Coal cutting circulation analysis method based on pressure data of hydraulic support of fully mechanized coal mining face

Abstract

The invention relates to a coal cutting circulation analysis method based on pressure data of hydraulic supports of a fully mechanized coal mining face, and belongs to the technical field of coal cutting circulation analysis. The coal cutting circulation analysis method comprises the following steps: S1, collecting pressure monitoring data of each hydraulic support of the fully mechanized coal mining face to form a data set D; s2, the data set D is preprocessed; s3, calculating the number of times of the initial supporting force of each support by using the initial supporting force identification model; and S4, counting the mode of the number of times of the initial supporting force of all supports according to shifts, and taking the mode as the number of coal cutting cycles of the shifts.

Description

Technical Field

[0001] The present invention belongs to the technical field of coal cutting cycle analysis, and relates to a coal cutting cycle analysis method based on pressure data of hydraulic support of fully mechanized mining working face. Background Art

[0002] With the rapid development of automation and information technology in comprehensive mechanized coal mining (comprehensive mining) working faces, more and more comprehensive mining working faces have introduced electric hydraulic control hydraulic support systems, and widely integrated column pressure and hydraulic support status monitoring sensor networks. These high-precision sensor systems continuously and automatically collect and store monitoring data, significantly enhancing the collection accuracy and operating efficiency of hydraulic support operation data, and building a solid data support platform for in-depth research on the working resistance characteristics of hydraulic supports. However, there is still a technical gap in the automatic monitoring and analysis of coal cutting cycles in the current comprehensive mining working faces. The method of relying on manual counting of the number of coal cutting cycles is not only inefficient, but also easily leads to lags, errors, and even omissions and concealments in data reporting, which seriously affects the timeliness and accuracy of production management.

[0003] The existing coal cutting cycle analysis method uses data with too obvious regularity, high data quality, and obvious initial support and resistance reduction characteristics. However, in the actual production process, when the hydraulic support is moved, it is often not moved in place, resulting in multiple moves in a short time, the support is moved under pressure, and the initial support and resistance reduction characteristics are not obvious. These factors undoubtedly add difficulty to the accurate analysis of the initial support force of the support and the number of coal cutting cycles. Summary of the invention

[0004] In view of this, the object of the present invention is to provide a coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining working face.

[0005] In order to achieve the above object, the present invention provides the following technical solutions:

[0006] A coal cutting cycle analysis method based on hydraulic support pressure data of a fully mechanized mining face comprises the following steps:

[0007] S1: Collect the pressure monitoring data of each hydraulic support in the fully mechanized mining working face to form a data set D;

[0008] S2: preprocessing the data set D;

[0009] S3: using the initial support force identification model to calculate the number of initial support forces for each bracket;

[0010] S4: Count the mode of the initial support force times of all supports by shift, which is taken as the number of coal cutting cycles of the shift.

[0011] Furthermore, the pressure monitoring data of each hydraulic support of the fully mechanized mining working face collected in step S1 includes the collection time collectTime and the pressure value value of each support pressure data.

[0012] Further, the preprocessing in step S2 includes the following steps:

[0013] S21: Resample the data set D and convert it into a sequence with a regular interval time of T;

[0014] S22: Calculate the average value of the resampled data;

[0015] S23: Use linear interpolation to fill in missing values ​​to obtain a new data set D′.

[0016] Furthermore, in step S2, the time series data is first converted to a fixed time interval T. If the original data point D(t) exists at time t, then at the resampled time point t i Make a judgment at i If t matches the time of an original data point, the data point is used directly; i If it falls between two original data points, linear interpolation is used to fill it;

[0017] The average value calculation method includes:

[0018] If at a certain resampling time interval [t i ,t i +T] has multiple original data points D(t i ), where t i ≤t j <t i +T, the data value of this interval is expressed as the average value of these points, which can be expressed by the following formula:

[0019]

[0020] Where N is the number of original data points in the time interval;

[0021] The method of filling using linear interpolation includes:

[0022] At two known data points D(t a ) and D(t b ) at any time point t c , where t a <t c <t b , the interpolated value D(t c ) is expressed as:

[0023]

[0024] Further, the calculation of the number of initial support forces of each bracket using the initial support force identification model in step S3 specifically includes the following steps:

[0025] S31: Identify the local minimum point of the pressure value during the coal cutting cycle;

[0026] S32: screening the local minimum point;

[0027] S33: Identify the initial support force of the support.

[0028] Further, in step S31, identifying the local minimum point by using a local minimum point algorithm includes the following steps:

[0029] S311: Initialize a sliding window of 3 elements and traverse the entire data sequence;

[0030] S312: for each window, check whether there is a local minimum value less than 15; if there is, further look ahead to the next window of the same size to determine whether the minimum value inside it is greater than the minimum value of the current window; when the local minimum value of the current window is a relatively low point, and there is no lower point in the window immediately following it, the minimum value in the current window is determined as a valid local minimum point and collected into the output list;

[0031] S313: Move the sliding window forward in a jump manner by a distance twice the window size, and execute steps S312-S313 in a loop until the entire data sequence is completely scanned, and output an output list consisting of all valid local minimum points.

[0032] Further, in step S32, the local minimum point is screened by a filtering algorithm, including the following steps:

[0033] S321: using the index position and specific value of each local minimum point as the input of the filtering algorithm, wherein the index position uses the number of minutes for collecting the corresponding local minimum point as the index value;

[0034] S322: Traverse the input local minimum points in order, compare the index position differences of adjacent local minimum points, and eliminate the local minimum points whose distance from the previous local minimum point is less than 40 units, so as to select the bracket unloading time that meets the actual situation in the data.

[0035] Further, in step S33, the initial support force of the bracket is identified by using an initial support force identification algorithm, which specifically includes the following steps:

[0036] S331: using the pressure value when the support is unloaded and the corresponding index value as a dictionary and inputting it into the initial support force recognition algorithm;

[0037] S332: traverse the keys in the dictionary and define a sub-dataset for each key; the key is the input index value;

[0038] S333: sliding a fixed-size window on the input pressure value of the bracket when unloading, calculating the absolute differences between adjacent data points in each window, and making decisions based on these differences;

[0039] S334: If all the differences are greater than 0.5, the window continues to move forward; if all the differences are less than 0.5, the first data point of the current window is considered to be the initial support force value, and its index is recorded;

[0040] S335: If there is a change between the difference values, the window continues to move forward, and once the initial support force value is found, the initial support force value and its index position in the original data are recorded;

[0041] S336: Store all the initial support force values ​​and their indexes found in a new dictionary, where the key is the adjusted index position and the value is the initial support force value itself.

[0042] The beneficial effect of the present invention is that the present invention realizes real-time monitoring and intelligent prediction of the number of coal cutting cycles through the introduction of big data technology, which can not only promote the scientific and refined production decision-making, but also effectively warn of potential safety risks. Specifically, when abnormal fluctuations in the number of coal cutting cycles are detected, such as a significant increase, it may indicate that the geological conditions of the working face have deteriorated, the performance of the equipment has declined, or there are other safety hazards, thereby triggering an immediate response mechanism and taking necessary preventive measures to avoid the occurrence of production accidents and ensure the safe and stable progress of comprehensive mining operations.

[0043] Other advantages, objectives and features of the present invention will be described in the following description to some extent, and to some extent, will be obvious to those skilled in the art based on the following examination and study, or can be taught from the practice of the present invention. The objectives and other advantages of the present invention can be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be described in detail below in conjunction with the accompanying drawings, wherein:

[0045] Figure 1 It is a flow chart of the coal cutting cycle analysis method based on the pressure data of hydraulic support in fully mechanized mining working face;

[0046] Figure 2 There are two cases for uninstallation;

[0047] Figure 3This is the initial support force identification diagram;

[0048] Figure 4 This is the PT timing diagram. DETAILED DESCRIPTION

[0049] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner, and the following embodiments and features in the embodiments can be combined with each other without conflict.

[0050] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0051] In the following description, numerous details are discussed to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.

[0052] like Figure 1 As shown, the present invention provides a coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining working face, comprising the following steps:

[0053] Step 1: Collect the pressure monitoring data of each hydraulic support in the fully mechanized mining working face to form a data set D, which contains the collection time collectTime and pressure value value of each support pressure data.

[0054] Step 2: Resample the data set. Due to the complex production environment, there may be data loss or inconsistent data collection frequency during the support pressure data collection process. Therefore, after collecting the data set D, the data set is first converted into a regular N-minute interval time series, where N can be customized and is usually set to 30s or 1 minute. The present invention sets the resampling time frequency to 1 minute. During the resampling process, since the original data may not be collected completely at a frequency of every N minutes, many missing time points will be generated. In order to deal with these missing time points, the average value of the resampled data is first calculated. This is because there may be multiple original data points in the same time interval, and the average value can provide comprehensive information within the time period. However, since the original data may be irregular, some N-minute time intervals may have no data points, so after calculating the average value, there will still be missing values. In order to solve this problem, the present invention uses linear interpolation to fill in null values ​​to obtain a new data set D′, which estimates the missing values ​​based on the linear relationship between the two closest valid values ​​before and after the missing value. In this way, not only the data is converted into a regular time series, but also the missing values ​​are filled, ensuring the continuity and integrity of the data. The data resampling calculation method is as follows:

[0055] For time series data, we want to convert it to a fixed time interval T, such as every N minutes. If the original data point D(t) exists at time t, then at the resampled time point t i Make a judgment at i If the time matches that of an original data point, the data point is used directly; otherwise, if t i If the value falls between two original data points, interpolation is needed to fill it.

[0056] ①The average value is calculated as follows:

[0057] If at a certain resampling time interval [t i ,t i +T] has multiple original data points D(t i ), where t i ≤t j <t i +T, the data value of this interval can be expressed as the average value of these points, which can be expressed by the following formula:

[0058]

[0059] Where N is the number of original data points in the time interval.

[0060] ②The linear interpolation filling calculation method is as follows:

[0061] At two known data points D(t a) and D(t b ) at any time point t c (where t a <t c <t b ), the interpolated value D(t c ) can be expressed as:

[0062]

[0063] Step 3: Use the initial support force identification algorithm to identify the data set D'. The algorithm can use real-time data for streaming calculations, or use historical data for calculations. The present invention does not focus on the calculation method, but only describes the calculation method.

[0064] (1) Local minimum point identification

[0065] The support unloading and lowering is the end stage of the coal cutting cycle. At this time, the pressure value of the support is the lowest value, that is, in each coal cutting cycle, the pressure value at the moment of support unloading is the lowest point in the coal cutting cycle. When the support is completely unloaded, the pressure is between 0 and 2MPa; when it is not completely unloaded (due to the need to break the roof or operating habits, resulting in pressure-induced support movement), the maximum pressure requirement for the support to be moved is 15MPa, that is, the pressure value at this moment is roughly 10 to 15MPa. The two pressure conditions are as follows: Figure 2 shown.

[0066] However, the pressure-shifting situation reflected in the image may be caused by the frequency of data acquisition. For example, the data acquisition frequency used in the present invention is 1 minute, but in fact it may only take tens of seconds for the support to be completely decompressed and moved (the time from complete decompression to complete frame movement is usually 30s to 5 minutes). However, this does not affect our coal cutting cycle analysis, because the force of the support pressure is within 15MPa whether it is completely decompressed or under pressure, that is, 15MPa becomes the threshold for finding the local minimum point.

[0067] Local minimum point algorithm description: Define the find_local_lowest_point function, which is used to find the local minimum point from a given data sequence. The function first initializes a sliding window of size 3 elements and traverses the entire data sequence. For each window, the function checks whether there is a local minimum value less than 15. If such a local minimum value exists, the function will further look forward to the next window of the same size to determine whether the minimum value inside it is greater than the minimum value of the current window. Only when this condition is met, that is, the local minimum value of the current window is indeed a relative low point, and there is no lower point in the window that follows it, the minimum value in the current window will be recognized as a valid local minimum point and collected in the output list. Subsequently, in order to avoid repeated calculation of the confirmed local minimum point and its adjacent area, the function will jump forward the sliding window by twice the window size. This process continues until the entire data sequence is completely scanned, and finally the function returns a list of all valid local minimum points.

[0068] Specific operations:

[0069] ① Initialize variables:

[0070] i: is an index variable used to track the current position in the data sequence.

[0071] window_size: defines the size of the sliding window, which is 3 here.

[0072] local_lowest_points: is a dictionary that stores all the local lowest points found and the index of the point.

[0073] flag: is a Boolean variable used to mark whether a local minimum has been found and the minimum value of its next window has not decreased.

[0074] ②Main loop:

[0075] The loop condition is i+window_size<=len(data), which means that the loop will continue to execute when the end of the window does not exceed the length of the data sequence.

[0076] ③Window data extraction:

[0077] In each loop, a window data window_data of size window_size is extracted.

[0078] ④Find local minimum:

[0079] Calculate the minimum value local_min in the window and the index value of the point.

[0080] ⑤Determine the local minimum point:

[0081] If local_min is less than 15, the program will further check the minimum value of the next window, next_min, and make another judgment.

[0082] If next_min is less than local_min, it means that the condition for the local minimum is not met, so continue is used to skip the remainder of the current loop and continue to the next loop.

[0083] Otherwise, that is, next_min is not less than local_min, a local minimum point is considered to be found, the point value and index are added to local_lowest_points, and flag is set to True.

[0084] ⑥Update index i:

[0085] If flag is True, it means that a local minimum point is found, so i is updated to i+2*window_size to skip the data of the current window and its next window to prevent repeated calculations. If flag is False, i is updated to i+window_size, which is a regular window movement.

[0086] ⑦Reset flag:

[0087] Before the end of each loop, reset the flag to False so that the local minimum point can be correctly determined in the next loop.

[0088] ⑧Return result:

[0089] When the loop ends, the function returns a list local_lowest_points containing all local minimum points found.

[0090] (2) Data Filtering

[0091] The width of the fully mechanized mining face is usually set to 200 to 300 meters, and it takes at least 40 minutes to cut coal once, that is, the time interval of a single coal cutting cycle is at least 40 minutes. However, in actual production, the frame may be moved multiple times in a short period of time due to reasons such as the frame not being moved in place once, so it is necessary to screen the local minimum point obtained in the previous step.

[0092] Filtering algorithm description: In the present invention, the frequency of data collection is 1 minute, so the index value corresponding to each lowest point is the number of minutes. The function receives a dictionary as input, where the key of the dictionary represents the index position of the data point, and the value is the specific value of these points. Then, the function traverses these points in order, and by comparing the index position difference of adjacent points, eliminates those points that are less than 40 units away from the previous point, so as to filter the data in the data The stent unloading moment that conforms to the actual situation.

[0093] The specific operations are as follows:

[0094] ① Initialize variables:

[0095] filtered_points: Initialized as an empty dictionary to store filtered key-value pairs.

[0096] previous_key and previous_value: Initialized to None, used to store the last key-value pair added to filtered_points for easy comparison.

[0097] ②Traverse the keys of the dictionary:

[0098] Use sorted(turning_points_dict.keys()) to ensure that the dictionary keys (i.e. index positions) are traversed in ascending order. Explicit sorting ensures that the data is processed in index order in all cases.

[0099] ③ Check and filter key-value pairs:

[0100] For each key in the dictionary, get the corresponding value.

[0101] The conditional judgment (previous_key is None or (key-previous_key)>=40) is used to determine whether to add the current key-value pair to filtered_points:

[0102] If previous_key is still None, it means this is the first iteration and the current key-value pair is automatically added.

[0103] If the difference between the current key key and the previous key previous_key is greater than or equal to 40, the current key-value pair is retained; otherwise, the current key-value pair is skipped because it is too close to the previous point.

[0104] ④Update state variables:

[0105] If the current key-value pair is added to filtered_points, update previous_key and previous_value to the current key-value pair for comparison in the next iteration.

[0106] ⑤Return result:

[0107] The function finally returns the filtered_points dictionary, which contains the key-value pairs of all filtered local minimum points.

[0108] (3) Initial support force identification

[0109] When the support is initially supported, there are usually two situations. One is that the pressure value rises rapidly from the lowest point in a short period of time, reaches a stable state, and then the pressure value rises slowly or remains stable, which is a direct resistance increase phenomenon; the other is that the pressure value rises rapidly from the lowest point in a short period of time, reaches a stable state, and then slowly decreases within 1-5 minutes, with the decrease mostly being 0.5-3MPa, and then slowly increases or remains stable, which is the initial support resistance reduction phenomenon. Therefore, summarizing the two initial support situations, it can be found that from the unloading of the support to the initial support, the pressure value experiences a rapid growth period, and then enters a relatively stable stage, at which time the curve changes relatively slowly. This may be because the support has reached a state of force balance with the top plate, or the hydraulic system has entered the pressure maintenance stage, and only small adjustments are made to maintain a constant pressure level.

[0110] Initial support force identification algorithm description: Through the previous step, a dictionary containing the pressure values ​​and corresponding index values ​​when the bracket is unloaded is obtained. Traverse the keys of the dictionary, define a sub-dataset for each key (from key + 1 to key + 15), extract the bracket pressure data from this sub-dataset, and then search for the initial support force value. It slides on the data through a fixed-size window (the default size is 3), and the step size of each movement is 2. In each window, the function calculates the absolute difference between adjacent data points and makes decisions based on these differences. If all differences are greater than 0.5, the window continues to move forward; if all differences are less than 0.5, the first data point of the current window is considered to be the initial support force value, and its index is recorded; if there is a significant change between the difference values ​​(the first one is larger than the second one or vice versa), the window will continue to move forward. Once the initial support force value is found, the function returns the value and its index position in the original data. Finally, the obtained results (initial support value and its index) are stored in a new dictionary result_data, where the key is the adjusted index position (that is, the original key value plus the index offset of the initial support value) and the value is the initial support value itself.

[0111] Specific operations:

[0112] ①Define init_support_points_find(filter_data,col_name) This function is used to find multiple initial support points from a larger data set and return a dictionary containing the value of each initial support point and its adjusted index position.

[0113] ②Initialize an empty dictionary result_data to store the results.

[0114] ③Traverse the keys of filter_data, each key is regarded as the starting index of the data fragment.

[0115] ④For each key, define a data segment ranging from key+1 to key+15.

[0116] ⑤Extract the data of the specified column col_name from the data fragment and convert it into a list format.

[0117] ⑥Call the init_support_point_calc function, pass in the data fragment, and obtain the initial support point and its index.

[0118] ⑦ Store the value of the initial support point and the adjusted index (original key value plus the initial support point index) into result_data.

[0119] ⑧After completing the traversal, return a dictionary containing all initial support points and their locations.

[0120] ⑨Define init_support_point_calc(data) The goal of this function is to find the "initial support" point from a given one-dimensional data list, that is, the starting point where the pressure value change in the data sequence begins to become stable.

[0121] ⑩ Initialize variables i, window_size, step, init_support, init_support_index, which are used to track the current position of data traversal, window size, step length of window movement, initial support value and its index in the data.

[0122] Use a while loop to traverse the data, fix the window size to 3, and move 2 positions each time.

[0123] In each window, the absolute differences between adjacent data points are calculated to form a diff list.

[0124] If all differences in diff are greater than 0.5, it indicates that the data is still in a stage of drastic changes and the window continues to move.

[0125] If all the differences in diff are less than 0.5, the data is considered to be beginning to stabilize. At this time, the starting position of the window is the initial support point. The value and index of this point are saved, and the loop is exited.

[0126] If there is a significant change between the diff values ​​(the first difference is greater than the second or vice versa), it indicates that the data change pattern is unstable and the window continues to move.

[0127] The function returns the initial support value and its index position in the data.

[0128] Taking a certain bracket as an example, the initial support force identification diagram is as follows: Figure 3 shown.

[0129] Step 4: Group the data set by shift. Usually there are two or three shifts in a day. Most coal mines have production shifts from 0:00 to 8:00, maintenance shifts from 8:00 to 16:00, and production shifts from 16:00 to 24:00. Frequent rack shifting mostly occurs in the production shift. Through the above steps, the initial support force of all supports in the entire working face is identified, and then the initial support force points of each support in each shift are counted in the init_support_data set. Finally, the mode of the initial support force points of each shift in the set is counted as the number of coal cutting cycles for the shift.

[0130] Example:

[0131] The present invention takes 119 groups of hydraulic supports in the 81308 working face of a mine as an example, and selects the pressure data of 20 groups of supports from 70 to 89 from 0:00 to 24:00 on May 15, 2023. The 20 groups of pressure data are plotted into a PT time series diagram, such as Figure 4 shown.

[0132] It can be seen from the figure that there is a clear periodicity. The coal cutting cycle occurs frequently from 0:00 to 9:00 and from 17:00 to 24:00, while the support is basically not moved from 9:00 to 17:00. This is consistent with the start time of the production shift and maintenance shift arranged for this working face of the mine.

[0133] Through the above steps, the number of times the 20 sets of brackets were moved in each shift was counted, and Table 1 was obtained.

[0134] Table 1

[0135]

[0136] From the analysis of Table 1, we can get that the mode of the number of frame shifts from 0:00 to 8:00 is 5, the mode of the number of frame shifts from 8:00 to 16:00 is 0, and the mode of the number of frame shifts from 16:00 to 24:00 is 4. That is, from 0:00 to 24:00 on a certain day, the working face has a total of 9 coal cutting cycles, which is consistent with the number of coal cutting cycles filled in the system on that day.

[0137] In the above embodiments, the description's reference to "this embodiment" indicates that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least some embodiments, but not necessarily all embodiments. Multiple occurrences of "this embodiment" do not necessarily all refer to the same embodiment.

[0138] In the above-described embodiments, although the invention has been described in conjunction with specific embodiments of the invention, many substitutions, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other storage structures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed. Embodiments of the invention are intended to encompass all such substitutions, modifications, and variations that fall within the broad scope of the appended claims.

[0139] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, any one of the methods in this embodiment is implemented.

[0140] This embodiment also provides an electronic terminal, including: a processor and a memory;

[0141] The memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the terminal executes any one of the methods in this embodiment.

[0142] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0143] The electronic terminal provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run computer programs so that the electronic terminal executes each step of the above method.

[0144] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0145] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0146] The present invention can be used in many general or special computing system environments or configurations, such as personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and the like.

[0147] The present invention may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the purpose and scope of the technical solution, which should be included in the scope of the claims of the present invention.

Claims

1. A coal cutting cycle analysis method based on the pressure data of hydraulic support in fully mechanized mining working face, characterized by: The following steps are involved: S1: Collect the pressure monitoring data of each hydraulic support in the fully mechanized mining face to form a data set D; S2: preprocessing the data set D; S3: using the initial support force identification model to calculate the number of initial support forces for each bracket; S4: Count the mode of the initial support force times of all supports by shift, which is taken as the number of coal cutting cycles of the shift.

2. The coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining working face according to claim 1 is characterized in that: The pressure monitoring data of each hydraulic support of the fully mechanized mining working face collected in step S1 includes the collection time collectTime and the pressure value value of each support pressure data.

3. The coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining working face according to claim 1 is characterized in that: The pre-processing in step S2 comprises the following steps: S21: Resample the data set D and convert it into a sequence with a regular interval time of T; S22: Calculate the average value of the resampled data; S23: Use linear interpolation to fill in missing values ​​to obtain a new data set D′.

4. The coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining working face according to claim 3 is characterized in that: In step S2, the time series data is first converted to a fixed time interval T. If the original data point D(t) exists at time t, then at the resampled time point t i Make a judgment at i If the time matches that of an original data point, the data point is used directly; If t i If it falls between two original data points, linear interpolation is used to fill it; The average value calculation method includes: If at a certain resampling time interval [t i , t i +T] has multiple original data points D(t i ), where t i ≤t j <t i +T, the data value of this interval is expressed as the average value of these points, which can be expressed by the following formula: Where N is the number of original data points in the time interval; The method of filling using linear interpolation includes: At two known data points D(t a ) and D(t b ) at any time point t c , where t a <t c <t b , the interpolated value D(t c ) is expressed as:

5. The coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining working face according to claim 1 is characterized in that: The step S3 uses the initial support force identification model to calculate the number of initial support forces for each bracket, which specifically includes the following steps: S31: Identify the local minimum point of the pressure value during the coal cutting cycle; S32: screening the local minimum point; S33: Identify the initial support force of the support.

6. The coal cutting cycle analysis method based on the pressure data of the hydraulic support of the fully mechanized mining face according to claim 5 is characterized in that: In step S31, the local minimum point is identified by a local minimum point algorithm, including the following steps: S311: Initialize a sliding window of 3 elements and traverse the entire data sequence; S312: for each window, check whether there is a local minimum value less than 15; if there is, further look ahead to the next window of the same size to determine whether the minimum value inside it is greater than the minimum value of the current window; when the local minimum value of the current window is a relatively low point, and there is no lower point in the window immediately following it, the minimum value in the current window is determined as a valid local minimum point and collected into the output list; S313: Move the sliding window forward in a jump manner by a distance twice the window size, and execute steps S312-S313 in a loop until the entire data sequence is completely scanned, and output an output list consisting of all valid local minimum points.

7. The method for analyzing coal cutting cycles based on the pressure data of hydraulic supports in fully mechanized mining working faces according to claim 5 is characterized in that: In step S32, the local minimum point is screened by a filtering algorithm, including the following steps: S321: using the index position and specific value of each local minimum point as the input of the filtering algorithm, wherein the index position uses the number of minutes for collecting the corresponding local minimum point as the index value; S322: Traverse the input local minimum points in order, compare the index position differences of adjacent local minimum points, and eliminate the local minimum points whose distance from the previous local minimum point is less than 40 units, so as to select the bracket unloading time that meets the actual situation in the data.

8. The method for analyzing coal cutting cycles based on the pressure data of hydraulic supports in fully mechanized mining working faces according to claim 5 is characterized in that: In step S33, the initial support force of the bracket is identified by using an initial support force identification algorithm, which specifically includes the following steps: S331: using the pressure value when the support is unloaded and the corresponding index value as a dictionary and inputting it into the initial support force recognition algorithm; S332: traverse the keys in the dictionary and define a sub-dataset for each key; the key is the input index value; S333: sliding a fixed-size window over the inputted stress value when the bracket is unloaded, calculating the absolute differences between adjacent data points in each window, and making decisions based on these differences; S334: If all the differences are greater than 0.5, the window continues to move forward; if all the differences are less than 0.5, the first data point of the current window is considered to be the initial support force value, and its index is recorded; S335: If there is a change between the difference values, the window continues to move forward, and once the initial support force value is found, the initial support force value and its index position in the original data are recorded; S336: Store all the initial support force values ​​and their indexes found in a new dictionary, where the key is the adjusted index position and the value is the initial support force value itself.

Images