A gas curve correlation fluctuation anomaly identification method and device and related components

Abstract

The application discloses a gas curve correlation fluctuation anomaly identification method and device and related components, and relates to the methane sensor detection field, the method comprises the following steps: obtaining the original methane concentration data sent by the methane sensor at different positions on the same working surface based on a preset sampling rule; preprocessing all the original methane concentration data, aligning and standardizing each original methane concentration data, and obtaining a target methane concentration data curve; calculating and processing the shortest path distance values between each target methane concentration data curve after processing by using a DTW algorithm; comparing all the shortest path distance values with a preset abnormal distance threshold value, and if the current shortest path distance value exceeds the abnormal distance threshold value, an abnormal early warning signal is sent. The method can solve the problem that the methane sensor cannot be effectively monitored whether it is correctly installed.

Description

Technical Field

[0001] The present invention relates to the field of methane sensor detection, and in particular to a method and device for identifying abnormal gas curve correlation fluctuations, and related components. Background Art

[0002] Currently, the coal industry is one of the country's main sources of energy and an important pillar of the national economy. However, coal gas explosions frequently occur during coal mining, causing huge losses to people's lives and property.

[0003] The coal face, the primary site of coal mining, is a frequent site of mine accidents, particularly gas explosions. National law mandates the installation of multiple methane sensors at regular intervals within the same face to collect gas information and effectively prevent accidents. Methane is the primary cause of gas explosions, and properly installed methane sensors can effectively reduce the risk of accidents. However, there is currently no effective method for monitoring the correct installation of methane sensors. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, device and related components for identifying abnormal fluctuations in gas curve correlation, aiming to solve the problem of being unable to effectively monitor whether the methane sensor is correctly installed.

[0005] To solve the above technical problems, the present invention aims to achieve the following technical solutions: providing a method for identifying abnormal fluctuations in gas curve correlation, which includes:

[0006] Based on the preset sampling rules, the raw methane concentration data sent by the methane sensors at different positions on the same working surface are obtained;

[0007] Preprocessing all the raw methane concentration data to align and standardize the raw methane concentration data to obtain a target methane concentration data curve;

[0008] Calculating the shortest path distance between the target methane concentration data curves using the DTW dynamic time warping method;

[0009] All the shortest path distance values ​​are compared with a preset abnormal distance threshold, and if the current shortest path distance value exceeds the abnormal distance threshold, an abnormal warning signal is issued.

[0010] In addition, the technical problem to be solved by the present invention is to provide a device for identifying abnormal fluctuations in gas curve correlation, which includes:

[0011] A sampling unit is used to obtain raw methane concentration data sent by methane sensors at different positions on the same working surface based on a preset sampling rule;

[0012] a preprocessing unit, configured to preprocess all the raw methane concentration data to align and standardize the raw methane concentration data to obtain a target methane concentration data curve;

[0013] a calculation unit, configured to calculate the shortest path distance value between the processed target methane concentration data curves using a DTW dynamic time warping method;

[0014] The early warning unit is used to compare all the shortest path distance values ​​with a preset abnormal distance threshold, and issue an abnormal early warning signal if the current shortest path distance value exceeds the abnormal distance threshold.

[0015] In addition, an embodiment of the present invention provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for identifying abnormal gas curve correlation fluctuations described in the first aspect above is implemented.

[0016] In addition, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor executes the method for identifying abnormal gas curve correlation fluctuations described in the first aspect above.

[0017] The present invention discloses a method, device, and related components for identifying abnormal gas curve fluctuations. The method includes: obtaining raw methane concentration data transmitted by methane sensors at different locations on the same working surface based on preset sampling rules; preprocessing all of the raw methane concentration data to align and standardize the data to obtain a target methane concentration data curve; calculating the shortest path distance between the processed target methane concentration data curves using the DTW dynamic time warping method; and comparing all of the shortest path distance values ​​with a preset abnormal distance threshold. If the current shortest path distance value exceeds the abnormal distance threshold, an abnormality warning signal is issued. This method can effectively solve the problem of being unable to monitor whether methane sensors are properly installed. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1A flow chart of a method for identifying abnormal gas curve fluctuations provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of the position of a methane sensor on a working surface provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of methane concentration data under normal production conditions provided by an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the DTW optimal path provided by an embodiment of the present invention;

[0023] Figure 5 A schematic diagram comparing the Euclidean distance and the DTW distance provided in an embodiment of the present invention;

[0024] Figure 6 A schematic diagram of normal and abnormal DTW distribution provided by an embodiment of the present invention;

[0025] Figure 7 Schematic diagram of DTW calculation of methane sensors T0, T1, and T2 provided in an embodiment of the present invention;

[0026] Figure 8 A schematic block diagram of a device for identifying abnormal gas curve correlation fluctuations according to an embodiment of the present invention;

[0027] Figure 9 A schematic block diagram of a computer device provided in an embodiment of the present invention. Implementation Method

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0029] It will be understood that when used in this specification and the appended claims, the terms “comprises” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0030] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the present invention. As used in the specification and appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0031] It should be further understood that the term "and / or" used in the present description and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0032] See also Figure 1 , Figure 1 A flow chart of a method for identifying abnormal gas curve fluctuations provided by an embodiment of the present invention;

[0033] like Figure 1 As shown, the method includes steps S101 to S104.

[0034] S101, based on a preset sampling rule, obtaining raw methane concentration data sent by methane sensors at different positions on the same working surface;

[0035] In this embodiment, if Figure 2 As shown, one of the working surfaces of the present application has three methane sensors, which are installed at T0, T1, and T2. The flow direction of the methane gas is from the methane sensor T0 through the methane sensor T1, and then flows through the methane sensor T2. During the flow of the methane gas, the three methane sensors will collect the concentration data of the methane gas to obtain the original methane concentration data. In this embodiment, data collection can be performed at a frequency of five minutes, that is, the original methane concentration data collected by all methane sensors on the same working surface are received. It should be noted that data collection can also be performed according to other sampling time periods, and this application does not make specific limitations.

[0036] In a specific embodiment, step S101 includes:

[0037] S10. Acquire corresponding calibration information based on the original methane concentration data;

[0038] S11. Based on the calibration information, determine whether the current working surface is in a calibration state. If the current working surface is in a calibration state, discard the original methane concentration data sent by all methane sensors on the current working surface.

[0039] Combine Figure 2 It can be seen that when methane gas gushes out from the working face, the methane gas passes through the three methane sensors T0, T1, and T2 in sequence, from which we can get the following: Figure 3The curve fluctuation diagram shown in FIG. 3 shows the concentration curves corresponding to the three methane sensors T0, T1, and T2 from top to bottom. The horizontal axis of the curve is time, and the vertical axis is methane concentration. It can be seen that the fluctuation trends of the three methane gas concentration curves are similar, and the intensity has a certain attenuation. Therefore, in this embodiment, first, the original methane concentration data sent by the three methane sensors T0, T1, and T2 are obtained, thereby obtaining the calibration information corresponding to the three methane sensors T0, T1, and T2. Specifically:

[0040] Press the formula to obtain the corresponding adjustment information T ad :

[0041]

[0042] Where V represents the original methane concentration data, S represents the current status information of the methane sensor, and α represents the concentration threshold.

[0043] In this embodiment, since the raw methane concentration data is composed of continuous data collected within a sampling time period, a methane concentration curve for a time period can be obtained. Based on the judgment of the four concentration thresholds or the status information of the methane sensor, the calibration information corresponding to the current methane sensor can be obtained. For example, α1, α2, α3, and α4 can be set as follows based on a large amount of existing historical calibration status and the "Coal Safety Monitoring System and Detection Instrument Usage Specifications": α1=1.45, α2=1.55, α3=1.95, and α4=2.05. When the raw methane concentration data V is between the concentration thresholds α1 and α2, the calibration information is marked as 1. Similarly, when the raw methane concentration data V is between the concentration thresholds α3 and α4, the calibration information is marked as 1. At the same time, when the methane sensor is in maintenance, the maintenance personnel will set the current status information of the methane sensor, that is, set the current status information of the methane sensor to "4", and the calibration information is marked as 1 at this time.

[0044] When it is determined that the calibration information in the original methane concentration data is 1, the original methane concentration data sent by all methane sensors on the current working surface are discarded, that is, it is no longer determined whether the methane sensor on the current working surface is abnormal. Through the above method, some invalid data can be screened out, reducing computing costs and improving data processing efficiency.

[0045] S102, preprocessing all the raw methane concentration data to align and standardize the raw methane concentration data to obtain a target methane concentration data curve;

[0046] In this embodiment, since the original methane concentration data is transmitted too frequently, resulting in a large amount of data being transmitted, this application sets the storage method of the original methane concentration data to variable value storage, that is, there will be a corresponding record point only when the original methane concentration data changes.

[0047] Due to the existence of the variable value storage method, the length of the original methane concentration data transmitted between different methane sensors on the same working surface is different, that is, the various methane concentration curves lack comparability. Therefore, the points where the original methane concentration data are not recorded are filled with the original methane concentration data of the methane sensor in the previous sampling time period. After the original methane concentration data is filled, the original methane concentration data is converted into comparable target methane concentration data of equal length. The obtained target methane concentration data is standardized to obtain a target methane concentration data curve, so that the original methane concentration data values ​​with different fluctuation ranges can be compared, that is, the units of distance calculation can be unified. Among them, the normal standardization scheme is used for standardization to calculate the mean and standard deviation of each methane sensor. Specifically:

[0048] The standard normal standardization is calculated as follows:

[0049]

[0050] Where Z represents the variable under the standard normal distribution, V represents the original methane concentration data, μ represents the mean of the original methane concentration data, and σ represents the standard deviation.

[0051] S103, calculating the shortest path distance value between each target methane concentration data curve using the DTW dynamic time warping method;

[0052] like Figure 5 As shown, it should be noted that the traditional Euclidean distance algorithm is usually used to calculate the distance value between two target methane concentration data curves. However, due to the time delay between the two target methane concentration data curves, the calculated Euclidean distance value will be too large, resulting in inaccurate judgment of correlation anomalies between methane sensors. Therefore, the gas curve correlation fluctuation anomaly identification method of the present application utilizes the DTW dynamic time warping method. This application is mainly used to measure the similarity of target methane concentration data curves that are both time series. The reason for using the shortest path distance value (i.e., the DTW distance value calculated by the DTW dynamic time warping method) to measure the similarity between target methane concentration data curves rather than the Euclidean distance value is that compared with the traditional Euclidean distance value, the DTW distance value can effectively reduce the error caused by time delay, thereby reducing the occurrence of inaccurate correlation anomalies between methane sensors.

[0053] In a specific embodiment, the aligned and standardized target methane concentration data curves L1 and L2 are obtained. In order to facilitate the horizontal comparison of the similarity between the two target methane concentration data curves, we can form an n×n grid as follows: Figure 4 As shown. Combined Figure 4 , the target methane concentration data curves L1 and L2 are found to have a path from (0, 0) to (n, n) in the grid based on the DTW dynamic time warping method, so that the distance between the data points on the two target methane concentration data curves on this path is the shortest. This path is recorded as , where x i ,y i are integers between 0 and n, satisfying , and the limited window interval w should satisfy Among them, the window interval w is limited to limit the alignment path to the vicinity of the diagonal line, so the DTW distance value calculated by the path is:

[0054]

[0055] Among them, L1(x k ), L2(y k ) represents the xth corresponding to L1 and L2 k point and y k points, d(L1(x k ), L2(y k )) represents the xth k point and y k The Euclidean distance of points.

[0056] The DTW distance value calculated by the above formula can effectively measure the similarity of the target methane concentration data curves in two time series with a certain time delay. Compared with the traditional Euclidean distance algorithm, this application can effectively reduce the error caused by time delay.

[0057] S104 : Compare all the shortest path distance values ​​(ie, DTW distance values) with a preset abnormal distance threshold. If the current shortest path distance value exceeds the abnormal distance threshold, issue an abnormal warning signal.

[0058] In a specific embodiment, step S104 includes the following steps:

[0059] S20, obtaining a historical methane concentration data set, and obtaining a target normal methane concentration data set and a target abnormal methane concentration data set from the historical methane concentration data set;

[0060] S21. Based on the target normal methane concentration data set, calculate the corresponding DTW distance value using the DTW dynamic time warping method and obtain the corresponding normal DTW distance value normal distribution curve;

[0061] S22. Based on the target abnormal methane concentration data set, calculate the corresponding DTW distance value using the DTW dynamic time warping method and obtain the corresponding abnormal DTW distance value normal distribution curve;

[0062] S23 : Based on the intersection of the normal distribution curve of the normal DTW distance value and the normal distribution curve of the abnormal DTW distance value, the intersection is used as the abnormal distance threshold.

[0063] Specifically, in the early stage, the curve characterization method was used to extract curve extreme values, curve fluctuation range, curve fluctuation degree and other features, analyze the similarity between the methane concentration data curves of different methane sensors on the same working face, and generate early warnings and push them to the coal mine end. This batch of historical data was divided into two categories of data: associated normal fluctuations and associated abnormal fluctuations through the judgment and feedback of the coal mine and experts.

[0064] In actual application scenarios, the normal methane concentration data curve group and the abnormal methane concentration data curve group in the same working face and the same sampling time period can be selected from the two major types of data, namely, associated normal fluctuations and associated abnormal fluctuations. A series of normal DTW distance values ​​and abnormal DTW distance values ​​can be calculated using the DTW dynamic time warping method. Assuming that the normal DTW distance values ​​and the abnormal DTW distance values ​​obey a normal distribution with different means and variances, the normal DTW distance value distribution curve and the abnormal DTW distance value distribution curve can be calculated respectively. The corresponding curve distribution diagrams are shown in the figure below. Figure 6 As shown in the figure, specifically, the distribution curve on the left is the normal DTW distance value distribution curve, and the distribution curve on the right is the abnormal DTW distance value distribution curve. The two DTW distance value distribution curves have an intersection point. An auxiliary line perpendicular to the horizontal axis is drawn through the intersection point. The value shown by the auxiliary line is the abnormal threshold. The abnormal threshold is used as the judgment standard for DTW distance in subsequent analysis. If it is greater than the abnormal threshold, it is judged that there is an installation abnormality problem with the methane sensor.

[0065] In a specific embodiment, regarding the early warning mechanism of the methane sensor, step S104 further includes:

[0066] S30. If the DTW distance value of a methane sensor is greater than the abnormal threshold, determine the number of groups of the original methane concentration data obtained. If the number of groups of the original methane concentration data is 2, execute step S31. If the number of groups of the original methane concentration data is n, where n>2, execute step S32.

[0067] S31, executing the preset first abnormality determination step;

[0068] S32: Execute the preset second abnormality judgment step.

[0069] In a specific embodiment, step S31 includes:

[0070] S40, respectively calculating and comparing the standard deviations of the two original methane concentration data to obtain the abnormal methane concentration data with the smallest standard deviation;

[0071] S41. Based on the abnormal methane concentration data, obtain corresponding abnormal methane sensor information.

[0072] Specifically, in this embodiment, two methane sensors are installed on a working surface. After receiving the raw methane concentration data sent by the two methane sensors in the current sampling time period, the standard deviation of the two raw methane concentration data is calculated. Since the raw methane concentration data of the methane sensor in the normal state fluctuates greatly, the methane sensor with the smaller standard deviation between the two is taken as the abnormal methane sensor, that is, the methane sensor with the smaller gas concentration fluctuation has caused the installation abnormality.

[0073] In a specific embodiment, step S32 includes:

[0074] S50, traverse all the methane concentration data, and calculate the sum of the DTW distance values ​​corresponding to the current original methane concentration data t according to the following formula s :

[0075]

[0076] Among them, t a represents the DTW distance value corresponding to the methane sensor; n represents the number of groups of methane concentration data.

[0077] It should be noted that, because the number of groups of original methane concentration data is n>2, that is, at least three methane sensors are installed on a working surface, there will be n-1 DTW distance values ​​corresponding to one methane sensor.

[0078] S51, after obtaining the sum of the DTW distance values ​​corresponding to all the original methane concentration data, obtaining the sum of the DTW distance values ​​with the largest value as the abnormal methane concentration data;

[0079] S52. Based on the abnormal methane concentration data, obtain corresponding abnormal methane sensor information.

[0080] If there are more than two methane sensors on the same working surface, assuming there are n methane sensors, calculate the DTW distance between each of them, and based on the historical analysis of the abnormal threshold, filter out abnormal DTW distances greater than the abnormal threshold. Use the following logic to determine the methane sensor with installation problems:

[0081] (1) Initialize the maximum distance and max s is 0;

[0082] (2) Traverse each methane sensor t in the methane sensor group;

[0083] (3) Calculate the sum ts of the DTW distance values ​​corresponding to each methane sensor t;

[0084] (4) If the sum of the DTW distance values ​​corresponding to the methane sensor t is t s Greater than the maximum distance max s , then update the maximum distance and max s is the abnormal DTW distance value and t s , and record the information of methane sensor t;

[0085] (5) After the traversal is completed, get the maximum distance and max s The corresponding methane sensor t information is used as the methane sensor with abnormal installation.

[0086] Specific, combined Figure 7 If there are three methane sensors T0, T1, and T2 on the same working surface, calculate the DTW distance values ​​between methane sensor T0 and methane sensor T1, methane sensor T1 and methane sensor T2, and methane sensor T0 and methane sensor T2 respectively. Set the DTW distance value between methane sensor T0 and methane sensor T1 to a, the DTW distance value between methane sensor T1 and methane sensor T2 to b, and the DTW distance value between methane sensor T0 and methane sensor T2 to c. If methane sensor T0 has an installation abnormality, both a and c will be greater than the abnormal threshold, while b will be lower than the abnormal threshold. Add the DTW distance values ​​corresponding to the three methane sensors T0, T1, and T2. It can be found that a+c corresponding to methane sensor T0 is higher than a+b corresponding to methane sensor T1. Similarly, a+c corresponding to methane sensor T0 is higher than a+b corresponding to methane sensor T2. Therefore, it can be determined that the sum of the DTW distance values ​​corresponding to methane sensor T0 is the highest.

[0087] In this embodiment, the installation problem of the methane sensor T0 can be accurately located by comparing the sum of the DTW distance values. At the same time, the terminal will record the information of the methane sensor T0 and highlight it on the display screen as a reminder.

[0088] At this point, the data information of the abnormal methane sensor in the methane sensor group corresponding to the same working surface is obtained, and an early warning conclusion of abnormal installation of the methane sensor is given.

[0089] The embodiment of the present invention further provides a device for identifying abnormal gas curve fluctuations, which is used to perform any embodiment of the aforementioned method for identifying abnormal gas curve fluctuations. Figure 8 , Figure 8 It is a schematic block diagram of a method and device for identifying abnormal gas curve correlation fluctuations provided by an embodiment of the present invention.

[0090] like Figure 9 As shown, the gas curve correlation fluctuation abnormality identification device 500 includes:

[0091] The sampling unit 501 is used to obtain raw methane concentration data sent by methane sensors at different positions on the same working surface based on a preset sampling rule;

[0092] A preprocessing unit 502 is configured to preprocess all of the raw methane concentration data to align and standardize the raw methane concentration data to obtain a target methane concentration data curve;

[0093] A calculation unit 503 is configured to calculate the shortest path distance value between the processed target methane concentration data curves using a DTW algorithm;

[0094] The early warning unit 504 is configured to compare all the shortest path distance values ​​with a preset abnormal distance threshold, and issue an abnormal early warning signal if the current shortest path distance value exceeds the abnormal distance threshold.

[0095] The device can analyze the correlation of methane sensor curves on the same working face, identify and issue early warnings for abnormally installed methane sensors, effectively prevent accidents, and help improve production safety.

[0096] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0097] The above-mentioned gas curve correlation fluctuation abnormality identification device can be implemented in the form of a computer program. The computer program can be used in the following ways: Figure 9 Runs on the computer equipment shown.

[0098] See also Figure 9 , Figure 91 is a schematic block diagram of a computer device provided by an embodiment of the present invention. The computer device 1100 is a server, which can be an independent server or a server cluster composed of multiple servers.

[0099] See Figure 9 The computer device 1100 includes a processor 1102 , a memory, and a network interface 1105 connected via a system bus 1101 , wherein the memory may include a non-volatile storage medium 1103 and an internal memory 1104 .

[0100] The non-volatile storage medium 1103 can store an operating system 11031 and a computer program 11032. When the computer program 11032 is executed, the processor 1102 can execute a method for identifying abnormal gas curve correlation fluctuations.

[0101] The processor 1102 is used to provide computing and control capabilities to support the operation of the entire computer device 1100.

[0102] The internal memory 1104 provides an environment for the operation of the computer program 11032 in the non-volatile storage medium 1103. When the computer program 11032 is executed by the processor 1102, the processor 1102 can execute the gas curve correlation fluctuation anomaly identification method.

[0103] The network interface 1105 is used for network communication, such as providing data information transmission. Those skilled in the art will understand that Figure 9 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device 1100 to which the solution of the present invention is applied. The specific computer device 1100 may include more or fewer components than those shown in the figure, or combine certain components, or have a different component arrangement.

[0104] Those skilled in the art will understand that Figure 9 The embodiment of the computer device shown in the figure does not constitute a limitation on the specific composition of the computer device. In other embodiments, the computer device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. For example, in some embodiments, the computer device may only include a memory and a processor. In such an embodiment, the structure and function of the memory and processor are the same as those in the figure. Figure 9 The embodiments shown are consistent and will not be described again here.

[0105] It should be understood that in the embodiment of the present invention, the processor 1102 may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0106] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium may be a non-volatile computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the method for identifying abnormal gas curve correlation fluctuations according to an embodiment of the present invention.

[0107] The storage medium is a physical, non-transient storage medium, for example, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which can store program codes.

[0108] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0109] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for identifying abnormal fluctuations in gas curve correlation, characterized in that: include: Based on the preset sampling rules, the raw methane concentration data sent by the methane sensors at different positions on the same working surface are obtained; All the raw methane concentration data are preprocessed to align and standardize the raw methane concentration data to obtain a target methane concentration data curve; the shortest path distance value between the processed target methane concentration data curve is calculated using a DTW algorithm; all the shortest path distance values ​​are compared with a preset abnormal distance threshold, and if the current shortest path distance value exceeds the abnormal distance threshold, an abnormal warning signal is issued.

2. The method for identifying abnormal gas curve fluctuations according to claim 1, characterized in that: After obtaining the raw methane concentration data sent by methane sensors at different positions on the same working surface based on a preset sampling rule, the method includes: obtaining corresponding calibration information based on the raw methane concentration data; judging whether the current working surface is in a calibration state based on the calibration information; and if the current working surface is in a calibration state, discarding the raw methane concentration data sent by all methane sensors on the current working surface.

3. The method for identifying abnormal gas curve fluctuations according to claim 2, characterized in that: The obtaining of corresponding calibration information based on the original methane concentration data includes: obtaining corresponding calibration information Tad according to the following formula: ； Where V represents the original methane concentration data, S represents the current status information of the methane sensor, and α represents the concentration threshold.

4. The method for identifying abnormal gas curve fluctuations according to claim 1, characterized in that: Before comparing all the shortest path distance values ​​with the preset abnormal distance threshold, the method includes: obtaining a historical methane concentration data set, and obtaining a target normal methane concentration data group and a target abnormal methane concentration data group from the historical methane concentration data set; based on the target normal methane concentration data group, using the DTW algorithm to calculate the corresponding shortest path distance value and obtain the corresponding normal distribution curve; based on the target abnormal methane concentration data group, using the DTW algorithm to calculate the corresponding shortest path distance value and obtain the corresponding abnormal normal distribution curve; based on the intersection of the normal distribution curve and the abnormal distribution curve, using the intersection as the abnormal distance threshold.

5. The method for identifying abnormal gas curve fluctuations according to claim 2, characterized in that: After the current shortest path distance value exceeds the abnormal distance threshold and before the abnormal warning signal is issued, the method includes: determining the number of groups of the obtained original methane concentration data; if the number of groups of the original methane concentration data is 2, executing a preset first abnormality judgment step; if the number of groups of the original methane concentration data is n, executing a preset second abnormality judgment step, wherein n>2.

6. The method for identifying abnormal gas curve fluctuations according to claim 5, characterized in that: The first abnormality judgment step includes: respectively calculating and comparing the standard deviations of the two original methane concentration data to obtain abnormal methane concentration data with the smallest standard deviation; and obtaining corresponding abnormal methane sensor data based on the abnormal methane concentration data.

7. The method for identifying abnormal gas curve fluctuations according to claim 5, characterized in that: The second abnormality judgment step includes: traversing all the methane concentration data, and calculating the sum of the shortest path distance values ​​ts corresponding to the current original methane concentration data according to the following formula: ； Wherein, ta represents the DTW distance value corresponding to the methane sensor, and n represents the number of groups of methane concentration data. After obtaining the sum of the shortest path distance values ​​corresponding to all the original methane concentration data, the sum of the shortest path distance values ​​with the largest value is obtained as the abnormal methane concentration data. Based on the abnormal methane concentration data, the corresponding abnormal methane sensor data is obtained.

8. A method and device for identifying abnormal fluctuations in gas curve correlation, characterized in that: include: A sampling unit is used to obtain raw methane concentration data sent by methane sensors at different positions on the same working surface based on a preset sampling rule; a preprocessing unit, configured to preprocess all the raw methane concentration data to align and standardize the raw methane concentration data to obtain a target methane concentration data curve; A calculation unit is used to calculate the shortest path distance value between each of the processed target methane concentration data curves using the DTW algorithm; an early warning unit is used to compare all the shortest path distance values ​​with a preset abnormal distance threshold, and if the current shortest path distance value exceeds the abnormal distance threshold, an abnormal warning signal is issued.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for identifying abnormal gas curve correlation fluctuations according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to execute the method for identifying abnormal gas curve correlation fluctuations according to any one of claims 1 to 7.

Images