Method and system for measuring moisture content of coal

Abstract

The present invention relates to the technical field of coal moisture content measurement. Disclosed are a method and system for measuring moisture content of coal. The method comprises: acquiring absorbance data and moisture content data of a coal sample, so as to obtain an absorbance interval and a moisture content interval of the coal sample, and a correspondence between the absorbance data and the moisture content data of the coal sample; determining a segmentation threshold value of the moisture content interval, and, on the basis of the segmentation threshold value, dividing the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval; respectively fitting moisture content data in different fitting intervals to absorbance data corresponding thereto, so as to obtain a first fitting curve, a second fitting curve and a third fitting curve; and integrating the three fitting curves to obtain a complete coal absorbance-moisture content fitting curve, and measuring the moisture content of coal to be measured. The present invention improves the precision and accuracy of fitting results, takes into account fitting efficiency, and has strong adaptability in different coal types and moisture content intervals.

Description

Coal moisture content measurement method and system TECHNICAL FIELD

[0001] The present application relates to the technical field of coal moisture content detection, and particularly relates to a coal moisture content measurement method and system. BACKGROUND

[0002] Coal is one of the most abundant fuels stored on the entire earth, and is an indispensable energy in social life. Coal transportation by waterway has greater advantages in cost-effectiveness and capacity compared to railway and highway. Coal bulk cargo terminal, as a key link of transfer, is a coal distribution center, which ensures the stability of energy supply. However, the coal bulk cargo terminal has the problems of safety and environmental protection of coal spontaneous combustion and dust pollution. The most commonly used method for the safety and environmental protection problems existing in the bulk cargo terminal is water spraying operation. Since the critical spontaneous combustion moisture content and the dusting moisture content of different coals are different, too much water spraying will reduce the quality of coal and affect the characteristics of coal, and too little water spraying cannot effectively control dust pollution and prevent coal spontaneous combustion, so it is crucial to detect the moisture content of coal online.

[0003] The prior art has a scheme of detecting the moisture content of coal by combining near-infrared spectroscopy technology and fitting algorithm. However, the prior art cannot meet the demand of coal moisture content measurement in different situations by using a single algorithm, has poor adaptability in different coal types and moisture content intervals, cannot realize high-precision measurement, and has low detection efficiency.

[0004] Therefore, there is an urgent need for a coal moisture content measurement method and system which can improve the precision and accuracy of fitting results, take into account fitting efficiency, and have strong adaptability in different coal types and moisture content intervals. SUMMARY

[0005] In order to solve the above technical problems, the present application provides a coal moisture content measurement method and system which can improve the precision and accuracy of fitting results, take into account fitting efficiency, and have strong adaptability in different coal types and moisture content intervals.

[0006] The present application provides a coal moisture content measurement method and system, comprising the following steps:

[0007] S1, obtaining absorbance data and moisture content data of a coal sample; wherein the coal sample includes coking coal, chemical coal and power coal;

[0008] S2, obtaining an absorbance interval and a moisture content interval of the coal sample, and a corresponding relationship between the absorbance data and the moisture content data of the coal sample according to the absorbance data and the moisture content data of the coal sample;

[0009] S3, determining a segmentation threshold of the moisture content interval, and dividing the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold.

[0010] S4, respectively, the water content data of the first fitting interval, the second fitting interval and the third fitting interval and its corresponding absorbance data are fitted to obtain the first fitting curve, the second fitting curve and the third fitting curve;

[0011] S5, the first fitting curve, the second fitting curve and the third fitting curve are integrated to obtain a complete coal absorbance-water content fitting curve;

[0012] S6, the water content of the coal to be measured is measured by the coal absorbance-water content fitting curve.

[0013] Further, in S3, the segmentation threshold of the water content interval includes:

[0014] The first segmentation threshold and the second segmentation threshold of the water content interval are determined according to the water content critical interval of the coal sample; wherein the first segmentation threshold is 4.36%, and the second segmentation threshold is 10.46%.

[0015] Further, in S3, the water content interval is divided into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold, including:

[0016] The water content interval of the coal sample is divided into a first fitting interval, a second fitting interval and a third fitting interval according to the first segmentation threshold and the second segmentation threshold; wherein the first fitting interval is 0.93% to 4.36%, the second fitting interval is 4.36% to 10.46%, and the third fitting interval is 10.46% to 21.53%.

[0017] Further, in S4, the water content data of the first fitting interval, the second fitting interval and the third fitting interval and its corresponding absorbance data are fitted to obtain the first fitting curve, the second fitting curve and the third fitting curve, including:

[0018] S41, the water content data and its corresponding absorbance data of the coal sample in the first fitting interval are fitted by using support vector machine algorithm to obtain the first fitting curve;

[0019] S42, the water content data and its corresponding absorbance data of the coal sample in the second fitting interval are fitted by using Bernstein polynomial fitting algorithm to obtain the second fitting curve;

[0020] S43, the water content data and its corresponding absorbance data of the coal sample in the third fitting interval are fitted by using neural network algorithm to obtain the third fitting curve.

[0021] Further, S42, the second fitting interval is fitted with Bernstein polynomial fitting algorithm to the moisture content data and its corresponding absorbance data of coal sample, and the second fitting curve is obtained, including:

[0022] S421, determine the moisture content data contained in the second fitting interval, and the absorbance data corresponding to the moisture content data;

[0023] S422, according to the positive correlation corresponding relationship between the absorbance data and the moisture content data, the absorbance data and the moisture content data are pretreated, and the absorbance data and the moisture content data data group not meeting the positive correlation corresponding relationship are removed;

[0024] S423, according to the pretreated absorbance data and moisture content data, the order and coefficient of Bernstein polynomial fitting algorithm are determined;

[0025] S424, according to the order and coefficient, the Bernstein polynomial is regressed and fitted by using scalar function regression method, and the second fitting curve is obtained.

[0026] Further, in S43, the third fitting interval is fitted with neural network algorithm to the moisture content data and its corresponding absorbance data of coal sample, wherein the neural network algorithm adopts a neural network including: input layer, hidden layer and output layer;

[0027] The input layer includes two neurons for inputting corresponding absorbance data and moisture content data;

[0028] The output layer includes one neuron for outputting the third fitting curve of the absorbance data and the moisture content data;

[0029] The number of layers of the hidden layer is 2;

[0030] The neural network algorithm selects a normalization function premnmx.

[0031] Further, S5, the first fitting curve, the second fitting curve and the third fitting curve are integrated to obtain a complete coal absorbance-moisture content fitting curve, including:

[0032] The first fitting curve, the second fitting curve and the third fitting curve are integrated by a transition function to obtain a complete coal absorbance-moisture content fitting curve; wherein the transition function selects an exponential decay function.

[0033] The application also provides a coal moisture content measurement system for executing any one of the above-mentioned coal moisture content measurement methods, the system comprising the following modules:

[0034] The data acquisition module is configured to acquire absorbance data and moisture content data of the coal sample, wherein the coal sample includes coking coal, chemical coal and power coal; and the absorbance interval and the moisture content interval of the coal sample and the corresponding relationship between the absorbance data and the moisture content data of the coal sample are obtained according to the absorbance data and the moisture content data of the coal sample.

[0035] The moisture content interval segmentation module is connected with the data acquisition module and is configured to determine a segmentation threshold of the moisture content interval, and divide the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold.

[0036] The fitting algorithm module is connected with the moisture content interval segmentation module and is configured to fit the moisture content data and the corresponding absorbance data of the first fitting interval, the second fitting interval and the third fitting interval respectively, to obtain a first fitting curve, a second fitting curve and a third fitting curve.

[0037] The fitting curve integration module is connected with the fitting algorithm module and is configured to integrate the first fitting curve, the second fitting curve and the third fitting curve to obtain a complete coal absorbance-moisture content fitting curve.

[0038] The measurement module is connected with the fitting curve integration module and is configured to measure the moisture content of the coal to be measured by using the coal absorbance-moisture content fitting curve.

[0039] The embodiment of the present application has the following technical effects:

[0040] The present application segments the coal moisture content interval based on the coal moisture content critical interval, and combines multiple fitting algorithms to fit the coal absorbance and moisture content, to obtain high-precision fitting results of each interval segment. The fitting results of the three interval segments are integrated by using a transition function to obtain a final coal moisture content calculation model. The present application not only improves the precision and accuracy of the fitting results, but also takes into account the fitting efficiency, and has strong adaptability in different coal types and moisture content intervals. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the description of the specific embodiments or the prior art. Obviously, the drawings described below are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0042] Fig. 1 is a flowchart of a coal moisture content measurement method according to an embodiment of the present application;

[0043] Figure 2 is a flow chart of fitting the moisture content data and the corresponding absorbance data of the coal sample by using the support vector machine algorithm in the first fitting interval according to an embodiment of the present application;

[0044] Figure 3 is a flow chart of fitting the moisture content data and the corresponding absorbance data of the coal sample by using the Bernstein polynomial fitting algorithm in the second fitting interval according to an embodiment of the present application;

[0045] Figure 4 is a structural schematic diagram of a coal moisture content measurement system according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0047] Figure 1 is a flow chart of a coal moisture content measurement method according to an embodiment of the present application, referring to Figure 1, which specifically comprises:

[0048] S1, obtaining the absorbance data and the moisture content data of the coal sample.

[0049] Specifically, the absorbance data of the coal sample is measured by the near-infrared method, and the moisture content data of the coal sample is measured by the international drying method. The coal sample includes coking coal, chemical coal and power coal.

[0050] The experimental steps of measuring the absorbance and the moisture content by using the near-infrared method and the national standard drying method are as follows:

[0051] The instrument equipment includes: a blast high-temperature drying box; a balance: weighing 520g, with a graduation value of 0.1mg; a drying dish, a paper sheet, and a near-infrared moisture meter.

[0052] The calibration steps are as follows: firstly, weighing the drying dish with a weight A, secondly, taking 10g of the coal sample and placing it on the paper sheet, and then measuring the absorbance of the coal sample by using the near-infrared method. The coal sample on the paper sheet is transferred to the drying dish, and the weight B is recorded on the balance. The drying dish is placed in the drying box at 105° and dried for 3 hours, then taken out and cooled for about 15 minutes, and then weighed again by using the balance to record the weight B1. Then, the drying dish is placed in the drying box for 30 minutes, taken out and cooled, and weighed again to obtain the weight B2. The cycle is repeated until the difference between the two weights is not more than 1%.

[0053] The calculation formula of the moisture content of the coal sample is as follows:

[0054] Wherein, A represents the weight of the dry dish (g), B represents the weight of the coal sample and the dry dish (g), and C represents the weight of the dried coal sample and the dry dish (g).

[0055] Further, the obtained absorbance data and moisture content data of the coal sample are preprocessed, and the preprocessing includes data cleaning and normalization processing. The data cleaning is used to eliminate invalid or erroneous data, and the normalization processing is used to eliminate the deviation under different measurement conditions.

[0056] S2, according to the absorbance data and moisture content data of the coal sample, the absorbance interval and moisture content interval of the coal sample are obtained, and the corresponding relationship between the absorbance data and moisture content data of the coal sample is obtained.

[0057] Exemplarily, the absorbance interval of coking coal is 0.860-0.963, and the corresponding moisture content interval is 0.93%-12.17%; the absorbance interval of chemical coal is 0.89-1.024, and the corresponding moisture content interval is 7.46%-21.53%; the absorbance interval of power coal is 0.878-1.001, and the corresponding moisture content interval is 4.52%-12.78%. It can be seen that the moisture content interval of the coal sample is 0.93%-21.53%, and based on this, the near-infrared signal and the moisture content standard quantitative relationship of the coal sample are established, that is, the corresponding relationship between the absorbance data and the moisture content data of the coal sample.

[0058] S3, determining the segmentation threshold of the moisture content interval, and dividing the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold.

[0059] Specifically, by summarizing the critical dusting moisture content, the critical moisture content intervals of coking coal, chemical coal and power coal are 4.36%-5%, 10%-10.46% and 8%-9.86% respectively, and the characteristics of the coal will not change in the three intervals. It can be seen that the coal moisture content in the range of 4.36%-10.46% can well inhibit the spontaneous combustion and dusting of the coal, and will not affect its own properties. The first segmentation threshold and the second segmentation threshold of the moisture content interval are determined according to the critical moisture content interval of the coal sample; wherein the first segmentation threshold is 4.36%, and the second segmentation threshold is 10.46%.

[0060] According to the first segmentation threshold and the second segmentation threshold, the moisture content interval of the coal sample is divided into a first fitting interval, a second fitting interval and a third fitting interval; wherein the first fitting interval is 0.93%-4.36%, the second fitting interval is 4.36%-10.46%, and the third fitting interval is 10.46%-21.53%.

[0061] S4, respectively, the moisture content data and its corresponding absorbance data of the first fitting interval, the second fitting interval and the third fitting interval are fitted to obtain the first fitting curve, the second fitting curve and the third fitting curve.

[0062] S41, the moisture content data and its corresponding absorbance data of the coal sample in the first fitting interval are fitted by using the support vector machine algorithm to obtain the first fitting curve.

[0063] Specifically, the support vector machine algorithm is not sensitive to abnormal values and noises, and when the moisture content of coal is low, dusting is easy to occur, which may have certain influence on detection, and the use of support vector machine can reduce the influence of abnormal values and noises on fitting accuracy, and the support vector machine can effectively learn on limited data, that is, even in the low moisture content interval with less data and small change range, accurate prediction can be made. Therefore, the support vector machine algorithm is used for fitting in the first fitting interval.

[0064] Specifically, Fig. 2 is a flow chart of fitting the moisture content data and its corresponding absorbance data of the coal sample in the first fitting interval by using the support vector machine algorithm according to an embodiment of the present application, as shown in Fig. 2, when the support vector machine algorithm is used, the risk of empirical risk minimization (ERM) criterion and the risk of structural risk minimization (SRM) criterion need to be considered, and the calculation formula is as follows:

[0065] In the formula, L represents the confidence range, h represents the interval difference, μ represents the error, x i represents the i-th group of absorbance data, y i represents the i-th group of moisture content data, R ERM represents the risk value of empirical risk minimization, R SRM represents the risk value of structural risk minimization. According to different linear problems, the accuracy of the target sample is ensured, and the coal moisture content is detected by using radial organic function type classification, and the calculation formula is as follows: K(x i , y i )=R SRM |[(x i , y i )+1] n |;

[0066] In the formula, K represents the inner product of the space vector, and n represents the order of the polynomial.

[0067] The present scheme uses a linear function to divide the moisture content data and its corresponding absorbance data of the coal sample in the first fitting interval, divide the data points, select the support vector machine parameters, form the quadratic optimization condition and solve it, obtain the correlation coefficient, and finally perform fitting to obtain the final result. The formula for establishing the division plane is as follows: w×x i+b=0

[0068] In the formula, w is a normal vector, which determines the direction of the hyperplane; and b represents the displacement amount.

[0069] The division of the database needs to satisfy: y i (wx i +b) >= 1, i = 1,..., n

[0070] The parameter w 2 / 2 is selected to obtain the division result, and the given condition is: y i (wx i +b) - 1 >= 0, i = 1, 2,..., n

[0071] Under the given condition, the parameter w 2 / 2 is a vector w, and the Lagrange formula is used for calculation, and the formula is as follows:

[0072] The optimal radial organic function formula is obtained through the above formula, and thus the first fitting curve is obtained.

[0073] S42, the Bernstein polynomial fitting algorithm is used to fit the moisture content data and the corresponding absorbance data of the coal sample in the second fitting interval, and a second fitting curve is obtained.

[0074] Specifically, the Bernstein polynomial fitting algorithm can accurately control the fitting curve, and the moisture content interval is the critical value interval of the moisture content of the coal, and it is necessary to accurately describe the relationship between the moisture content and the absorbance, and the accuracy requirement is high. Therefore, the Bernstein polynomial fitting algorithm is used for fitting in the second fitting interval.

[0075] Specifically, FIG. 3 is a flowchart of fitting the moisture content data and the corresponding absorbance data of the coal sample in the second fitting interval by using the Bernstein polynomial fitting algorithm, and referring to FIG. 3:

[0076] S421, determine the moisture content data contained in the second fitting interval, and the absorbance data corresponding to the moisture content data.

[0077] S422, according to the positive correlation corresponding relationship between the absorbance data and the moisture content data, pre-process the absorbance data and the moisture content data, and remove the absorbance data and the moisture content data data group that does not conform to the positive correlation corresponding relationship.

[0078] Exemplarily, since the absorbance data and the water content data are in a positive correlation correspondence, that is, when the absorbance data x1 is less than the absorbance data x2, the corresponding water content data y1 should also be less than the water content data y2. Assuming that the size relationship of the absorbance data is x1 < x2 < x3, and the size relationship of the corresponding water content data is y2 < y1 < y3, then the set of absorbance-water content data x2-y2 does not conform to the positive correlation correspondence, and this set of data needs to be excluded, and all absorbance-water content data that do not conform to the positive correlation correspondence are excluded in the same way, so that the remaining absorbance-water content data all meet the positive correlation correspondence:

[0079] x1 < x2 < x3... < x n → y1 < y2 < y3... < y n , screen out abnormal values, and improve fitting accuracy.

[0080] S423. Determine the order and coefficients of the Bernstein polynomial fitting algorithm according to the preprocessed absorbance data and water content data.

[0081] Specifically, the Bernstein polynomial is preliminarily determined according to the preprocessed absorbance data and water content data, and the formula is as follows:

[0082] Wherein, m represents the order, x1,..., x n represent the absorbance data, n represents the total number of data, A represents the undetermined coefficient, P m represents a set of algebraic polynomials not exceeding m.

[0083] According to the definition of m-order Bernstein polynomial and simple algebra, the recursive polynomial definition can be written as:

[0084] Wherein, B n，m-1 represents a plurality of m-1 order Bernstein polynomials for mixing to obtain the nth m order Bernstein polynomial, and the formula is to prove the recursive property of the Bernstein polynomial.

[0085] The power base index is used to determine the m order, and the binomial is taken as an example to obtain the following formula:

[0086] Wherein, B n,m represents the nth m order polynomial, and the formula can be obtained by the definition of Bernstein polynomial and binomial theorem.

[0087] Power base [1, x, x 2 ,..., x nThe Bernstein polynomial space with the degree less than or equal to m is constituted, so any m-order Bernstein polynomial can be expressed by the power basis. The Bernstein basis is converted into the power basis, and the m-order is determined by using the promotion formula as follows:

[0088] wherein, B i,m represents the i-th m-order Bernstein polynomial of the number.

[0089] According to the matrix form of the input of the absorbance-moisture content data points, the polynomial coefficients of the linear combination of the Bernstein basis functions are determined, and the calculation formula is as follows:

[0090] The formula is an m-order matrix expression, which is expressed in the form of vector point multiplication, wherein, B(x) represents a polynomial, B n,m (x) represents m-order data, which is used to determine the power basis coefficients of the corresponding Bernstein polynomial.

[0091] According to the power basis, the above formula can be written as:

[0092] S424, according to the order and the coefficient, the Bernstein polynomial is fitted by using the scalar function regression to obtain a second fitting curve.

[0093] Specifically, the Bernstein polynomial is fitted by using the scalar function regression, the coefficients and the order obtained by the above formula are combined, and finally the second fitting curve of the coal sample is fitted.

[0094] wherein, Y i represents the finally output second fitting curve, and a represents a scalar constant, and m represents an order.

[0095] S43, the moisture content data and the corresponding absorbance data of the coal sample in the third fitting interval are fitted by using a neural network algorithm to obtain a third fitting curve.

[0096] Specifically, the neural network algorithm is good at capturing and learning the nonlinear relationship between the input data (such as absorbance) and the output data (such as moisture content), and can better handle the obvious nonlinear relationship in the high-moisture content interval, and the neural network algorithm is simple to calculate. For the high-moisture content interval with more data, the calculation efficiency can be considered on the basis of ensuring the calculation accuracy. Therefore, the neural network algorithm is used for fitting in the third fitting interval.

[0097] Specifically, the neural network used by the neural network algorithm includes: an input layer, a hidden layer and an output layer;

[0098] The input layer includes two neurons for inputting corresponding absorbance data and moisture content data;

[0099] The output layer comprises one neuron for outputting the third fitting curve of the absorbance data and the moisture content data;

[0100] The number of layers of the hidden layer is 2;

[0101] The neural network algorithm selects a normalization function premnmx.

[0102] The input value of the neuron processing unit is u i When passing through the hidden layer, the data is compared and screened, and the strength weight W of the interaction between the processing units is used. i The internal threshold q is used to output the result U together.

[0103] The input of the neuron is:

[0104] The output of the neuron is:

[0105] In the formula, f is the action function.

[0106] S5, integrating the first fitting curve, the second fitting curve and the third fitting curve to obtain a complete coal absorbance-moisture content fitting curve.

[0107] Specifically, the first fitting curve, the second fitting curve and the third fitting curve are integrated by a transition function to obtain a complete coal absorbance-moisture content fitting curve; wherein the transition function selects an exponential decay function.

[0108] The calculation formula for integrating the fitting curves of the adjacent two fitting intervals by the exponential decay function is as follows: f(x)=a+(b-a)×e -λ×(x-c) ;

[0109] Wherein, λ represents the decay rate, a is the end point of the first fitting curve, b is the initial end point of the second fitting curve, c represents the center point of the function transition from a to b, and x represents the independent variable parameter.

[0110] According to the above formula, the three fitting curves are integrated to obtain a complete coal absorbance-moisture content fitting curve.

[0111] S6, measuring the moisture content of the coal to be measured through the coal absorbance-moisture content fitting curve.

[0112] The embodiment of the present application segments the coal moisture content interval based on the critical interval of coal moisture content, and then combines various fitting algorithms to fit the coal absorbance and moisture content, so as to obtain high-precision fitting results of each interval segment, and finally obtain the final coal moisture content calculation model by integrating the fitting results of the three interval segments through a transition function, which not only improves the precision and accuracy of the fitting results, but also takes into account the fitting efficiency, and has strong adaptability in different coal types and moisture content intervals.

[0113] Fig. 4 is a structural schematic diagram of a coal moisture content measurement system provided by the embodiment of the present application, which is used to execute the coal moisture content measurement method described in the above embodiment, as shown in Fig. 4, the system includes the following modules:

[0114] A data acquisition module is configured to acquire the absorbance data and moisture content data of the coal sample, wherein the coal sample includes coking coal, chemical coal and power coal, and the corresponding relationship between the absorbance data and the moisture content data of the coal sample is obtained according to the absorbance data and the moisture content data of the coal sample, and the absorbance interval and the moisture content interval of the coal sample are obtained.

[0115] A moisture content interval segmentation module is connected with the data acquisition module and is configured to determine a segmentation threshold of the moisture content interval, and divide the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold.

[0116] A fitting algorithm module is connected with the moisture content interval segmentation module and is configured to fit the moisture content data and the corresponding absorbance data of the first fitting interval, the second fitting interval and the third fitting interval respectively, so as to obtain a first fitting curve, a second fitting curve and a third fitting curve.

[0117] A fitting curve integration module is connected with the fitting algorithm module and is configured to integrate the first fitting curve, the second fitting curve and the third fitting curve, so as to obtain a complete coal absorbance-moisture content fitting curve.

[0118] A measurement module is connected with the fitting curve integration module and is configured to measure the moisture content of the coal to be measured through the coal absorbance-moisture content fitting curve.

[0119] It should be noted that the terms used in the present application are only intended to describe specific embodiments and are not intended to limit the scope of the present application. As shown in the specification of the present application, unless the context clearly indicates otherwise, "one", "a", "an", and / or "the" do not specifically refer to the singular, but can also include the plural. The terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method or device including the element.

[0120] It should also be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application. Unless otherwise specified and limited, the terms "mounting", "connection", "connection" and the like should be broadly understood, for example, it can be a fixed connection, or it can be a detachable connection, or an integral connection; it can be a mechanical connection, or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions described in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present application.

Claims

1. A coal moisture measurement method, characterized by, The method comprises the following steps: S1, obtaining absorbance data and moisture content data of the coal sample; wherein the coal sample comprises coking coal, chemical coal and power coal; S2, obtaining an absorbance interval and a moisture content interval of the coal sample and a corresponding relationship between the absorbance data and the moisture content data of the coal sample according to the absorbance data and the moisture content data of the coal sample; S3, determining a segmentation threshold of the moisture content interval, and dividing the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold; S4, fitting the moisture content data and the corresponding absorbance data of the first fitting interval, the second fitting interval and the third fitting interval respectively to obtain a first fitting curve, a second fitting curve and a third fitting curve; specifically comprising: S41, fitting the moisture content data and the corresponding absorbance data of the coal sample in the first fitting interval by using a support vector machine algorithm to obtain the first fitting curve; S42, fitting the moisture content data and the corresponding absorbance data of the coal sample in the second fitting interval by using a Bernstein polynomial fitting algorithm to obtain the second fitting curve; S43, fitting the moisture content data and the corresponding absorbance data of the coal sample in the third fitting interval by using a neural network algorithm to obtain the third fitting curve; S5, integrating the first fitting curve, the second fitting curve and the third fitting curve to obtain a complete coal absorbance-moisture content fitting curve; specifically comprising: integrating the first fitting curve, the second fitting curve and the third fitting curve by using a transition function to obtain the complete coal absorbance-moisture content fitting curve; wherein the transition function is an exponential decay function; S6, measuring the moisture content of the coal to be measured by using the coal absorbance-moisture content fitting curve.

2. The coal moisture measurement method according to claim 1, characterized by, In the S3, the determination of the segmentation threshold of the moisture content interval comprises: determining a first segmentation threshold and a second segmentation threshold of the moisture content interval according to a critical interval of the moisture content of the coal sample; wherein the first segmentation threshold is 4.36%, and the second segmentation threshold is 10.46%.

3. The coal moisture measurement method according to claim 2, wherein In the S3, the division of the moisture content interval into the first fitting interval, the second fitting interval and the third fitting interval according to the segmentation threshold comprises: dividing the moisture content interval of the coal sample into the first fitting interval, the second fitting interval and the third fitting interval according to the first segmentation threshold and the second segmentation threshold; wherein the first fitting interval is 0.93%-4.36%, the second fitting interval is 4.36%-10.46%, and the third fitting interval is 10.46%-21.53%.

4. The coal moisture measurement method of claim 1, wherein, In the S42, the fitting of the moisture content data and the corresponding absorbance data of the coal sample in the second fitting interval by using the Bernstein polynomial fitting algorithm to obtain the second fitting curve comprises: S421, determining the moisture content data contained in the second fitting interval and the absorbance data corresponding to the moisture content data; S422, pre-processing the absorbance data and the moisture content data according to the positive correlation relationship between the absorbance data and the moisture content data, and removing the absorbance data and the moisture content data data set not conforming to the positive correlation relationship; S423、According to the pre-processed absorbance data and the moisture content data, determine the order and coefficients of the Bernstein polynomial fitting algorithm; S424, according to the order and coefficient, using scalar function regression method to carry out regression fitting to Bernstein polynomial, obtain the second fitting curve.

5. The coal moisture measurement method according to claim 4, wherein In the S43, the neural network algorithm is used to fit the moisture content data and the corresponding absorbance data of the coal sample in the third fitting interval, wherein the neural network used in the neural network algorithm includes an input layer, a hidden layer and an output layer; The input layer includes two neurons for inputting corresponding absorbance data and moisture content data; The output layer includes one neuron for outputting the third fitting curve of the absorbance data and the moisture content data; The number of layers of the hidden layer is 2; The neural network algorithm selects the normalization function premnmx.

6. A coal moisture measurement system for performing a coal moisture measurement method according to any one of claims 1 to 5, characterized by The system includes the following modules: A data acquisition module is configured to acquire absorbance data and moisture content data of a coal sample, wherein the coal sample includes coking coal, chemical coal and power coal; and obtain an absorbance interval and a moisture content interval of the coal sample, and a corresponding relationship between the absorbance data and the moisture content data of the coal sample according to the absorbance data and the moisture content data of the coal sample; A moisture content interval segmentation module is connected with the data acquisition module and configured to determine a segmentation threshold of the moisture content interval, and divide the moisture content interval into a first fitting interval, a second fitting interval and a third fitting interval according to the segmentation threshold; A fitting algorithm module is connected with the moisture content interval segmentation module and configured to fit the moisture content data and the corresponding absorbance data of the coal sample in the first fitting interval, the second fitting interval and the third fitting interval respectively to obtain a first fitting curve, a second fitting curve and a third fitting curve; specifically, the support vector machine algorithm is used to fit the moisture content data and the corresponding absorbance data of the coal sample in the first fitting interval to obtain the first fitting curve; the Bernstein polynomial fitting algorithm is used to fit the moisture content data and the corresponding absorbance data of the coal sample in the second fitting interval to obtain the second fitting curve; and the neural network algorithm is used to fit the moisture content data and the corresponding absorbance data of the coal sample in the third fitting interval to obtain the third fitting curve; A fitting curve integration module is connected with the fitting algorithm module and configured to integrate the first fitting curve, the second fitting curve and the third fitting curve to obtain a complete coal absorbance-moisture content fitting curve; specifically, an exponential decay function is selected as a transition function to integrate the first fitting curve, the second fitting curve and the third fitting curve to obtain the complete coal absorbance-moisture content fitting curve; A measurement module is connected with the fitting curve integration module and configured to measure the moisture content of a to-be-measured coal through the coal absorbance-moisture content fitting curve.

Images