plurality of segments within the inflection points; and
for a low-rank coal sample, the coal rank and the phase fraction are estimated using the Gaussian fit on the histogram values in each of the plurality of segments in the cumulative histogram.

8. An estimation system for automated estimation of coal rank and phase fraction of a coal sample, the estimation system comprising:
a processor; and
a memory, communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution cause the processor to:
capture a predefined number of images of the coal sample using one or more standard reflectance values;
generate a reflectance histogram for each of the predefined number of images by dividing grey values of the images with corresponding one or more standard reflectance values;
generate a cumulative histogram by aggregating the reflectance histogram of each of the predefined number of images;
segment the cumulative histogram into a plurality of segments based on one or more inflection points, wherein each segment of the plurality of segments represents a maceral type of the coal sample; and
estimate the coal rank and the phase fraction of the coal sample by calculating histogram values in the plurality of segments.

9. The estimation system as claimed in claim 8, wherein the processor generates the reflectance histogram by:
binarizing each of the predefined number of images for segmenting maceral coal region from a background region; and
converting a plurality of phase pixel values corresponding to the maceral coal region into reflectance values for generating the reflectance histogram.

10. The estimation system as claimed in claim 8, wherein the reflectance histogram represents a distribution of reflectance values of each class of macerals within the maceral coal region.

11. The estimation system as claimed in claim 8, wherein the processor generate the cumulative histogram by:
smoothening the reflectance histogram by determining a mean and standard deviation of reflectance values using a sliding window of predefined length.

12. The estimation system as claimed in claim 11, wherein the processor estimates a maximum likelihood of the mean and standard deviation to optimally fit the smoothened reflectance histogram data to a Gaussian distribution.

13. The estimation system as claimed in claim 8, wherein the processor segments the cumulative histogram by:
normalizing the cumulative histogram;
computing a first-order derivative of the normalized cumulative histogram;
determining an end point of a leading flat portion and a start point of a trailing flat portion of the cumulative histogram based on the first-order derivative; and
designating the end point and the start point as the one or more inflection points for the cumulative histogram.
14. The estimation system as claimed in claim 8, wherein:
for a high-rank coal sample, the processor estimates the coal rank and the phase fraction using a Gaussian fit on histogram values in the plurality of segments within the inflection points; and
for a low-rank coal sample, the processor estimates the coal rank and the phase fraction using the Gaussian fit on the histogram values in each of the plurality of segments in the cumulative histogram.

Dated this 16th Day of March, 2022

NIKHIL S R
OF K & S PARTNERS
AGENT FOR THE APPLICANT(S)
IN/PA-2127
, Description:FORM 2
THE PATENTS ACT 1970
[39 OF 1970]
&
THE PATENTS RULES, 2003

COMPLETE SPECIFICATION
[See section 10; Rule 13]

TITLE: “METHOD AND SYSTEM FOR AUTOMATED ESTIMATION OF COAL RANK AND PHASE FRACTION OF COAL SAMPLES”

Name and Address of the Applicants:
TATA STEEL LIMITED, Jamshedpur, Jharkhand, India 831001, AND Indian Statistical Institute, 203, Barracpore Trunk Road, Kolkata-700108

Nationality: INDIAN

The following specification particularly describes the invention and the manner in which it is to be performed.

TECHNICAL FIELD

The present subject matter is, in general, related to coal petrography and more particularly, but not exclusively, to a method and system for automated estimation of coal rank and phase fraction of coal samples.

BACKGROUND

It is well known that coal is the backbone of the steel industry because of its manifold use in coke making, pulverized coal injection and electricity generation. Coke quality in terms of its use as fuel, reducing agent and permeable blast furnace load bearer depends on nature of individual coal and their blend proportion. Petrography is a critical art for measuring heterogeneity of coal in terms of phase fractions and coal rank. While phase fraction is a direct measure to coal quality, coal rank is a measure of the relative amount of coalification, that is, maturity of the coal. Calculation of phase fractions and coal rank are important but challenging problems in coal petrography.

Expert driven coal petrography is in use in the industries over the years. However, manual calculation of phase fraction and coal rank is a time-consuming process, and mostly depends on the expertise of a petrologist. Generally, a single manual coal petrography analysis takes almost whole day, and this creates delay in quicker decision making for coal blend formulation. But for industrial purposes, quicker analysis of individual coal is required for charging of coal blend in coke plant.

To cater to the industry demand for faster and more objective petrographic analysis, automatic calculation of phase fractions and coal rank has been a trend in coal petrography. One of the existing techniques for coal petrography uses reflected light microscopy for imaging coal pellet. Another existing method uses a random forest based machine learning model to calculate maceral percentages in coal microscopic images. Both these methods reported almost an accuracy of 90%. However, these methods do not calculate coal rank and are limited to calculating the maceral percentages. Also, these methods rely on local texture properties based on an expert-marked ground truth pixel. Moreover, the existing methods focus on a limited spectrum of coal, without considering coal samples from various geographical locations.

The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

SUMMARY

Disclosed herein is a method for automated estimation of coal rank and phase fraction of a coal sample. The method comprises capturing, by an estimation system, a predefined number of images of the coal sample using one or more standard reflectance values. Further, the method comprises generating a reflectance histogram for each of the predefined number of images by dividing grey values of the images with corresponding one or more standard reflectance values. Further, the method comprises generating a cumulative histogram by aggregating the reflectance histogram of each of the predefined number of images. Thereafter, the method comprises segmenting the cumulative histogram into a plurality of segments based on one or more inflection points, wherein each segment of the plurality of segments represents a maceral type of the coal sample. Finally, the method comprises estimating the coal rank and the phase fraction of the coal sample by calculating histogram values in the plurality of segments.

Further, the present disclosure relates to an estimation system for automated estimation of coal rank and phase fraction of a coal sample. The estimation system comprises a processor and a memory. The memory is communicatively coupled to the processor and stores processor-executable instructions, which on execution cause the processor to capture a predefined number of images of the coal sample using one or more standard reflectance values. Further, the instructions cause the processor to generate a reflectance histogram for each of the predefined number of images by dividing grey values of the images with corresponding one or more standard reflectance values. Further, the instructions cause the processor to generate a cumulative histogram by aggregating the reflectance histogram of each of the predefined number of images. Furthermore, the instructions cause the processor to segment the cumulative histogram into a plurality of segments based on one or more inflection points, wherein each segment of the plurality of segments represents a maceral type of the coal sample. Finally, the instructions cause the processor to estimate the coal rank and the phase fraction of the coal sample by calculating histogram values in the plurality of segments.

In an embodiment of the present disclosure, the reflectance histogram is generated by binarizing each of the predefined number of images for segmenting maceral coal region from a background region and then converting a plurality of phase pixel values corresponding to the maceral coal region into reflectance values for generating the reflectance histogram.

In a further embodiment of the present disclosure, the reflectance histogram represents a distribution of reflectance values of each class of macerals within the maceral coal region.

In a further embodiment of the present disclosure, the cumulative histogram may be generated by smoothening the reflectance histogram by determining a mean and standard deviation of reflectance values using a sliding window of predefined length. Further, a maximum likelihood of the mean and standard deviation may be estimated to optimally fit the smoothened reflectance histogram data to a Gaussian distribution.

In a further embodiment of the present disclosure, the cumulative histogram may be segmented by normalizing the cumulative histogram, computing a first-order derivative of the normalized cumulative histogram, and then determining an end point of a leading flat portion and a start point of a trailing flat portion of the cumulative histogram based on the first-order derivative. Further, the end point and the start point may be designated as the one or more inflection points for the cumulative histogram.

In a further embodiment of the present disclosure, for a high-rank coal sample, the coal rank and the phase fraction are estimated using a Gaussian fit on histogram values in the plurality of segments within the inflection points. Similarly, for a low-rank coal sample, the coal rank and the phase fraction are estimated using the Gaussian fit on the histogram values in each of the plurality of segments in the cumulative histogram.

The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.

BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which:

FIG. 1 shows an overview of a method for automated estimation of coal rank and phrase fraction of a coal sample in accordance with some embodiments of the present disclosure.

FIG. 2 shows a detailed block diagram of an estimation system in accordance with some embodiments of the present disclosure.

FIGS. 3A and 3B respectively show an exemplary reflectance histogram and a smoothened reflectance histogram in accordance with some embodiments of the present disclosure.

FIGS. 3C and 3D repectively illustrate maximum likelihood values and Gaussian distibution for different values of mean and standard deviation in accordance with some exemplary embodiments of the present disclosure.

FIG. 4A shows a cumulative histogram of the reflectance histogram in accordance with some exemplary embodiments of the present disclosure.

FIG. 4B shows a first order derivative of normalized cumulative frequency in accordance with some exemplary embodiments of the present disclosure.

FIG. 4C indicates Gaussian fit for low-rank coal considering the entire reflectance data in accordance with some exemplary embodiments of the present disclosure.

FIG. 4D shows Truncated Gaussian fit for high rank coal considering reflectance data within arbitrary inflection points (a, ß) in accordance with some exemplary embodiments of the present disclosure.

FIG. 4E shows an exemplary representation of range of reflectance value for minerals in accordance with some exemplary embodiments of the present disclosure.

FIG. 5A shows a flowchart illustrating a method for automated estimation of coal rank and phrase fraction of a coal sample in accordance with some embodiments of the present disclosure.

FIG. 5B shows a flowchart illustrating variations in the method for automated estimation based on type/rank of coal in accordance with some embodiments of the present disclosure.

FIG. 6 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.

It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether such computer or processor is explicitly shown.

DETAILED DESCRIPTION

In the present document, the word “exemplary” is used herein to mean “serving as an example, instance, or illustration”. Any embodiment or implementation of the present subject matter described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.
The terms “comprises”, “comprising”, “includes”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
The present disclosure relates to a method and estimation system for automated estimation of coal rank and phase fraction of a coal sample. In an embodiment, the present disclosure proposes an automatic method for characterizing coal based on reflectogram and/or reflectance data. The coal reflectance data is obtained with the help of an optical microscope attached to a photomultiplier tube. Generally, coal properties are dependent on composition and rank of the coal, which is determined manually under microscope. The coal composition refers to the organic phases (macerals) and inorganic phases (minerals) present in the coal. The coal rank or coal maturity depends on the reflectance of one of the macerals called vitrinite. Since the manual analysis of the microscopic images is time consuming and depends on the expertise level of the operator, to cut-short the time and labor, the present disclosure provides an automated method to perform an optical characterization of the coal. An outcome of the present disclosure is helpful in coal procurement and utilization.

In an embodiment, the present disclosure uses an image processing-based method that automatically determines the rank of a coal sample as well as its phase fraction. The proposed method and system are simple to use, and a person having a limited knowledge of the domain can also perform coal petrography/characterization. The results show almost 90% accuracy both in coal rank detection and phase fraction classification. Also, the proposed method is fast and unsupervised compared to expert-driven phase fraction analysis and rank determination methods. For instance, the proposed method can determine the coal rank and phase fraction of a given sample as quickly as 5 minutes.

In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

FIG. 1 shows an overview 100 of a method for automated estimation of coal rank 107 and phrase fraction of a coal sample in accordance with some embodiments of the present disclosure.

In an embodiment, the estimation system 105 may be any computing system including, without limiting to, a desktop computer, a laptop or a smartphone with adequate memory and processing resources for performing various processes proposed in the present disclosure. In an implementation, the estimation system 105 may be deployed at a petrographic laboratory and/or a coal preparation plant for dynamically performing a qualitative analysis of the coal samples. In an alternative implementation, the estimation system 105 may be deployed as a remote server and configured to perform the desired functions using images of the coal sample 103 sent to it over a predefined communication channel. In an embodiment, the estimation system 105 may be operated even by a person with limited knowledge of the domain, as the estimation system 105 functions unsupervised and does not require any manual interventions.

In an embodiment, the estimation system 105 may estimate the coal rank 107 and phase fraction 109 of the coal sample using a predefined number of images of the coal sample 103. In an embodiment, the images of the coal sample 103 may be captured/obtained using an image capturing unit 101 associated with the estimation system 105. As an example, the predefined number of images may be a minimum 220 images.

The image capturing unit 101 may include, without limiting to, an optical microscope. In an implementation, Leica® DM6000M microscope may be used for capturing images of a coal pellet. Each digitized image may be of size 1280×960 pixels. Also, the images may be captured with 8-bit grey space under an exposure time of 56.8 milliseconds, gamma level (i.e., contrast scale) at 0.86 and keeping the intensity of light between 7 to 8 Volts. In an implementation, all the images may be taken under 200x magnification of white reflected light having oil immersion. The oil immersion may be used to enhance the resolving power of the microscope. In an embodiment, a microscope of any other make and model may be used for capturing the predefined number of images of the coal sample 103.

In an embodiment, the images of the coal sample 103 may be captured using different reflectance standard values. The reflectance value indicates a measure of the amount of visible and usable light that reflects from (or absorbs into) a surface. In the case of coal samples, the reflectance value represents a proportion of incident light that is reflected from various maceral components of the coal sample. Each maceral component, including Vitrinite, Liptinite and Inertinite, reflect different amounts of incident light and therefore correspond to different reflectance values. Therefore, to effectively distinguish and capture details of each maceral type, the images are captured at different reflectance standard values.

In an embodiment, after receiving the images of the coal sample 103 from the image capturing unit 101, the estimation system 105 may generate a reflectance histogram for each of the predefined number of images by dividing grey values of the images with corresponding one or more standard reflectance values. As exemplary reflectance histogram is shown in FIG. 3A. In an embodiment, after generating the reflectance histogram, the estimation system 105 may generate a cumulative histogram by aggregating the reflectance histogram of each of the predefined number of images. An exemplary representation of the cumulative histogram generated from the reflectance histogram is shown in FIG. 4A.

In an embodiment, subsequent to generating the cumulative histogram, the estimation system 105 may segment the cumulative histogram into a plurality of segments based on one or more inflection points, such that, each segment of the plurality of segments represents a maceral type of the coal sample. The inflection points may correspond to the points on the cumulative histogram, where cumulative function changes concavity, i.e., from being “concave up” to being “concave down” or vice versa. That is, the inflection points indicate a sharp deviation/variation in the slope of the cumulative histogram.

In an embodiment, once the cumulative histogram is segmented into the plurality of segments, the estimation system 105 may estimate the coal rank 107 and the phase fraction 109 of the coal sample by calculating histogram values in the plurality of segments. In an embodiment, for low-rank coal, the phase fraction 109 (i.e., the maceral percentage) and the coal rank 107 may be calculated using a Gaussian fit on the whole region of reflectance histogram, as indicated in FIG. 4C. Alternatively, for high-rank coals, the phase fraction 109 and the coal rank 107 may be calculated using the Gaussian fit on the selected segments (i.e., with the help of inflection points) of the reflectance histogram, as indicated in FIG. 4D.

Thus, the proposed method and the estimation system 105 help in automatically determining the coal rank 107 and phase fraction 109 of the coal sample from different geographical locations, as well as reduce time and labour required for performing a qualitative analysis of the coal samples.

FIG. 2 shows a detailed block diagram of an estimation system 105 in accordance with some embodiments of the present disclosure.

In some implementations, the estimation system 105 may include an I/O interface 201, a processor 203, a User Interface 205 and a memory 207. The I/O interface 201 may be interfaced for providing one or more user inputs to the estimation system 105. For instance, the I/O interface 201 may be used to feed and/or upload the images of the coal sample 103 that are captured using an optical microscope. In an embodiment, the User Interface 205 may include a display screen and be used for, without limitation, displaying the estimated results, that is coal rank 107 and phase fraction 109 of the coal sample, along with information useful to a user of the estimation system 105. In an embodiment, the memory 207 may be communicatively coupled to the processor 203 and may store data 209 and one or more modules 211. The processor 203 may be configured to perform and control each functions of the estimation system 105 during automated estimation of the coal rank 107 and phase fraction 109 of the coal sample, using the data 209 and the one or more modules 211.

In an embodiment, the data 209 stored in the memory 207 may include, without limitation, the images of coal sample 103, a reflectance histogram 213 corresponding to the images 103, a cumulative histogram 215, plurality of segments 217 and other data 219. In some implementations, the data 209 may be stored within the memory 207 in the form of various data structures. Additionally, the data 209 may be organized using data models, such as relational or hierarchical data models. The other data 219 may include various temporary data and files generated by the one or more modules 211 while performing various functions of the estimation system 105. As an example, the other data 219 may include, without limitation, inflection points identified on the histogram, cumulative frequencies and first order derivatives of the histogram etc.

In an embodiment, the images of the coal sample 103 are captured by an image capturing unit 101 associated with the estimation system 105. As discussed in the above section, the image capturing unit 101 may be an optical microscope.

In an embodiment, the reflectance histogram 213 may be generated by dividing grey values of the images with corresponding one or more standard reflectance values. In an embodiment, the reflectance histogram 213 may be generated from a predefined number of images, which is a minimum of 220 images of the coal sample 103.

In an embodiment, the cumulative histogram 215 may be obtained by aggregating the individual reflectance histograms 213 of each image of the coal sample. As the name suggests, the cumulative histogram 215 indicates an average distribution of frequencies of the reflectance histograms 213 corresponding to the predefined number of images of the coal sample 103.

In an embodiment, the plurality of segments 217 corresponds to the segments and/or partitions of the cumulative histogram 215 which is obtained by dividing the cumulative histogram 215 based on the one or more inflection points identified on the cumulative histogram 215. As an example, as shown in FIG. 4D, the portion of reflectance histogram 213 that is inside the two inflection points ‘a’ and ‘ß’ may be considered as one segment of the reflectance histogram 213. Similarly, the portions to the left of inflection point ‘a’ and the portion to the right of the inflection point ‘ß’ may be considered as the other two segments of the reflectance histogram 213. In an embodiment, each segment of the reflectance histogram 213 may correspond to a maceral type of the coal sample.

In an embodiment, the data 209 may be processed by the one or more modules 211 of the estimation system 105. In some implementations, the one or more modules 211 may be communicatively coupled to the processor 203 for performing one or more functions of the estimation system 105. In an implementation, the one or more modules 211 may include, without limiting to, a histogram generation module 221, a segmentation module 223, an estimation module 225 and other modules 227.

As used herein, the term module may refer to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a hardware processor (shared, dedicated, or group) and memory that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality. In an implementation, each of the one or more modules 211 may be configured as stand-alone hardware computing units. In an embodiment, the other modules 227 may be used to perform various miscellaneous functionalities of the estimation system 105. It will be appreciated that such one or more modules 211 may be represented as a single module or a combination of different modules.

In an embodiment, the histogram generation module 221 may be used for generating the reflectance histogram 213. Initially, the histogram generation module 221 binarizes the images of the coal sample 103 after identifying black background region and white front region. The white/front region correspond to Vitrinite and Inertinite maceral components. Further, black portions inside the Vitrinite and Inertinite regions may correspond to the minerals. That is, the histogram generation module 221 generates the reflectance histogram 213 from the phase pixel values using linear transformation and calibration parameters in the images of the coal sample 103.

Additionally, the histogram generation module 221 may be also configured for generating a cumulative histogram 215 by aggregating the reflectance histogram 213 of each of the predefined number of images. In an embodiment, the shape of the reflectance histogram 213 in FIG. 3A suggests that smoothing of the histogram will provide a better representation of the reflectance distribution and minimizes intermittent noises. In an embodiment, for smoothening the reflectance histogram 213, a sliding window of length l is moved across a vector of frequency values and a mean of the frequency values is calculated within the moving window. Further, the moving window is centered about the element in the current position. For few elements in the beginning and at the end of the histogram, the average may be taken without zero-padding of the moving window.

In an embodiment, FIG. 3C and FIG. 3D represent an estimate maximum likelihood of the mean and the standard deviation respectively, which may be used to optimally fit the smoothened reflectance histogram 213 data to a Gaussian distribution. Subsequent to determining the mean and stand deviation, a cumulative frequency of the smoothened histogram is generated using the equation (1) below:

CFj = Fj-1+Fj … (1)

here, a predefined condition CF1 = F1 is used, where ‘CFj’ and ‘Fj’ represent the cumulative frequency and frequency of a ‘jth’ bin of the reflectance histogram 213.

In an embodiment, the segmentation module 223 may be configured for segmenting the cumulative histogram 215 into a plurality of segments 217 based on one or more inflection points. As an example, the the cumulative reflectance frequency curve (shown in FIG. 4A) may be segmented into three segments, each segment representing Vitrinite, Inertinite and mineral components. To obtain three segments, definition of two points on the cumulative reflectance histogram 213 may be required. These points may correspond to regions at the start and at the tail of the cumulative reflectance frequency curve.

In an embodiment, a measure like first order derivative of the cumulative reflectance frequency curve may be used to isolate the leading and the trailing flat regions from a steep middle segment representing the Vitrinite. To calculate the first order derivative, the cumulative frequency (CF) is normalized between [0-1]. Subsequently, a first order derivative of the normalized cumulative frequency curve may be calculated. FIG. 4B represents the first order derivative (NC) of the normalized cumulative frequency of FIG. 4A. In FIG. 4B, the end of the leading flat portion is marked with the inflection point ‘a’, and the start of the trailing flat portion is marked with the inflection point ‘ß’.

In an embodiment, the estimation module 225 may be configured for estimating the coal rank 107 and the phase fraction 109 of the coal sample by calculating histogram values in the plurality of segments 217. In an embodiment, for the low-rank coal, the maceral percentages and coal rank 107 may be calculated using Gaussian fit on the whole coal reflectance histogram 213, as shown in FIG. 4C. Alternatively, for the high-rank coal, the maceral percentages and the coal rank 107 may be calculated using the Gaussian fit on the reflectance data that is within the inflection points, as shown in FIG. 4D.

In an embodiment, different combinations of the standard deviation, along with the mean of the approximated Gaussian fit of the reflectance values, may be used to calculate the rank of the vitrinite and the intensity boundaries of the mineral and inertinite material. For example, (‘Mean + std/2’, ‘Mean - std/2’) may be one of possible ranges of the vitrinite reflectance. The reflectance value above the vitrinite point may be the bright maceral inertinite. Further, to find out other lower rank phases, that is, mineral and liptinite, the concavity points on the cumulative histogram values within the starting point of the cumulative histogram values and the left limit of the vitrinite may be calculated, as represented in FIG. 4E.

Table 1 below shows a comparison between the existing manual approach and the proposed automated approach for determining coal rank 107 for a plurality of datasets (i.e., images) A-G belonging to a plurality of coal samples.

Dataset Manual coal rank Automated coal rank
A 0.93 0.89
B 0.91 0.98
C 0.91 0.91
D 1.03 0.98
E 1.1 1.03
F 1.12 1.07
G 0.78 0.83

Table 1: Comparison of accuracy in manual ranking and automated ranking.

The comparison shows that the accuracy of ranking obtained by the proposed method is comparable to, and in some cases even better than the accuracy of the manual ranking process. Additionally, an important aspect here is the time and labour required for performing the ranking. While the manual ranking takes up a whole day, the proposed automated ranking completes the same estimation in less than 5 minutes. Moreover, the proposed automated ranking method does not require an expert human resource.

Table 2 below shows a comparison between the manual phase fraction estimation method and the proposed automated phase fraction estimation method based on analysis of the set of images A-G of the coal samples.

Dataset Manual phase analysis Automated phase analysis
A Vitrinite-50.6%
Inertinite-45.1%
Mineral +Liptinite-4.3% Vitrinite- 56.67%
Inertinite- 38.31%
Mineral +Liptinite-5.02%
B Vitrinite-65.7%
Inertinite-23.7%
Mineral +Liptinite-10.6% Vitrinite-68.99%
Inertinite-27.81%
Mineral +Liptinite-3.2%
C Vitrinite- 62.5%
Inertinite-30.3%
Mineral +Liptinite-7.2% Vitrinite-57.78%
Inertinite-36.01%
Mineral +Liptinite-6.21%
D Vitrinite-43%
Inertinite-44.1%
Mineral +Liptinite-12.9% Vitrinite-55.47%
Inertinite-41.62%
Mineral +Liptinite-2.91%
E Vitrinite-55.49%
Inertinite-39.51%
Mineral +Liptinite-5.00% Vitrinite-58.8%
Inertinite-35.9%
Mineral +Liptinite-5.3%

Table 2: Comparison of manual phase fraction determination and automated phase fraction estimation

Based on the comparison, it may be observed that that the proposed automated method for estimating the coal phase fraction 109 (i.e., maceral percentage) closely matches with the manual petrographic approaches. Moreover, the proposed automated method is at least 100 times faster than the manual method.

FIG. 5A shows a flowchart illustrating a method for automated estimation of coal rank 107 and phase fraction 109 of a coal sample in accordance with some embodiments of the present disclosure.

As illustrated in FIG. 5A, the method 500 may include one or more blocks illustrating a method for automated estimation of coal rank 107 and phase fraction 109 of a coal sample using an estimation system 105 illustrated in FIG. 1 or FIG. 2. The method 500 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform specific functions or implement specific abstract data types.

The order in which the method 500 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.

At block 501, the method 500 includes capturing, by the estimation system 105, a predefined number of images of the coal sample 103 using one or more standard reflectance values. In an embodiment, the images of the coal sample 103 may be obtained using an optical microscope.

At block 503, the method 500 includes generating, by the estimation system 105, a reflectance histogram 213 for each of the predefined number of images by dividing grey values of the images with corresponding one or more standard reflectance values. In an embodiment, generating the reflectance histogram 213 may comprise binarizing each of the predefined number of images for segmenting maceral coal region from a background region. After binarizing, a plurality of phase pixel values corresponding to the maceral coal region are converted into reflectance values for generating the reflectance histogram 213. In an embodiment, the reflectance histogram 213 may represent a distribution of reflectance values of each class of macerals within the maceral coal region.

At block 505, the method 500 includes generating, by the estimation system 105, a cumulative histogram 215 by aggregating the reflectance histogram 213 of each of the predefined number of images. In an embodiment, generating the cumulative histogram 215 comprises smoothening the reflectance histogram 213 by determining a mean and standard deviation of reflectance values using a sliding window of predefined length. After smoothening the reflectance histogram 213, a maximum likelihood of the mean and standard deviation may be estimated to optimally fit the smoothened reflectance histogram 213 data to a Gaussian distribution.

At block 507, the method 500 includes segmenting, by the estimation system 105, the cumulative histogram 215 into a plurality of segments 217 based on one or more inflection points. Here, each segment of the plurality of segments 217 may represent a maceral type of the coal sample, such as vitrinite, inertinite, and liptinite contents of the coal sample. In an embodiment, segmenting the cumulative histogram 215 comprises normalizing the cumulative histogram 215 and then computing a first-order derivative of the normalized cumulative histogram 215. Thereafter, end point of a leading flat portion and a start point of a trailing flat portion of the cumulative histogram 215 may be determined based on the first-order derivative. Subsequently, the end point and the start point may be designated as the one or more inflection points for the cumulative histogram 215.

At block 509, the method 500 includes estimating, by the estimation system 105, the coal rank 107 and the phase fraction 109 of the coal sample by calculating histogram values in the plurality of segments 217. The estimation of the coal rank 107 and phase fraction 109 are further explained with reference to FIG. 5B in the below paragraphs.

Particularly, FIG. 5B shows a flowchart illustrating variations in the method for automated estimation based on type/rank of coal in accordance with some embodiments of the present disclosure. In an embodiment, for a high-rank coal sample, the coal rank 107 and the phase fraction 109 are estimated using a Gaussian fit on histogram values in the plurality of segments 217 within the inflection points. On the other hand, for a low-rank coal sample, the coal rank 107 and the phase fraction 109 are estimated using the Gaussian fit on the histogram values in each of the plurality of segments 217 in the cumulative histogram 215.

That is, for the low rank coal, the maceral percentages and the coal rank 107 may be calculated using Gaussian fit on the whole coal reflectance data, as shown in FIG. 4C. For the high-rank coals, the maceral percentages and coal rank 107 may be calculated using the Gaussian fit on the reflectance data within the inflection points, as shown in FIG. 4D. In an embodiment, different combinations of the standard deviation, along with the mean of the approximated Gaussian of reflectance values, may be used to calculate the rank of the vitrinite and the intensity boundaries of the mineral and inertinite material. For example, “Mean + Standard deviation / 2” and “Mean – Standard deviation / 2” may be one of the possible ranges of the Vitrinite reflectance. The reflectance value above the vitrinite point may be the bright maceral Inertinite. Further, the other phases of the lower rank coal, that is, Mineral and Liptinite may be calculated from the concavity points on the cumulative histogram values, within starting point of the cumulative histogram values and a left limit of the Vitrinite, as shown in FIG. 4E.

Computer System
FIG. 6 illustrates a block diagram of an exemplary computer system 600 for implementing embodiments consistent with the present disclosure. In an embodiment, the computer system 600 may be the estimation system 105 illustrated in FIG. 2 of the present disclosure, which may be used for automated estimation of coal rank 107 and phrase fraction of a coal sample. The computer system 600 may include a Central Processing Unit (“CPU” or “processor”) 602. The processor 602 may comprise at least one data processor for executing program components for executing user- or system-generated business processes. A user may include a technician, a researcher, a petrographic analyst, or an operator of the estimation system 105 or any system/sub-system being operated parallelly to the computer system 600. The processor 602 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.
The processor 602 may be disposed in communication with one or more Input/Output (I/O) devices (611 and 612) via I/O interface 601. The I/O interface 601 may employ communication protocols/methods such as, without limitation, audio, analog, digital, stereo, IEEE®-1394, serial bus, Universal Serial Bus (USB), infrared, PS/2, BNC, coaxial, component, composite, Digital Visual Interface (DVI), high-definition multimedia interface (HDMI), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), IEEE® 802.n /b/g/n/x, Bluetooth, cellular (e.g., Code-Division Multiple Access (CDMA), High-Speed Packet Access (HSPA+), Global System For Mobile Communications (GSM), Long-Term Evolution (LTE) or the like), etc. Using the I/O interface 601, the computer system 600 may communicate with one or more I/O devices 611 and 612.
In some embodiments, the processor 602 may be disposed in communication with a communication network 609 via a network interface 603. The network interface 603 may communicate with the communication network 609. The network interface 603 may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), Transmission Control Protocol/Internet Protocol (TCP/IP), token ring, IEEE® 802.11a/b/g/n/x, etc. Using the network interface 603 and the communication network 609, the computer system 600 may connect with an image repository 103 for receiving a petrographic image 105 of a coal sample. Further, the communication network 609 may be used for interfacing the computer system 600 with an image capturing unit 101 that is capturing and/or storing the one or more images of the coal sample 103.
In an implementation, the communication network 609 may be implemented as one of the several types of networks, such as intranet or Local Area Network (LAN) and such within the organization. The communication network 609 may either be a dedicated network or a shared network, which represents an association of several types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), etc., to communicate with each other. Further, the communication network 609 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, etc.
In some embodiments, the processor 602 may be disposed in communication with a memory 605 (e.g., RAM 613, ROM 614, etc. as shown in FIG. 6) via a storage interface 604. The storage interface 604 may connect to memory 605 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as Serial Advanced Technology Attachment (SATA), Integrated Drive Electronics (IDE), IEEE-1394, Universal Serial Bus (USB), fiber channel, Small Computer Systems Interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.
The memory 605 may store a collection of program or database components, including, without limitation, user/application interface 606, an operating system 607, a web browser 608, and the like. In some embodiments, computer system 600 may store user/application data 606, such as the data, variables, records, etc. as described in this invention. Such databases may be implemented as fault-tolerant, relational, scalable, secure databases such as Oracle® or Sybase®.
The operating system 607 may facilitate resource management and operation of the computer system 600. Examples of operating systems include, without limitation, APPLE® MACINTOSH® OS X®, UNIX®, UNIX-like system distributions (E.G., BERKELEY SOFTWARE DISTRIBUTION® (BSD), FREEBSD®, NETBSD®, OPENBSD, etc.), LINUX® DISTRIBUTIONS (E.G., RED HAT®, UBUNTU®, KUBUNTU®, etc.), IBM® OS/2®, MICROSOFT® WINDOWS® (XP®, VISTA®/7/8, 10 etc.), APPLE® IOS®, GOOGLE TM ANDROID TM, BLACKBERRY® OS, or the like.
The user interface 606 may facilitate display, execution, interaction, manipulation, or operation of program components through textual or graphical facilities. For example, the user interface 606 may provide computer interaction interface elements on a display system operatively connected to the computer system 600, such as cursors, icons, check boxes, menus, scrollers, windows, widgets, and the like. Further, Graphical User Interfaces (GUIs) may be employed, including, without limitation, APPLE® MACINTOSH® operating systems’ Aqua®, IBM® OS/2®, MICROSOFT® WINDOWS® (e.g., Aero, Metro, etc.), web interface libraries (e.g., ActiveX®, JAVA®, JAVASCRIPT®, AJAX, HTML, ADOBE® FLASH®, etc.), or the like.

The web browser 608 may be a hypertext viewing application. Secure web browsing may be provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TLS), and the like. The web browsers 608 may utilize facilities such as AJAX, DHTML, ADOBE® FLASH®, JAVASCRIPT®, JAVA®, Application Programming Interfaces (APIs), and the like. Further, the computer system 600 may implement a mail server stored program component. The mail server may utilize facilities such as ASP, ACTIVEX®, ANSI® C++/C#, MICROSOFT®, .NET, CGI SCRIPTS, JAVA®, JAVASCRIPT®, PERL®, PHP, PYTHON®, WEBOBJECTS®, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), MICROSOFT® exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system 600 may implement a mail client stored program component. The mail client may be a mail viewing application, such as APPLE® MAIL, MICROSOFT® ENTOURAGE®, MICROSOFT® OUTLOOK®, MOZILLA® THUNDERBIRD®, and the like.

Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present invention. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., non-transitory. Examples include Random Access Memory (RAM), Read-Only Memory (ROM), volatile memory, nonvolatile memory, hard drives, Compact Disc (CD) ROMs, Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media.

Advantages of the embodiments of the present disclosure are illustrated herein.
In an embodiment, the method of present disclosure helps in automatically characterizing quality of a coal sample in terms of its rank and phase fraction.

In an embodiment, the method of present disclosure replaces existing manual processes with an automated method, which is faster, reliable, and cheaper compared to the existing manual petrographic approaches.

In an embodiment, the method of present disclosure enhances accuracy of determining coal rank and phrase fraction of a sample, compared to existing manual approaches, whose outcome depends on experience and expertise of the human operator.

In an embodiment, the method of present disclosure eliminates requirement of manual feature engineering as the deep learning models are data driven and capable of replacing hand-crafted feature extraction.

In an embodiment, the present disclosure helps in quicker decision making for coal blend formulation.

Considering the abovesaid technical advancements provided by the proposed method and the estimation system, it shall be noted that the claimed steps, as discussed above, are not routine, conventional, or well-known aspects in the art, as the claimed steps provide the aforesaid solutions to the technical problems existing in the conventional technologies. Further, the claimed steps clearly bring an improvement in the functioning of the system itself, as the claimed steps provide a technical solution to a technical problem.

The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise.

The enumerated listing of items does not imply that any or all the items are mutually exclusive, unless expressly specified otherwise. The terms "a", "an" and "the" mean "one or more", unless expressly specified otherwise.

A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

When a single device or article is described herein, it will be clear that more than one device/article (whether they cooperate) may be used in place of a single device/article. Similarly, where more than one device/article is described herein (whether they cooperate), it will be clear that a single device/article may be used in place of the more than one device/article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of invention need not include the device itself.

Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the embodiments of the present invention are intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Referral Numerals:
Reference Number Description
100 Overview of the invention
101 Image capturing unit
103 Images of coal sample
105 Estimation system
107 Coal rank
109 Phase fraction
201 I/O Interface
203 Processor
205 User interface
207 Memory
209 Data
211 Modules
213 Reflectance histogram
215 Cumulative histogram
217 Plurality of segments
219 Other data
221 Histogram generation module
223 Segmentation module
225 Estimation module
227 Other modules
600 Exemplary computer system
601 I/O Interface of the exemplary computer system
602 Processor of the exemplary computer system
603 Network interface
604 Storage interface
605 Memory of the exemplary computer system
606 User/Application
607 Operating system
608 Web browser
609 Communication network
611 Input devices
612 Output devices
613 RAM
614 ROM