Abnormity identification and processing method and device for coal mine tunnel displacement monitoring data
By using the least squares method to fit the linear regression model in the coal mine tunnel displacement monitoring data and iteratively update iteratively to identify and eliminate abnormal data points, the reliability of coal mine tunnel displacement monitoring data is solved, and the accuracy of monitoring data and the reliability of safety management is improved.
Patent Information
- Application Number
- CN202411775231.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-04
- Publication Date
- 2025-03-28
AI Technical Summary
The coal mine tunnel displacement monitoring data is affected by environmental interference and sensor performance attenuation, resulting in a decrease in data reliability and cannot provide robust safety management support.
The linear regression model is fitted by the least squares method, and the optimal linear regression model is obtained through iterative updates, and anomaly data points are identified and eliminated to ensure the accuracy and completeness of the data.
It improves the accuracy and reliability of coal mine tunnel displacement monitoring data, enhances the monitoring and early warning capabilities of tunnel safety, and effectively prevents coal mine safety accidents.
Smart Images
Figure CN119720118A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of coal mine tunnel displacement monitoring, and in particular to a method and device for abnormal identification and processing of coal mine tunnel displacement monitoring data. Background Art
[0002] With the continuous development of the coal industry and the deepening of mining depth, the safety issues of coal mine tunnels have become increasingly prominent. As an important part of the coal mine production system, the displacement and deformation of the tunnel has become an important factor affecting the safe production of coal mines. The causes of tunnel displacement and deformation are universal and complex, and are mainly affected by the combined influence of ground stress changes, geological conditions and mining activities. Tunnel displacement monitoring also faces many environmental interference factors, including drift of monitoring equipment caused by changes in temperature and humidity, decreased monitoring accuracy caused by dust, and interference from human factors such as tunnel ventilation, mechanical equipment vibration, transportation activities, and blasting operations. In addition, the long-term operation of sensor systems also has performance attenuation problems, which are mainly manifested in sensor fatigue, zero drift, and decreased signal transmission quality. These factors have seriously affected the reliability of monitoring data and cannot provide more robust data support for coal mine tunnel safety management. Summary of the invention
[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.
[0004] To this end, the first embodiment of the present disclosure proposes a method for identifying and processing abnormalities in coal mine tunnel displacement monitoring data, comprising the following steps:
[0005] Obtain n displacement monitoring data points of the coal mine tunnel within a preset time period, where n is a positive integer;
[0006] Selecting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, where k is a positive integer and n>k;
[0007] fitting a linear regression model based on the sample subset using the least squares method;
[0008] Iteratively updating the linear regression model according to the distance between each displacement monitoring data point among the n displacement monitoring data points and the linear regression model to obtain an optimal linear regression model;
[0009] Determine the residual of each displacement monitoring data point and the standard deviation of the residual based on the optimal linear regression model;
[0010] Comparing the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and identifying normal data points and abnormal data points among the n displacement monitoring data points based on the comparison result;
[0011] The abnormal data points are eliminated from the n displacement monitoring data points.
[0012] In some embodiments of the present disclosure, the linear regression model is expressed as follows:
[0013] v(t)=at+b
[0014]
[0015] Wherein, v(t) is the linear regression model, t i is the time corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points, v i is the displacement value corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points.
[0016] In some embodiments of the present disclosure, the iterative updating of the linear regression model according to the distance between each of the displacement monitoring data points and the linear regression model to obtain the optimal linear regression model includes: determining an optimal number, the optimal number being the number of data points among the n displacement monitoring data points whose distance from the optimal linear regression model is less than a preset distance threshold, and the initial value of the optimal number is preset; determining a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than the preset distance threshold; comparing the first number with the optimal number to obtain a comparison result, and selecting one of the linear regression model and the optimal linear regression model as a new optimal linear regression model according to the comparison result; returning to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, until the number of iterations reaches a preset N times, and determining the optimal linear regression model.
[0017] In some embodiments of the present disclosure, the iterative updating of the linear regression model according to the distance between each of the displacement monitoring data points and the linear regression model to obtain the optimal linear regression model includes: determining a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than a preset distance threshold; comparing the first number with a preset number threshold; if the first number is less than the preset number threshold, returning to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, until the first number is greater than or equal to the preset number threshold, and determining the linear regression model as the optimal linear regression model.
[0018] In some embodiments of the present disclosure, the residual of each displacement monitoring data point is compared with the standard deviation to obtain a comparison result, and the normal data points and abnormal data points among the N displacement monitoring data points are determined based on the comparison result, including: comparing the residual of each displacement monitoring data point with the standard deviation; determining the displacement monitoring data point among the n displacement monitoring data points whose residual is less than or equal to a preset T times of the standard deviation as the normal data point, and determining the displacement monitoring data point among the n displacement monitoring data points whose residual is greater than a preset T times of the standard deviation as the abnormal data point, where T is a positive integer.
[0019] The second aspect of the present disclosure provides a device for identifying and processing abnormalities in coal mine tunnel displacement monitoring data, comprising:
[0020] An acquisition module is used to acquire n displacement monitoring data points of a coal mine tunnel within a preset time period, where n is a positive integer;
[0021] A sampling module, used for extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, where k is a positive integer and n>k;
[0022] A fitting module, used for fitting a linear regression model based on the sample subset using a least squares method;
[0023] An updating module, configured to iteratively update the linear regression model according to the distance between each displacement monitoring data point among the n displacement monitoring data points and the linear regression model, so as to obtain an optimal linear regression model;
[0024] A determination module, configured to determine the residual of each displacement monitoring data point and the standard deviation of the residual based on the optimal linear regression model;
[0025] an identification module, configured to compare the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and identify normal data points and abnormal data points among the n displacement monitoring data points based on the comparison result;
[0026] A processing module is used to remove the abnormal data points from the n displacement monitoring data points.
[0027] In some embodiments of the present disclosure, the update module is specifically used to: determine an optimal number, the optimal number being the number of data points among the n displacement monitoring data points whose distance to the optimal linear regression model is less than a preset distance threshold, and the initial value of the optimal number is pre-set; determine a first number, the first number being the number of data points among the n displacement monitoring data points whose distance to the linear regression model is less than the preset distance threshold; compare the first number with the optimal number to obtain a comparison result, and select one from the linear regression model and the optimal linear regression model as a new optimal linear regression model according to the comparison result; return to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, until the number of iterations reaches a preset N times, and the optimal linear regression model is determined.
[0028] In some embodiments of the present disclosure, the update module is specifically used to: determine a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than a preset distance threshold; comparing the first number with a preset number threshold; if the first number is less than the preset number threshold, returning to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, until the first number is greater than or equal to the preset number threshold, and determining the linear regression model as the optimal linear regression model.
[0029] A third aspect of the present disclosure provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;
[0030] The memory stores computer-executable instructions;
[0031] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.
[0032] The fourth aspect of the present disclosure provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method described in the first aspect.
[0033] The present invention provides a method for identifying and processing abnormalities in displacement monitoring data of coal mine lanes, establishes an iterative data sampling and fitting model evaluation mechanism, combines the displacement monitoring data of coal mine lanes with the inherent consistency characteristics, and effectively identifies and eliminates abnormal data in displacement monitoring data points by fitting a linear regression model, thereby ensuring the accuracy and integrity of the data. Compared with the prior art method that mainly relies on fixed thresholds and manual experience for abnormality identification, the present invention uses a random sampling iteration method to establish an optimal model, improves the robustness of identification through multiple sampling optimizations, and effectively overcomes the shortcomings of traditional methods that are susceptible to noise interference. It is convenient for the accuracy of safety analysis of coal mines using displacement monitoring data points in the later stage, can improve the accuracy of lane displacement deformation monitoring and the reliability of early warning, and can effectively prevent coal mine safety accidents.
[0034] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0036] Figure 1 A schematic diagram of a flow chart of a method for identifying and processing abnormalities in coal mine tunnel displacement monitoring data provided by an embodiment of the present disclosure;
[0037] Figure 2 A schematic diagram of a displacement monitoring data point provided by an embodiment of the present disclosure;
[0038] Figure 3 A schematic diagram of a normal data point or an abnormal data point in a displacement monitoring data point provided by an embodiment of the present disclosure;
[0039] Figure 4 A schematic diagram of displacement monitoring data points after removing abnormal data points provided by an embodiment of the present disclosure;
[0040] Figure 5 A schematic diagram of an abnormality identification and processing device for coal mine tunnel displacement monitoring data provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0041] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.
[0042] Specifically, the method and device for identifying and processing abnormalities in coal mine tunnel displacement monitoring data according to an embodiment of the present disclosure will be described below with reference to the accompanying drawings.
[0043] Figure 1 The following is a flow chart of a method for identifying and processing abnormalities in coal mine tunnel displacement monitoring data provided by an embodiment of the present disclosure. Figure 1 As shown, the method for identifying and processing abnormalities in coal mine tunnel displacement monitoring data may include the following steps:
[0044] Step 101, obtaining n displacement monitoring data points of a coal mine tunnel within a preset time period, where n is a positive integer.
[0045] Among them, the n displacement monitoring data points are the displacement monitoring data of the same monitoring point in the coal mine tunnel. Figure 2 A schematic diagram of a displacement monitoring data point provided by an embodiment of the present disclosure. Figure 2 As shown, multiple displacement monitoring data points within a period of time are obtained, and each displacement monitoring data point corresponds to a time value and its corresponding displacement value.
[0046] Step 102: extract k displacement monitoring data points from n displacement monitoring data points as a sample subset, where k is a positive integer and n>k.
[0047] Wherein, k is a preset value. When extracting the sample subset, random extraction may be performed, or extraction may be performed according to a certain rule such as time interval, which is not limited.
[0048] Step 103: Fitting a linear regression model using the least squares method based on the sample subset.
[0049] Among them, the linear regression model can be expressed as follows:
[0050] v(t)=at+b
[0051]
[0052] Among them, v(t) is the linear regression model, t i is the time corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points in the sample subset, v i is the displacement value corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points in the sample subset.
[0053] Step 104 , iteratively updating the linear regression model according to the distance between each displacement monitoring data point among the n displacement monitoring data points and the linear regression model, to obtain an optimal linear regression model.
[0054] The present disclosure takes into account that the displacement monitoring data of coal mine tunnels has an inherent consistency feature, and based on this, proposes a method for fitting the data in the sample subset based on a mathematical model, and performs a consistency evaluation on the fitted model to evaluate the degree of conformity of all displacement monitoring data points with the model. Through multiple sampling-evaluations, the optimal linear regression model is found to achieve effective identification and elimination of abnormal data in the detection data. In this embodiment, the distance between the displacement monitoring data point and the fitting model reflects the degree of conformity of the displacement monitoring data point with the model. It is determined whether the distance between each of the n displacement monitoring data points and the fitting model meets the preset requirements. When the distances corresponding to the n displacement monitoring data points meet the preset requirements, the optimal linear regression model is determined.
[0055] In one possible implementation, the distance between n displacement monitoring data points and the linear regression model fitted using the sample subset can be calculated to represent the error between the actual measured displacement monitoring data points and the data points predicted by the fitted linear regression model. The smaller the error, the more consistent the linear regression model is with the actual data. The distance between the displacement monitoring data points and the linear regression model can be referred to the following formula:
[0056] d i =|v i -(at i +b)|
[0057] Among them, d i is the distance between the ith displacement monitoring data point among the n displacement monitoring data points and the linear regression model, t i is the time corresponding to the ith displacement monitoring data point among the n displacement monitoring data points, v i is the displacement value corresponding to the ith displacement monitoring data point among the n displacement monitoring data points, at i +b is the linear regression model based on the time t of the i-th displacement monitoring data point among the n displacement monitoring data points i The predicted corresponding displacement values.
[0058] Count the number of data points whose distance is less than the preset distance threshold θ among the n displacement monitoring data points (the preset distance threshold θ is used to determine whether the data point conforms to the fitting model), and obtain the first number. The formula for the first number is as follows:
[0059]
[0060] Where I(x) is the indicative function:
[0061]
[0062] Determine the number of data points among n displacement monitoring data points whose distance to the optimal linear regression model is less than a preset distance threshold, and obtain the optimal number. It should be noted that the optimal linear regression model is the historical optimal model determined in multiple iterations, and is the linear regression model with the largest number of data points whose distance to the displacement monitoring data points is less than a preset distance threshold among multiple fitting models. The initial value of the optimal number can be preset. Compare the first number with the optimal number to obtain a comparison result. According to the comparison result, select one of the linear regression model and the optimal linear regression model as the new optimal linear regression model. If the first number InlierCount is greater than the optimal number BestCount, update the model parameters {a best ,b best}, the linear regression model fitted this time is determined as the new optimal linear regression model:
[0063] If InlierCount>BestCount:{a best ,b best}={a,b}
[0064] If the first number InlierCount is less than or equal to the optimal number BestCount, the optimal linear regression model remains unchanged. After completing the number comparison and determining the new optimal linear regression model, return to execute the step of extracting k displacement monitoring data points from n displacement monitoring data points as the sample subset, re-extract the sample subset, fit the linear regression model, compare the linear regression model with the optimal linear regression model, select a new optimal linear regression model, and continue until the number of iterations reaches the preset N times to determine the optimal linear regression model.
[0065] In another possible implementation, a first number is determined, the first number being the number of data points in the n displacement monitoring data points whose distance from the linear regression model is less than a preset distance threshold. The first number is compared with the preset number threshold. The larger the value of the preset number threshold is, the higher the evaluation standard for the linear regression model is. If the first number is less than the preset number threshold, return to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, until the first number is greater than or equal to the preset number threshold, and the linear regression model is determined to be the optimal linear regression model.
[0066] The iterative optimization step in this embodiment only requires setting a small number of basic parameters to automatically optimize through iteration, which greatly reduces the professional threshold for parameter adjustment and improves the degree of system automation.
[0067] Step 105 , determining the residual of each displacement monitoring data point and the standard deviation of the residual based on the optimal linear regression model.
[0068] The residual error of each displacement monitoring data point can be referred to the following formula:
[0069] r i =|v i -(a best t i +b best )|
[0070] Among them, r i is the residual of the ith displacement monitoring data point among the n displacement monitoring data points, v i is the displacement value corresponding to the ith displacement monitoring data point among the n displacement monitoring data points, t i is the time corresponding to the ith displacement monitoring data point among the n displacement monitoring data points, a best t i +b best is the optimal linear regression model according to the time t of the ith displacement monitoring data point among the n displacement monitoring data points i The predicted corresponding displacement values.
[0071] The standard deviation σ of the residual can be referred to the following formula:
[0072]
[0073] in, is the residual mean value of the i-th displacement monitoring data point among the n displacement monitoring data points.
[0074] Step 106 , comparing the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and identifying normal data points and abnormal data points among the n displacement monitoring data points based on the comparison result.
[0075] In a possible implementation, the residual range of normal data points and the residual range of abnormal data points can be constructed based on the standard deviation. The residual of each displacement monitoring data point is compared with the constructed residual range to determine whether the displacement monitoring data point is a normal data point or an abnormal data point.
[0076] In one embodiment, the residual of each displacement monitoring data point can be compared with the standard deviation. Among the n displacement monitoring data points, the displacement monitoring data point whose residual is less than or equal to T times the preset standard deviation is determined as a normal data point, and the displacement monitoring data point whose residual is greater than T times the preset standard deviation is determined as an abnormal data point, where T is a positive integer.
[0077] As an example, when the residual of the displacement monitoring data point is greater than twice the standard deviation of the residual, that is, r i >2σ, the displacement monitoring data point is identified as an abnormal data point. When the residual of the displacement monitoring data point is less than or equal to twice the standard deviation of the residual, that is, ri ≤2σ, the displacement monitoring data point is identified as a normal data point. Figure 3 A schematic diagram of normal data points or abnormal data points in a displacement monitoring data point provided by an embodiment of the present disclosure.
[0078] Optionally, the data type can be further refined based on the actual needs of the coal mine scenario. For example, the displacement monitoring data points can be divided into normal data points, abnormal data points, and suspicious data points. For example, when the residual of the displacement monitoring data point is greater than the standard deviation of the double residual, that is, r i >3σ, the displacement monitoring data point is identified as an abnormal data point. When the residual of the displacement monitoring data point is between two and three times the standard deviation of the residual, that is, 2σ <r i ≤3σ, then the displacement monitoring data point is identified as a suspicious data point. When the residual of the displacement monitoring data point is less than or equal to twice the standard deviation of the residual, that is, r i ≤2σ, the displacement monitoring data point is identified as a normal data point. By establishing a multi-level abnormality judgment standard and residual analysis method, the recognition of sudden abnormalities is realized, filling the gap in the existing technology in abnormality recognition.
[0079] Step 107: Eliminate abnormal data points from the n displacement monitoring data points.
[0080] Figure 4 A schematic diagram of displacement monitoring data points after removing abnormal data points provided by an embodiment of the present disclosure.
[0081] By implementing the disclosed embodiments, an iterative data sampling and fitting model evaluation mechanism is established, and the displacement monitoring data of coal mine tunnels has the inherent consistency characteristics. By fitting a linear regression model, the abnormal data in the displacement monitoring data points are effectively identified and eliminated to ensure the accuracy and integrity of the data. Moreover, it is able to maintain a high recognition accuracy rate in the presence of a large amount of abnormal data, providing more robust data support for the safety management of coal mine tunnels. Compared with the prior art method that mainly relies on fixed thresholds and manual experience for abnormality identification, the present invention uses a random sampling iteration method to establish an optimal model, improves the robustness of identification through multiple sampling optimizations, and effectively overcomes the shortcomings of traditional methods that are susceptible to noise interference. It is convenient to use the displacement monitoring data points to conduct safety analysis of coal mines in the later stage, which can improve the accuracy of tunnel displacement deformation monitoring and the reliability of early warning, and can effectively prevent coal mine safety accidents.
[0082] Figure 5 A schematic diagram of an abnormal identification and processing device for coal mine tunnel displacement monitoring data provided by an embodiment of the present disclosure. Figure 5As shown, the device for identifying and processing abnormalities in coal mine tunnel displacement monitoring data may include: an acquisition module 501, a sampling module 502, a fitting module 503, an update module 504, a determination module 505, an identification module 506 and a processing module 507.
[0083] The acquisition module 501 is used to acquire n displacement monitoring data points of the coal mine tunnel within a preset time period, where n is a positive integer.
[0084] The sampling module 502 is used to extract k displacement monitoring data points from n displacement monitoring data points as a sample subset, where k is a positive integer and n>k.
[0085] The fitting module 503 is used to fit the linear regression model using the least square method based on the sample subset.
[0086] In some embodiments of the present disclosure, the linear regression model is expressed as follows:
[0087] v(t)=at+b
[0088]
[0089] Among them, v(t) is the linear regression model, t i is the time corresponding to the ith displacement monitoring data point among the k displacement monitoring data points, v i is the displacement value corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points.
[0090] The updating module 504 is used to iteratively update the linear regression model according to the distance between each displacement monitoring data point among the n displacement monitoring data points and the linear regression model to obtain an optimal linear regression model.
[0091] In some embodiments of the present disclosure, the update module 504 is specifically used to: determine an optimal number, the optimal number being the number of data points among n displacement monitoring data points whose distance to the optimal linear regression model is less than a preset distance threshold, and the initial value of the optimal number is pre-set; determine a first number, the first number being the number of data points among n displacement monitoring data points whose distance to the linear regression model is less than a preset distance threshold; compare the first number with the optimal number to obtain a comparison result, and select one from the linear regression model and the optimal linear regression model as a new optimal linear regression model according to the comparison result; return to execute the step of extracting k displacement monitoring data points from n displacement monitoring data points as a sample subset, until the number of iterations reaches the preset N times, and the optimal linear regression model is determined.
[0092] In some embodiments of the present disclosure, the update module 504 is specifically used to: determine a first number, which is the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than a preset distance threshold; compare the first number with the preset number threshold; if the first number is less than the preset number threshold, return to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, until the first number is greater than or equal to the preset number threshold, and determine the linear regression model as the optimal linear regression model.
[0093] The determination module 505 is used to determine the residual of each displacement monitoring data point and the standard deviation of the residual based on the optimal linear regression model.
[0094] The identification module 506 is used to compare the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and identify normal data points and abnormal data points among the n displacement monitoring data points based on the comparison result.
[0095] In some embodiments of the present disclosure, the identification module 506 is specifically used to: compare the residual of each displacement monitoring data point with the standard deviation; determine the displacement monitoring data point whose residual is less than or equal to T times the preset standard deviation among n displacement monitoring data points as a normal data point; determine the displacement monitoring data point whose residual is greater than T times the preset standard deviation among n displacement monitoring data points as an abnormal data point, where T is a positive integer.
[0096] The processing module 507 is used to remove abnormal data points from the n displacement monitoring data points.
[0097] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0098] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.
[0099] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.
[0100] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.
[0101] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.
[0102] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0103] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.
[0104] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0105] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0106] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
[0107] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.
[0108] The storage medium mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present disclosure have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present disclosure. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present disclosure.
Claims
1. A method for identifying and processing abnormalities in coal mine tunnel displacement monitoring data, characterized in that: The following steps are involved: Obtain n displacement monitoring data points of the coal mine tunnel within a preset time period, where n is a positive integer; Selecting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, where k is a positive integer and n>k; fitting a linear regression model based on the sample subset using the least squares method; Iteratively updating the linear regression model according to the distance between each displacement monitoring data point among the n displacement monitoring data points and the linear regression model to obtain an optimal linear regression model; Determine the residual of each displacement monitoring data point and the standard deviation of the residual based on the optimal linear regression model; Comparing the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and identifying normal data points and abnormal data points among the n displacement monitoring data points based on the comparison result; The abnormal data points are eliminated from the n displacement monitoring data points.
2. The method according to claim 1, characterized in that The linear regression model is expressed as follows: v(t)=at+b Wherein, v(t) is the linear regression model, t i is the time corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points, v i is the displacement value corresponding to the i-th displacement monitoring data point among the k displacement monitoring data points.
3. The method according to claim 1, characterized in that The iterative updating of the linear regression model according to the distance between each displacement monitoring data point and the linear regression model to obtain the optimal linear regression model includes: Determine an optimal number, the optimal number being the number of data points among the n displacement monitoring data points whose distance to the optimal linear regression model is less than a preset distance threshold, and an initial value of the optimal number is preset; Determine a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than the preset distance threshold; Comparing the first number with the optimal number to obtain a comparison result, and selecting one of the linear regression model and the optimal linear regression model as a new optimal linear regression model according to the comparison result; Return to the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset until the number of iterations reaches a preset N times, and determine the optimal linear regression model.
4. The method according to claim 1, characterized in that: The iterative updating of the linear regression model according to the distance between each displacement monitoring data point and the linear regression model to obtain the optimal linear regression model includes: Determine a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than the preset distance threshold; Comparing the first number with a preset number threshold; The first number is smaller than the preset number threshold, and the process returns to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset until the first number is greater than or equal to the preset number threshold, and the linear regression model is determined as the optimal linear regression model.
5. The method according to any one of claims 1 to 4, characterized in that The step of comparing the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and determining normal data points and abnormal data points among the N displacement monitoring data points based on the comparison result, comprises: Comparing the residual of each displacement monitoring data point with the standard deviation; The displacement monitoring data points whose residuals among the n displacement monitoring data points are less than or equal to T times the preset standard deviation are determined as the normal data points, and the displacement monitoring data points whose residuals among the n displacement monitoring data points are greater than T times the preset standard deviation are determined as the abnormal data points, where T is a positive integer.
6. A device for identifying and processing abnormalities in coal mine tunnel displacement monitoring data, characterized in that: include: An acquisition module is used to acquire n displacement monitoring data points of a coal mine tunnel within a preset time period, where n is a positive integer; A sampling module, used for extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset, where k is a positive integer and n>k; A fitting module, used for fitting a linear regression model based on the sample subset using a least squares method; An updating module, configured to iteratively update the linear regression model according to the distance between each displacement monitoring data point among the n displacement monitoring data points and the linear regression model, so as to obtain an optimal linear regression model; A determination module, configured to determine the residual of each displacement monitoring data point and the standard deviation of the residual based on the optimal linear regression model; an identification module, configured to compare the residual of each displacement monitoring data point with the standard deviation to obtain a comparison result, and identify normal data points and abnormal data points among the n displacement monitoring data points based on the comparison result; A processing module is used to remove the abnormal data points from the n displacement monitoring data points.
7. The device according to claim 6, characterized in that The update module is specifically used for: Determine an optimal number, the optimal number being the number of data points among the n displacement monitoring data points whose distance to the optimal linear regression model is less than a preset distance threshold, and an initial value of the optimal number is preset; Determine a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than the preset distance threshold; Comparing the first number with the optimal number to obtain a comparison result, and selecting one of the linear regression model and the optimal linear regression model as a new optimal linear regression model according to the comparison result; Return to the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset until the number of iterations reaches a preset N times, and determine the optimal linear regression model.
8. The device according to claim 6, characterized in that The update module is specifically used for: Determine a first number, the first number being the number of data points among the n displacement monitoring data points whose distance from the linear regression model is less than the preset distance threshold; Comparing the first number with a preset number threshold; The first number is smaller than the preset number threshold, and the process returns to execute the step of extracting k displacement monitoring data points from the n displacement monitoring data points as a sample subset until the first number is greater than or equal to the preset number threshold, and the linear regression model is determined as the optimal linear regression model.
9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 5.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 5 when executed by a processor.