Ultrathin coal seam hydraulic support positioning method and system

Abstract

The invention relates to the technical field of coal mining, in particular to an ultra-thin coal seam hydraulic support positioning method and system, and the method comprises the steps that s1, an action time sequence, state data and environment data of a hydraulic support and geological information of an ultra-thin coal seam are obtained; s2, the state data of the hydraulic support are monitored in real time, and an abnormal alarm signal is generated according to a monitoring result or the operation of the step s3 is carried out; s3, constructing a state estimation model, and performing state estimation on the state data of the current acquisition period; and s4, carrying out adaptive control operation according to a state estimation result, carrying out fuzzy comprehensive evaluation, and obtaining an optimal action time sequence of the current acquisition period. The working efficiency and safety of the hydraulic support are improved, and the adaptive capacity of the hydraulic support in the complex and changeable ultra-thin coal seam mining environment is enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of coal mining, and in particular to a positioning method and system for an ultra-thin coal seam hydraulic support. Background Art

[0002] CN118395163A "A method and system for positioning a hydraulic support in an extremely thin coal seam" extracts and optimizes the features of the pressure exerted by the hydraulic support on the extremely thin coal seam, the tilt of the monitoring support and the position change of the monitoring support relative to the extremely thin coal seam, and fuses the optimized features through weighted averaging and then reduces the dimension; establishes a prediction model for the position of the hydraulic support, uses the reduced-dimensional features as the input of the prediction model, constructs an objective function with the minimum noise covariance as a parameter, calculates the gradient of the objective function, optimizes the noise covariance by calculating the gradient of the objective function, adjusts the parameters of the prediction model, obtains the trained prediction model for the position of the hydraulic support, uses the collected data as the input of the prediction model for real-time prediction, and outputs the position information of the hydraulic support.

[0003] CN118361273A "A ultra-thin coal seam hydraulic support positioning control system and support data transmission method" sets UWB modules and 5G module CPE on each hydraulic support in the ultra-thin coal seam, uses the broadband wireless technology of UWB technology to achieve centimeter-level high-precision positioning of the hydraulic support, and uses the high bandwidth and low latency characteristics of the 5G module CPE to realize real-time transmission of the position data and status information of the hydraulic support to the operating end, thereby realizing high-precision real-time control and monitoring of the position and status information of the hydraulic support.

[0004] In recent years, with the advancement of coal mining equipment and technology and over-mining, the reserves of thick and medium-thick coal seams have been sharply reduced or even exhausted, and thin and ultra-thin coal seams have gradually become the main mining areas. The mining of ultra-thin coal seams is of great significance for solving the contradiction of mining continuity in mining areas, improving resource recovery rates, and alleviating the contradiction between regional coal supply and demand. However, due to the narrow mining space of ultra-thin coal seams, the complex structure of coal seams, the coexistence of folds, faults, gas and other problems, the harsh working environment, and many production safety hazards, the adaptability requirements of mechanical equipment are particularly high. Therefore, it is particularly important to develop a method and system that can adjust the position of hydraulic supports in real time. Summary of the invention

[0005] In order to solve the above technical problems, the object of the present invention is to provide a positioning method for an ultra-thin coal seam hydraulic support, comprising the following steps:

[0006] Step s1: obtaining the action timing sequence, status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam, marking the acquisition time, and setting the acquisition cycle;

[0007] Step s2: monitor the status data of the hydraulic support in real time, and generate an abnormal alarm signal or perform the operation of step s3 according to the monitoring result;

[0008] Step s3: construct a state prediction model to perform state prediction on the state data of the current acquisition cycle;

[0009] Step s4: Adaptive control operations are performed according to the state prediction results to obtain the vulnerability probabilities of various types of indicators in the state data under different environmental data and geological information conditions, as well as the simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions, and then fuzzy comprehensive evaluation is performed to obtain the optimal action timing sequence for the current acquisition cycle.

[0010] Furthermore, the process of monitoring the status data of the hydraulic support in real time and generating an abnormal alarm signal or performing the operation of step s3 according to the monitoring result includes:

[0011] Obtain the preset threshold interval corresponding to each type of indicator in the status data of the hydraulic support in the current acquisition period, compare the numerical time series corresponding to each type of indicator in the current acquisition period with the threshold interval corresponding to each type of indicator, obtain the cumulative time during which the numerical time series corresponding to each type of indicator is not within the corresponding threshold interval, compare the cumulative time with the preset cumulative time threshold, if the cumulative time of the indicator is greater than the cumulative time threshold, mark the indicator as an abnormal indicator, and generate an abnormal alarm signal according to the abnormal indicator, if the cumulative time of each type of indicator is less than or equal to the cumulative time threshold, perform step s3.

[0012] Furthermore, the process of building a state prediction model includes:

[0013] Extract the status data of the hydraulic support in several historical collection cycles, extract the historical collection cycle that generates abnormal alarm signals, mark the historical collection cycle as an abnormal historical collection cycle, mark the historical collection cycle that does not generate abnormal alarm signals as a normal historical collection cycle, obtain the Pearson correlation coefficient between the abnormal indicator and other indicators in the abnormal historical collection cycle and the average fluctuation coefficient of the abnormal indicator, and simultaneously obtain the Pearson correlation coefficient between each indicator and other indicators in the normal historical collection cycle and the average fluctuation coefficient of each indicator;

[0014] A state prediction model is constructed based on deep learning. The Pearson correlation coefficient between abnormal indicators and other indicators in the abnormal historical acquisition period and the average fluctuation coefficient of abnormal indicators, the Pearson correlation coefficient between each indicator and other indicators in the normal historical acquisition period and the average fluctuation coefficient of each indicator are used as training sets and test sets. The training set is input into the state prediction model for training until the loss function training is stable, and the model parameters are saved. The state prediction model is tested by the test set until it meets the preset requirements and the state prediction model is output.

[0015] Furthermore, the state data of the current collection cycle is estimated, and the process includes:

[0016] Obtain the Pearson correlation coefficients between various types of indicators and the average fluctuation coefficients of various types of indicators in the current collection cycle, input the Pearson correlation coefficients between various types of indicators and the average fluctuation coefficients of various types of indicators into the state prediction model, mark the current collection cycle according to the state prediction model, and mark the current collection cycle as an estimated normal collection cycle or an estimated abnormal collection cycle.

[0017] Furthermore, the process of performing adaptive control operations according to the state prediction results and obtaining the vulnerability probability of each type of indicator in the state data under different environmental data and geological information conditions includes:

[0018] If the current acquisition cycle is marked as an estimated abnormal acquisition cycle, an adaptive control operation is performed to extract the status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam in several historical acquisition cycles, and perform statistical analysis on the status data, environmental data, and geological information in several historical acquisition cycles to obtain the cumulative number of times each type of indicator in the status data is marked as an abnormal indicator under different environmental data and geological information conditions, and based on the cumulative number of times, obtain the vulnerability probability of each type of indicator in the status data under different environmental data and geological information conditions.

[0019] Furthermore, the process of obtaining the simulation state data corresponding to different simulation action timing sequences of the hydraulic support under different simulation environment data and simulation geological information conditions includes:

[0020] Use a simulator to generate a number of simulated environmental data, simulated geological information and simulated action timing sequences, conduct simulation experiments on the hydraulic support in advance, and obtain simulation state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions;

[0021] Obtain the environmental data and geological information of the current acquisition period, obtain the vulnerability probability corresponding to each type of indicator in the state data of the hydraulic support under the environmental data and geological information conditions of the current acquisition period, and at the same time obtain the simulated state data corresponding to different simulation action timing sequences of the hydraulic support under the environmental data and geological information conditions of the current acquisition period, and obtain the average fluctuation coefficient of each type of indicator in the simulated state data corresponding to different simulation action timing sequences.

[0022] Furthermore, the process of performing fuzzy comprehensive evaluation to obtain the best action timing sequence of the current acquisition cycle includes:

[0023] The average fluctuation coefficient of each type of indicator in the simulation state data corresponding to different simulation action time series under the environmental data and geological information conditions of the current acquisition period is used as an evaluation indicator. According to the vulnerability probability corresponding to each type of indicator under the environmental data and geological information conditions of the current acquisition period, the weight coefficient of each type of indicator is set, the membership function and several stability levels are preset, and the membership matrix of different simulation action time series for different stability levels is obtained through fuzzy comprehensive evaluation;

[0024] According to the membership matrix and the weight coefficients of various types of indicators, the stability levels of different simulated action timing sequences are obtained, and the simulated action timing sequences with stability levels greater than a preset stability level threshold are screened out, and the simulated action timing sequences are marked as first action timing sequences, and the total action execution time of each first action timing sequence is obtained, and the first action timing sequence with the shortest total action execution time is screened out, and the first action timing sequence is marked as the best action timing sequence, and the action timing sequence of the current acquisition cycle is updated to the best action timing sequence.

[0025] An ultra-thin coal seam hydraulic support positioning system comprises a monitoring center, wherein the monitoring center is communicatively connected with a data acquisition unit, a real-time monitoring unit, a state estimation unit and an adaptive control unit;

[0026] The data acquisition unit is used to obtain the action timing sequence, status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam, mark the acquisition time, and set the acquisition cycle;

[0027] The real-time monitoring unit is used to monitor the status data of the hydraulic support in real time, and generate an abnormal alarm signal or perform the operation of step s3 according to the monitoring result;

[0028] The state estimation unit is used to construct a state estimation model to perform state estimation on the state data of the current acquisition cycle;

[0029] The adaptive control unit is used to perform adaptive control operations according to the state prediction results, obtain the vulnerability probability of each type of indicator in the state data under different environmental data and geological information conditions, and the simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions, and then perform fuzzy comprehensive evaluation to obtain the optimal action timing sequence of the current acquisition cycle.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. Improve response speed: By monitoring the status data of the hydraulic support in real time, abnormal situations can be quickly identified and alarm signals can be issued in time. This instant feedback mechanism can help operators take corrective measures faster to avoid potential problems from worsening.

[0032] 2. Enhanced decision-making accuracy: The state prediction model built using deep learning algorithms, combined with abnormal pattern analysis in historical data, enables the system to accurately judge possible future problems at an early stage. This helps plan response strategies in advance and reduce downtime caused by unexpected failures.

[0033] 3. Optimize the action sequence selection: By simulating the behavior of the hydraulic support under different simulation environments and using fuzzy comprehensive evaluation to determine the optimal action sequence, it is ensured that each action can be executed with the highest efficiency. This method not only takes into account the best practices under current working conditions, but also takes into account the stability and economy in long-term operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a schematic diagram of a positioning method for an ultra-thin coal seam hydraulic support according to an embodiment of the present application.

[0035] Figure 2 This is a schematic diagram of an ultra-thin coal seam hydraulic support positioning system according to an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0037] like Figure 1 As shown, a method for positioning an extremely thin coal seam hydraulic support comprises the following steps:

[0038] Step s1: Obtain the action timing sequence, state data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam through the sensor terminal, mark the acquisition time, and set the acquisition cycle. The various types of indicators in the state data include pressure data, cutting inclination data, and position change data; the action timing sequence refers to the order of occurrence of various actions of the hydraulic support, the occurrence time of each action, and the time interval between each action. These actions include but are not limited to operations such as raising the frame, lowering the frame, moving the frame, and pushing the frame; the environmental parameters include but are not limited to temperature, humidity, gas concentration, etc., and the geological information includes the specific structure of the overburden above the coal seam (such as thickness, hardness, etc.);

[0039] Step s2: monitor the status data of the hydraulic support in real time, and generate an abnormal alarm signal or perform the operation of step s3 according to the monitoring result;

[0040] Step s3: construct a state prediction model to perform state prediction on the state data of the current acquisition cycle;

[0041] Step s4: Adaptive control operations are performed according to the state prediction results to obtain the vulnerability probabilities of various types of indicators in the state data under different environmental data and geological information conditions, as well as the simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions, and then fuzzy comprehensive evaluation is performed to obtain the optimal action timing sequence for the current acquisition cycle.

[0042] It should be further explained that, in the specific implementation process, the state data of the hydraulic support is monitored in real time, and the process of generating an abnormal alarm signal or performing the operation of step s3 according to the monitoring result includes:

[0043] Obtain the preset threshold interval corresponding to each type of indicator in the status data of the hydraulic support in the current acquisition period, compare the numerical time series corresponding to each type of indicator in the current acquisition period with the threshold interval corresponding to each type of indicator, obtain the cumulative time during which the numerical time series corresponding to each type of indicator is not within the corresponding threshold interval, compare the cumulative time with the preset cumulative time threshold, if the cumulative time of the indicator is greater than the cumulative time threshold, mark the indicator as an abnormal indicator, and generate an abnormal alarm signal according to the abnormal indicator, if the cumulative time of each type of indicator is less than or equal to the cumulative time threshold, perform step s3.

[0044] It should be further explained that, in the specific implementation process, the process of building a state prediction model includes:

[0045] Extract the status data of the hydraulic support in several historical collection cycles, extract the historical collection cycle that generates abnormal alarm signals, mark the historical collection cycle as an abnormal historical collection cycle, mark the historical collection cycle that does not generate abnormal alarm signals as a normal historical collection cycle, obtain the Pearson correlation coefficient between the abnormal indicator and other indicators in the abnormal historical collection cycle and the average fluctuation coefficient of the abnormal indicator, and simultaneously obtain the Pearson correlation coefficient between each indicator and other indicators in the normal historical collection cycle and the average fluctuation coefficient of each indicator;

[0046] The calculation formula of average volatility coefficient is:

[0047]

[0048] z i represents the average volatility coefficient of indicator i, N represents the total number of moments of the numerical time series of indicator i, and x it Represents the value of index i at the tth moment in the numerical time series;

[0049] A state prediction model is constructed based on deep learning. The Pearson correlation coefficient between abnormal indicators and other indicators in the abnormal historical acquisition period and the average fluctuation coefficient of abnormal indicators, the Pearson correlation coefficient between each indicator and other indicators in the normal historical acquisition period and the average fluctuation coefficient of each indicator are used as training sets and test sets. The training set is input into the state prediction model for training until the loss function training is stable, and the model parameters are saved. The state prediction model is tested by the test set until it meets the preset requirements and the state prediction model is output.

[0050] It should be further explained that, in the specific implementation process, the process of estimating the state of the state data of the current collection cycle includes:

[0051] Obtain the Pearson correlation coefficients between various types of indicators and the average fluctuation coefficients of various types of indicators in the current collection cycle, input the Pearson correlation coefficients between various types of indicators and the average fluctuation coefficients of various types of indicators into the state prediction model, mark the current collection cycle according to the state prediction model, and mark the current collection cycle as an estimated normal collection cycle or an estimated abnormal collection cycle.

[0052] It should be further explained that, in the specific implementation process, the process of performing adaptive control operations according to the state prediction results and obtaining the vulnerability probability of each type of indicator in the state data under different environmental data and geological information conditions includes:

[0053] If the current acquisition cycle is marked as an estimated abnormal acquisition cycle, an adaptive control operation is performed to extract the status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam in several historical acquisition cycles, and perform statistical analysis on the status data, environmental data, and geological information in several historical acquisition cycles to obtain the cumulative number of times each type of indicator in the status data is marked as an abnormal indicator under different environmental data and geological information conditions, and based on the cumulative number of times, obtain the vulnerability probability of each type of indicator in the status data under different environmental data and geological information conditions.

[0054] It should be further explained that, in the specific implementation process, the process of obtaining the simulation state data corresponding to different simulation action timing sequences of the hydraulic support under different simulation environment data and simulation geological information conditions includes:

[0055] Use a simulator to generate a number of simulated environmental data, simulated geological information and simulated action timing sequences, conduct simulation experiments on the hydraulic support in advance, and obtain simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions;

[0056] Obtain the environmental data and geological information of the current acquisition period, obtain the vulnerability probability corresponding to each type of indicator in the state data of the hydraulic support under the environmental data and geological information conditions of the current acquisition period, and at the same time obtain the simulated state data corresponding to different simulation action timing sequences of the hydraulic support under the environmental data and geological information conditions of the current acquisition period, and obtain the average fluctuation coefficient of each type of indicator in the simulated state data corresponding to different simulation action timing sequences.

[0057] It should be further explained that, in the specific implementation process, the process of performing fuzzy comprehensive evaluation to obtain the best action timing sequence of the current acquisition cycle includes:

[0058] The average fluctuation coefficient of each type of indicator in the simulation state data corresponding to different simulation action time series under the environmental data and geological information conditions of the current acquisition period is used as an evaluation indicator. According to the vulnerability probability corresponding to each type of indicator under the environmental data and geological information conditions of the current acquisition period, the weight coefficient of each type of indicator is set, the membership function and several stability levels are preset, and the membership matrix of different simulation action time series for different stability levels is obtained through fuzzy comprehensive evaluation;

[0059] According to the membership matrix and the weight coefficients of various types of indicators, the stability levels of different simulated action timing sequences are obtained, and the simulated action timing sequences with stability levels greater than the preset stability level threshold are screened out, and the simulated action timing sequences are marked as first action timing sequences. The total action execution time of each first action timing sequence (that is, the total time for the hydraulic support to complete the predetermined action sequence) is obtained, and the first action timing sequence with the shortest total action execution time is screened out, and the first action timing sequence is marked as the best action timing sequence, and the action timing sequence of the current acquisition cycle is updated to the best action timing sequence.

[0060] like Figure 2 As shown, a very thin coal seam hydraulic support positioning system includes a monitoring center, wherein the monitoring center is communicatively connected to a data acquisition unit, a real-time monitoring unit, a state estimation unit and an adaptive control unit;

[0061] The data acquisition unit is used to obtain the action timing sequence, state data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam through the sensor terminal, mark the acquisition time, and set the acquisition cycle. The various types of indicators in the state data include pressure data, cutting inclination data, and position change data; the action timing sequence refers to the order of occurrence of various actions of the hydraulic support, the occurrence time of each action, and the time interval between each action. These actions include but are not limited to operations such as raising the frame, lowering the frame, moving the frame, and pushing the slide; the environmental parameters are but not limited to temperature, humidity, gas concentration, etc., and the geological information includes the specific structure of the overburden above the coal seam (such as thickness, hardness, etc.);

[0062] The real-time monitoring unit is used to monitor the status data of the hydraulic support in real time, and generate an abnormal alarm signal or perform the operation of step s3 according to the monitoring result;

[0063] The state estimation unit is used to construct a state estimation model to perform state estimation on the state data of the current acquisition cycle;

[0064] The adaptive control unit is used to perform adaptive control operations according to the state prediction results, obtain the vulnerability probability of each type of indicator in the state data under different environmental data and geological information conditions, and the simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions, and then perform fuzzy comprehensive evaluation to obtain the optimal action timing sequence of the current acquisition cycle.

[0065] The above embodiments are only used to illustrate the technical method 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 method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for positioning a hydraulic support in an extremely thin coal seam, characterized in that: The following steps are involved: Step s1: obtaining the action timing sequence, status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam, marking the acquisition time, and setting the acquisition cycle; Step s2: monitor the status data of the hydraulic support in real time, and generate an abnormal alarm signal or perform the operation of step s3 according to the monitoring result; Step s3: construct a state prediction model to perform state prediction on the state data of the current acquisition cycle; Step s4: Adaptive control operations are performed according to the state prediction results to obtain the vulnerability probabilities of various types of indicators in the state data under different environmental data and geological information conditions, as well as the simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions, and then fuzzy comprehensive evaluation is performed to obtain the optimal action timing sequence for the current acquisition cycle.

2. The method for positioning an ultra-thin coal seam hydraulic support according to claim 1, characterized in that: The process of real-time monitoring of the status data of the hydraulic support and generating an abnormal alarm signal or performing the operation of step s3 according to the monitoring result includes: Obtain the preset threshold interval corresponding to each type of indicator in the status data of the hydraulic support in the current acquisition period, compare the numerical time series corresponding to each type of indicator in the current acquisition period with the threshold interval corresponding to each type of indicator, obtain the cumulative time during which the numerical time series corresponding to each type of indicator is not within the corresponding threshold interval, compare the cumulative time with the preset cumulative time threshold, if the cumulative time of the indicator is greater than the cumulative time threshold, mark the indicator as an abnormal indicator, and generate an abnormal alarm signal according to the abnormal indicator, if the cumulative time of each type of indicator is less than or equal to the cumulative time threshold, perform step s3.

3. The method for positioning an ultra-thin coal seam hydraulic support according to claim 2, characterized in that: The process of building a state prediction model includes: Extract the status data of the hydraulic support in several historical collection cycles, extract the historical collection cycle that generates abnormal alarm signals, mark the historical collection cycle as an abnormal historical collection cycle, mark the historical collection cycle that does not generate abnormal alarm signals as a normal historical collection cycle, obtain the Pearson correlation coefficient between the abnormal indicator and other indicators in the abnormal historical collection cycle and the average fluctuation coefficient of the abnormal indicator, and simultaneously obtain the Pearson correlation coefficient between each indicator and other indicators in the normal historical collection cycle and the average fluctuation coefficient of each indicator; A state prediction model is constructed based on deep learning. The Pearson correlation coefficient between abnormal indicators and other indicators in the abnormal historical acquisition period and the average fluctuation coefficient of abnormal indicators, the Pearson correlation coefficient between each indicator and other indicators in the normal historical acquisition period and the average fluctuation coefficient of each indicator are used as training sets and test sets. The training set is input into the state prediction model for training until the loss function training is stable, and the model parameters are saved. The state prediction model is tested by the test set until it meets the preset requirements and the state prediction model is output.

4. The method for positioning an ultra-thin coal seam hydraulic support according to claim 3, characterized in that: The process of estimating the status of the status data in the current collection cycle includes: Obtain the Pearson correlation coefficients between various types of indicators and the average fluctuation coefficients of various types of indicators in the current collection cycle, input the Pearson correlation coefficients between various types of indicators and the average fluctuation coefficients of various types of indicators into the state prediction model, mark the current collection cycle according to the state prediction model, and mark the current collection cycle as an estimated normal collection cycle or an estimated abnormal collection cycle.

5. The method for positioning an ultra-thin coal seam hydraulic support according to claim 4, characterized in that: The process of performing adaptive control operations based on the state prediction results and obtaining the vulnerability probability of each type of indicator in the state data under different environmental data and geological information conditions includes: If the current acquisition cycle is marked as an estimated abnormal acquisition cycle, an adaptive control operation is performed to extract the status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam in several historical acquisition cycles, and perform statistical analysis on the status data, environmental data, and geological information in several historical acquisition cycles to obtain the cumulative number of times each type of indicator in the status data is marked as an abnormal indicator under different environmental data and geological information conditions, and based on the cumulative number of times, obtain the vulnerability probability of each type of indicator in the status data under different environmental data and geological information conditions.

6. The method for positioning a hydraulic support in an ultra-thin coal seam according to claim 5, characterized in that: The process of obtaining the simulation state data corresponding to different simulation action timing sequences of the hydraulic support under different simulation environment data and simulation geological information conditions includes: Use a simulator to generate a number of simulated environmental data, simulated geological information and simulated action timing sequences, conduct simulation experiments on the hydraulic support in advance, and obtain simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions; Obtain the environmental data and geological information of the current acquisition period, obtain the vulnerability probability corresponding to each type of indicator in the state data of the hydraulic support under the environmental data and geological information conditions of the current acquisition period, and at the same time obtain the simulated state data corresponding to different simulation action timing sequences of the hydraulic support under the environmental data and geological information conditions of the current acquisition period, and obtain the average fluctuation coefficient of each type of indicator in the simulated state data corresponding to different simulation action timing sequences.

7. The method for positioning an ultra-thin coal seam hydraulic support according to claim 6, characterized in that: The process of performing fuzzy comprehensive evaluation to obtain the best action timing sequence for the current acquisition cycle includes: The average fluctuation coefficient of each type of indicator in the simulation state data corresponding to different simulation action time series under the environmental data and geological information conditions of the current acquisition period is used as an evaluation indicator. According to the vulnerability probability corresponding to each type of indicator under the environmental data and geological information conditions of the current acquisition period, the weight coefficient of each type of indicator is set, the membership function and several stability levels are preset, and the membership matrix of different simulation action time series for different stability levels is obtained through fuzzy comprehensive evaluation; According to the membership matrix and the weight coefficients of various types of indicators, the stability levels of different simulated action timing sequences are obtained, and the simulated action timing sequences with stability levels greater than a preset stability level threshold are screened out, and the simulated action timing sequences are marked as first action timing sequences, and the total action execution time of each first action timing sequence is obtained, and the first action timing sequence with the shortest total action execution time is screened out, and the first action timing sequence is marked as the best action timing sequence, and the action timing sequence of the current acquisition cycle is updated to the best action timing sequence.

8. An ultra-thin coal seam hydraulic support positioning system, specifically applied to an ultra-thin coal seam hydraulic support positioning method according to any one of claims 1 to 7, characterized in that: It includes a monitoring center, which is communicatively connected with a data acquisition unit, a real-time monitoring unit, a state estimation unit and an adaptive control unit; The data acquisition unit is used to obtain the action timing sequence, status data and environmental data of the hydraulic support and the geological information of the extremely thin coal seam, mark the acquisition time, and set the acquisition cycle; The real-time monitoring unit is used to monitor the status data of the hydraulic support in real time, and generate an abnormal alarm signal or perform the operation of step s3 according to the monitoring result; The state estimation unit is used to construct a state estimation model to perform state estimation on the state data of the current acquisition cycle; The adaptive control unit is used to perform adaptive control operations according to the state prediction results, obtain the vulnerability probability of each type of indicator in the state data under different environmental data and geological information conditions, and the simulated state data corresponding to different simulated action timing sequences of the hydraulic support under different simulated environmental data and simulated geological information conditions, and then perform fuzzy comprehensive evaluation to obtain the optimal action timing sequence of the current acquisition cycle.

Images