Bituminous coal colloid layer thickness monitoring method and system based on artificial intelligence

Abstract

The present application relates to the field of intelligent control, and in particular to a method and system for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence. The method includes the following steps: constructing a first curve about the distance from the upper edge of the colloid layer to the bottom of the cup and the heating time, obtaining the extreme points in the first curve and the curve segments between adjacent extreme points; calculating the abnormal evaluation of the first curve, and judging the first curve corresponding to the abnormal evaluation value less than or equal to the preset evaluation threshold as invalid; calculating the verification coefficient, if the verification coefficient is less than or equal to the coefficient threshold, taking the extreme point with the largest smoothness as the abnormal point, eliminating the abnormal point, repeatedly calculating the abnormal evaluation, judging whether the first curve is invalid, and if so, controlling the heating device to stop heating and generating an alarm signal. The present application has the effect of monitoring the heating process. If the data is abnormal during the test, the heating device is promptly controlled to stop.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and in particular to a method and system for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence. Background Art

[0002] The bituminous coal colloid layer refers to the colloid layer formed by the softening and melting of the coal sample during the heating process. During the heating process of coal, the coal sample will experience different temperature stages and form different isothermal layers. The coal sample will soften and melt during the heating process to form a colloid. When the temperature reaches a certain value, the coal sample will form a semi-coke and a colloid layer. The colloid layer index can be used to characterize the plasticity of the coal.

[0003] The test process is: the coal sample is placed in a steel cup and heated. During the heating process, the coal sample forms three parts: a semi-coke layer, a gelatinous layer and an unsoftened coal sample layer. The thickness of the gelatinous layer is measured with a special gelatinous layer probe to obtain the maximum thickness Y value of the gelatinous layer. The larger the Y value, the better the plasticity of the coal, and it is suitable for coking.

[0004] When measuring the thickness of the coal colloid layer, due to the operator's experience and proficiency, different colloid layer volume curves will appear during measurement. Therefore, it is necessary to evaluate and judge whether the measured thickness value is a valid thickness value. If the measured thickness value does not meet the expectations or standards, it may be necessary to re-test. In addition, the test time is relatively long, requiring heating for 2-3 hours. If the thickness is judged to be invalid after heating, it is necessary to re-test, which increases the cost and operation time of the test. Summary of the invention

[0005] In order to solve the technical problem of increased cost and time caused by repeated experiments, the present application provides a method and system for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence.

[0006] In the first aspect, the present application provides a method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence, which adopts the following technical solutions:

[0007] The method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence comprises the following steps: constructing a first curve about the distance from the upper edge of the colloid layer to the bottom of the cup and the heating time, obtaining the extreme value points in the first curve and the curve segments between the adjacent extreme value points, and the number of the extreme value points is at least 2; calculating the abnormal evaluation of the first curve, and determining the first curve corresponding to the abnormal evaluation value being less than or equal to the preset evaluation threshold value as invalid; the calculation method of the abnormal evaluation is:

[0008] ,in, is the abnormal evaluation of the first curve, is the smoothness of the first extreme point, For the The smoothness of the extreme points, represents the maximum value function, represents the standard deviation, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points is calculated; the verification coefficient is calculated. If the verification coefficient is less than or equal to the coefficient threshold, the extreme point with the largest smoothness is taken as an abnormal point, the abnormal point is eliminated, and the abnormal evaluation is repeatedly calculated to determine whether the first curve is invalid. If so, the heating equipment is controlled to stop heating and an alarm signal is generated.

[0009] The beneficial effect is: the heating process is monitored, and if the data is abnormal during the test, the heating equipment is stopped in time. In the calculation formula of abnormal evaluation, in addition to the analysis of smoothness, the factor of change between extreme points is added to comprehensively judge the abnormal degree of the first curve. At the same time, the verification coefficient is used to screen out abnormal points caused by non-human factors (abnormal pressurization or abnormal temperature) to reduce unnecessary equipment stops.

[0010] Optionally, smoothness is calculated as:

[0011] ,in, Indicates extreme point Smoothness, extreme points is the target extreme point, represents the normalization function, represents the maximum value function, Indicates extreme point The first sequence of distance changes of the adjacent curve segments before, the heating time range of the first sequence is , Indicates extreme point The second sequence of distance changes of adjacent curve segments, the heating time range of the second sequence is , Represents the mean function, extreme point The corresponding heating time is , Indicates heating time The corresponding distance, Indicates heating time The corresponding distance.

[0012] The beneficial effect is: in the formula for calculating smoothness, the reason for analyzing the curve segments on both sides of the extreme point is that the changing speed of the curve before and after the extreme point may be inconsistent. Therefore, it is necessary to calculate separately on both sides of the extreme point to ensure that both segments are smooth curves and that the extreme point is also smooth.

[0013] Optionally, the method for constructing the first sequence and the second sequence is: in adjacent distances, the ratio of the latter distance to the former distance is taken as the distance change, and in each curve segment, a sequence about the distance change is constructed, and the sequence of the curve segment before the target extreme point is taken as the first sequence, and the sequence of the curve segment after the target extreme point is taken as the second sequence.

[0014] Optionally, in adjacent distances, the ratio of the previous distance to the next distance is taken as the distance change, and in each curve segment, a sequence of distance changes is constructed, with the sequence of the curve segment before the target extreme point as the first sequence and the sequence of the curve segment after the target extreme point as the second sequence.

[0015] Optionally, the normalization function is a hyperbolic tangent function.

[0016] Optionally, the method for calculating the verification coefficient includes: constructing a second curve about the distance from the lower edge of the gelatinous layer to the bottom of the cup and the heating time; at the same heating time, obtaining the midpoint of the straight-line distance between the upper edge and the lower edge of the gelatinous layer, taking the midpoint sequence of the curve segment before the target extreme point as the third sequence, and taking the midpoint sequence of the curve segment after the target extreme point as the fourth sequence; taking the Pearson correlation coefficient between the third sequence and the fourth sequence as the verification coefficient.

[0017] Beneficial effect: The Pearson correlation coefficient is used to express the correlation between the third sequence and the fourth sequence, that is, whether the change characteristics of the third sequence are consistent with the change characteristics of the fourth sequence. If they are consistent, it means that the abnormal point has not mutated, indicating that it is more likely to be caused by abnormal pressurization and abnormal temperature. If they are inconsistent, it means that the abnormal point has mutated, and the mutation is more likely to be caused by improper manual operation. The verification coefficient is used to screen out abnormal points caused by non-human factors.

[0018] In the second aspect, the present application provides a bituminous coal colloid layer thickness monitoring system based on artificial intelligence, which adopts the following technical solutions:

[0019] The bituminous coal colloid layer thickness monitoring system based on artificial intelligence includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the bituminous coal colloid layer thickness monitoring method based on artificial intelligence is implemented.

[0020] The beneficial effect is: the above-mentioned artificial intelligence-based bituminous coal colloid layer thickness monitoring method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0021] This application has the following technical effects:

[0022] 1. Monitor the heating process. If the data is abnormal during the test, stop the heating equipment in time. In the calculation formula of abnormal evaluation, in addition to the analysis of smoothness, the factor of change between extreme points is added to comprehensively judge the abnormality of the first curve.

[0023] 2. Use the verification coefficient to screen out abnormal points caused by non-human factors (abnormal pressurization or abnormal temperature) to reduce unnecessary equipment shutdowns. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0025] Figure 1 It is a method flow chart of the method for monitoring the thickness of the bituminous coal colloid layer based on artificial intelligence in an embodiment of the present application.

[0026] Figure 2 It is a curve schematic diagram showing the first curve and the second curve in the bituminous coal colloid layer thickness monitoring method based on artificial intelligence in an embodiment of the present application.

[0027] Figure 3 It is a flow chart of the method for calculating the verification coefficient in the artificial intelligence-based bituminous coal colloid layer thickness monitoring method in the embodiment of the present application. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0029] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0030] The present application embodiment discloses a method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence, referring to Figure 1 , including steps S1 to S3, which are specifically as follows:

[0031] S1: construct a first curve about the distance from the upper edge of the colloid layer to the bottom of the cup and the heating time, and obtain the extreme points in the first curve and the curve segments between adjacent extreme points.

[0032] The upper edge in the present application refers to the edge of the cross-sectional view of the gelatin layer close to the bottom of the cup, and the lower edge refers to the edge of the cross-sectional view of the gelatin layer close to the mouth of the cup, and the heating source is placed at the bottom of the cup.

[0033] Reference Figure 2 , the distance from the upper edge of the colloid layer to the bottom of the cup can be used as the ordinate, and the heating time can be used as the abscissa to obtain the first curve representing the upper edge curve 1, the second curve representing the lower edge curve 2, and curve 3 is obtained by fitting the lower edge curve 2. d represents the thickness of the colloid layer. Since the heating is carried out from the upper edge to the lower edge, the first curve fluctuates first, and then the second curve fluctuates. Since the lower edge contacts the solid above the colloid layer and the upper edge contacts the molten material below the colloid layer, the curve at the upper edge fluctuates more violently, and the curve at the lower edge fluctuates more gently.

[0034] Or the distance from the upper edge of the gelatin layer to the bottom of the cup is used as the horizontal axis, and the heating time is used as the vertical axis.

[0035] During the heating process, when two extreme value points appear, the first curve begins to be analyzed, so the number of extreme value points in the first curve is set to at least two.

[0036] S2: Calculate the abnormality evaluation of the first curve, and determine that the first curve corresponding to the abnormality evaluation value is less than or equal to the preset evaluation threshold is invalid.

[0037] The calculation method of abnormal evaluation is:

[0038] ,in, is the abnormal evaluation of the first curve, is the smoothness of the first extreme point, For the The smoothness of the extreme points, represents the maximum value function, represents the standard deviation, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points, For the The distance refers to the distance from the upper edge of the gelatin layer to the bottom of the cup.

[0039] Expressed the The maximum value in . Calculation of any extreme point For example, the calculation formula for smoothness is:

[0040] ,in, Indicates extreme point Smoothness, extreme points is the target extreme point, represents the normalization function, represents the maximum value function, Indicates extreme point The first sequence of distance changes of the adjacent curve segments before, the heating time range of the first sequence is , Indicates extreme point The second sequence of distance changes of adjacent curve segments, the heating time range of the second sequence is , Represents the mean function, extreme point The corresponding heating time is , Indicates heating time The corresponding distance, Indicates heating time The corresponding distance. Exemplarily, the normalization function is a hyperbolic tangent function.

[0041] In one embodiment, the method for constructing the first sequence and the second sequence is: in adjacent distances, the ratio of the latter distance to the former distance is taken as the distance change, and in each curve segment, a sequence about the distance change is constructed, and the sequence of the curve segment before the target extreme point is taken as the first sequence, and the sequence of the curve segment after the target extreme point is taken as the second sequence.

[0042] Exemplarily, the expressions of the first sequence and the second sequence are:

[0043] ,in, represents the first sequence, represents the second sequence, It indicates the The distance of the heating moment, Indicates The distance of the heating moment, It indicates the The distance of the heating moment, It indicates the The distance of the heating moment, Indicates The distance of the heating moment, It indicates the The distance at which the heating occurs.

[0044] In other embodiments, the ratio of the previous distance to the next distance may also be used as the distance change, which will not be elaborated here.

[0045] The first curve corresponding to the abnormal evaluation value being less than or equal to the preset evaluation threshold is determined to be invalid. Otherwise, the test is continued. Exemplarily, the evaluation threshold is set to 0.7.

[0046] The normal glial layer measurement curve should be a relatively smooth S-shaped curve. The change speed on both sides of the extreme point is calculated by smoothness. The smaller the change speed, the better the smoothness of the curve. Conversely, the possibility of abnormality is higher.

[0047] In the formula for calculating smoothness, the reason for analyzing the curve segments on both sides of the extreme point is that the changing speed of the curve before and after the extreme point may be inconsistent. Therefore, it is necessary to calculate separately on both sides of the extreme point to characterize the smoothness characteristics of both the curve and the extreme point.

[0048] In the calculation formula for abnormal evaluation, in addition to the analysis of smoothness, the factor of changes between extreme points is added to comprehensively judge the abnormality of the first curve. The reason for analyzing the points on the upper edge is that in the cross-sectional view of the bituminous coal colloid layer, the distance value from the lower edge to the bottom of the cup is relatively average and the variation is small, while the distance value from the upper edge to the bottom of the cup varies greatly. Analyzing only the upper edge can reduce the amount of data analyzed.

[0049] The main reasons for the abnormal fluctuation of the curve are human operation errors or abnormal temperature and pressure rise. When human operation problems occur, the internal structure of the coking coal changes, resulting in irreversible changes in the structure. At this time, the measured value is unavailable. In case of abnormal temperature rise or pressure increase, the curve will keep pace with the abnormal temperature and pressure rise, and the subsequent changes will not necessarily affect the curve excessively. At this time, the measured value is still available. In order to identify this situation, the verification coefficient is calculated.

[0050] S3: Calculate the verification coefficient. If the verification coefficient is less than or equal to the coefficient threshold, take the extreme point with the largest smoothness as the abnormal point, remove the abnormal point, repeat the calculation of the abnormal evaluation, and determine whether the first curve is invalid. If so, control the heating device to stop heating and generate an alarm signal.

[0051] Reference Figure 3 The calculation method of the verification coefficient includes steps S30 to S32, which are as follows:

[0052] S30: constructing a second curve of the distance from the lower edge of the gelatin layer to the bottom of the cup and the heating time.

[0053] S31: At the same heating moment, the midpoint of the straight-line distance between the upper edge and the lower edge of the colloid layer is obtained, and the midpoint sequence of the curve segment before the target extreme point is used as the third sequence, and the midpoint sequence of the curve segment after the target extreme point is used as the fourth sequence.

[0054] S32: Use the Pearson correlation coefficient between the third sequence and the fourth sequence as the verification coefficient.

[0055] The expression for the third sequence can be , the expression of the fourth sequence can be The expression of the verification coefficient can be:

[0056] ,in, represents the validation coefficient, Indicates the distance from the upper edge corresponding to the first heating moment, Indicates the distance from the lower edge corresponding to the first heating moment, Indicates The distance from the upper edge corresponding to the heating moment, Indicates The distance from the lower edge corresponding to the heating moment, It indicates the The distance from the upper edge corresponding to the heating moment, It indicates the The distance from the lower edge corresponding to the heating moment.

[0057] It represents the Pearson correlation coefficient, and its value range is The Pearson correlation coefficient is used to express the correlation between the third sequence and the fourth sequence, that is, whether the change characteristics of the third sequence are consistent with the change characteristics of the fourth sequence. If they are consistent, it means that the abnormal point has not undergone a mutation, indicating that it is more likely to be caused by abnormal pressurization and abnormal temperature. If they are inconsistent, it means that the abnormal point has undergone a mutation, and the mutation is more likely to be caused by improper manual operation.

[0058] When the value of the Pearson correlation coefficient is close to 1, it means that there is a positive correlation between the two sequences. When the Pearson correlation coefficient is close to 1, it indicates that there is a negative correlation between the two series. When the Pearson correlation coefficient is close to 1, it indicates that there is a positive correlation between the two series.

[0059] Exemplarily, the coefficient threshold can be set to 0.8. When the verification coefficient at a certain moment is greater than the coefficient threshold, it means that it is caused by abnormal temperature rise or abnormal pressurization, and the impact is small, and the corresponding abnormal point can be ignored, so the abnormal point is removed, and the abnormal evaluation is calculated repeatedly to determine whether the first curve is invalid. If so, the heating device is controlled to stop heating and generate an alarm signal. Otherwise, the test continues. Exemplarily, the alarm signal is a sound signal or a light signal, that is, an alarm sound is emitted by a buzzer or an alarm is emitted by a light.

[0060] An embodiment of the present application also discloses an artificial intelligence-based bituminous coal colloid layer thickness monitoring system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an artificial intelligence-based bituminous coal colloid layer thickness monitoring method according to the present application is implemented.

[0061] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0062] In the present application, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high bandwidth memory HBM (High Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0063] Although this specification has shown and described a plurality of embodiments of the present application, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, modifications and alternatives without departing from the thought and spirit of the present application. It should be understood that in the process of practicing the present application, various alternatives to the embodiments of the present application described herein may be adopted.

[0064] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence, characterized in that: Includes steps: Constructing a first curve about the distance from the upper edge of the colloid layer to the bottom of the cup and the heating time, obtaining extreme value points in the first curve and curve segments between adjacent extreme value points, wherein the number of extreme value points is at least 2; Calculate the abnormal evaluation of the first curve, and determine that the first curve corresponding to the abnormal evaluation value is less than or equal to the preset evaluation threshold is invalid; the calculation method of the abnormal evaluation is: ,in, is the abnormal evaluation of the first curve, is the smoothness of the first extreme point, For the The smoothness of the extreme points, represents the maximum value function, represents the standard deviation, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points, For the The distance between extreme points, For the The distance between the extreme points refers to the distance from the upper edge of the colloid layer to the bottom of the cup; Calculate the verification coefficient. If the verification coefficient is less than or equal to the coefficient threshold, take the extreme point with the largest smoothness as the abnormal point, remove the abnormal point, repeat the calculation of the abnormal evaluation, and determine whether the first curve is invalid. If so, control the heating equipment to stop heating and generate an alarm signal.

2. The method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence according to claim 1, characterized in that: The calculation formula for smoothness is: ， in, Indicates extreme point Smoothness, extreme points is the target extreme point, represents the normalization function, represents the maximum value function, Indicates extreme point The first sequence of distance changes of the previous curve segment, the heating time range of the first sequence is , Indicates extreme point The second sequence of distance changes of the next curve segment, the heating time range of the second sequence is , Represents the mean function, extreme point The corresponding heating time is , Indicates heating time The corresponding distance, Indicates heating time distance.

3. The method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence according to claim 2 is characterized in that: The method for constructing the first sequence and the second sequence is: in adjacent distances, the ratio of the latter distance to the former distance is taken as the distance change, and in each curve segment, a sequence about the distance change is constructed, and the sequence of the curve segment before the target extreme point is taken as the first sequence, and the sequence of the curve segment after the target extreme point is taken as the second sequence.

4. The method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence according to claim 2, characterized in that: In adjacent distances, the ratio of the previous distance to the next distance is taken as the distance change. In each curve segment, a sequence of distance changes is constructed, with the sequence of the curve segment before the target extreme point as the first sequence and the sequence of the curve segment after the target extreme point as the second sequence.

5. The method for monitoring the thickness of a bituminous coal colloid layer based on artificial intelligence according to claim 2, characterized in that: The normalization function is the hyperbolic tangent function.

6. The method for monitoring the thickness of bituminous coal colloid layer based on artificial intelligence according to claim 2, characterized in that: The calculation method of the verification coefficient includes: Constructing a second curve of the distance from the lower edge of the gelatin layer to the bottom of the cup and the heating moment; At the same heating moment, the midpoint of the straight-line distance between the upper edge and the lower edge of the colloid layer is obtained, and the midpoint sequence of the curve segment before the target extreme point is used as the third sequence, and the midpoint sequence of the curve segment after the target extreme point is used as the fourth sequence; The Pearson correlation coefficient between the third and fourth sequences is used as the verification coefficient.

7. The bituminous coal colloid layer thickness monitoring system based on artificial intelligence is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for monitoring the thickness of the bituminous coal colloid layer based on artificial intelligence according to any one of claims 1-6 is implemented.

Images