An underground information data acquisition method and system

Abstract

The present invention relates to the technical field of data processing, and particularly relates to a method and system for collecting underground information data. The method includes the steps of: collecting underground information data, and constructing a plurality of isolation trees for all the underground information data by using the isolation forest algorithm; obtaining the degree of node change of each underground information data in each isolation tree; according to the degree of node change, obtaining the overall degree of node change of each underground information data, obtaining the noise factor of each underground information data, and according to the obtained noise factor and the overall degree of node change of each underground information data, obtaining the noise level of each underground information data, and according to the noise level, obtaining the filtering weight of each surrounding data of each underground information data for each underground information data, and based on the filtering weight, obtaining the filtered value of each underground information data. The present invention improves the filtering effect.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method and system for collecting downhole information data. Background Art

[0002] With the continuous growth of global energy demand and the continuous progress of oil exploration and development technologies, oil logging, as a crucial part in the processes of oil and gas exploration, development, and production, has become one of the core tools for judging the reserves of underground oil and gas resources. During the oil exploration process, since the downhole environment is usually full of dangerous factors such as gas explosion, cave-in, gas poisoning, etc., by real-time monitoring data such as gas concentration, temperature, and humidity, potential dangers can be detected in time to ensure the safety of the staff.

[0003] Currently, the patent application document with the publication number CN106980491A discloses an improved mean filtering algorithm for A / D sampling, including: using an MCU to collect data, performing A / D conversion on the collected data, and storing it in an array AD[N], where the value of N is greater than or equal to 100. When the sampled values stored in the array are full, perform a bubble sort on the N numbers in ascending order, then remove the first N / 5 and the last N / 5 data in the sorted array, sum the remaining 3×N / 5, and take the average value to obtain the final sampled value.

[0004] When collecting downhole information data, due to factors such as the malfunction of the sensor itself, there will be noise data and abnormal data in the collected downhole information data. Therefore, the present invention needs to perform denoising processing on several collected downhole information data. Also, since the mean filtering algorithm is an algorithm for filtering noise data, its principle is to obtain the surrounding data of each downhole information data and use the mean value of all the surrounding data of each downhole information data to perform filtering processing on each downhole information data to eliminate noise data. However, if there is noise data in the surrounding data of each downhole information data, the filtering result will be inaccurate. Summary of the Invention

[0005] To solve the technical problem that the presence of noise data in the surrounding data of downhole information data will make the filtering result of the mean filtering algorithm for downhole information data inaccurate, the present invention provides a method and system for collecting downhole information data.

[0006] In the first aspect, the present invention provides a method for collecting downhole information data, adopting the following technical solution:

[0007] A method for collecting downhole information data includes the steps:

[0008] Collect downhole information data; construct several isolation trees for all downhole information data; obtain the degree of node change of each downhole information data in each isolation tree; take the mean value of the degree of node change of each downhole information data in all isolation trees as the overall degree of node change of each downhole information data; obtain the noise factor of each downhole information data:

[0009] , represents the noise factor of the i-th downhole information data; represents the mean value of the deepest layer number of the i-th downhole information data in all isolation trees; k represents the mean value of the deepest layer number of all isolation trees; N represents the number of isolation trees; represents the deepest layer number of the i-th downhole information data in the a-th isolation tree; exp() represents the exponential function with the natural constant as the base;

[0010] Obtain the noise degree of each downhole information data, and the noise degree is positively correlated with the noise factor and the overall degree of node change of each downhole information data;

[0011] According to the noise degree, obtain the filtering weight of each surrounding data of each downhole information data for each downhole information data; based on the filtering weight, obtain the filtering value of each downhole information data.

[0012] The innovation of the present invention lies in obtaining the overall degree of node change of each downhole information data and the noise factor of each downhole information data according to the performance of normal data, abnormal data and noise data in the isolation tree segmentation process of downhole information data, and then obtaining the noise degree of each downhole information data according to the overall degree of node change and the noise factor. Subsequently, according to the noise degree of each downhole information data, obtain the filtering weight of each surrounding data of each downhole information data for each downhole information data to correct the value of each downhole information data, avoiding the influence of noise data on the filtering result during filtering and improving the accuracy of downhole information data filtering.

[0013] Preferably, the obtaining the degree of node change of each downhole information data in each isolation tree includes:

[0014] ;

[0015] In the formula, represents the degree of node change of the i-th downhole information data in the a-th isolation tree; represents the deepest layer number of the a-th isolation tree; represents the number of data points at the node where the i-th downhole information data is located in the b-th layer of the a-th isolation tree; denotes the mean of the number of data points at all levels of the \(i\)-th downhole information data in the \(a\)-th isolated tree; denotes the standard normalization function.

[0016] It is convenient to subsequently obtain the noise factor of each downhole information data according to the degree of node change of each downhole information data in each isolated tree.

[0017] Preferably, the obtaining of the noise degree of each downhole information data includes:

[0018] Taking the product of the overall node change degree of each downhole information data and the noise factor of each downhole information data as the noise degree of each downhole information data.

[0019] It is convenient to subsequently correct the value of each downhole information data according to the noise degree of each downhole information data.

[0020] Preferably, the obtaining of the filtering weight of each surrounding data of each downhole information data for each downhole information data includes:

[0021] Obtaining the surrounding data of each downhole information data;

[0022] ;

[0023] In the formula, represents the filtering weight of the \(g\)-th surrounding data of the \(i\)-th downhole information data for the \(i\)-th downhole information data; represents the noise factor of the \(g\)-th surrounding data of the \(i\)-th downhole information data; represents the sum of the noise factors of all the surrounding data of the \(i\)-th downhole information data.

[0024] It is convenient to filter each downhole information data by weighted averaging the values of each surrounding data of each downhole information data according to the filtering weight of each surrounding data of each downhole information data for each downhole information data, improving the filtering result.

[0025] Preferably, the obtaining of the surrounding data of each downhole information data includes:

[0026] Presetting the number of data \(c\), and recording the \(c\) downhole information data before the sampling moment corresponding to each downhole information data and the \(c\) downhole information data after the sampling moment as the surrounding data of each downhole information data.

[0027] Preferably, the obtaining of the filtered value of each downhole information data based on the filtering weight includes:

[0028] ;

[0029] In the formula, represents the filtered value of the i-th downhole information data; represents the number of surrounding data of the i-th downhole information data; represents the filtering weight of the g-th surrounding data of the i-th downhole information data for the i-th downhole information data; represents the value of the g-th surrounding data of the i-th downhole information data.

[0030] The obtained filtered value is more accurate, avoiding the influence of noise data.

[0031] Preferably, constructing several isolation trees for all downhole information data includes:

[0032] Presetting the number N of isolation trees, and using the isolation forest algorithm to construct N isolation trees for all downhole information data.

[0033] In a second aspect, the present invention provides a downhole information data acquisition system, adopting the following technical solution:

[0034] A downhole information data acquisition system includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned downhole information data acquisition method is implemented.

[0035] By adopting the above technical solution, the above-mentioned downhole information data acquisition method is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0036] The present invention has the following technical effects: The purpose of the present invention is to obtain the overall node change degree of each downhole information data and the noise factor of each downhole information data according to the performance of normal data, abnormal data and noise data in the isolation tree segmentation process of downhole information data, and then obtain the noise degree of each downhole information data according to the overall node change degree and the noise factor. Then, according to the noise degree of each downhole information data, the filtering weight of each surrounding data of each downhole information data for each downhole information data is obtained to correct the value of each downhole information data, avoiding the influence of noise data on the filtering result during filtering and improving the accuracy of downhole information data filtering. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By referring to the accompanying drawings and reading the following detailed description, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become easily understandable. In the drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0038] Figure 1 It is the flowchart of a method in an embodiment of the present invention for collecting downhole information data;

[0039] Figure 2 It represents a schematic diagram of an isolated tree. Specific embodiments

[0040] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0041] It should be understood that when the claims, specifications, and drawings of the present invention use terms such as "first" and "second", they are only used to distinguish different objects, rather than to describe a specific order. The terms "including" and "comprising" used in the specifications and claims of the present invention indicate the existence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the existence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0042] An embodiment of the present invention discloses a method for collecting downhole information data. Refer to Figure 1 , including steps S1 - S4:

[0043] S1: Collect downhole information data.

[0044] It should be noted that downhole information data refers to the data collected about the underground operation environment in the underground operation environment of an oil well. Since the downhole environment is usually full of dangerous factors, such as gas explosion, landslide, gas poisoning, etc., by real-time monitoring of data such as gas concentration, temperature, and humidity, potential dangers can be detected in time to ensure the safety of the staff.

[0045] In an embodiment of the present invention, the preset sampling time is 2 seconds / time. By arranging temperature sensors, humidity sensors, and gas sensors downhole to collect the temperature, humidity, and gas concentration downhole, the temperature, humidity, and gas concentration collected at the same sampling time are used as a downhole information data, and several downhole information data are obtained.

[0046] S2: Use the isolation forest algorithm to construct several isolated trees for all downhole information data; obtain the degree of node change of each downhole information data in each isolated tree; according to the degree of node change of each downhole information data in each isolated tree, obtain the overall degree of node change of each downhole information data.

[0047] It should be noted that when collecting downhole information data, due to factors such as the sensor's own failure, there will be noise data and abnormal data in the collected downhole information data. Therefore, the present invention needs to perform denoising processing on a number of collected downhole information data. Also, since the mean filtering algorithm is an algorithm for filtering noise data, its principle is to obtain the surrounding data of each downhole information data, and use the mean of all the surrounding data of each downhole information data to perform filtering processing on each downhole information data to eliminate noise data. However, if there is noise data among the surrounding data of each data point, it will make the filtering result inaccurate. Therefore, the present invention needs to analyze the characteristics of the data points, obtain the noise level of each downhole information data, so as to facilitate subsequent correction of the value of each downhole information data to avoid the influence of noise data on the filtering result during filtering.

[0048] It should be further noted that the abnormal data in the downhole information data is an abnormal situation caused by equipment failure and emergencies. Therefore, there are significant differences between the abnormal data and the normal data in the downhole information data. The noise data generated in the downhole information data is random error data caused by acquisition errors, external environmental interference, etc. Therefore, the difference between the noise data and the normal data usually has a fluctuating change, and the difference from the normal data is slightly smaller.

[0049] It is known that the core idea of the isolation forest algorithm is to gradually "isolate" a small number of abnormal data points by randomly selecting splitting thresholds. Therefore, since the difference between the abnormal data and the normal data in the downhole information data is large, the abnormal data in the downhole information data will be quickly split out. Therefore, the change in the node position of the abnormal data in the isolation tree is very small. However, the difference between the noise data and the normal data in the downhole information data has fluctuations. Therefore, the noise data will have a large change in the node position of the isolation tree. Therefore, the present invention first constructs multiple isolation trees for all downhole information data, and according to the change situation of the node position of each downhole information data in all isolation trees, obtains the degree of node change of each downhole information data in each isolation tree, so as to facilitate subsequent obtaining the noise level of each downhole information data according to the degree of node change.

[0050] In the embodiment of the present invention, a preset number of isolation trees N is set, and the isolation forest algorithm is used to construct N isolation trees for all downhole information data. In the embodiment of the present invention, the preset number of isolation trees N = 7. In other embodiments, the implementer can preset the value of the number of isolation trees N according to the specific implementation situation.

[0051] Obtain the degree of node change of each downhole information data in each isolation tree:

[0052] ;

[0053] In the formula, Represents the degree of node change of the \(i\)-th downhole information data in the \(a\)-th isolated tree; Represents the deepest layer number of the \(a\)-th isolated tree; Represents the number of data points at the node where the \(i\)-th downhole information data is located in the \(b\)-th layer of the \(a\)-th isolated tree; Represents the mean value of the number of data points at the nodes where the \(i\)-th downhole information data is located in all layers of the \(a\)-th isolated tree; Represents the standard normalization function.

[0054] Among them, Represents the change situation of the number of data points at the node where the \(i\)-th downhole information data is located in the \(a\)-th isolated tree. The larger its value, the greater the change in the number of downhole information data at its node, that is, the greater the degree of node change of the \(i\)-th downhole information data in the \(a\)-th isolated tree.

[0055] The mean value of the degree of node change of each downhole information data in each isolated tree is used as the overall node change degree of each downhole information data.

[0056] S3: Obtain the noise factor of each downhole information data, and obtain the noise degree of each downhole information data according to the obtained noise factor of each downhole information data and the overall node change degree.

[0057] It should be noted that the noise data in the known downhole information data has large fluctuations in different isolated trees and will be separated when approaching the middle position of the isolated tree. Therefore, when any downhole information data is noise data, the difference in the deepest layer numbers of the downhole information data in different isolated trees is large, and the absolute value of the difference between the mean value of the deepest layer numbers of the downhole information data in all isolated trees and the mean value of the deepest layer numbers of all isolated trees is small.

[0058] In the embodiment of the present invention, obtain the noise factor of each downhole information data:

[0059] ;

[0060] In the formula, represents the noise factor of the \(i\)-th downhole information data; represents the mean value of the deepest layer numbers of the \(i\)-th downhole information data in all isolated trees; \(k\) represents the mean value of the deepest layer numbers of all isolated trees; \(N\) represents the number of isolated trees; represents the deepest layer number of the \(i\)-th downhole information data in the \(a\)-th isolated tree; \(\exp()\) represents the exponential function with the natural constant as the base;

[0061] represents the mean value of the deepest layer of the i-th downhole information data among all isolated trees, which is the absolute value of the difference relative to the mean value of the deepest layer of all isolated trees. The smaller the absolute value of the difference, the closer the i-th downhole information data is separated near the middle position of the isolated tree, and the more likely the i-th downhole information data is noise data, with a larger noise factor for it.

[0062] The larger the value of [[ID=]], the greater the difference in the deepest layer of the i-th downhole information data among different isolated trees, indicating that the i-th downhole information data has greater volatility among different isolated trees, that is, the noise factor of this downhole information data is larger.

[0063] Take the product of the overall node change degree of each downhole information data and the noise factor of each downhole information data as the noise degree of each downhole information data.

[0064] It should be noted that the acquisition of the deepest layer of each downhole information data in the isolated tree and the deepest layer of the isolated tree is as Figure 2 shown. The layer where the root node of the isolated tree is located is the 0th layer of the isolated tree. Therefore, taking the data point "20" in Figure 2 as an example, the deepest layer of this data point in the isolated tree of Figure 2 is 2, and the deepest layer of this isolated tree is 3.

[0065] S4: According to the noise degree of each downhole information data, obtain the filtering weight of each surrounding data of each downhole information data for each downhole information data, and based on the filtering weight, obtain the filtering value of each downhole information data.

[0066] It should be noted that when using mean filtering to filter downhole information data, if the noise degree of any surrounding data of any downhole information data is greater, then the weight value of this surrounding data is made smaller during filtering to reduce the influence of this surrounding data on this downhole information data, making the filtering value of this downhole information data more accurate.

[0067] In the embodiment of the present invention, the c downhole information data before the sampling moment corresponding to each downhole information data and the c downhole information data after the sampling moment are recorded as the surrounding data of each downhole information data. In the embodiment of the present invention, the preset number of data c = 5. In other embodiments, the implementer can preset the value of c according to the specific implementation situation.

[0068] Obtain the filtering weight of each surrounding data of each downhole information data for each downhole information data:

[0069] ;

[0070] In the formula, represents the filtering weight of the g-th surrounding data of the i-th downhole information data with respect to the i-th downhole information data; represents the noise factor of the g-th surrounding data of the i-th downhole information data; represents the sum of the noise factors of all the surrounding data of the i-th downhole information data; for any one of the surrounding data of the i-th downhole information data, if the noise level of this surrounding data is greater, then the filtering weight value of this surrounding data with respect to the i-th downhole information data is smaller.

[0071] Obtain the filtering value of each downhole information data:

[0072] ;

[0073] In the formula, represents the filtering value of the i-th downhole information data; represents the number of surrounding data of the i-th downhole information data; represents the filtering weight of the g-th surrounding data of the i-th downhole information data with respect to the i-th downhole information data; represents the value of the g-th surrounding data of the i-th downhole information data.

[0074] Store the filtering values of all the downhole information data in the data storage module, which is convenient for the staff to analyze, so as to complete the acquisition of downhole data.

[0075] The embodiment of the present invention also discloses a downhole information data acquisition system, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a downhole information data acquisition method according to the present invention is implemented.

[0076] The above system also includes other components well known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be elaborated here.

[0077] In the present invention, the aforementioned memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or device. For example, a computer-readable storage medium can be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high-bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium can be a part of the device or accessible or connectable to the device.

[0078] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in the practice of the present invention.

[0079] The above are all preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A method for collecting downhole information data, characterized in that, Including the steps: Collect downhole information data; construct a number of isolation trees for all downhole information data; obtain the degree of node change of each downhole information data in each isolation tree; take the mean value of the degree of node change of each downhole information data in all isolation trees as the overall degree of node change of each downhole information data; obtain the noise factor of each downhole information data: , represents the noise factor of the i-th downhole information data; represents the mean of the deepest layer numbers of the i-th downhole information data in all isolated trees; k represents the mean of the deepest layer numbers of all isolated trees; N represents the number of isolated trees; represents the deepest layer number of the i-th downhole information data in the a-th isolated tree; exp() represents the exponential function with the natural constant as the base; Obtaining the noise level of each downhole information data includes: taking the product of the overall degree of node change of each downhole information data and the noise factor of each downhole information data as the noise level of each downhole information data, and the noise level is positively correlated with the noise factor and the overall degree of node change of each downhole information data; According to the noise level, obtain the filtering weight of each surrounding data of each downhole information data for each downhole information data, including: obtaining the surrounding data of each downhole information data; ； Wherein, represents the filtering weight of the g-th surrounding data of the i-th downhole information data with respect to the i-th downhole information data; represents the noise level of the g-th surrounding data of the i-th downhole information data; represents the sum of the noise levels of all the surrounding data of the i-th downhole information data; Based on the filtering weight, the filtered value of each downhole information data is obtained.

2. The downhole information data acquisition method according to claim 1, characterized in that, The obtaining the degree of node change of each downhole information data in each isolation tree includes: ； Wherein, represents the degree of node change of the i-th downhole information data in the a-th isolated tree; represents the deepest layer number of the a-th isolated tree; represents the number of data points of the node where the i-th downhole information data is located in the b-th layer of the a-th isolated tree; represents the mean value of the number of data points of the nodes where the i-th downhole information data is located in all layers of the a-th isolated tree; represents the standard normalization function.

3. A downhole information data acquisition method according to claim 1, characterized in that, The obtaining the surrounding data of each downhole information data includes: Preset the number of data c, and record the c downhole information data before the sampling moment corresponding to each downhole information data and the c downhole information data after the sampling moment as the surrounding data of each downhole information data.

4. A downhole information data acquisition method according to claim 1, characterized in that, Based on the filtering weight, obtaining the filtering value of each downhole information data includes: ； Wherein, represents the filtered value of the i-th downhole information data; represents the number of surrounding data of the i-th downhole information data; represents the filtering weight of the g-th surrounding data of the i-th downhole information data on the i-th downhole information data; represents the value of the g-th surrounding data of the i-th downhole information data.

5. A downhole information data acquisition method according to claim 1, characterized in that, The constructing a number of isolation trees for all downhole information data includes: Preset the number of isolation trees N, and use the isolation forest algorithm to construct N isolation trees for all downhole information data.

6. An underground information data acquisition system, characterized in that, Including: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, it implements a method for collecting downhole information data according to any one of claims 1-5.

Images