Method and system for extracting support resistance data coal cutting circulation demarcation point

Abstract

The invention discloses a method and system for extracting a support resistance data coal cutting circulation demarcation point, and relates to the technical field of coal mining safety. Comprising the steps of collecting real-time data of a hydraulic support; processing to ensure the integrity and accuracy of the data; fitting the processed data by using a least square method to obtain a fitting function; gaussian filtering processing is adopted to obtain a smooth data function; and traversing a difference value array of the filtering smoothing function and the original fitting function through a heap sorting algorithm, and finding out the first k maximum and non-adjacent difference values and corresponding positions thereof, thereby accurately determining the coal cutting circulation demarcation point. The method effectively solves the problems of poor extraction precision and poor timeliness due to the fact that manual input modes such as frame moving actions are mostly adopted in a traditional method. In addition, the method improves the automation degree of identification of the initial supporting force and the circulating end resistance of the roof in the recovery process, and further promotes the improvement of the intelligent level of roof prevention and control.

Description

Technical Field

[0001] The present invention relates to the technical field of coal mining safety, in particular to a method and system for extracting the coal cutting cycle demarcation point of support resistance data. Background Art

[0002] During the coal mining process, the resistance data of hydraulic supports reflects the change of the support state of the working face. The accurate extraction of the coal cutting cycle demarcation point is of great significance for analyzing the initial support force and final resistance characteristics of the supports in the coal mining face. However, the traditional methods for extracting the coal cutting cycle demarcation point mainly rely on the support moving action or manual marking, and there are the following disadvantages in this method for extracting the coal cutting cycle demarcation point:

[0003] (1) Low extraction accuracy: Manual input or methods based on empirical rules are easily affected subjectively, resulting in inaccurate positioning of the coal cutting cycle demarcation point.

[0004] (2) Poor timeliness: The manual marking process takes a long time and is difficult to meet the real-time requirements.

[0005] (3) Low intelligence level: The traditional methods for extracting the coal cutting cycle demarcation point cannot effectively process the massive data of hydraulic supports, restricting the development of intelligent roof control. Summary of the Invention

[0006] In view of the above problems, the present invention proposes a method and system for extracting the coal cutting cycle demarcation point of support resistance data.

[0007] The embodiment of the present invention provides a method for extracting the coal cutting cycle demarcation point of support resistance data, and the method includes:

[0008] Obtain the real-time data of the hydraulic support;

[0009] Process the real-time data of the hydraulic support to ensure the integrity and accuracy of the real-time data of the hydraulic support;

[0010] Use the least squares method to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function;

[0011] Adopt Gaussian filtering to smooth the fitting function to obtain a Gaussian-filtered smoothed function;

[0012] According to the Gaussian-filtered smoothed function and the fitting function, calculate to obtain a difference function, and the difference function is a discrete array;

[0013] Use the heap sort algorithm to traverse the discrete array of the difference function, find the first k non-adjacent maximum values and their corresponding indexes to form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic support;

[0014] Determine the positioning of the index array in the real-time data of the hydraulic support as the coal cutting cycle demarcation point.

[0015] Optionally, obtain the real-time data of the hydraulic support, including:

[0016] Obtain the resistance data of any one of the hydraulic supports with normal working conditions among all the hydraulic supports;

[0017] Divide the resistance data into several time periods to construct the real-time data of the hydraulic support with continuous time series.

[0018] Optionally, process the real-time data of the hydraulic support, including:

[0019] Perform missing value processing and outlier processing on the real-time data of the hydraulic support.

[0020] Optionally, perform missing value processing on the real-time data of the hydraulic support, including:

[0021] Traverse the real-time data of the hydraulic support to determine whether there are missing values in the real-time data of the hydraulic support;

[0022] If there are missing values in the real-time data of the hydraulic support, based on the time points corresponding to the missing values, combine the real-time data corresponding to the adjacent time points for difference filling to complete the missing values.

[0023] Optionally, perform outlier processing on the real-time data of the hydraulic support, including:

[0024] Traverse the real-time data of the hydraulic support to determine whether there are outliers in the real-time data of the hydraulic support;

[0025] If there are outliers in the real-time data of the hydraulic support, replace the outliers with a value less than the preset value with the preset value.

[0026] Optionally, use the least squares method to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function, including:

[0027] Using the least squares method, by selecting an nth-order polynomial, make the numerical points corresponding to the processed real-time data of the hydraulic support all on the fitting curve, thereby obtaining the fitting function.

[0028] Optionally, according to the Gaussian filter smoothing function and the fitting function, calculate to obtain a difference function, including:

[0029] Perform a subtraction operation on the Gaussian filter smoothing function and the fitting function to obtain the difference function;

[0030] The difference function H(x) is:

[0031]

[0032] In the above formula, S(x) is the Gaussian filtering smoothing function, F(x) is the fitting function, j is the index of the real-time data of the hydraulic support, and F(x j ) is the value of the real-time data of the hydraulic support at x j at, and G(x j -x i ) is the value of the first-order Gaussian function at x j -x i at.

[0033] Optionally, traverse the discrete array of the difference function using the heap sort algorithm to find the first k non-adjacent maximum values and their corresponding indices, and form an index array, including:

[0034] Construct key-value pairs from each element in the discrete array and its corresponding index, and insert them into the max heap to ensure that the top element of the heap is always the current maximum value;

[0035] Pop the top element of the heap one by one, and use a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition;

[0036] If the index corresponding to any top element of the heap meets the preset filtering condition, add the index corresponding to the top element of the heap to the result set until there are k indices in the result set, and the maximum values corresponding to the k indices are the first k non-adjacent maximum values;

[0037] Sort the result set in ascending order of the indices in the set to form the index array.

[0038] Optionally, pop the top element of the heap one by one, and use a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition, including:

[0039] Define a variable to record the index corresponding to each time the top element of the heap is popped;

[0040] After the current top element is taken out of the heap, determine whether the index corresponding to the current top element of the heap is adjacent to the index corresponding to the top element taken out last time;

[0041] If the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element taken out last time is not greater than the threshold, then the two indices are adjacent;

[0042] If the two indices are adjacent, then the index corresponding to the current top element of the heap does not meet the preset filtering condition;

[0043] If the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element of the heap taken out last time is greater than the threshold, then these two indexes are not adjacent;

[0044] If two indexes are not adjacent, then the index corresponding to the current top element of the heap satisfies the preset filtering condition.

[0045] An embodiment of the present invention provides a system for extracting the coal cutting cycle demarcation point of the support resistance data, and the system includes:

[0046] A data acquisition module, configured to acquire real-time data of hydraulic supports;

[0047] A data processing module, configured to process the real-time data of the hydraulic supports to ensure the integrity and accuracy of the real-time data of the hydraulic supports;

[0048] A fitting module, configured to fit the processed real-time data of the hydraulic supports by using the least squares method to obtain a corresponding fitting function;

[0049] A smoothing processing module, configured to process the processed real-time data of the hydraulic supports by using Gaussian filtering to obtain a Gaussian filtering smoothing function;

[0050] A difference function module, configured to calculate a difference function according to the Gaussian filtering smoothing function and the fitting function, and the difference function is a discrete array;

[0051] An index module, configured to traverse the discrete array of the difference function by using the heap sorting algorithm, find the first k non-adjacent maximum values and their corresponding indexes, and form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic supports;

[0052] A demarcation point determination module, configured to determine the positioning of the index array in the real-time data of the hydraulic supports as the coal cutting cycle demarcation point.

[0053] Optionally, the data acquisition module is specifically configured to:

[0054] Acquire the resistance data of any hydraulic support with normal working conditions among all hydraulic supports;

[0055] Divide the resistance data into several time periods, and construct real-time data of the hydraulic supports with continuous time series.

[0056] Optionally, the data processing module is specifically configured to:

[0057] Perform missing value processing and outlier processing on the real-time data of the hydraulic supports.

[0058] Optionally, the data processing module includes: a missing value processing sub-module; the missing value processing sub-module is configured to:

[0059] Traverse the real-time data of the hydraulic support to determine whether there are missing values in the real-time data of the hydraulic support;

[0060] If there are missing values in the real-time data of the hydraulic support, then based on the time points corresponding to the missing values, fill in the differences by combining the real-time data corresponding to adjacent time points to complete the missing values.

[0061] Optionally, the data processing module includes: an outlier processing sub-module; the outlier processing sub-module is used for:

[0062] Traverse the real-time data of the hydraulic support to determine whether there are outliers in the real-time data of the hydraulic support;

[0063] If there are outliers in the real-time data of the hydraulic support, then replace the outliers with a value less than the preset value with the preset value.

[0064] Optionally, the fitting module is specifically used for:

[0065] Using the least squares method, by selecting an nth-order polynomial, make the numerical points corresponding to the processed real-time data of the hydraulic support all on the fitting curve, and then obtain the fitting function.

[0066] Optionally, the difference function module is specifically used for:

[0067] Perform a subtraction operation on the Gaussian filter smoothing function and the fitting function to obtain the difference function;

[0068] The difference function H(x) is:

[0069]

[0070] In the above formula, S(x) is the Gaussian filter smoothing function, F(x) is the fitting function, j is the index of the real-time data of the hydraulic support, F(x j ) is the value of the real-time data of the hydraulic support at x j , G(x j -x i ) is the value of the first-order Gaussian function at x j -x i .

[0071] Optionally, the index module includes:

[0072] Construct an insertion sub-module for constructing key-value pairs of each element in the discrete array and its corresponding index and inserting them into the maximum heap to ensure that the top element of the heap is always the current maximum value;

[0073] A pop-up judgment sub-module, which is used to pop up the top elements of the heap one by one, and use a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition;

[0074] An addition sub-module, which is used to add the index corresponding to the top element to the result set if the index corresponding to any top element meets the preset filtering condition, until there are k indexes in the result set, and the maximum value corresponding to the k indexes is the top k non-adjacent maximum values;

[0075] A sorting sub-module, which is used to sort the result set in ascending order of the indexes in the set to form the index array.

[0076] Optionally, the pop-up judgment sub-module is specifically used for:

[0077] Based on all the maximum values and their corresponding indexes, determine whether the indexes corresponding to each maximum value are adjacent;

[0078] If the difference between the index corresponding to any maximum value and the index corresponding to any other maximum value is less than the threshold, the two indexes with the difference less than the threshold are adjacent;

[0079] If two indexes are adjacent, take the maximum value corresponding to the smaller index as one of the top k non-adjacent maximum values.

[0080] The method for extracting the coal cutting cycle demarcation point of the support resistance data provided by the present invention includes: first, obtaining the real-time data of the hydraulic support; then processing the real-time data of the hydraulic support to ensure the integrity and accuracy of the real-time data of the hydraulic support.

[0081] After that, use the least squares method to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function; then use Gaussian filtering to smooth the fitting function to obtain the Gaussian filtering smoothed function, and calculate the difference function according to the Gaussian filtering smoothed function and the fitting function.

[0082] After obtaining the difference function, use the heap sorting algorithm to traverse the discrete array of the difference function to find the top k non-adjacent maximum values and their corresponding indexes to form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic support; finally, determine the position of the index array in the real-time data of the hydraulic support as the coal cutting cycle demarcation point.

[0083] In view of the problems existing in the traditional method for extracting the cut coal cycle demarcation point, the present invention proposes to collect and preprocess the real-time data of hydraulic supports, and then combine processing methods such as fitting, smoothing, and difference analysis, and use the heap sorting algorithm to accurately extract key points, and finally obtain the accurate cut coal cycle demarcation point. The method for extracting the cut coal cycle demarcation point proposed by the present invention realizes the technical solution of automatically extracting the cut coal cycle demarcation point from the massive data of hydraulic supports in real time, effectively solving the problems of poor extraction accuracy, poor timeliness, and low intelligence level existing in the traditional methods that mostly use manual input methods such as the support moving action. It can significantly improve the extraction accuracy, timeliness, and intelligence level. It improves the automation level of identifying the initial roof support force and the final resistance of the cycle during the coal mining process, further promotes the improvement of the intelligent level of roof control, and then improves the intelligent level of roof control and the safety of coal mining, and further promotes the intelligent process in the field of coal mining, with high practicability. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. And throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0085] Figure 1 is a flowchart of a method for extracting the cut coal cycle demarcation point of the support resistance data according to an embodiment of the present invention;

[0086] Figure 2 is a modular schematic diagram of a system for extracting the cut coal cycle demarcation point of the support resistance data according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0087] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, which is only a part of the embodiments of the present invention, rather than all of the embodiments, and are not used to limit the present invention.

[0088] Referring to Figure 1 , which shows a flowchart of a method for extracting the cut coal cycle demarcation point of the support resistance data according to an embodiment of the present invention. The method for extracting the cut coal cycle demarcation point of the support resistance data includes:

[0089] Step 101: Obtain the real-time data of the hydraulic support.

[0090] The method for extracting the coal cutting cycle demarcation point of the support resistance data proposed by the present invention first requires obtaining the real-time data of the hydraulic support. There are various ways to obtain the real-time data of the hydraulic support. A relatively optimal way to obtain the real-time data of the hydraulic support includes:

[0091] Obtain the resistance data of any one of the hydraulic supports with normal working conditions among all hydraulic supports; that is, obtain the resistance data of any normally working hydraulic support. Then divide these resistance data into several time periods, and construct the real-time data of the hydraulic support in a continuous time series according to the chronological order.

[0092] The process of obtaining the real-time data of the hydraulic support can be combined with devices such as coal mine intelligent monitoring, such as support load sensors, etc., and through these devices, the real-time acquisition of a large amount of real-time data can be realized.

[0093] Step 102: Process the real-time data of the hydraulic support to ensure the integrity and accuracy of the real-time data of the hydraulic support.

[0094] After obtaining the real-time data of the hydraulic support, it is also necessary to process the real-time data of the hydraulic support to ensure the integrity and accuracy of the real-time data of the hydraulic support. Lay a good foundation for the subsequent extraction of the coal cutting cycle demarcation point.

[0095] A relatively optimal method for processing the real-time data of the hydraulic support includes: performing missing value processing and outlier processing on the real-time data of the hydraulic support. For a large amount of real-time data of the hydraulic support, due to various factors, there may be missing values and outliers in these data, and these missing values and outliers may affect the accuracy of subsequent processing. Therefore, it is necessary to process these data.

[0096] For missing values, a relatively optimal method for processing missing values in the real-time data of the hydraulic support includes:

[0097] Traverse all the real-time data of the hydraulic support to determine whether there are missing values in the real-time data of the hydraulic support; since the real-time data of the hydraulic support is formed in chronological order, the presence of missing values in the real-time data of the hydraulic support can be determined through the time correlation.

[0098] If there are missing values in the real-time data of the hydraulic support, based on the time point corresponding to the missing value, combine the real-time data corresponding to the adjacent time points for difference filling to complete the missing values. Naturally, it can be understood that if there are no missing values in the real-time data of the hydraulic support, there is no need for difference filling.

[0099] For outliers, a relatively optimal method for processing outliers in the real-time data of the hydraulic support includes:

[0100] Traverse the real-time data of the hydraulic support to determine whether there are outliers in the real-time data of the hydraulic support. Generally speaking, the real-time resistance of the hydraulic support definitely cannot be a value below 0 tons. Therefore, when a resistance value below 0 appears, it is considered an outlier. Of course, this is just an example. A preset value can be set according to actual experience values. For example, if the preset value is 15 tons, then when the real-time data of the hydraulic support less than 15 tons appears, the real-time data is considered an outlier.

[0101] Therefore, if there are outliers in the real-time data of the hydraulic support, then replace the outliers with a value less than the preset value, for example: replace the real-time data of the hydraulic support less than the preset value of 15 tons with the preset value of 15 tons. Naturally, it can be understood that if there are no outliers in the real-time data of the hydraulic support, there is naturally no need to perform outlier processing.

[0102] Step 103: Use the least squares method to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function.

[0103] After the real-time data of the hydraulic support is processed through the above Step 102, the least squares method can be used to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function. That is, perform fitting analysis on the processed real-time data of the hydraulic support, and use the least squares method to generate the corresponding fitting function. This fitting function can reflect the overall trend of the real-time data of the hydraulic support and reduce noise interference.

[0104] A relatively optimal method for using the least squares method to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function includes:

[0105] Using the least squares method, by selecting an nth-order polynomial, make the numerical points corresponding to the processed real-time data of the hydraulic support all on the fitting curve, and then obtain the fitting function. That is, the fitting function is a polynomial fitting.

[0106] Step 104: Use Gaussian filtering to smooth the fitting function to obtain a Gaussian-filtered smoothed function.

[0107] In addition to fitting the processed real-time data of the hydraulic support to obtain the corresponding fitting function, it is also necessary to use Gaussian filtering to process the processed real-time data of the hydraulic support to obtain a Gaussian-filtered smoothed function. Preferably, a first-order Gaussian filter can be used to smooth the fitting function obtained in Step 103 to obtain the corresponding Gaussian-filtered smoothed function. The purpose of generating the Gaussian-filtered smoothed function is to further eliminate the influence of local fluctuations on the analysis.

[0108] Step 105: Calculate the difference function based on the Gaussian-filtered smoothed function and the fitting function. The difference function is a discrete array.

[0109] After obtaining the Gaussian filter smoothing function and the fitting function, it is creatively proposed that: according to the Gaussian filter smoothing function and the fitting function, a difference function is calculated. Specifically:

[0110] The method for calculating the difference function according to the Gaussian filter smoothing function and the fitting function includes:

[0111] Perform a subtraction operation on the Gaussian filter smoothing function and the fitting function to obtain the difference function; that is: the difference function H(x) is:

[0112]

[0113] In the above formula, S(x) is the Gaussian filter smoothing function, F(x) is the fitting function, j is the index of the real-time data of the hydraulic support, F(x j ) is the value of the real-time data of the hydraulic support at x j , G(x j -x i ) is the value of the first-order Gaussian function at x j -x i . The purpose of obtaining the difference function is to reflect the characteristics of the fluctuations of the real-time data of the hydraulic support.

[0114] Step 106: Use the heap sort algorithm to traverse the discrete array of the difference function, find the first k non-adjacent maximum values and their corresponding indexes, and form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic support.

[0115] After obtaining the difference function through the foregoing steps 101 to 105, since the difference function is a discrete array, the heap sort algorithm is then used to traverse the discrete array of the difference function, and the first k non-adjacent maximum values and their corresponding indexes can be found to form an index array. Among them, k is the total number of coal cutting cycles included in the real-time data of the hydraulic support.

[0116] A better method for using the heap sort algorithm to traverse the discrete array of the difference function, find the first k non-adjacent maximum values and their corresponding indexes, and form an index array includes:

[0117] First, construct key-value pairs for each element in the discrete array and its corresponding index, and insert them into the maximum heap to ensure that the top element of the heap is always the current maximum value; then pop the top element of the heap one by one, and use a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition.

[0118] If the index corresponding to any top element of the heap meets the preset filtering condition, add the index corresponding to the top element of the heap to the result set until there are k indexes in the result set. The maximum values corresponding to the k indexes are the first k non-adjacent maximum values; finally, sort the result set in ascending order of the indexes in the set to form an index array..

[0119] Among them, the method of popping the top element of the heap one by one and using the preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition includes:

[0120] Define a variable, which is used to record the index corresponding to the popped top element each time. After the top element of the heap is taken out this time, determine whether the index corresponding to the current top element of the heap is adjacent to the index corresponding to the top element taken out last time.

[0121] If the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element taken out last time is not greater than the threshold, then these two indexes are adjacent; if two indexes are adjacent, then the index corresponding to the current top element of the heap does not meet the preset filtering condition, and the index corresponding to the current top element of the heap is not added to the result set.

[0122] If the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element taken out last time is greater than the threshold, then these two indexes are not adjacent; if two indexes are not adjacent, then the index corresponding to the current top element of the heap meets the preset filtering condition, and the index corresponding to the current top element of the heap is added to the result set. For example: assuming the threshold is 1, if the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element taken out last time is greater than 1, then these two indexes with a difference greater than 1 are considered non-adjacent indexes.

[0123] Step 107: Determine the position of the index array in the real-time data of the hydraulic support as the coal cutting cycle demarcation point.

[0124] After obtaining the index array, determine the position of the index array in the real-time data of the hydraulic support as the coal cutting cycle demarcation point, so as to obtain an accurate coal cutting cycle demarcation point.

[0125] In addition, for the result of the coal cutting cycle demarcation point obtained in the above process, it can also be optimized and verified, that is: verify and optimize the result of the initially extracted coal cutting cycle demarcation point in combination with expert experience. If the index distance between the obtained coal cutting cycle demarcation points is less than a certain value, the optimal coal cutting cycle demarcation point can be retained.

[0126] Through the above method, the coal cutting cycle demarcation point of the support resistance data can be quickly, effectively and accurately extracted.

[0127] In the embodiment of the present invention, based on the above method for extracting the coal cutting cycle demarcation point of the support resistance data, a system for extracting the coal cutting cycle demarcation point of the support resistance data is also proposed. This system can execute the method for extracting the coal cutting cycle demarcation point of the support resistance data as described in any one of steps 101 to 107 above, and can quickly, effectively and accurately extract the coal cutting cycle demarcation point of the support resistance data. Refer to Figure 2Modular schematic diagram of a system for extracting the coal cutting cycle demarcation point of support resistance data, the system comprising:

[0128] A data acquisition module 210, configured to acquire real-time data of hydraulic supports;

[0129] A data processing module 220, configured to process the real-time data of the hydraulic supports to ensure the integrity and accuracy of the real-time data of the hydraulic supports;

[0130] A fitting module 230, configured to fit the processed real-time data of the hydraulic supports by using the least squares method to obtain a corresponding fitting function;

[0131] A smoothing processing module 240, configured to process the processed real-time data of the hydraulic supports by using Gaussian filtering to obtain a Gaussian filtering smoothing function;

[0132] A difference function module 250, configured to calculate a difference function according to the Gaussian filtering smoothing function and the fitting function, where the difference function is a discrete array;

[0133] An indexing module 260, configured to traverse the discrete array of the difference function by using a heap sorting algorithm to find the first k non-adjacent maximum values and their corresponding indexes to form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic supports;

[0134] A demarcation point determination module 270, configured to determine the positioning of the index array in the real-time data of the hydraulic supports as the coal cutting cycle demarcation point.

[0135] Optionally, the data acquisition module 210 is specifically configured to:

[0136] Acquire the resistance data of any one of the hydraulic supports with normal working conditions among all the hydraulic supports;

[0137] Divide the resistance data into several time periods to construct real-time data of the hydraulic supports in continuous time series.

[0138] Optionally, the data processing module 220 is specifically configured to:

[0139] Perform missing value processing and outlier processing on the real-time data of the hydraulic supports.

[0140] Optionally, the data processing module 220 includes: a missing value processing sub-module; the missing value processing sub-module is configured to:

[0141] Traverse the real-time data of the hydraulic supports to determine whether there are missing values in the real-time data of the hydraulic supports;

[0142] If there are missing values in the real-time data of the hydraulic support, interpolation filling is performed based on the time points corresponding to the missing values in combination with the real-time data corresponding to adjacent time points to complete the missing values.

[0143] Optionally, the data processing module 220 includes: an outlier processing sub-module; the outlier processing sub-module is configured to:

[0144] Traverse the real-time data of the hydraulic support to determine whether there are outliers in the real-time data of the hydraulic support;

[0145] If there are outliers in the real-time data of the hydraulic support, the outliers with values less than the preset value are replaced with the preset value.

[0146] Optionally, the fitting module 230 is specifically configured to:

[0147] Using the least squares method, by selecting an nth-order polynomial, the numerical points corresponding to the processed real-time data of the hydraulic support are all on the fitting curve, and then the fitting function is obtained.

[0148] Optionally, the difference function module 250 is specifically configured to:

[0149] Perform a subtraction operation on the Gaussian filter smoothing function and the fitting function to obtain the difference function;

[0150] The difference function H(x) is:

[0151]

[0152] In the above formula, S(x) is the Gaussian filter smoothing function, F(x) is the fitting function, j is the index of the real-time data of the hydraulic support, and F(x j ) is the value of the real-time data of the hydraulic support at x j , and G(x j - x i ) is the value of the first-order Gaussian function at x j - x i .

[0153] Optionally, the index module 260 includes:

[0154] A construction and insertion sub-module, configured to construct key-value pairs of each element in the discrete array and its corresponding index and insert them into the max heap to ensure that the top element of the heap is always the current maximum value;

[0155] A pop-up judgment sub-module, configured to pop the top element of the heap one by one and use a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition;

[0156] A sub-module is added, which is used to add the index corresponding to any top element to the result set if the index corresponding to any top element meets the preset filtering condition, until there are k indexes in the result set, and the maximum value corresponding to these k indexes is the top k non-adjacent maximum values.

[0157] A sorting sub-module is used to sort the result set in ascending order of the indexes in the set to form the index array.

[0158] Optionally, the pop judgment sub-module is specifically used for:

[0159] Based on all the maximum values and their corresponding indexes, determine whether the indexes corresponding to each maximum value are adjacent.

[0160] If the difference between the index corresponding to any maximum value and the index corresponding to any other maximum value is less than the threshold, the two indexes with the difference less than the threshold are adjacent.

[0161] If two indexes are adjacent, take the maximum value corresponding to the smaller index as one of the top k non-adjacent maximum values.

[0162] In summary, the method for extracting the coal cutting cycle demarcation point of the support resistance data provided by the present invention includes: first, obtaining the real-time data of the hydraulic support; then processing the real-time data of the hydraulic support to ensure the integrity and accuracy of the real-time data of the hydraulic support.

[0163] After that, use the least squares method to fit the processed real-time data of the hydraulic support to obtain the corresponding fitting function; then use Gaussian filtering to smooth the fitting function to obtain the Gaussian filtering smoothed function, and calculate the difference function based on the Gaussian filtering smoothed function and the fitting function. The difference function is a discrete array.

[0164] After obtaining the difference function, use the heap sort algorithm to traverse the discrete array of the difference function to find the top k non-adjacent maximum values and their corresponding indexes to form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic support; finally, determine the positioning of the index array in the real-time data of the hydraulic support as the coal cutting cycle demarcation point.

[0165] In view of the problems existing in the traditional method for extracting the demarcation points of coal cutting cycles, the present invention proposes to collect and preprocess the real-time data of hydraulic supports, and then, through processing methods such as fitting, smoothing, and difference analysis, use the heap sorting algorithm to accurately extract key points, and finally obtain accurate demarcation points of coal cutting cycles. The method for extracting the demarcation points of coal cutting cycles proposed by the present invention realizes the technical solution of automatically and real-time extracting the demarcation points of coal cutting cycles from the massive data of hydraulic supports, effectively solving the problems of poor extraction accuracy, poor timeliness, and low intelligence level existing in the traditional methods that mostly adopt manual input methods such as the support moving operation. It can significantly improve the extraction accuracy, timeliness, and intelligence level. It improves the automation degree of identifying the initial roof support force and the final resistance of the cycle during the coal winning process, further promotes the improvement of the intelligent level of roof control, and thus improves the intelligent level of roof control and the safety of coal mining, further promoting the intelligent process in the field of coal mining, and has high practicability.

[0166] Although the preferred embodiments of the embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concepts. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

[0167] Finally, it should also be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or terminal device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or terminal device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the existence of additional identical elements in the process, method, article or terminal device comprising the element.

[0168] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims. All of these are within the protection scope of the present invention.

Claims

1. A method for extracting the cut coal cycle demarcation point of support resistance data, characterized in that, The method includes: Obtaining real-time data of hydraulic supports; Processing the real-time data of the hydraulic supports to ensure the integrity and accuracy of the real-time data of the hydraulic supports; Using the least squares method to fit the processed real-time data of the hydraulic supports to obtain a corresponding fitting function; Performing smoothing processing on the fitting function by using Gaussian filtering to obtain a Gaussian filtering smoothed function; According to the Gaussian filtering smoothed function and the fitting function, calculating a difference function, and the difference function is a discrete array; Using the heap sort algorithm to traverse the discrete array of the difference function, finding the first k non-adjacent maximum values and their corresponding indexes to form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic supports; Determining the positioning of the index array in the real-time data of the hydraulic supports as the coal cutting cycle demarcation point.

2. The method according to claim 1, wherein Obtaining real-time data of hydraulic supports includes: Obtaining the resistance data of any hydraulic support with normal working conditions among all hydraulic supports; Dividing the resistance data into several time periods to construct real-time data of the hydraulic supports with continuous time series.

3. The method according to claim 1, wherein Processing the real-time data of the hydraulic supports includes: Performing missing value processing and outlier processing on the real-time data of the hydraulic supports.

4. The method according to claim 3, characterized in that Performing missing value processing on the real-time data of the hydraulic supports includes: Traversing the real-time data of the hydraulic supports to determine whether there are missing values in the real-time data of the hydraulic supports; If there are missing values in the real-time data of the hydraulic supports, then based on the time points corresponding to the missing values, combining the real-time data corresponding to adjacent time points for difference filling to complete the missing values.

5. The method according to claim 3, characterized in that, Performing outlier processing on the real-time data of the hydraulic supports includes: Traversing the real-time data of the hydraulic supports to determine whether there are outliers in the real-time data of the hydraulic supports; If there are outliers in the real-time data of the hydraulic supports, then replacing the outliers with a value less than the preset value with the preset value.

6. The method according to claim 1, characterized in that, Using the least squares method to fit the processed real-time data of the hydraulic supports to obtain a corresponding fitting function includes: Using the least squares method, by selecting an nth-order polynomial, making the numerical points corresponding to the processed real-time data of the hydraulic supports all on the fitting curve, and then obtaining the fitting function.

7. The method according to claim 1, characterized in that, According to the Gaussian filtering smoothed function and the fitting function, calculating a difference function includes: Performing a subtraction operation on the Gaussian filtering smoothed function and the fitting function to obtain the difference function; The difference function H(x) is: In the above formula, S(x) is the Gaussian filtering smoothing function, F(x) is the fitting function, j is the index of the real-time data of the hydraulic support, and F(x j ) is the value of the real-time data of the hydraulic support at x j . G(x j - x i ) is the value of the first-order Gaussian function at x j - x i .

8. The method according to claim 1, wherein Using the heap sort algorithm to traverse the discrete array of the difference function, finding the first k non-adjacent maximum values and their corresponding indexes includes: Constructing key-value pairs for each element in the discrete array and its corresponding index and inserting them into the max heap to ensure that the top element of the heap is always the current maximum value; Popping the top element of the heap one by one and using a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition; If the index corresponding to any top element of the heap meets the preset filtering condition, then adding the index corresponding to the top element of the heap to the result set until there are k indexes in the result set, and the maximum values corresponding to the k indexes are the first k non-adjacent maximum values; Arrange the result set in ascending order of the centralized index to form the index array.

9. The method according to claim 8, characterized in that, Pop the top element of the heap one by one, and use a preset filtering condition to determine whether the index corresponding to each top element of the heap meets the preset filtering condition, including: Define a variable to record the index corresponding to each time the top element of the heap is popped. After the top element of the heap is taken out this time, judge whether the index corresponding to the current top element of the heap is adjacent to the index corresponding to the top element of the heap taken out last time. If the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element of the heap taken out last time is not greater than the threshold, then these two indexes are adjacent. If two indexes are adjacent, then the index corresponding to the current top element of the heap does not meet the preset filtering condition. If the difference between the index corresponding to the current top element of the heap and the index corresponding to the top element of the heap taken out last time is greater than the threshold, then these two indexes are not adjacent. If two indexes are not adjacent, then the index corresponding to the current top element of the heap meets the preset filtering condition.

10. A system for extracting the cut coal cycle demarcation point of support resistance data, characterized in that, The system includes: A data acquisition module for acquiring real-time data of hydraulic supports. A data processing module for processing the real-time data of the hydraulic supports to ensure the integrity and accuracy of the real-time data of the hydraulic supports. A fitting module for fitting the processed real-time data of the hydraulic supports using the least squares method to obtain a corresponding fitting function. A smoothing processing module for processing the processed real-time data of the hydraulic supports using Gaussian filtering to obtain a Gaussian filtering smoothing function. A difference function module for calculating a difference function based on the Gaussian filtering smoothing function and the fitting function, and the difference function is a discrete array. An index module for traversing the discrete array of the difference function using a heap sort algorithm to find the first k non-adjacent maximum values and their corresponding indexes to form an index array, where k is the total number of coal cutting cycles included in the real-time data of the hydraulic supports. A demarcation point determination module for determining the positioning of the index array in the real-time data of the hydraulic supports as the coal cutting cycle demarcation point.

Images