A system and method for monitoring the expansion degree of bituminous coal based on big data

Abstract

The present invention relates to the field of coal chemical technology, and in particular to a system and method for monitoring the Oya expansion degree of bituminous coal based on big data; the method comprises: obtaining the Oya expansion degree data of the current bituminous coal in the heating process; clustering the Oya expansion degree data using the MST clustering algorithm to obtain multiple clusters; performing anomaly detection on the multiple clusters to obtain abnormal data in the corresponding clusters. That is, the present invention analyzes the Oya expansion degree data in the heating process of the bituminous coal, and introduces the analysis results into the outlier detection algorithm to monitor the bituminous coal data, thereby improving the accuracy of the current Oya expansion degree data monitoring of the bituminous coal.

Description

Technical Field

[0001] The present invention relates to the technical field of coal chemical industry, and more specifically, to a system and method for monitoring the expansion degree of bituminous coal based on big data. Background Art

[0002] The Oya expansion degree of bituminous coal is an important indicator for testing the cohesiveness and plasticity of bituminous coal. It not only reflects the amount of colloid, but also reflects the quality of colloid. It plays an irreplaceable role in understanding the coking mechanism of coal, guiding coal processing and utilization, and improving the quality of coke.

[0003] Among them, the Oya expansion degree determination experiment of bituminous coal is to make the coal sample into a coal pen of a certain specification, place it in a heated expansion tube, and calculate the Oya expansion degree by measuring the displacement curve of the expansion rod. The Oya expansion degree characterizes the impermeability of the coal colloid by the degree of volume expansion or contraction during the distillation of bituminous coal. The change of the Oya expansion degree of bituminous coal is directly reflected in the expansion curve.

[0004] Therefore, in order to accurately evaluate the coking and coking properties of bituminous coal and improve production quality, it is particularly important to test the Oya expansion degree of bituminous coal.

[0005] In the prior art, there is a patent application document with publication number CN103275740A, entitled "Method for evaluating the quality of fat coal", which discloses the key indicators for detecting the quality of fat coal, obtains the coarse-grained mosaic structure ratio, the maximum Kiel fluidity and the Oya expansion, and obtains the fat coal quality evaluation index based on the coarse-grained mosaic structure ratio, the maximum Kiel fluidity and the Oya expansion, so as to evaluate the quality of fat coal.

[0006] However, when conducting the evaluation, the Oya expansion degree of fat coal is greatly affected by gas and environmental conditions during the measurement process, which may cause inaccurate Oya expansion degree and thus biased evaluation. That is, when the Oya expansion degree b value is very large, the evaluation score of the coal will be very high, but in fact this type of coal does not play such a good role, so there is a problem of inaccurate evaluation.

[0007] Therefore, how to improve the accuracy and reliability of Oya expansion is particularly important for improving coke quality and optimizing coal utilization. Summary of the invention

[0008] The purpose of the present invention is to propose a system and method for monitoring the Oya expansion degree of bituminous coal based on big data, so as to solve the problem that the Oya expansion degree of bituminous coal in the prior art is greatly affected by gas and environmental conditions during the measurement process, and may be inaccurate; to this end, the present invention provides solutions in the following two aspects.

[0009] In a first aspect, the present invention provides a method for monitoring the expansion degree of bituminous coal based on big data, comprising:

[0010] Obtain the current Oya expansion data of bituminous coal during the heating process;

[0011] The MST clustering algorithm is used to cluster the Oya expansion degree data and obtain multiple clusters;

[0012] Perform anomaly detection on multiple clusters to obtain abnormal data in the corresponding clusters;

[0013] Among them, the edge weight between two nodes corresponding to any two Oya expansion degrees in the clustering process is:

[0014] ; For edge rights, , are the Oya expansion corresponding to temperature i The fluctuation index and the Oya expansion degree corresponding to temperature j The volatility index, exp() is an exponential function with the natural constant e as the base;

[0015] The volatility indicators are:

[0016] Obtain the Oya expansion data of multiple other bituminous coals during the heating process;

[0017] Calculate the Pearson correlation coefficient of the Oya expansion data of any other bituminous coal in a set temperature range and the current bituminous coal, and use the normalized value of each Pearson correlation coefficient as a weight; the set temperature range is composed of multiple temperatures centered on any temperature;

[0018] Calculate the absolute value of the difference between the Oya expansion degree of any other bituminous coal and the current bituminous coal at any of the above temperatures; and use various weights to weight all the absolute values ​​of the differences to obtain a fluctuation index.

[0019] The above scheme obtains the fluctuation index of the Oya expansion degree of the current bituminous coal by analyzing the change characteristics of the Oya expansion degree data of the current bituminous coal and the relationship between the Oya expansion degree data of multiple other bituminous coals, so as to characterize the suspected abnormal situation of the Oya expansion degree of the current bituminous coal, and then uses the fluctuation index to calculate the edge weight in the clustering process to replace the weight measurement method in the traditional MST clustering, which can more accurately and efficiently identify the abnormal data and improve the accuracy of anomaly detection.

[0020] Optionally, the method further includes the step of screening multiple other bituminous coals, specifically, sorting all obtained Pearson correlation coefficients in descending order, and selecting other bituminous coals corresponding to the first m Pearson correlation coefficients, where m is greater than 1.

[0021] The above scheme selects the bituminous coal that is the same or similar to the current bituminous coal through correlation analysis between the current bituminous coal and other bituminous coals, which is conducive to the subsequent analysis of the change of the Oya expansion degree of the current bituminous coal, thereby improving the accuracy of the calculated fluctuation index.

[0022] Optionally, the weight is:

[0023] ;

[0024] In the formula, represents the weight of the current bituminous coal at temperature i, is the Pearson correlation coefficient of the Oya expansion data of the jth other bituminous coal and the current bituminous coal in the set temperature range centered at temperature i, is the total number of other bituminous coals.

[0025] The above scheme can determine the importance of the absolute value of the difference between different other bituminous coals and the current bituminous coal by determining the correlation between the current bituminous coal and other bituminous coals.

[0026] Optionally, after obtaining the volatility index, the volatility index is corrected to obtain a corrected volatility index. , specifically:

[0027] ;

[0028] In the formula, is the Oya expansion corresponding to temperature i Volatility index before correction, represents the fitting value corresponding to the qth Oya expansion degree in the local temperature section, is the qth Oya expansion degree in the local temperature segment, exp() is an exponential function with the natural constant e as the base, and the local temperature segment is a temperature segment centered on temperature i taken from the current bituminous coal heating process, Indicates the total number of Oya expansion degrees within the local temperature range.

[0029] The above scheme takes the influence of noise into consideration, introduces fitting error to correct the Oya expansion degree, and reduces the influence of noise.

[0030] Optionally, the process of obtaining the fitting value is: using the least squares method to perform curve fitting on all Oya expansion degrees in the local temperature section to obtain the fitting value corresponding to each Oya expansion degree.

[0031] Optionally, the specific process of performing anomaly detection on multiple clusters to obtain abnormal data in corresponding clusters is:

[0032] In response to the number of nodes in the cluster being greater than the set number, the corresponding cluster is a normal cluster; in response to the number of nodes in the cluster being less than or equal to the set number, the corresponding cluster is a suspected abnormal cluster;

[0033] The outlier detection algorithm is used to perform anomaly detection on suspected abnormal clusters to obtain abnormal data.

[0034] When performing anomaly detection, the above scheme first screens the clusters and then performs anomaly analysis, which reduces the amount of calculation.

[0035] Optionally, the outlier detection algorithm is a box plot, an isolation forest algorithm, or a local outlier factor.

[0036] In a second aspect, a big data-based bituminous coal Oya expansion degree monitoring system comprises:

[0037] processor;

[0038] A memory stores computer instructions for monitoring the expansion degree of bituminous coal based on big data. When the computer instructions are executed by the processor, the system executes the above-mentioned method for monitoring the expansion degree of bituminous coal based on big data.

[0039] The beneficial effects of the present invention are:

[0040] The scheme of the present invention identifies abnormal data in the Oya expansion degree data through outlier detection based on MST clustering, which can avoid detecting normal data as abnormal or detecting abnormal data as normal, improves the accuracy of abnormal detection of Oya expansion degree data, and provides data support for subsequent bituminous coal coking process and coal quality evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0042] Figure 1 A flowchart of the steps of a method for monitoring the Oya expansion degree of bituminous coal based on big data in this embodiment is schematically shown;

[0043] Figure 2 The structural block diagram of a bituminous coal Oya expansion degree monitoring system based on big data in this embodiment is schematically shown. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0045] The present invention is aimed at the problem that the measured Oya expansion degree may be inaccurate when evaluating coal quality, optimizing coal utilization, etc. (that is, under normal circumstances, bituminous coal will begin to expand after reaching a certain temperature, and push the expansion rod to rise. If the displacement curve shows that the bituminous coal stops expanding before reaching the expected temperature, or even exhibits negative expansion (that is, the expansion rod drops), this may be a manifestation of abnormal properties of the bituminous coal or improper experimental conditions (such as inaccurate temperature control), that is, during the heating process of the bituminous coal, the Oya expansion degree may be much higher or much lower than the average value of similar bituminous coal, which manifests as abnormality). Therefore, a method for monitoring the Oya expansion degree of bituminous coal is proposed, which can accurately monitor whether there is any abnormality in the Oya expansion degree of the bituminous coal.

[0046] like Figure 1 As shown, a method for monitoring the expansion degree of bituminous coal based on big data in this embodiment includes the following steps:

[0047] Step S1, obtaining the Oya expansion degree data of the current bituminous coal during the heating process. Specifically, using an Oya expansion measuring instrument to collect the Oya expansion degree of the current bituminous coal at different temperatures in real time, and obtaining the Oya expansion degree data (Oya expansion degree sequence).

[0048] Among them, the process of measuring the Oya expansion degree is: the current bituminous coal is made into a coal pen of a certain specification according to the prescribed method, and is placed in an expansion tube with an inner diameter of 8mm. An expansion rod that can slide freely in the tube is placed on the coal pen. The above device is placed in a special electric heating furnace and heated at a heating rate of 3℃ / min. When heated to 500-550℃, the coal sample begins to decompose, volatile matter and colloid are precipitated, causing the coal pen to deform, shorten or expand. At this time, the displacement curve of the expansion rod is recorded, and the maximum distance of the displacement curve rises as a percentage of the original length of the coal pen, indicating the Oya expansion degree of the coal. Since the specific process of the determination is a prior art, it will not be repeated here.

[0049] The different temperatures mentioned above are determined by setting temperature intervals. For example, taking a temperature interval of 3°C as an example, the Oya expansion degree of the bituminous coal is recorded every 3°C, thereby obtaining the Oya expansion degree of the current bituminous coal at different temperatures.

[0050] Step S2, clustering the Oya expansion degree data using the MST clustering algorithm to obtain multiple clusters.

[0051] In this embodiment, when clustering the current bituminous coal Oya expansion data, the MST (minimum spanning tree) clustering algorithm is used. The clustering algorithm constructs and splits the minimum spanning tree to obtain the minimum spanning subtree that determines the sample space division, and then generates local density parameters according to the subtree characteristics, and finally performs local density clustering on the spanning subtree to obtain the clustering result.

[0052] Specifically, the clustering process is:

[0053] (1) For a given data set (current bituminous coal volatility index sequence), the similarity between two volatility indexes is calculated as the tree weight (edge ​​weight) to obtain the weight matrix;

[0054] (2) Use Kruskal's algorithm or Prim's algorithm to construct a minimum spanning tree (MST);

[0055] (3) After the minimum spanning tree is established, find the edge with the largest edge weight in the minimum spanning tree, then remove this edge, and split the minimum spanning tree into M+1 minimum spanning subtrees; the M+1 minimum spanning subtrees are first split into two subtrees, and then the two subtrees are split iteratively, and so on; the iteration termination condition is that when the maximum edge weight in the subtree is less than 0.3, the iteration is stopped;

[0056] (4) M+1 minimum spanning subtrees are multiple clusters.

[0057] Based on the specific process of the above algorithm, this embodiment takes into account that the traditional MST clustering algorithm is based on the difference between two data (such as the data can be the Oya expansion degree) as the edge weight; however, the Oya expansion degree in this embodiment changes with the change of temperature and is easily interfered by noise. Directly using the difference between the two Oya expansion degrees as the edge weight cannot reflect the actual similarity between the two Oya expansion degrees. Therefore, when performing outlier analysis, it is easy to cause abnormal data to be detected as normal or normal data to be detected as abnormal.

[0058] Therefore, this embodiment calculates the edge weight by calculating the volatility index of the Oya expansion degree, which represents the degree of suspected abnormal performance of the data, and then calculates the edge weight according to the difference of the volatility index.

[0059] Specifically, in this embodiment, the edge weight between two nodes corresponding to any two Oya expansion degrees includes steps S21 to S23, which are specifically:

[0060] Step S21, obtaining the Oya expansion data of a plurality of other bituminous coals during the heating process. Specifically, using an Oya expansion measuring instrument to collect the Oya expansion data of other bituminous coals during the heating process in real time.

[0061] Among them, the multiple other bituminous coals are bituminous coals of the same type as the current bituminous coal; the bituminous coal of the same type may be bituminous coal with a heating process similar to that of the current bituminous coal.

[0062] The above-mentioned bituminous coal acquisition process similar to the current bituminous coal heating process is:

[0063] First, the Oya expansion degrees of the current bituminous coal and other bituminous coals within a set temperature range are obtained respectively to obtain a sequence of each Oya expansion degree; wherein the set temperature range is a temperature range centered at any temperature;

[0064] Secondly, the Pearson correlation coefficient between the Oya expansion degree series of the current bituminous coal and the Oya expansion degree series of any other bituminous coal is calculated, and multiple Pearson correlation coefficients can be obtained;

[0065] Then, all the obtained Pearson correlation coefficients are sorted in order from large to small, and other bituminous coals corresponding to the first m Pearson correlation coefficients are selected as bituminous coals of the same type, where m is greater than 1.

[0066] For example, the Oya expansion corresponding to the calculated temperature i is For example, taking the expansion degree of Oya The Oya expansion degree sequence is formed by selecting the first S and the last S Oya expansion degrees of the Oya expansion degree sequence, wherein the Oya expansion degrees in the Oya expansion degree sequence correspond to the temperatures in the set temperature section one by one. The value of S is less than the number of Oya expansion degree data measured. For example, S can be 50, 100 or more.

[0067] The larger the Pearson correlation coefficient between any of the other bituminous coals mentioned above and the current bituminous coal, the more similar the changes in the Oya expansion degree series of the two are, and the higher the possibility that the two are the same type of bituminous coal.

[0068] Of course, as another embodiment, the bituminous coal of the same type may also be bituminous coal with the same composition.

[0069] It should be noted that, in theory, for bituminous coal with the same composition, when the Oya expansion degree test is carried out, the Oya expansion degrees of different coal samples at the same temperature must be similar or the same; however, bituminous coal with similar heating process is not necessarily bituminous coal with the same composition, and they may differ in composition.

[0070] The other bituminous coals may be bituminous coals selected from other different coal mines, or may be bituminous coals selected from the current coal mine.

[0071] It should be noted that different types of bituminous coal have different changes in their Oya expansion data. When performing subsequent calculations of the fluctuation index of any Oya expansion degree of the current bituminous coal, it is necessary to screen out some Oya expansion data that are consistent with the current bituminous coal type from multiple other bituminous coals, that is, the expansion data of the same type of bituminous coal, and then calculate the suspected abnormal degree of the Oya expansion degree change of the current bituminous coal based on the difference between the Oya expansion data of the bituminous coal at the current moment and the Oya expansion data at the current position in the expansion data of the same type of bituminous coal. The larger the difference, the more likely the Oya expansion degree change of the current bituminous coal is to be abnormal.

[0072] Step S22, calculate the absolute value of the difference in Oya expansion degree between any other bituminous coal and the current bituminous coal at any of the above temperatures; use various weights to weight all the absolute values ​​of the differences to obtain a fluctuation index, wherein each weight is a normalized value of the corresponding Pearson correlation coefficient.

[0073] Specifically, the volatility indicators are: ;

[0074] In the formula, represents the weight of the current bituminous coal at temperature i, is the Oya expansion corresponding to temperature i The volatility index, Represents the total number of other bituminous coals of the same type as the current bituminous coal, It represents the Oya expansion degree of the jth other bituminous coal at temperature i. is the absolute value of the difference between the Oya expansion degree of the current bituminous coal at temperature i and the Oya expansion degree of the jth other bituminous coal of the same type, which represents the Oya expansion degree of the current bituminous coal. The degree of suspected abnormality.

[0075] In one embodiment, the normalized values ​​of the Pearson correlation coefficients are used as weights, including: ;

[0076] In the formula, represents the weight of the current bituminous coal at temperature i, is the Pearson correlation coefficient of the Oya expansion data of the jth other bituminous coal and the current bituminous coal in the set temperature range centered at temperature i, is the total number of other bituminous coals.

[0077] Of course, as another implementation, the maximum and minimum normalization method may be used to normalize each Pearson correlation coefficient to obtain a corresponding weight.

[0078] The above embodiment introduces bituminous coal of the same type, calculates the difference in Oya expansion degree between each other bituminous coal and the current bituminous coal at a certain temperature, and uses the similarity of changes between the current bituminous coal and other bituminous coals as weights to perform weighted averaging on the differences, so that the other bituminous coals with greater similarity have higher credibility, and conversely, the other bituminous coals with smaller similarity have lower credibility, thereby improving the accuracy of the volatility index of the current bituminous coal.

[0079] At this point, the fluctuation index of each O-As expansion degree in the current bituminous coal can be obtained.

[0080] Furthermore, considering that the Oya expansion degree data obtained by the Oya expansion measuring instrument may be interfered by noise, such as environmental noise, such noise may cause noise points in the Oya expansion degree data sequence. The appearance of noise points may cause deviations in the calculation of the above-mentioned volatility index. Therefore, the volatility index needs to be corrected. The specific correction process is as follows:

[0081] First, taking any temperature as the center, a section of temperature is intercepted from the temperature range corresponding to the real-time collected Oya expansion data to obtain a local temperature section, and then the Oya expansion data corresponding to the local temperature section is obtained. The local temperature section can include 21 consecutive temperatures.

[0082] Secondly, the least square method is used to fit the curve of the Oya expansion data corresponding to the local temperature section; during the fitting, the Oya expansion is the ordinate and the temperature and time are the abscissas.

[0083] Then, the absolute value of the difference between the Oya expansion degree and the fitting value in the local temperature section is calculated, and the fluctuation index corresponding to the Oya expansion degree at any temperature is corrected according to the mean of the absolute value of the difference to obtain the corrected fluctuation index.

[0084] Specifically, the modified volatility index for:

[0085] ;

[0086] In the formula, is the Oya expansion corresponding to temperature i The volatility index, represents the fitting value corresponding to the qth Oya expansion degree in the local temperature segment centered at temperature i, is the qth Oya expansion degree in the local temperature range centered at temperature i, exp() is an exponential function with the natural constant e as the base, It represents the total number of Oya expansion degrees in the local temperature range centered on temperature i.

[0087] in, It represents the absolute value of the difference between the fitting value and the actual value of the qth data point in the local range centered on temperature i. The absolute value of the difference is the fitting error. The mean value of the fitting error is used to calculate the Oya expansion degree. The fluctuation index is corrected. When the fitting error is larger, The smaller it is, the greater the degree of noise interference is on the Oya expansion, and the lower the degree of smoothness is, so the greater the degree of correction of the volatility index is, so that the corrected volatility index is smaller.

[0088] In this embodiment, when analyzing the smoothness of the Oya expansion degree, a curve fitting is performed on the Oya expansion degree data in a local range to obtain a fitting error, and the fitting error is used to represent the smoothness, wherein the smaller the fitting error, the better the smoothness.

[0089] The above curve fitting is performed because the emergence of mutation points will affect the fitting process of surrounding data and cause the fitting error to increase. The smoother the Oya expansion data, the smaller the fitting error.

[0090] The reason for the above correction is that, since noise points often appear as mutation points, when there is no noise, the Oya expansion data often shows a smooth change trend, and the appearance of noise breaks this smooth change trend. Therefore, the smoothness of the expansion data in the time series can be used to correct the volatility index. The higher the smoothness, the less the noise affects the current data, the higher the credibility of the volatility index, and the less the volatility index needs to be corrected.

[0091] Step S23, obtaining edge weights according to fluctuation indicators of any two Oya expansion degrees in the Oya expansion degree data corresponding to the current bituminous coal.

[0092] The specific calculation formula of edge weight is:

[0093] ; for , The edge rights, , They are the Oya expansion degree corresponding to temperature i and the Oya expansion degree corresponding to temperature j in the Oya expansion degree data corresponding to the current bituminous coal, , are the Oya expansion corresponding to temperature i The fluctuation index and the Oya expansion degree corresponding to temperature j The volatility indicator, exp() is an exponential function with the natural constant e as the base.

[0094] Among them, when The larger the value of , the lower the edge weight of the Oya expansion degree at the two temperatures, and the lower the similarity of the two data. Conversely, the higher the edge weight.

[0095] Since MST clustering is a clustering method based on graph theory, it discovers natural groups in the data by constructing a minimum spanning tree (MST) between data points. In MST, outliers are usually nodes with higher edge weights connecting to other points, that is, they have lower similarity with other points in the group. Therefore, by calculating edge weights using the above-mentioned volatility indicator method, normal data can be effectively distinguished from abnormal data.

[0096] Step S3, performing anomaly detection on multiple clusters to obtain abnormal data in corresponding clusters.

[0097] The specific process of anomaly detection in this embodiment is as follows:

[0098] In response to the number of nodes in the cluster being greater than the set number, the corresponding cluster is a normal cluster. In response to the number of nodes in the cluster being less than or equal to the set number, the corresponding cluster is a suspected abnormal cluster. An outlier detection algorithm is used to perform abnormality detection on the suspected abnormal cluster to obtain abnormal data.

[0099] The value of the above-mentioned set number can be 3. Of course, it can also be determined according to actual conditions.

[0100] The outlier detection algorithm may be a box plot, an isolation forest algorithm, or a local outlier factor algorithm. For example, taking the local outlier factor algorithm as an example, the local outlier factor of each Oya expansion degree in the suspected abnormal cluster is calculated. When the local outlier factor of any Oya expansion degree is greater than a set value, the any Oya expansion degree is abnormal data, and then all abnormal data are obtained.

[0101] The above setting value can be set to 1, and can also be set according to actual conditions.

[0102] In this embodiment, after detecting an abnormal result, not only can the test environment information be controlled based on the abnormal result feedback, but the quality of the current bituminous coal can also be evaluated based on the normal data obtained and combined with other bituminous coal data, such as the softening point, initial expansion point, solidification point and other key indicators of the bituminous coal.

[0103] Specifically, the test environment information is controlled based on the abnormal result feedback: according to the abnormal data, the gas composition, temperature, humidity and other environmental conditions of the test environment are adjusted to improve the accuracy of subsequent tests on the Oya expansion degree of other bituminous coals.

[0104] For example, since changes in temperature may affect the physical and chemical properties of the coal sample and thus affect the measurement of the Oya expansion, the temperature can be regulated by controlling the temperature field of the furnace.

[0105] The present invention provides a bituminous coal Oya expansion degree monitoring system and method based on big data; the system calculates a fluctuation index by analyzing the change characteristics of Oya expansion degree data and the relationship between bituminous coal Oya expansion degree data at multiple locations, and performs clustering of the MST clustering algorithm based on the difference of the fluctuation index as the measure of edge weight to perform anomaly detection, thereby improving the accuracy of anomaly detection and providing reliable data for subsequent bituminous coal quality evaluation and coal utilization.

[0106] The present invention also provides a bituminous coal Oya expansion degree monitoring system based on big data. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a method for monitoring the expansion degree of bituminous coal based on big data according to the present invention is implemented.

[0107] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0108] In the present invention, 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. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0109] In the description of this specification, "plurality" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0110] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for monitoring the expansion degree of bituminous coal based on big data, characterized in that: include: Obtain the current Oya expansion data of bituminous coal during the heating process; The MST clustering algorithm is used to cluster the Oya expansion degree data and obtain multiple clusters; Perform anomaly detection on multiple clusters to obtain abnormal data in the corresponding clusters; Among them, the edge weight between two nodes corresponding to any two Oya expansion degrees in the clustering process is: ; For edge rights, , are the Oya expansion corresponding to temperature i The fluctuation index and the Oya expansion degree corresponding to temperature j The volatility index, exp() is an exponential function with the natural constant e as the base; The volatility indicators are: Obtain the Oya expansion data of multiple other bituminous coals during the heating process; Calculate the Pearson correlation coefficient of the Oya expansion data of any other bituminous coal in a set temperature range and the current bituminous coal, and use the normalized value of each Pearson correlation coefficient as a weight; the set temperature range is composed of multiple temperatures centered on any temperature; Calculate the absolute value of the difference between the Oya expansion degree of any other bituminous coal and the current bituminous coal at any of the above temperatures; and use various weights to weight all the absolute values ​​of the differences to obtain a fluctuation index.

2. The method for monitoring the expansion degree of bituminous coal based on big data according to claim 1, characterized in that: The method also includes the step of screening multiple other bituminous coals, specifically, sorting all the obtained Pearson correlation coefficients in order from large to small, and selecting other bituminous coals corresponding to the first m Pearson correlation coefficients, where m is greater than 1.

3. A method for monitoring the expansion degree of bituminous coal based on big data according to claim 1 or 2, characterized in that: The weights are: In the formula, represents the weight of the current bituminous coal at temperature i, is the Pearson correlation coefficient of the Oya expansion data of the jth other bituminous coal and the current bituminous coal in the set temperature range centered at temperature i, is the total number of other bituminous coals.

4. The method for monitoring the expansion degree of bituminous coal based on big data according to claim 1, characterized in that: After obtaining the volatility index, the volatility index is corrected to obtain a corrected volatility index. , specifically: In the formula, is the Oya expansion corresponding to temperature i The volatility index, represents the fitting value corresponding to the qth Oya expansion degree in the local temperature section, is the qth Oya expansion degree in the local temperature segment, exp() is an exponential function with the natural constant e as the base, and the local temperature segment is a temperature segment centered on temperature i taken from the current bituminous coal heating process, Indicates the total number of Oya expansion degrees within the local temperature range.

5. The method for monitoring the expansion degree of bituminous coal based on big data according to claim 4 is characterized in that: The process of obtaining the fitting value is: using the least square method to perform curve fitting on all Oya expansion degrees in the local temperature section to obtain the fitting value corresponding to each Oya expansion degree.

6. The method for monitoring the expansion degree of bituminous coal based on big data according to claim 1, characterized in that: The specific process of performing anomaly detection on multiple clusters to obtain abnormal data in the corresponding clusters is as follows: In response to the number of nodes in the cluster being greater than the set number, the corresponding cluster is a normal cluster; in response to the number of nodes in the cluster being less than or equal to the set number, the corresponding cluster is a suspected abnormal cluster; The outlier detection algorithm is used to perform anomaly detection on suspected abnormal clusters to obtain abnormal data.

7. The method for monitoring the expansion degree of bituminous coal based on big data according to claim 6 is characterized in that: The outlier detection algorithm is a box plot, an isolation forest algorithm, or a local outlier factor.

8. A bituminous coal Oya expansion degree monitoring system based on big data, characterized in that: include: processor; A memory storing computer instructions for monitoring the Oya expansion degree of bituminous coal based on big data. When the computer instructions are executed by the processor, the system executes a method for monitoring the Oya expansion degree of bituminous coal based on big data according to any one of claims 1 to 7.

Images