Ground stress real-time monitoring method based on multi-source data fusion

Abstract

The invention relates to the technical field of data processing, in particular to a crustal stress real-time monitoring method based on multi-source data fusion, and the method comprises the steps: collecting three-dimensional crustal stress data of a crustal stress monitoring site, constructing a crustal stress ratio depth sequence, a horizontal crustal stress difference value depth sequence, a maximum horizontal crustal stress depth sequence and a minimum horizontal crustal stress depth sequence; calculating a stress ratio abnormal value according to the difference between the crustal stress ratio depth sequences; respectively obtaining a maximum horizontal stress abnormal value and a minimum horizontal stress abnormal value according to the distribution relation between the horizontal ground stress difference value depth sequence and the maximum horizontal ground stress depth sequence and the distribution relation between the horizontal ground stress difference value depth sequence and the minimum horizontal ground stress depth sequence; and obtaining a data fusion weight of each sensor at each acquisition moment based on the stress ratio abnormal value, the maximum horizontal stress abnormal value and the minimum horizontal stress abnormal value, and completing real-time monitoring of the crustal stress. Therefore, the reliability and the confidence degree of crustal stress monitoring data are improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a real-time monitoring method for ground stress based on multi-source data fusion. Background Art

[0002] Geostress refers to the forces that exist within the crustal rocks, which are caused by factors such as the Earth's tectonic activities, gravity, and surface processes. Real-time monitoring of geostress can help researchers understand geodynamic processes, prevent natural disasters, ensure the safety of engineering construction, and develop resources such as oil fields and coal.

[0003] Accurate geostress monitoring data is crucial to decision-making processes such as geological disaster prevention and resource development. However, geostress monitoring data may be affected by many factors, such as system deviations of monitoring equipment, environmental noise, equipment installation deviations, etc., which will cause deviations in the collected geostress data. The data fusion method based on weighted average method is a commonly used multi-source data fusion technology. This method performs weighted averaging on multiple data sources of geostress and reasonably distributes weights. It can reduce the impact of errors or outliers from a single data source on the overall monitoring results of geostress, and reduce the possibility of certain data sources with important information being ignored or having their contributions reduced. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a real-time monitoring method of ground stress based on multi-source data fusion to solve the existing problems.

[0005] The real-time monitoring method of geostress based on multi-source data fusion in this application adopts the following technical solutions:

[0006] An embodiment of the present application provides a real-time monitoring method for ground stress based on multi-source data fusion, the method comprising the following steps:

[0007] Collect three-dimensional geostress data at the geostress monitoring site at each moment, and obtain the vertical geostress sequence, maximum horizontal geostress sequence, minimum horizontal geostress sequence and formation depth value of each sensor on each grating line;

[0008] Based on the vertical geostress sequence, maximum horizontal geostress sequence, minimum horizontal geostress sequence and formation depth value of each sensor, the geostress ratio depth sequence, horizontal geostress difference depth sequence and maximum horizontal geostress depth sequence of each grating line at different acquisition times are constructed;

[0009] Determine the stress ratio abnormal value at each acquisition moment in the in-situ stress ratio sequence of each sensor according to the difference between the in-situ stress ratio depth sequences of each grating line at each acquisition moment and the data point of each sensor in the in-situ stress ratio depth sequence corresponding to the acquisition moment;

[0010] Determine the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal stress sequence of each sensor according to the distribution relationship between the horizontal stress difference depth sequence of each grating line at each acquisition moment and the maximum horizontal stress depth sequence;

[0011] The minimum horizontal geostress depth sequence is obtained by adopting the construction method of the maximum horizontal geostress depth sequence, and the minimum horizontal geostress depth sequence is obtained by adopting the same calculation method as the maximum horizontal stress anomaly value for the data points in the horizontal geostress difference depth sequence and the minimum horizontal geostress depth sequence, so as to obtain the minimum horizontal stress anomaly value at each acquisition time in the minimum horizontal geostress sequence;

[0012] Determine the data fusion weight of each sensor at each acquisition moment based on the stress ratio outlier, the maximum horizontal stress outlier, and the minimum horizontal stress outlier of each sensor at each acquisition moment;

[0013] The real-time monitoring of ground stress is completed by using the data fusion weight of each sensor at each acquisition moment.

[0014] Preferably, the method for constructing the in-situ stress ratio depth sequence is:

[0015] Calculate the mean between the data points at each acquisition time in the maximum horizontal in-situ stress sequence of each sensor and the data points at the corresponding acquisition time in the minimum horizontal in-situ stress sequence, record it as the first mean, and compose the horizontal in-situ stress sequence of each sensor with the first means of all acquisition times;

[0016] Calculate the ratio between the data point at each acquisition time in the horizontal geostress sequence of each sensor and the data point at the corresponding acquisition time in the vertical geostress sequence, and the ratios at all acquisition times constitute the geostress ratio sequence of each sensor;

[0017] The values ​​of the data points at the same acquisition time in the geostress ratio sequence of all sensors on each grating line are arranged in ascending order according to the stratum depth values ​​of the sensors to form the geostress ratio depth sequence of each grating line at the same acquisition time.

[0018] Preferably, the calculation method of the stress ratio abnormal value at each acquisition moment in the in-situ stress ratio sequence of each sensor is:

[0019] Calculate the Pearson correlation coefficient between the value of each data point in the geostress ratio depth sequence of each grating line at each acquisition time and the sequence composed of the subscript value of each data in the geostress ratio depth sequence as the ratio depth correlation coefficient of the geostress ratio depth sequence of each grating line at each acquisition time;

[0020] The ratio sequence abnormal value of the ground stress ratio depth sequence of each grating line at each acquisition time is calculated according to the difference between the ground stress ratio depth sequences of each grating line at each acquisition time and the ratio depth correlation coefficient;

[0021] Calculate the stress ratio characteristic value at each acquisition moment in the in-situ stress ratio sequence of each sensor according to the formation depth value of each sensor and the value of the data point at each acquisition moment in the in-situ stress ratio sequence;

[0022] The product of the ratio sequence abnormal value and the stress ratio characteristic value at the corresponding moment is taken as the stress ratio abnormal value at each acquisition moment in the ground stress ratio sequence of each sensor.

[0023] Preferably, the calculation method of the ratio sequence abnormal value of the ground stress ratio depth sequence of each grating line at each acquisition moment is:

[0024] Calculate the mean of the DTW distances between the in-situ stress ratio depth sequence of each grating line at each acquisition time and the in-situ stress ratio depth sequences of the remaining grating lines at the corresponding acquisition time, and record it as the second mean;

[0025] The product of the calculation result of the exponential function with the natural constant as the base and the ratio depth correlation coefficient as the exponent and the second mean value is used as the ratio sequence anomaly of the ground stress ratio depth sequence of each grating line at each acquisition moment.

[0026] Preferably, the stress ratio characteristic value at each acquisition moment in the in-situ stress ratio sequence of each sensor is calculated by the formula:

[0027]

[0028] In the formula, s ′ m ′ ,n,t represents the stress ratio characteristic value at the tth acquisition time in the ground stress ratio sequence of the nth sensor on the mth grating line; H m,n Indicates the formation depth value of the nth sensor on the mth grating line; b m,n,t It represents the value of the data point at the tth acquisition time in the ground stress ratio sequence of the nth sensor on the mth grating line; β is the parameter adjustment constant; max() represents the function of outputting the maximum value in the brackets.

[0029] Preferably, the method for constructing the horizontal geostress difference depth sequence and the maximum horizontal geostress depth sequence is:

[0030] The horizontal in-situ stress difference sequence of each sensor on each grating line is obtained according to the difference between the data points at each acquisition time in the maximum horizontal in-situ stress sequence and the data points at the corresponding acquisition time in the minimum horizontal in-situ stress sequence;

[0031] Arrange the values ​​of the data points at the same acquisition time in the horizontal geostress difference value sequence of all sensors on each grating line in ascending order according to the formation depth value of the sensor to form the horizontal geostress difference value depth sequence of each grating line at the same acquisition time;

[0032] The values ​​of the data points at the same corresponding acquisition time in the maximum horizontal geostress sequence of all sensors on each grating line are arranged in ascending order according to the formation depth values ​​of the sensors to form the maximum horizontal geostress depth sequence of each grating line at the same acquisition time.

[0033] Preferably, the method for determining the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal in-situ stress sequence of each sensor is:

[0034] Obtaining the difference sequence abnormal value of the depth sequence of the horizontal in-situ stress difference change rate at each acquisition moment according to the horizontal in-situ stress difference depth sequence of each grating line at each acquisition moment and the maximum horizontal in-situ stress depth sequence, and obtaining the maximum horizontal in-situ stress depth correlation coefficient of the maximum horizontal in-situ stress depth sequence;

[0035] Based on the data points in the maximum horizontal in-situ stress depth series, linear fitting is performed to calculate the Euclidean distance from each data point to the straight line, and the point-line distance of each data point in the maximum horizontal in-situ stress depth series is obtained;

[0036] The maximum horizontal stress anomaly value at each acquisition time in the maximum horizontal stress sequence of each sensor is calculated as follows:

[0037]

[0038] In the formula, represents the stress sequence anomaly value of the maximum horizontal ground stress depth sequence of the mth grating line at the tth acquisition time; w ′ m,t It represents the abnormal value of the difference sequence of the horizontal stress difference depth sequence of the mth grating line at the tth acquisition time; The maximum horizontal in-situ stress depth correlation coefficient representing the maximum horizontal in-situ stress depth series;

[0039] Calculate the mean of the point-line distance difference between the data point of the nth sensor and the remaining data points in the maximum horizontal in-situ stress depth sequence at the tth acquisition time of the mth grating line, record it as the third mean, and record the product of the third mean and the point-line distance of the data point of the nth sensor in the maximum horizontal in-situ stress depth sequence at the tth acquisition time of the mth grating line as It is the maximum horizontal stress anomaly value of the data point at the tth acquisition time in the maximum horizontal stress sequence of the nth sensor of the mth grating line.

[0040] Preferably, the step of obtaining the difference sequence abnormal value of the depth sequence of the horizontal geostress difference change rate of each grating line at each acquisition moment, and obtaining the maximum horizontal geostress depth correlation coefficient of the maximum horizontal geostress depth sequence includes:

[0041] Perform first-order difference on the horizontal geostress difference depth sequence to obtain the depth sequence of the horizontal geostress difference change rate of each grating line at each acquisition time;

[0042] Calculate the Pearson correlation coefficient between the depth sequence of the horizontal geostress difference change rate of each grating line at each acquisition moment and the sequence composed of the subscript values ​​of each data in the depth sequence of the horizontal geostress difference change rate as the depth correlation coefficient of the horizontal geostress difference change rate of each grating line at each acquisition moment, and record the opposite number of the depth correlation coefficient of the difference change rate as the abnormal value of the difference sequence;

[0043] Based on the maximum horizontal geostress depth sequence, the maximum horizontal geostress depth correlation coefficient of the maximum horizontal geostress depth sequence of each grating line at each acquisition moment is obtained by using the same calculation method of the difference change rate depth correlation coefficient.

[0044] Preferably, the calculation method of the data fusion weight at each acquisition moment of each sensor is:

[0045] Calculate the product of the stress ratio anomaly at each acquisition moment in the in-situ stress ratio sequence of each sensor, the maximum horizontal stress anomaly at each acquisition moment in the maximum horizontal in-situ stress sequence, and the minimum horizontal stress anomaly at each acquisition moment in the minimum horizontal in-situ stress sequence;

[0046] The normalized result of the reciprocal of the product is used as the weight distribution coefficient of each sensor at each acquisition moment;

[0047] The proportion of the weight distribution coefficient of each sensor at each acquisition moment in the weight distribution coefficients of all sensors at each acquisition moment is used as the data fusion weight of each sensor at each acquisition moment.

[0048] Preferably, the method for completing real-time monitoring of ground stress based on the data fusion weight of each sensor at each acquisition moment is:

[0049] Calculate the product of the vertical geostress in the original three-dimensional geostress data of each sensor at each acquisition moment and the data fusion weight at each acquisition moment, and use the average of the products of all sensors as the vertical geostress monitoring data at each acquisition moment at the geostress monitoring location;

[0050] For the maximum horizontal geostress and the minimum horizontal geostress, the same acquisition method of the vertical geostress monitoring data is adopted to obtain the maximum horizontal geostress monitoring data and the minimum horizontal geostress monitoring data at the geostress monitoring site at each acquisition time;

[0051] Based on the vertical geostress monitoring data, the maximum horizontal geostress monitoring data and the minimum horizontal geostress monitoring data, the geostress is monitored in combination with the preset thresholds.

[0052] This application has at least the following beneficial effects:

[0053] The present application constructs stress ratio anomalies by analyzing the distribution of data points in the geostress ratio sequence and the geostress ratio depth sequence constructed by each geostress sequence, and has the beneficial effect of improving the recognition accuracy when the vertical geostress has data deviation anomalies in the original three-dimensional geostress data; constructs the maximum horizontal stress anomalies by analyzing the distribution of data points in the horizontal geostress difference depth sequence and the maximum horizontal geostress depth sequence, and constructs the difference sequence anomalies and the stress sequence anomalies, and has the beneficial effect of improving the distinction between the maximum horizontal geostress and the minimum horizontal geostress with data deviation anomalies when the original three-dimensional geostress data has data deviation anomalies; constructs data fusion weights by combining the sampling data anomaly characteristic values ​​constructed by the stress ratio anomalies, the maximum horizontal stress anomalies, and the minimum horizontal stress anomalies, and has the beneficial effect of improving the distinction between the degree of data deviation that occurs when different sensors collect the original three-dimensional geostress data, and adaptively obtains the weight value of the original three-dimensional geostress data of each sensor at each collection time when performing data fusion, reduces the influence of the original three-dimensional geostress data with large deviations on the overall geostress monitoring results, and improves the reliability and confidence of the geostress monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A flowchart of the steps of the real-time monitoring method of ground stress based on multi-source data fusion provided in this application;

[0056] Figure 2 A distribution map of fiber gratings and sensors in the ground stress monitoring sites provided for this application;

[0057] Figure 3 This is a flowchart of the steps for obtaining the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal geostress sequence provided in this application. DETAILED DESCRIPTION

[0058] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, describes in detail the specific implementation method, structure, characteristics and effects of the real-time monitoring method of ground stress based on multi-source data fusion proposed in the present application. 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.

[0059] 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 application belongs.

[0060] The specific scheme of the real-time monitoring method of ground stress based on multi-source data fusion provided by the present application is described in detail below with reference to the accompanying drawings.

[0061] An embodiment of the present application provides a method for real-time monitoring of ground stress based on multi-source data fusion. Specifically, the following method for real-time monitoring of ground stress based on multi-source data fusion is provided. Figure 1 , the method comprises the following steps:

[0062] Step 1: Collect three-dimensional geostress data at the geostress monitoring site at each moment, and obtain the vertical geostress sequence, maximum horizontal geostress sequence, minimum horizontal geostress sequence and formation depth value of each sensor on each grating line.

[0063] M grating lines are evenly buried in the vertical direction at the ground stress monitoring site, and M high-precision three-dimensional ground stress sensors based on fiber gratings are evenly installed on each grating line, so that there are N sensors at the same stratum depth at the ground stress monitoring site to collect the original three-dimensional ground stress data at various positions at different depths of the ground stress monitoring site, which are vertical ground stress, maximum horizontal ground stress, and minimum horizontal ground stress. The empirical values ​​of M and N are 16 and 20 respectively, and the empirical values ​​of the data sampling time interval and sampling time of each sensor are 20 seconds and 10 minutes respectively. This embodiment only provides a method for distributing fiber gratings and sensors and a data sampling time scheme, and other implementers can set them by themselves. To facilitate subsequent processing, the set of all sensors on the mth grating line is recorded as sensor set G. m , get the set G m The value of the formation depth where each sensor is located, and the set G m The nth sensor in is denoted as sensor g. m,n .

[0064] Furthermore, in one embodiment of the present application, the distribution of the fiber gratings and sensors in the ground stress monitoring site is as follows: Figure 2 shown.

[0065] The original three-dimensional geostress data of each sensor and the values ​​of the formation depth of all sensors are normalized and dimensionless using the "max-min" normalization method. The "max-min" normalization method is a well-known technology and will not be described in detail. The geostress series and formation depth of each sensor after dimensionless processing are obtained, and the sensor g is used as the g of the sensor. m,n For example, the depth of the formation is H m,n , the geostress sequence includes the vertical geostress sequence Maximum horizontal stress sequence and the minimum horizontal stress sequence The values ​​of the data points in each sequence obtained are arranged in ascending order according to the time when the data points were collected.

[0066] At this point, the vertical geostress sequence, maximum horizontal geostress sequence, minimum horizontal geostress sequence and formation depth value of each sensor on each grating line are obtained.

[0067] Step 2: construct the in-situ stress ratio depth sequence, the horizontal in-situ stress difference depth sequence and the maximum horizontal in-situ stress depth sequence for each grating line at each acquisition time.

[0068] Generally, at the same acquisition time, the ratio of the average horizontal geostress to the vertical geostress will decrease with the increase of the formation depth and approach 1. The average horizontal geostress is the average of the maximum horizontal geostress and the minimum horizontal geostress collected by the sensor at each acquisition time. In addition, since sensors at the same formation depth on different grating lines generally have similar geological conditions, such as rock type and formation structure, and are subject to similar external influences, such as surface load and climate change, the ratio of the average horizontal geostress to the vertical geostress of sensors in different sensor sets at the same acquisition time has similar data changes with the change of the formation depth of the sensor.

[0069] Based on the above analysis, the sensor g m,n For example, calculate the sequence The average value between the data points at the same position in the , and the average horizontal ground stress series Calculate the sequence separately Each data point in the sequence The ratio of the data points at the same position in is recorded as the ground stress ratio, and the ground stress ratio sequence B is obtained. m,n .

[0070] Further, the calculation sequence The difference between the data points at the same position in the horizontal in-situ stress difference is recorded as the horizontal in-situ stress difference, and the horizontal in-situ stress difference sequence ΔA is obtained. m,n . Take the set G m For example, get the set G m The value of the tth data point in the horizontal stress difference sequence of each sensor in , all the obtained values ​​are arranged in ascending order according to the value of the formation depth of the sensor, and the set G is obtained. m The depth sequence of horizontal stress difference at the tth acquisition time GA m,t .

[0071] The set G m The values ​​of the t-th data point in the maximum horizontal ground stress sequence of all sensors in are arranged in ascending order according to the values ​​of the formation depth of the sensors, and the set G is obtained. m The maximum horizontal stress depth sequence at the tth acquisition time

[0072] At this point, the in-situ stress ratio depth sequence, the horizontal in-situ stress difference depth sequence and the maximum horizontal in-situ stress depth sequence of each grating line at each acquisition moment are obtained.

[0073] Step 3, determining the stress ratio abnormal value at each acquisition moment in the geostress ratio sequence of each sensor according to the difference between the geostress ratio depth sequences of each grating line at each acquisition moment and the data points of each sensor at each acquisition moment in the geostress ratio depth sequence.

[0074] With set G m For example, get the set G m The value of the tth data point in the in-situ stress ratio sequence of each sensor in , all the obtained values ​​are arranged in ascending order according to the formation depth value of the sensor, and the set G is obtained m The depth series GB of the ground stress ratio at the tth acquisition time m,t , calculate the sequence GB m,t The Pearson correlation coefficient between the sequence composed of the subscript values ​​of each data point in and the value of the data point is obtained, and the sequence GB m,t The ratio depth correlation coefficient p m,t , wherein the subscript value of each data point is numbered in ascending order starting from 1 according to the formation depth value. The calculation of the Pearson correlation coefficient is a well-known technology, and the specific process will not be repeated here.

[0075] Construct stress ratio anomaly values ​​to characterize the possibility of abnormality of each data point in the ground stress ratio sequence of each sensor. Calculate sequence B m,n The tth data point B in m,n,t The stress ratio abnormal value S m,n,t :

[0076]

[0077] S m,n,t =s ′ m,t *s ′ m ′ ,n,t

[0078] In the formula, s ′ m,t Represents the sequence GB m,t The ratio sequence outliers of DGB m,t Denotes the set G m The mean of the DTW distances between the ground stress ratio depth series of the rest of the sensor sets at the tth acquisition time; p m,t Represents the sequence GB m,t The ratio depth correlation coefficient; β represents the parameter adjustment constant. In order to prevent the denominator from being 0, the empirical value of β is 0.01; s ′ m ′ ,n,t Indicates sensor g m,n The characteristic value of the stress ratio at the tth acquisition time in the in-situ stress ratio sequence; H m,n Indicates sensor g m,n The value of the formation depth; b m,n,t Represents sequence Bm,n The tth data point B in m,n,t The value of; max() represents a function that outputs the maximum value in the brackets.

[0079] It should be understood that the embodiment of the present application only provides a method for measuring the difference between two sensor set sequences, namely, the DTW algorithm. As other implementation methods, on the premise that the purpose of the method for measuring the difference between two sensor set sequences can be achieved, the existing measurement method can be used to measure the difference between the two sensor set sequences. This embodiment does not impose any special restrictions on this.

[0080] Collection G m The less similar the data changes are between the depth series of the ground stress ratio at the tth acquisition time and the other sensor sets, the greater the DGB m,t The larger the value, the greater the sequence GB m,t The weaker the negative correlation between the in-situ stress ratio of the data point and the formation depth, the m,t The larger the value of s ′ m,t The larger the value, the greater the sequence GB m,t The greater the probability that the data points in the

[0081] In sensor g m,n The deeper the formation, the more points B m,n,t The closer the value is to 1, The smaller the value, or the smaller the sensor g m,n The smaller the depth of the formation, the smaller the base B m,n,t The less close the value of is to 1, The smaller the value of is, the smaller the data point B is. m,n,t The smaller the possibility of abnormality, the ′ m ′ ,n,t The smaller the value of m,n,t The greater the possibility of abnormality, S m,n,t The larger the value, the greater the sensor g m,n The greater the possibility that the vertical geostress, maximum horizontal geostress, or minimum horizontal geostress collected at the tth collection moment will have data deviation anomalies.

[0082] At this point, the stress ratio anomaly values ​​at each acquisition moment in the in-situ stress ratio sequence of each sensor are obtained.

[0083] Step 4, according to the distribution relationship between the horizontal geostress difference depth sequence of each grating line at each acquisition moment and the maximum horizontal geostress depth sequence and the minimum horizontal geostress depth sequence, respectively calculate the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal geostress sequence of each sensor and the minimum horizontal stress anomaly value at each acquisition moment in the minimum horizontal geostress sequence.

[0084] Furthermore, the maximum horizontal geostress and the minimum horizontal geostress will increase linearly with the depth of the formation, and the difference in the geostress values ​​between the two will increase with the increase in depth.

[0085] Based on the above analysis, the sequence GA m,t Perform first-order difference processing to obtain the depth series ΔGA of the horizontal stress difference change rate m,t , use and calculate the correlation coefficient p m,t The same method is used to obtain the sequence ΔGA m,t The depth correlation coefficient of the difference change rate p ′ m,t , the correlation coefficient p ′ m,t The opposite number of is recorded as the sequence ΔGA m,t The difference sequence outlier w ′ m,t , w ′ m,t The larger the value of m,t The weaker the positive correlation between the value of the data point and the formation depth, the stronger the sequence ΔGA m,t The greater the possibility that the data points in G are abnormal, the m The greater the possibility that the maximum horizontal geostress and the minimum horizontal geostress collected by the sensor at the tth collection time are abnormal.

[0086] With set G m For example, use and calculate the correlation coefficient p m,t The same method is used to obtain the sequence Correlation coefficient of maximum horizontal ground stress depth

[0087] Secondly, for the sequence The data points in the linear fit are The serial number of the data point and the value of the data point are the horizontal and vertical coordinates, and the fitting straight line is obtained. Calculation sequence Each data point in the The Euclidean distance on The point-to-line distance of each data point in , linear fitting is a well-known technology, and the specific process will not be repeated here.

[0088] The maximum horizontal stress anomaly value is constructed to characterize the possibility of anomalies in each data point in the maximum horizontal stress series of each sensor. The tth data point collected at the time The maximum horizontal stress anomaly

[0089]

[0090] In the formula, Representation sequence The stress series abnormal value at the tth acquisition moment in w ′ m,t Represents the sequence ΔGA m,t The difference series of outliers; Representation sequence The maximum horizontal stress depth correlation coefficient; Indicates sensor g m,n In sequence The corresponding data points with sequence The mean of the point-to-line distance difference between the remaining data points and the data point The product of the distances between the points and the lines.

[0091] Among them, the set G m The greater the possibility that the maximum horizontal ground stress and the minimum horizontal ground stress collected by the sensor at the tth collection time are abnormal, the greater the probability that w ′ m,t The larger the value of The less the value of the data point increases linearly with the depth of the formation, The larger the value of The more likely the data points in The larger the value of The greater the distance between the points and lines, and The greater the difference in the point-line distances between the remaining data points in The larger the value of , the smaller the data point The greater the possibility of abnormality, the greater the sensor g m,n The greater the possibility of abnormal data deviation in the maximum horizontal in-situ stress collected at the tth acquisition time, The larger the value of .

[0092] In one embodiment of the present application, the flowchart of the method for obtaining the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal ground stress sequence of each sensor is as follows: Figure 3 shown.

[0093] Based on the same method as above, the minimum horizontal stress depth series is constructed And the sequence Replace with sequence Build sequence The data point at the tth collection time in The minimum horizontal stress anomaly

[0094] At this point, the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal in-situ stress sequence of each sensor and the minimum horizontal stress anomaly value at each acquisition moment in the minimum horizontal in-situ stress sequence are obtained.

[0095] Step 5: Calculate the data fusion weight of each sensor at each acquisition moment based on the stress ratio outlier, the maximum horizontal stress outlier, and the minimum horizontal stress outlier of each sensor at each acquisition moment.

[0096] Furthermore, the sensor g m,n For example, the ratio sequence outlier S m,n,t , maximum horizontal stress anomaly Minimum horizontal stress anomaly The product of the three is the sensor g m,n The abnormal characteristic value f of the sampled data at the tth acquisition time m,n,t . Construct data fusion weights to characterize the weight value of each sensor when fusing the original 3D geostress data at each acquisition moment. Calculate sensor g m,n The data fusion weight γ at the tth acquisition time m,n,t :

[0097]

[0098] In the formula, α m,n,t Indicates sensor g m,n The weight distribution coefficient at the tth acquisition moment; f m,n,t Indicates sensor g m,n The abnormal characteristic value of the sampling data at the tth acquisition moment; β represents the parameter adjustment constant. In order to prevent the denominator from being 0, the empirical value of β is 0.01; norm() represents the function that normalizes the values ​​in the brackets.

[0099] Eigenvalue F m,n,t The larger the value, the greater the sensor g m,n The greater the possibility that the original three-dimensional geostress data collected at the t-th collection time has a large deviation, the smaller the weight should be assigned when using the three-dimensional geostress data for data fusion, α m,n,t The smaller the value of sensor g is, the lower the impact of the data deviation of the three-dimensional geostress data on the overall monitoring result of geostress.m,n The data fusion weight γ at the tth acquisition time m,n,t The smaller the value of .

[0100] At this point, the data fusion weight of each sensor at each acquisition moment is obtained.

[0101] Step 6: Use the data fusion weight of each sensor at each acquisition moment to complete the real-time monitoring of ground stress.

[0102] Taking the vertical geostress in the original three-dimensional geostress data collected at the t-th collection time as an example, the product of the vertical geostress in the original three-dimensional geostress data collected by each sensor at the t-th collection time and the data fusion weight of the sensor at the t-th collection time is calculated respectively, and the average of all the products is taken as the vertical geostress monitoring number of the geostress monitoring site at the t-th collection time. The vertical geostress monitoring data of the geostress monitoring site at each collection time is obtained by the same method and uploaded to the geostress monitoring system.

[0103] Based on the same method as above, the vertical geostress is replaced by the maximum horizontal geostress and the minimum horizontal geostress, respectively, and the maximum horizontal geostress monitoring data and the minimum horizontal geostress monitoring data of the geostress monitoring site at each collection time are obtained and uploaded to the geostress monitoring system.

[0104] The obtained vertical geostress monitoring data, maximum horizontal geostress monitoring data, and minimum horizontal geostress monitoring data are collectively referred to as three-dimensional geostress monitoring data. If the value of any data in the three-dimensional geostress monitoring data exceeds the monitoring threshold, an alarm is issued to remind the staff, wherein the monitoring threshold is set by the staff according to the geological conditions of the geostress monitoring site.

[0105] It should be noted that the above sequence of the embodiments of the present application is for description only 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.

[0106] 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.

[0107] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Modifications to the technical solutions recorded in the aforementioned embodiments, or equivalent replacement of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A real-time monitoring method for ground stress based on multi-source data fusion, characterized in that: The method comprises the following steps: Collect three-dimensional geostress data at the geostress monitoring site at each moment, and obtain the vertical geostress sequence, maximum horizontal geostress sequence, minimum horizontal geostress sequence and formation depth value of each sensor on each grating line; Based on the vertical geostress sequence, maximum horizontal geostress sequence, minimum horizontal geostress sequence and stratum depth value of each sensor, the geostress ratio depth sequence, horizontal geostress difference depth sequence and maximum horizontal geostress depth sequence of each grating line at each acquisition time are constructed; Determine the stress ratio abnormal value at each acquisition moment in the in-situ stress ratio sequence of each sensor according to the difference between the in-situ stress ratio depth sequences of each grating line at each acquisition moment and the data point of each sensor in the in-situ stress ratio depth sequence corresponding to the acquisition moment; Determine the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal stress sequence of each sensor according to the distribution relationship between the horizontal stress difference depth sequence of each grating line at each acquisition moment and the maximum horizontal stress depth sequence; The minimum horizontal geostress depth sequence is obtained by adopting the construction method of the maximum horizontal geostress depth sequence, and the minimum horizontal geostress depth sequence is obtained by adopting the same calculation method as the maximum horizontal stress anomaly value for the data points in the horizontal geostress difference depth sequence and the minimum horizontal geostress depth sequence, so as to obtain the minimum horizontal stress anomaly value at each acquisition time in the minimum horizontal geostress sequence; Determine the data fusion weight of each sensor at each acquisition moment based on the stress ratio outlier, the maximum horizontal stress outlier, and the minimum horizontal stress outlier of each sensor at each acquisition moment; The real-time monitoring of ground stress is completed by using the data fusion weight of each sensor at each acquisition moment.

2. The method for real-time monitoring of ground stress based on multi-source data fusion according to claim 1, characterized in that: The construction method of the in-situ stress ratio depth series is as follows: Calculate the mean between the data points at each acquisition time in the maximum horizontal in-situ stress sequence of each sensor and the data points at the corresponding acquisition time in the minimum horizontal in-situ stress sequence, record it as the first mean, and compose the horizontal in-situ stress sequence of each sensor with the first means of all acquisition times; Calculate the ratio between the data point at each acquisition time in the horizontal geostress sequence of each sensor and the data point at the corresponding acquisition time in the vertical geostress sequence, and the ratios at all acquisition times constitute the geostress ratio sequence of each sensor; The values ​​of the data points at the same acquisition time in the geostress ratio sequence of all sensors on each grating line are arranged in ascending order according to the stratum depth values ​​of the sensors to form the geostress ratio depth sequence of each grating line at the same acquisition time.

3. The method for real-time monitoring of geostress based on multi-source data fusion according to claim 2, characterized in that: The calculation method of the stress ratio abnormal value at each acquisition moment in the in-situ stress ratio sequence of each sensor is as follows: Calculate the Pearson correlation coefficient between the value of each data point in the geostress ratio depth sequence of each grating line at each acquisition time and the sequence composed of the subscript value of each data in the geostress ratio depth sequence as the ratio depth correlation coefficient of the geostress ratio depth sequence of each grating line at each acquisition time; The ratio sequence abnormal value of the ground stress ratio depth sequence of each grating line at each acquisition time is calculated according to the difference between the ground stress ratio depth sequences of each grating line at each acquisition time and the ratio depth correlation coefficient; Calculate the stress ratio characteristic value at each acquisition moment in the in-situ stress ratio sequence of each sensor according to the formation depth value of each sensor and the value of the data point at each acquisition moment in the in-situ stress ratio sequence; The product of the ratio sequence abnormal value and the stress ratio characteristic value at the corresponding moment is taken as the stress ratio abnormal value at each acquisition moment in the ground stress ratio sequence of each sensor.

4. The method for real-time monitoring of geostress based on multi-source data fusion according to claim 3, characterized in that: The calculation method of the ratio sequence abnormal value of the ground stress ratio depth sequence of each grating line at each acquisition time is: Calculate the mean of the DTW distances between the in-situ stress ratio depth sequence of each grating line at each acquisition time and the in-situ stress ratio depth sequences of the remaining grating lines at the corresponding acquisition time, and record it as the second mean; The product of the calculation result of the exponential function with the natural constant as the base and the ratio depth correlation coefficient as the exponent and the second mean value is used as the ratio sequence anomaly of the ground stress ratio depth sequence of each grating line at each acquisition moment.

5. The method for real-time monitoring of ground stress based on multi-source data fusion according to claim 3, characterized in that: The stress ratio characteristic value at each acquisition moment in the in-situ stress ratio sequence of each sensor is calculated by the following formula: In the formula, s ′ m ′ ,n,t It represents the characteristic value of the stress ratio at the tth acquisition time in the ground stress ratio sequence of the nth sensor on the mth grating line; H m,n Indicates the formation depth value of the nth sensor on the mth grating line; b m,n,t It represents the value of the data point at the tth acquisition time in the ground stress ratio sequence of the nth sensor on the mth grating line; β is the parameter adjustment constant; max() represents the function of outputting the maximum value in the brackets.

6. The method for real-time monitoring of ground stress based on multi-source data fusion according to claim 1, characterized in that: The method for constructing the horizontal geostress difference depth sequence and the maximum horizontal geostress depth sequence is as follows: The horizontal in-situ stress difference sequence of each sensor on each grating line is obtained according to the difference between the data points at each acquisition time in the maximum horizontal in-situ stress sequence and the data points at the corresponding acquisition time in the minimum horizontal in-situ stress sequence; Arrange the values ​​of the data points at the same acquisition time in the horizontal geostress difference value sequence of all sensors on each grating line in ascending order according to the formation depth value of the sensor to form the horizontal geostress difference value depth sequence of each grating line at the same acquisition time; The values ​​of the data points at the same corresponding acquisition time in the maximum horizontal geostress sequence of all sensors on each grating line are arranged in ascending order according to the formation depth values ​​of the sensors to form the maximum horizontal geostress depth sequence of each grating line at the same acquisition time.

7. The method for real-time monitoring of geostress based on multi-source data fusion according to claim 6, characterized in that: The method for determining the maximum horizontal stress anomaly value at each acquisition moment in the maximum horizontal in-situ stress sequence of each sensor is as follows: Obtaining the difference sequence abnormal value of the depth sequence of the horizontal in-situ stress difference change rate at each acquisition moment according to the horizontal in-situ stress difference depth sequence of each grating line at each acquisition moment and the maximum horizontal in-situ stress depth sequence, and obtaining the maximum horizontal in-situ stress depth correlation coefficient of the maximum horizontal in-situ stress depth sequence; Based on the data points in the maximum horizontal in-situ stress depth series, linear fitting is performed to calculate the Euclidean distance from each data point to the straight line, and the point-line distance of each data point in the maximum horizontal in-situ stress depth series is obtained; The maximum horizontal stress anomaly value at each acquisition time in the maximum horizontal stress sequence of each sensor is calculated as follows: In the formula, represents the stress sequence anomaly value of the maximum horizontal ground stress depth sequence of the mth grating line at the tth acquisition time; w ′ m,t It represents the abnormal value of the difference sequence of the horizontal stress difference depth sequence of the mth grating line at the tth acquisition time; The maximum horizontal in-situ stress depth correlation coefficient representing the maximum horizontal in-situ stress depth series; Calculate the mean of the point-line distance difference between the data point of the nth sensor and the remaining data points in the maximum horizontal in-situ stress depth sequence at the tth acquisition time of the mth grating line, record it as the third mean, and record the product of the third mean and the point-line distance of the data point of the nth sensor in the maximum horizontal in-situ stress depth sequence at the tth acquisition time of the mth grating line as It is the maximum horizontal stress anomaly value of the data point at the tth acquisition time in the maximum horizontal stress sequence of the nth sensor of the mth grating line.

8. The method for real-time monitoring of geostress based on multi-source data fusion according to claim 7, characterized in that: The method of obtaining the difference sequence abnormal value of the depth sequence of the horizontal geostress difference change rate of each grating line at each acquisition moment, and obtaining the maximum horizontal geostress depth correlation coefficient of the maximum horizontal geostress depth sequence, includes: Perform first-order difference on the horizontal geostress difference depth sequence to obtain the depth sequence of the horizontal geostress difference change rate of each grating line at each acquisition time; Calculate the Pearson correlation coefficient between the depth sequence of the horizontal geostress difference change rate of each grating line at each acquisition moment and the sequence composed of the subscript values ​​of each data in the depth sequence of the horizontal geostress difference change rate as the depth correlation coefficient of the horizontal geostress difference change rate of each grating line at each acquisition moment, and record the opposite number of the depth correlation coefficient of the difference change rate as the abnormal value of the difference sequence; Based on the maximum horizontal geostress depth sequence, the maximum horizontal geostress depth correlation coefficient of the maximum horizontal geostress depth sequence of each grating line at each acquisition moment is obtained by using the same calculation method of the difference change rate depth correlation coefficient.

9. The method for real-time monitoring of ground stress based on multi-source data fusion according to claim 1, characterized in that: The calculation method of the data fusion weight of each sensor at each acquisition moment is: Calculate the product of the stress ratio anomaly at each acquisition moment in the in-situ stress ratio sequence of each sensor, the maximum horizontal stress anomaly at each acquisition moment in the maximum horizontal in-situ stress sequence, and the minimum horizontal stress anomaly at each acquisition moment in the minimum horizontal in-situ stress sequence; The normalized result of the reciprocal of the product is used as the weight distribution coefficient of each sensor at each acquisition moment; The proportion of the weight distribution coefficient of each sensor at each acquisition moment in the weight distribution coefficients of all sensors at each acquisition moment is used as the data fusion weight of each sensor at each acquisition moment.

10. The method for real-time monitoring of ground stress based on multi-source data fusion according to claim 1, characterized in that: The method for completing real-time monitoring of ground stress based on the data fusion weight of each sensor at each acquisition moment is: Calculate the product of the vertical geostress in the original three-dimensional geostress data of each sensor at each acquisition moment and the data fusion weight at each acquisition moment, and use the average of the products of all sensors as the vertical geostress monitoring data at each acquisition moment at the geostress monitoring location; For the maximum horizontal geostress and the minimum horizontal geostress, the same acquisition method of the vertical geostress monitoring data is adopted to obtain the maximum horizontal geostress monitoring data and the minimum horizontal geostress monitoring data at the geostress monitoring site at each acquisition time; Based on the vertical geostress monitoring data, the maximum horizontal geostress monitoring data and the minimum horizontal geostress monitoring data, the geostress is monitored in combination with the preset thresholds.

Images