Ventilation data detection and analysis method for coal mine production

Abstract

The invention relates to the technical field of ventilation data detection and analysis, in particular to a ventilation data detection and analysis method for coal mine production. The method comprises the following steps: acquiring a first sequence, a second sequence and a third sequence; intercepting historical data from the current moment of the first sequence to the previous moment by using the initial time window, and calculating the difference of the historical data; further obtaining an optimized time window, and calculating a historical weighted mean value of the first sequence; the condition variance of each moment in the optimization time window is calculated, and the condition variance of the future moment is acquired to form a future sequence; calculating the correlation between the condition variance of each moment in the optimization time window and the future sequence, and then calculating the abnormal degree of the first sequence; similarly, obtaining the abnormal degrees of the second and third sequences; and judging whether ventilation is abnormal or not according to the abnormal degrees of the first, second and third sequences, and if not, further judging by utilizing the carbon dioxide concentration. According to the invention, the ventilation abnormity of the coal mine can be accurately detected.

Description

Technical Field

[0001] The present invention relates to the technical field of ventilation data detection and analysis, and in particular to a ventilation data detection and analysis method for coal mine production. Background Art

[0002] Ventilation systems are widely used in the coal mining industry, and their operational safety and efficiency have become the focus of the industry. At present, the monitoring of ventilation systems in complex environments often faces problems such as difficulty in identifying potential risks and frequent false alarms, which makes it difficult to meet the needs of modern chemical environments for high-precision monitoring.

[0003] At present, the monitoring of ventilation systems faces many challenges in complex environments, mainly manifested in the difficulty in identifying potential risks and frequent false alarms and missed reports. In coal mine production, the collection of ventilation data mainly relies on sensors, often involving key parameters such as wind speed, wind pressure and carbon dioxide concentration. However, existing monitoring methods usually analyze the collected multidimensional feature data and use the generalized autoregressive conditional heteroskedasticity algorithm (GARCH algorithm) to predict the volatility of ventilation parameters. The algorithm identifies the volatility of data in the historical window by introducing delay terms and conditional variance, and gradually analyzes the multidimensional features in the historical window, and sets a threshold range to distinguish normal and abnormal fluctuations. The algorithm can accurately model the dynamic fluctuation characteristics of ventilation parameters, conduct a comprehensive analysis of the correlation between multiple features, and provide accurate analysis and risk assessment of fluctuation trends. However, since it is limited to the prediction results within the historical window, it is easily interfered by external factors, which leads to misjudgment or failure to timely discover potential risks. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a ventilation data detection and analysis method for coal mine production. The technical solution adopted is as follows: An embodiment of the present invention provides a ventilation data detection and analysis method for coal mine production, the method comprising: Collect wind speed data, wind pressure data and carbon dioxide concentration data and perform preprocessing to obtain the first sequence, the second sequence and the third sequence respectively; The initial time window is used to intercept historical data from the current moment of the first sequence to the previous moment, and the difference of historical data of the first sequence is calculated according to the historical data of each moment in the initial time window and the smoothed value obtained by the exponential smoothing algorithm; The time length of the initial time window is adjusted according to the difference of historical data to obtain the optimized time window corresponding to the first sequence; the historical weighted mean of the first sequence is calculated based on the historical data in the optimized time window; The conditional variance of each moment in the optimized time window is calculated by using the GARCH algorithm using the historical weighted mean; the conditional variance of future moments is calculated by sliding the optimized time window backward from the current moment; the future sequence is formed by taking a preset number of conditional variances from the first future moment after the current moment as the starting point; Calculate the conditional variance at each moment in the optimized time window and the correlation of the future sequence; calculate the degree of abnormality of the first sequence based on the correlation, the conditional variance at the current moment and the next moment; similarly, obtain the degree of abnormality of the second and third sequences; Whether the ventilation is abnormal is determined based on the degree of abnormality of the first, second and third sequences. If not, the carbon dioxide concentration in the middle of the ventilation duct outside the exhaust port and inside the exhaust port is used to determine whether the ventilation is abnormal.

[0005] Preferably, wind speed data, wind pressure data and carbon dioxide concentration data are collected and preprocessed to obtain a first sequence, a second sequence and a third sequence respectively, including: Preprocessing includes filling in missing values, removing outliers, denoising and normalization. The normalized wind speed data, wind pressure data and carbon dioxide concentration data are respectively organized into three different sequences.

[0006] Preferably, the calculation formula of the historical data difference of the first sequence is: , in, represents the difference of historical data of the first sequence; θ and represents the weight coefficient, which has the same value; N represents the number of moments in the initial time window; Norm represents the normalization operation; Represents the historical data at the i-th moment in the initial time window; represents the smoothed value obtained by the exponential smoothing algorithm at the i-th moment in the initial time window; δ represents the sensitivity parameter; λ and μ represent the first scaling factor and the second scaling factor; e represents the natural constant; σ represents the third scaling factor; Indicates the wind speed data at the current moment.

[0007] Preferably, adjusting the time length of the initial time window according to the difference of historical data to obtain the optimized time window corresponding to the first sequence includes: Set a difference weight coefficient. If the difference of historical data is greater than or equal to the threshold, the difference weight coefficient takes the first preset value. If the difference of historical data is less than the threshold, the difference weight coefficient takes the second preset value. Multiply the difference weight coefficient by the difference of historical data, add the multiplication result to the third preset value and take the inverse to obtain the window time length adjustment coefficient. Multiply the window time length adjustment coefficient by the time length of the initial time window and round it to obtain the time length of the optimized time window.

[0008] Preferably, calculating the historical weighted mean of the first sequence based on the historical data within the optimization time window includes: Subtract the current moment from the moment of a historical data in the optimized time window to obtain the difference result; set the time distance scaling parameter, and use an exponential function with a natural constant as the base to normalize the value obtained by multiplying the time distance scaling parameter and the difference result to obtain the average weight of the historical data; based on each historical data in the optimized time window and the corresponding average weight, perform weighted averaging to obtain the historical weighted mean of the first sequence.

[0009] Preferably, the conditional variance at each moment in the optimization time window is calculated using the historical weighted mean through the GARCH algorithm, including: Obtain the calculation formula for the conditional variance in the GARCH algorithm; calculate the residuals at each moment in the optimization time window, where the residual at each moment is the difference between the data value at the previous moment and the historical weighted mean; obtain the conditional variance at a moment based on the calculation formula for the conditional variance and the residual and conditional variance at the previous moment.

[0010] Preferably, the conditional variance at future moments is calculated by sliding the optimized time window backward from the current moment, including: The residual and conditional variance at the current moment and the calculation formula of the conditional variance are used to calculate the conditional variance of the first future moment from the current moment; when calculating the conditional variance of the second future moment, the optimization time window slides backward by a preset step from the current moment, and the mean of the residuals at other moments in the optimization time window except the first future moment is used as the residual in the calculation formula of the conditional variance to calculate the conditional variance of the second future moment; when calculating the conditional variance of the third future moment, the optimization time window slides backward by two preset steps from the current moment, and the mean of the residuals at other moments in the optimization time window except the first and second future moments is used as the residual in the calculation formula of the conditional variance to calculate the conditional variance of the third future moment, and so on, the conditional variance of each future moment is calculated.

[0011] Preferably, calculating the abnormality degree of the first sequence according to the correlation and the conditional variance at the current moment and the next moment includes: A first weight corresponding to the conditional variance at the current moment and a second weight corresponding to the conditional variance at the first future moment are set; the conditional variances at the current moment and the first future moment are weightedly summed using the first weight and the second weight to obtain a summation result; an exponential function with a natural constant as the base is used to negatively map the summation result to obtain a mapping result; the difference between the third preset value and the mapping result is the abnormality degree of the first sequence; wherein, if the correlation is greater than zero, the values ​​of the first weight and the second weight are the fourth preset value and the fifth preset value respectively, and if the correlation is less than or equal to zero, the values ​​of the first weight and the second weight are the fifth preset value and the fourth preset value respectively, and the fourth preset value is greater than the fifth preset value.

[0012] Preferably, judging whether ventilation is abnormal according to the abnormality degree of the first, second and third sequences includes: When the abnormality levels of the first, second and third sequences are all less than the reference threshold, the ventilation is normal; when one of the abnormality levels of the first, second and third sequences is greater than or equal to the reference threshold, the ventilation is abnormal.

[0013] Preferably, the carbon dioxide concentration outside the exhaust port and in the middle of the ventilation duct inside the exhaust port is used to determine whether the ventilation is abnormal, including: The sigmoid function is used to map the difference in carbon dioxide concentration between the outside of the exhaust port and the middle of the ventilation duct inside the exhaust port to obtain the concentration difference; if the concentration difference is greater than the concentration difference threshold, the ventilation is normal; if the concentration difference is less than or equal to the concentration difference threshold, the ventilation is abnormal.

[0014] The embodiments of the present invention have at least the following beneficial effects: the present application pre-processes wind speed data, wind pressure data and carbon dioxide concentration data to obtain a first sequence, a second sequence and a third sequence, which can improve data quality and improve the accuracy of subsequent analysis; further, the historical data difference of the first sequence is calculated, and then the time length of the initial time window is adjusted according to the difference to obtain an optimized time window, so as to ensure that the change of wind speed data in the first sequence can be accurately captured; the conditional variance of each moment in the optimized time window is calculated by the GARCH algorithm, and the conditional variance of the future moment is obtained to form a future sequence, and then the correlation between the conditional variance of each moment in the optimized time window and the future sequence is calculated, and the correlation, the current moment and the next moment are used to obtain the conditional variance of the future sequence. The conditional variance at one moment calculates the degree of abnormality of the first sequence, that is, analyzes the volatility of the subordinate data within the optimized time window and the volatility of the data predicted at future moments, analyzes the correlation between the two, and further analyzes the data fluctuation at the current moment based on the correlation to obtain the degree of abnormality, which can solve the defects of the single historical window under the traditional method, achieve comprehensive and accurate detection effects, and obtain a more accurate degree of abnormality; finally, judge whether the ventilation is abnormal based on the degree of abnormality of the first, second and third sequences. If not, use the carbon dioxide concentration in the middle of the ventilation duct outside the exhaust port and inside the exhaust port to judge whether the ventilation is abnormal. When the ventilation is judged to be normal, further judgment is made to further improve the accuracy of detection of ventilation abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A method flow chart of a ventilation data detection and analysis method for coal mine production provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the ventilation data detection and analysis method for coal mine production proposed by the present invention, its specific implementation method, structure, characteristics and effects are described in detail as follows in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0018] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0019] The following is a detailed description of a ventilation data detection and analysis method for coal mine production provided by the present invention in conjunction with the accompanying drawings.

[0020] Example: The main application scenarios of the present invention are: the present invention is mainly used for analyzing key ventilation data in the ventilation system under coal mine production scenarios, and then judging whether the ventilation is abnormal to ensure the production safety of the coal mine.

[0021] See also Figure 1 , which shows a method flow chart of a ventilation data detection and analysis method for coal mine production provided by an embodiment of the present invention, the method comprising the following steps: Step S1, collecting wind speed data, wind pressure data and carbon dioxide concentration data and preprocessing them to obtain a first sequence, a second sequence and a third sequence respectively.

[0022] In the coal mine production environment, sensors are placed in key locations such as the main tunnel, branch tunnel, and fan outlet to collect core parameters of the ventilation system in real time, including wind speed data, wind pressure data, carbon dioxide concentration data, etc. These sensors must meet the use requirements of complex mine environments and have the ability to resist moisture, high temperature, and dust. The collected data is uploaded to the ground monitoring center via wireless transmission (such as LoRa or WiFi), and edge computing devices are used for preliminary processing. The collection frequency is generally set to once a minute to ensure that dynamic changes in system operation can be captured.

[0023] The collected wind speed data, wind pressure data and carbon dioxide concentration data need to be preprocessed, which includes filling in missing values, removing outliers, denoising and normalizing.

[0024] Specifically, for missing values, interpolation can be used to complete them; for outliers (such as wind speed <0 or carbon dioxide concentration exceeds the physical limit), they can be eliminated by combining upper and lower limit rules. All sensor data are aligned by timestamp to ensure the time series consistency of different features. Kalman filtering is used to reduce data noise, smooth short-term fluctuations, and eliminate noise caused by sensor errors or environmental interference. For example, in wind speed data, small irrelevant fluctuations caused by excessive equipment sensitivity are filtered out to make the results more stable. Finally, the wind speed data, wind pressure data, and carbon dioxide concentration data are normalized to ensure that the three data scales are consistent, which is convenient for comprehensive analysis of different features.

[0025] The normalized wind speed data, wind pressure data and carbon dioxide concentration data are respectively formed into three different sequences to obtain a first sequence, a second sequence and a third sequence.

[0026] Step S2, using the initial time window to intercept historical data from the current moment of the first sequence to the previous moment, and calculating the difference of the historical data of the first sequence according to the historical data of each moment in the initial time window and the smoothing value obtained by the exponential smoothing algorithm.

[0027] In the coal mine production environment, in order to judge the operating status of the ventilation system, multi-feature hierarchical analysis is combined to make progressive judgments on wind speed, wind pressure and carbon dioxide concentration data.

[0028] A brief overview of the generalized autoregressive conditional heteroskedasticity algorithm is as follows: Determine the structure of the time series data and assume that its mean fits a specific regression model (such as an autoregressive model). Model the variance of the residuals, assuming that its conditional variance depends on the weighted sum of the squares of the historical residuals and the past conditional variances; Based on historical data, the model parameters, including the regression coefficients and the weights of the conditional variance, are fitted through maximum likelihood estimation or other optimization methods. Based on the estimated parameters, the conditional variance is calculated step by step to quantify the volatility of the time series at each moment; Using the fitted model, the conditional variance of the future time period is predicted and the future volatility trend is analyzed. At the same time, the historical volatility and predicted volatility are combined to evaluate the risk characteristics of the data and provide support for decision-making.

[0029] Furthermore, it is necessary to conduct a preliminary analysis of the wind speed data, wind pressure data, and carbon dioxide concentration data, and then optimize and adjust the fixed historical time window so that it can more accurately quantify the characteristics of the data.

[0030] There are three types of data in this application, and the operations required are basically the same, so the wind speed data, that is, the first sequence, is taken as an example for analysis.

[0031] First, set a fixed historical time window, recorded as the initial time window , At the same time, it indicates the time length of the window. The initial time window is used to intercept historical data from the current moment of the first sequence to the previous moment, and the historical data of each moment in the initial time window is obtained. The historical data of each moment in the initial time window is from the past moment. To the current time Wind speed data between and Furthermore, the difference of the historical data of the first sequence is calculated based on the historical data of each moment in the initial time window and the smoothed value obtained by the exponential smoothing algorithm.

[0032] The specific calculation formula for the difference in historical data is: , in, represents the difference of historical data of the first sequence, which can also be called the difference of historical data corresponding to the current moment of the first sequence; θ and represents the weight coefficient, which has the same value; N represents the number of moments in the initial time window; Norm represents the normalization operation; Represents the historical data at the i-th moment in the initial time window; represents the smoothed value obtained by the exponential smoothing algorithm at the i-th moment in the initial time window; δ represents the sensitivity parameter; λ and μ represent the first scaling factor and the second scaling factor; e represents the natural constant; σ represents the third scaling factor; Indicates the wind speed data at the current moment.

[0033] In the above formula, the weight coefficient is 0.5, and the implementer can adjust it according to the actual situation; represents the smoothed value at the i-th moment obtained by the exponential smoothing algorithm, which is a well-known technology. The specific calculation formula is: , represents the smoothed value obtained by the exponential smoothing algorithm at the i-th moment, represents the historical data at the i-th moment in the initial time window, that is, the real data at the i-th moment. The value of α can be corrected by the smoothing value result. In the embodiment of the present invention, a reference value is given as 0.8. It represents the smoothed value obtained by the exponential smoothing algorithm at the i-1th moment; the reference value of the sensitivity parameter δ can be 2, which is to control the sensitivity of the difference between the actual historical data and the smoothed value. When the smoothed value is predicted, the law of data mutation will not be known in advance. Therefore, if the wind speed data suddenly changes at a certain moment, the difference between the actual value and the smoothed value will be large. Therefore, the greater the difference between the smoothed value and the actual historical data, the more unstable the historical data is; It is to balance the difference between the actual historical data and the smoothed value, amplify the difference, and improve the sensitivity to abnormal data mutations. The values ​​of λ and μ are 0.5 and 0.1 respectively. μ is the scaling coefficient of the exponential function with e as the base, and λ is the exponential function with e as the base to adjust the growth and decay amplitude, which can determine the maximum impact of the exponential term. The implementer can adjust it according to the actual situation. It represents the normalized value of the difference between the wind speed data at the current moment and other data in the initial time window. σ is its scaling factor. The greater the difference between the wind speed data at the current moment and other data in the window, the more unstable the data is.

[0034] In this way, the historical data differences corresponding to the first sequence can be obtained, and then the initial time window can be optimized and adjusted.

[0035] Step S3, adjusting the time length of the initial time window according to the difference of historical data to obtain the optimized time window corresponding to the first sequence; and calculating the historical weighted mean of the first sequence based on the historical data in the optimized time window.

[0036] In step S2, the difference of historical data of the first sequence is obtained. When the difference of historical data is large, it means that the data volatility is strong, which means that the system state may change rapidly, indicating that the wind speed data has unstable fluctuations. At this time, if the initial time window is too large, the smoothing effect of historical data will reduce the sensitivity of the model to sudden changes, so that the abnormal signal is diluted. For example, if the ventilation system fails in a short time and the window is too large, the model may not be able to quickly identify this problem due to the long-term average effect. Reducing the window can reduce the interference of historical data on current decisions and enhance the response speed to sudden changes. In the case of strong volatility, the short-term trend information of the data is more important. If the window is too large, short-term changes will be masked by longer historical data, thereby reducing the accurate assessment of the current state. In the coal mine ventilation system, if the wind speed data rises rapidly in a short time and the window is too large, the model may still think that the overall trend is stable, resulting in a lag in abnormal detection. Reducing the window can focus on recent data and improve the perception of the latest changes.

[0037] When the historical data of the first sequence has little difference and the data fluctuations are weak, the system is usually in a relatively stable state, and small short-term changes may just be random noise. If the window is too small, the model may be overly sensitive to these small fluctuations, resulting in false alarms. For example, when the ventilation system is operating normally, the wind speed may fluctuate slightly, but these fluctuations do not represent system abnormalities. If the window is too small, the model may mistakenly believe that there is a problem with the system, and a larger window can smooth out these short-term disturbances, ensuring that the model does not make wrong judgments about insignificant fluctuations. Data changes at a single moment may not reflect the overall state of the system. Enlarging the window can provide more comprehensive time series information, allowing the model to more accurately identify trends.

[0038] Furthermore, the time length of the initial time window is adjusted according to the difference of historical data to obtain the optimized time window corresponding to the first sequence. Specifically, the difference weight coefficient is set, if the difference of historical data is greater than or equal to the threshold, the difference weight coefficient takes the first preset value, if the difference of historical data is less than the threshold, the difference weight coefficient takes the second preset value; the difference weight coefficient is multiplied by the difference of historical data, the multiplication result is added to the third preset value and the inverse is calculated to obtain the window time length adjustment coefficient; the window time length adjustment coefficient is multiplied by the time length of the initial time window and rounded to obtain the time length of the optimized time window.

[0039] The specific calculation formula is: , Among them, W represents the result of multiplying the window time length adjustment coefficient by the time length of the initial time window. Further, W needs to be rounded. The principle of rounding follows the principle of rounding to get the time length of the optimized time window. , represents the length of the initial time window; β represents the difference weight coefficient, Indicates the difference of historical data. If the difference of historical data is greater than or equal to the threshold, it is considered that the difference is large and the wind speed data fluctuates unsteadily. In this case, it is necessary to shorten the time length of the initial time window. The value of the difference weight coefficient is the first preset value, which is 0.9. If the difference of historical data is less than the threshold, it is considered that the difference is small and the wind speed data is stable. In this case, it is necessary to expand the time length of the initial time window. The value of the difference weight coefficient is the second preset value, which is -1. The value of the threshold is 0.5. The implementer can adjust the values ​​of the first preset value, the second preset value and the threshold according to the actual situation. However, it should be noted that when adjusting the first preset value and the second preset value, it is necessary to follow the principle of shortening the window time length when the difference is large and increasing the window time length when the difference is small; the window time length adjustment coefficient is , the third preset value is 1.

[0040] Next, after obtaining the optimized time window corresponding to the first sequence, it is necessary to use the historical data within the optimized time window for analysis and calculate the historical weighted mean of the first sequence to facilitate the subsequent application of the GARCH algorithm.

[0041] The data at the last moment in the optimized time window is the wind speed data at the current moment, and the other data are the historical wind speed data before the current moment.

[0042] Subtract the current moment from the moment of a historical data in the optimized time window to obtain the difference result; set the time distance scaling parameter, and use an exponential function with a natural constant as the base to normalize the value obtained by multiplying the time distance scaling parameter and the difference result to obtain the average weight of the historical data; based on each historical data in the optimized time window and the corresponding average weight, perform weighted averaging to obtain the historical weighted mean of the first sequence.

[0043] The specific calculation formula is: , in, represents the historical weighted mean of the first series; represents the time length of the optimization time window of the first sequence, which can also be represented as a set of moments in the optimization time window; e represents a natural constant; p represents a time distance scaling parameter, and the reference value in the embodiment of the present invention is 0.5. It is the difference between the current moment and the moment of a historical data in the optimization time window. The farther away from the current moment, the lower its average weight. The smaller, Represents the historical data at the tth moment in the optimization time window. From this, the historical weighted mean of the first sequence can be obtained, and the GARCH algorithm is applied based on the historical weighted mean.

[0044] Step S4, using the historical weighted mean to calculate the conditional variance of each moment in the optimization time window through the GARCH algorithm; using the optimization time window to slide backward from the current moment to calculate the conditional variance of future moments; taking the first future moment after the current moment as the starting point and taking a preset number of conditional variances backward to form a future sequence.

[0045] In step S3, the historical weighted mean of the first sequence is obtained. In order to evaluate the volatility of historical data, it is necessary to calculate the conditional variance at each moment in the optimization time window using the GARCH algorithm based on the historical weighted mean of the first sequence.

[0046] Obtain the calculation formula for the conditional variance in the GARCH algorithm; calculate the residuals at each moment in the optimization time window, where the residual at each moment is the difference between the data value at the previous moment and the historical weighted mean; obtain the conditional variance at a moment based on the calculation formula for the conditional variance and the residual and conditional variance at the previous moment.

[0047] Specifically, the calculation formula of conditional variance is: , in, represents the conditional variance at time t; , , It represents the parameters of the model, and the initial reference values ​​can be 0.4, 0.3, and 0.3; Represents the residual of the previous moment, which is the difference between the data value of the previous moment and the historical weighted mean ; It represents the conditional variance of the previous moment, that is, the volatility calculated based on known information (historical data) at time t-1, which is used to measure the volatility intensity of the data at the previous moment. Thus, the conditional variance of each moment in the optimized time window can be obtained, which is a well-known technology and will not be described in detail here.

[0048] In this way, the conditional variance of each moment in the optimized time window can be obtained. Further, it is necessary to judge the correlation between the volatility of future moments and the volatility of historical moments, and then analyze the operating status of the ventilation system at the current moment. Therefore, it is necessary to calculate the conditional variance of future moments.

[0049] Specifically, it is necessary to slide the optimization time window backward and set a preset step size. Preferably, in the embodiment of the present invention, the preset step size is set to a moment, and the residual and conditional variance at the current moment and the calculation formula of the conditional variance are used to calculate the conditional variance of the first future moment from the current moment; when calculating the conditional variance of the second future moment, the optimization time window slides backward from the current moment by a preset step size, and the mean of the residuals at other moments in the optimization time window except the first future moment is used as the residual in the calculation formula of the conditional variance to calculate the conditional variance of the second future moment; when calculating the conditional variance of the third future moment, the optimization time window slides backward from the current moment by two preset steps, and the mean of the residuals at other moments in the optimization time window except the first and second future moments is used as the residual in the calculation formula of the conditional variance to calculate the conditional variance of the third future moment, and so on, the conditional variance of each future moment is calculated.

[0050] Residuals are the core of calculating conditional variance, which reflects the impact of past errors on current fluctuations. However, since some historical residuals will exceed the current calculation window when the window slides, these residuals cannot be used directly. Using the residual mean of the historical window to replace the lost residuals has a smoothing effect and can effectively reduce the impact of short-term fluctuations on predictions. By using the mean to approximate, the interference of sudden abnormal data on model predictions can be reduced, especially when some specific residual information is missing. The mean can provide a reasonable estimate to ensure the accuracy of the prediction of conditional variance at future moments.

[0051] After obtaining the conditional variance of the future moment, a preset number of conditional variances are taken backwards from the first future moment after the current moment to form a future sequence, where the preset number is equal to the number of moments included in the optimization time window.

[0052] Step S5, calculate the conditional variance at each moment in the optimization time window and the correlation of the future sequence; calculate the abnormality degree of the first sequence according to the correlation, the conditional variance at the current moment and the next moment; similarly obtain the abnormality degree of the second and third sequences.

[0053] In step S4, the future sequence is obtained, that is, the conditional variance corresponding to each future moment, and then the correlation between the conditional variance at each moment in the optimization time window and the conditional variance of the future sequence is analyzed, and the correlation between the volatility of the historical moment and the volatility of the future moment is analyzed. Specifically, the Pearson correlation coefficient of the conditional variance at each moment in the optimization time window and the conditional variance of the future sequence is calculated. The larger the coefficient is, the more correlation there is between the volatility of the historical moment and the volatility of the future moment, and the smaller the coefficient is, the more correlation there is between the volatility of the historical moment and the volatility of the future moment, or the correlation is weak.

[0054] The correlation between the conditional variance at each moment in the optimization time window and the future sequence is recorded as ,like If is greater than 0, the conditional variance at each moment in the optimization time window is positively correlated with the future sequence; if If it is less than or equal to 0, the conditional variance at each moment in the optimization time window is negatively correlated or weakly correlated with the future sequence.

[0055] Positive correlation indicates that the greater the volatility of historical wind speed data, the greater the volatility of future wind speed data is likely to be, and the smaller the volatility of historical wind speed data, the smaller the volatility of future wind speed data is likely to be. By amplifying the weight of historical volatility, the volatility of the current moment can be more accurately represented. Negative correlation and weak correlation indicate that the greater the volatility of historical wind speed data, the smaller the volatility of future wind speed data is likely to be or remain unchanged, and the smaller the volatility of historical wind speed data, the greater the volatility of future wind speed data is likely to be or remain unchanged. At this time, it is necessary to amplify the weight of wind speed volatility at future moments to strengthen and weaken the impact of historical wind speed data and increase attention to volatility at future moments.

[0056] Further, the abnormality of the first sequence is calculated according to the correlation, the conditional variance at the current moment and the next moment. A first weight corresponding to the conditional variance at the current moment and a second weight corresponding to the conditional variance at the first future moment are set; the conditional variance at the current moment and the first future moment are weighted and summed using the first weight and the second weight to obtain a summation result; an exponential function with a natural constant as the base is used to negatively map the summation result to obtain a mapping result; the difference between the third preset value and the mapping result is the abnormality of the first sequence; wherein, if the correlation is greater than zero, the values ​​of the first weight and the second weight are the fourth preset value and the fifth preset value, respectively; if the correlation is less than or equal to zero, the values ​​of the first weight and the second weight are the fifth preset value and the fourth preset value, respectively, and the fourth preset value is greater than the fifth preset value.

[0057] The specific calculation formula is: , in, Indicates the degree of abnormality of the first sequence, represents a natural constant, represents the result of weighted summation of the conditional variance at the current moment and the first future moment using the first weight and the second weight, represents the negative correlation mapping of the summation result, and They represent the conditional variance at the current moment and the first future moment respectively. The smaller these two values ​​are, the more stable the wind speed data is. and Represent the first weight and the second weight respectively. If is greater than 0, and the values ​​are respectively the fourth preset value 0.6 and the fifth preset value 0.4. This is done to amplify the importance of historical wind speed data. Less than or equal to 0, the values ​​are respectively the fifth preset value 0.4 and the fourth preset value 0.6, which increases the attention to the future moment.

[0058] The larger the value of the abnormality, the higher the degree of fluctuation. At this time, the higher the degree of abnormality, the more staff need to be reminded to conduct further inspections. Similarly, the second and third sequences can be processed in the same way to obtain the corresponding difference degrees.

[0059] The abnormality levels of the first, second and third sequences are the differences in wind speed data, wind pressure data and carbon dioxide concentration data, respectively, which can also be called the abnormality level of each data at the current moment. As time goes on, an abnormality level can be calculated at each moment, and then the operating status of the ventilation system can be analyzed in real time.

[0060] Step S6, judging whether the ventilation is abnormal according to the abnormality degree of the first, second and third sequences, and if not abnormal, judging whether the ventilation is abnormal according to the carbon dioxide concentration in the middle of the ventilation duct outside the exhaust port and inside the exhaust port.

[0061] In step S5, the difference between wind speed data, wind pressure data and carbon dioxide concentration data is obtained, and then a comprehensive analysis can be performed based on the three different data. A reference threshold is set, and the initial value of the reference threshold is 0.8, which is recorded as. The reference threshold can be based on Make adjustments, Indicates the mean value of the abnormal degree of one of the three data in a stable state. It indicates the standard deviation of the abnormal degree of a data when it reaches a stable state. k indicates the adjustment coefficient, and its value is 2, which can be adjusted according to the actual situation. Each of the three types of data corresponds to a reference threshold, which can be adjusted later.

[0062] When the abnormality levels of the first, second and third sequences are all less than the reference threshold, the ventilation is normal; when one of the abnormality levels of the first, second and third sequences is greater than or equal to the reference threshold, the ventilation is abnormal; if the ventilation is abnormal, the staff is prompted to check whether there is any abnormality in the hardware equipment, circuits, ventilation ducts, etc. of the ventilation system.

[0063] When ventilation is normal, further judgment is required for more accurate judgment. Specifically, a carbon dioxide concentration detection sensor is installed in the middle of the ventilation duct outside the exhaust outlet and inside the exhaust outlet to obtain the carbon dioxide concentration in the middle of the ventilation duct outside the exhaust outlet and inside the exhaust outlet; the difference of the carbon dioxide concentration in the middle of the ventilation duct outside the exhaust outlet and inside the exhaust outlet is mapped using the sigmoid function to obtain the concentration difference; if the concentration difference is greater than the concentration difference threshold, the ventilation is normal; if the concentration difference is less than or equal to the concentration difference threshold, the ventilation is abnormal. The concentration difference threshold is 0.5.

[0064] Carbon dioxide will diffuse outward through the fan installed at the exhaust port. If the ventilation is normal, the carbon dioxide concentration in the middle of the ventilation duct inside the exhaust port or in the ventilation duct far away from the exhaust port will be low. The difference between the carbon dioxide concentration outside the air duct and the middle of the ventilation duct inside the exhaust port is greater than zero, and is greater than 0.5 after sigmoid function mapping. If the difference between the carbon dioxide concentration outside the air duct and the middle of the ventilation duct inside the exhaust port is less than or equal to zero, it is generally due to poor ventilation, resulting in a higher carbon dioxide concentration in the ventilation duct than outside the fan exhaust port. This can provide a more accurate judgment.

[0065] Finally, the latest wind speed, wind pressure and carbon dioxide concentration data are collected from the coal mine production environment on a regular basis, and preprocessing techniques are used to remove noise and outliers to ensure data quality. The adaptability of the model to the current environment is evaluated by dynamically monitoring the model prediction error. If the error gradually increases, indicating that the environmental conditions or data distribution have changed, the model is retrained using new data, and parameters such as exponential smoothing factors or weighted window strategies are adjusted to better capture the changing trends of the current features. In addition, during the update process, the results of dual-window analysis and volatility assessment are fully combined to further optimize the model's feature extraction capabilities and ensure that it can continuously and accurately judge the abnormal state of ventilation data. Through this dynamic parameter adjustment mechanism, it can meet the detection needs of coal mine ventilation systems for a long time.

[0066] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0068] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A ventilation data detection and analysis method for coal mine production, characterized in that: The method includes: Collect wind speed data, wind pressure data and carbon dioxide concentration data and perform preprocessing to obtain the first sequence, the second sequence and the third sequence respectively; The initial time window is used to intercept historical data from the current moment of the first sequence to the previous moment, and the difference of historical data of the first sequence is calculated according to the historical data of each moment in the initial time window and the smoothed value obtained by the exponential smoothing algorithm; The time length of the initial time window is adjusted according to the difference of historical data to obtain the optimized time window corresponding to the first sequence; the historical weighted mean of the first sequence is calculated based on the historical data in the optimized time window; The conditional variance of each moment in the optimized time window is calculated by using the GARCH algorithm using the historical weighted mean; the conditional variance of future moments is calculated by sliding the optimized time window backward from the current moment; the future sequence is formed by taking a preset number of conditional variances from the first future moment after the current moment as the starting point; Calculate the conditional variance at each moment in the optimized time window and the correlation of the future sequence; calculate the degree of abnormality of the first sequence based on the correlation, the conditional variance at the current moment and the next moment; similarly, obtain the degree of abnormality of the second and third sequences; Whether the ventilation is abnormal is determined based on the degree of abnormality of the first, second and third sequences. If not, the carbon dioxide concentration in the middle of the ventilation duct outside the exhaust port and inside the exhaust port is used to determine whether the ventilation is abnormal.

2. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The wind speed data, wind pressure data and carbon dioxide concentration data are collected and preprocessed to obtain a first sequence, a second sequence and a third sequence respectively, including: Preprocessing includes filling in missing values, removing outliers, denoising and normalization. The normalized wind speed data, wind pressure data and carbon dioxide concentration data are respectively organized into three different sequences.

3. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The calculation formula of the historical data difference of the first sequence is: ， in, represents the difference of historical data of the first sequence; θ and ϑ represent weight coefficients, which are equal; N represents the number of moments in the initial time window; Norm represents the normalization operation; Represents the historical data at the i-th moment in the initial time window; represents the smoothed value obtained by the exponential smoothing algorithm at the i-th moment in the initial time window; δ represents the sensitivity parameter; λ and μ represent the first scaling factor and the second scaling factor; e represents the natural constant; σ represents the third scaling factor; Indicates the wind speed data at the current moment.

4. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The step of adjusting the time length of the initial time window according to the difference of historical data to obtain the optimized time window corresponding to the first sequence includes: Set a difference weight coefficient. If the difference of historical data is greater than or equal to the threshold, the difference weight coefficient takes the first preset value. If the difference of historical data is less than the threshold, the difference weight coefficient takes the second preset value. Multiply the difference weight coefficient by the difference of historical data, add the multiplication result to the third preset value and take the inverse to obtain the window time length adjustment coefficient. Multiply the window time length adjustment coefficient by the time length of the initial time window and round it to obtain the time length of the optimized time window.

5. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The calculating the historical weighted mean of the first sequence based on the historical data in the optimization time window includes: Subtract the current moment from the moment of a historical data in the optimized time window to obtain the difference result; set the time distance scaling parameter, and use an exponential function with a natural constant as the base to normalize the value obtained by multiplying the time distance scaling parameter and the difference result to obtain the average weight of the historical data; based on each historical data in the optimized time window and the corresponding average weight, perform weighted averaging to obtain the historical weighted mean of the first sequence.

6. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The method of using the historical weighted mean to calculate the conditional variance at each moment in the optimization time window through the GARCH algorithm includes: Obtain the calculation formula for the conditional variance in the GARCH algorithm; calculate the residuals at each moment in the optimization time window, where the residual at each moment is the difference between the data value at the previous moment and the historical weighted mean; obtain the conditional variance at a moment based on the calculation formula for the conditional variance and the residual and conditional variance at the previous moment.

7. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The method of calculating the conditional variance at future moments by sliding the optimized time window backward from the current moment includes: The residual and conditional variance at the current moment and the calculation formula of the conditional variance are used to calculate the conditional variance of the first future moment from the current moment; when calculating the conditional variance of the second future moment, the optimization time window slides backward by a preset step from the current moment, and the mean of the residuals at other moments in the optimization time window except the first future moment is used as the residual in the calculation formula of the conditional variance to calculate the conditional variance of the second future moment; when calculating the conditional variance of the third future moment, the optimization time window slides backward by two preset steps from the current moment, and the mean of the residuals at other moments in the optimization time window except the first and second future moments is used as the residual in the calculation formula of the conditional variance to calculate the conditional variance of the third future moment, and so on, the conditional variance of each future moment is calculated.

8. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The calculating the abnormality degree of the first sequence according to the correlation and the conditional variance at the current moment and the next moment comprises: A first weight corresponding to the conditional variance at the current moment and a second weight corresponding to the conditional variance at the first future moment are set; the conditional variances at the current moment and the first future moment are weightedly summed using the first weight and the second weight to obtain a summation result; an exponential function with a natural constant as the base is used to negatively map the summation result to obtain a mapping result; the difference between the third preset value and the mapping result is the abnormality degree of the first sequence; wherein, if the correlation is greater than zero, the values ​​of the first weight and the second weight are the fourth preset value and the fifth preset value respectively, and if the correlation is less than or equal to zero, the values ​​of the first weight and the second weight are the fifth preset value and the fourth preset value respectively, and the fourth preset value is greater than the fifth preset value.

9. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The step of judging whether ventilation is abnormal according to the abnormality levels of the first, second and third sequences includes: When the abnormality levels of the first, second and third sequences are all less than the reference threshold, the ventilation is normal; when one of the abnormality levels of the first, second and third sequences is greater than or equal to the reference threshold, the ventilation is abnormal.

10. A ventilation data detection and analysis method for coal mine production according to claim 1, characterized in that: The method of judging whether ventilation is abnormal by using the carbon dioxide concentration outside the exhaust port and in the middle of the ventilation duct inside the exhaust port includes: The sigmoid function is used to map the difference in carbon dioxide concentration between the outside of the exhaust port and the middle of the ventilation duct inside the exhaust port to obtain the concentration difference; if the concentration difference is greater than the concentration difference threshold, the ventilation is normal; if the concentration difference is less than or equal to the concentration difference threshold, the ventilation is abnormal.

Images