CN116582134B - Drilling and testing integrated equipment data processing method - Google Patents
Drilling and testing integrated equipment data processing method Download PDFInfo
- Publication number
- CN116582134B CN116582134B CN202310842552.6A CN202310842552A CN116582134B CN 116582134 B CN116582134 B CN 116582134B CN 202310842552 A CN202310842552 A CN 202310842552A CN 116582134 B CN116582134 B CN 116582134B
- Authority
- CN
- China
- Prior art keywords
- data
- time point
- drilling
- abnormal
- attention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005553 drilling Methods 0.000 title claims abstract description 96
- 238000012360 testing method Methods 0.000 title claims abstract description 37
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 230000002159 abnormal effect Effects 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000005259 measurement Methods 0.000 claims abstract description 42
- 238000012545 processing Methods 0.000 claims abstract description 38
- 238000007906 compression Methods 0.000 claims abstract description 20
- 230000006835 compression Effects 0.000 claims abstract description 20
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 16
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000012163 sequencing technique Methods 0.000 claims abstract description 4
- 230000004913 activation Effects 0.000 claims description 5
- 238000010586 diagram Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 15
- 230000005540 biological transmission Effects 0.000 abstract description 10
- 230000008859 change Effects 0.000 description 19
- 230000005856 abnormality Effects 0.000 description 6
- 230000002708 enhancing effect Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 238000010606 normalization Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000002285 radioactive effect Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002844 continuous effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005755 formation reaction Methods 0.000 description 2
- 230000005251 gamma ray Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/46—Conversion to or from run-length codes, i.e. by representing the number of consecutive digits, or groups of digits, of the same kind by a code word and a digit indicative of that kind
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3059—Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of electric digital data processing, in particular to a drilling and testing integrated equipment data processing method. Acquiring drilling measurement data, and acquiring a fluctuation coefficient according to the data fluctuation condition of the drilling measurement data at all time points; carrying out time sequence decomposition on the fluctuation coefficient to obtain a residual error item, carrying out data analysis on the residual error item, determining an abnormal time point, and determining a concern weight value of the abnormal time point according to the fluctuation coefficient of a time point adjacent to the abnormal time point; dividing the time points into a high attention time point and a low attention time point, carrying out data unified processing on drilling measurement data of the low attention time point to obtain unified data, and sequencing to obtain sequences to be compressed of drilling measurement data of different types; and performing run-length coding compression processing on the sequence to be compressed to obtain compressed data. The invention can enhance the data processing efficiency of the drilling measurement data, reduce the data transmission time and enhance the timeliness of the data transmission in the drilling measurement process.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a drilling and testing integrated equipment data processing method.
Background
Drilling and logging integration generally refers to a technology of integrating two links of drilling and logging into a whole operation in drilling, and conventional drilling operation generally needs to be performed first and then logging operation; but the drilling and logging integrated technology can realize measurement and data acquisition of underground rock formations by installing logging tools in a drill bit and a drill string while drilling. When the drilling and testing integrated equipment performs geological exploration, the situation that the geological structure changes is often required to be processed and analyzed through data fed back by various sensors in the drilling and testing integrated equipment.
In the related art, data fed back by each sensor in the drilling and testing integrated equipment is compressed in a lossless compression mode, and the compressed data is input into a console, so that the volume of data output by a scene is huge in the mode; when each sensor is directly used for compressing and transmitting output data respectively in a lossless compression mode, a large amount of memory is occupied, and the processing efficiency is low; the method is also inconvenient to distinguish and process abnormal data in the running state of the drilling and testing integrated equipment in real time, so that the data processing efficiency of drilling and testing data in the related technology is poor, the data transmission time is long, and the timeliness of data transmission in the drilling and testing process is insufficient.
Disclosure of Invention
In order to solve the technical problems that the drilling and testing data processing efficiency is poor, the data transmission time is long, and the timeliness of data transmission in the drilling and testing process is insufficient in the related art, the invention provides a drilling and testing integrated equipment data processing method, which adopts the following specific technical scheme:
the invention provides a drilling and testing integrated equipment data processing method, which comprises the following steps:
acquiring at least two types of drilling measurement data at different time points, and acquiring a fluctuation coefficient of each time point according to the data fluctuation condition of the drilling measurement data at all the time points;
performing time sequence decomposition on the fluctuation coefficient to obtain a residual error item of the fluctuation coefficient, performing data analysis on the residual error item, determining an abnormal fluctuation coefficient, taking a time point corresponding to the abnormal fluctuation coefficient as an abnormal time point, and determining a concern weight of the abnormal time point according to the fluctuation coefficient of a time point adjacent to the abnormal time point;
dividing all time points into a high attention time point and a low attention time point according to the attention weight, respectively carrying out data unified processing on the drilling measurement data of the low attention time point of different data types to obtain unified data respectively corresponding to the different data types, and sequencing the drilling measurement data of the high attention time point and the unified data of the low attention time point of the same data type according to a time sequence to obtain a sequence to be compressed of the drilling measurement data of different types;
performing run-length coding compression processing on different types of sequences to be compressed respectively to obtain compressed data;
the drilling measurement data comprises the intensity data of a natural gamma logging instrument and the stress data of a drill string stress sensor, and the fluctuation coefficient of each time point is obtained according to the data fluctuation conditions of different types of drilling measurement data at all time points, and the method comprises the following steps:
calculating the average value of the intensity data at all time points to obtain an intensity characteristic value; calculating the average value of the stress data at all time points to obtain a stress characteristic value;
obtaining the fluctuation coefficient of any time point according to the intensity data and the stress data, the intensity characteristic value and the stress characteristic value of the time point;
the obtaining the fluctuation coefficient of the time point according to the intensity data and the stress data, the intensity characteristic value and the stress characteristic value of any time point comprises the following steps:
calculating a difference normalized value of the intensity data and the intensity characteristic value as an intensity influence coefficient, and calculating a difference normalized value of the stress data and the stress characteristic value as a stress influence coefficient;
taking the sum of the intensity influence coefficient and the stress influence coefficient as a fluctuation coefficient;
the classifying all the time points into a high attention time point and a low attention time point according to the attention weight comprises the following steps:
taking the abnormal time point with the attention weight larger than a preset weight threshold as a high attention time point;
all other time points except the high attention time point are taken as low attention time points.
Further, the data analysis of the residual term, determining an abnormal fluctuation coefficient, includes:
determining an upper limit value and a lower limit value of a residual error item based on a box diagram method;
taking a range corresponding to the upper limit value and the lower limit value as a fluctuation range;
and taking the fluctuation coefficient of which the residual error item does not belong to the fluctuation range as an abnormal fluctuation coefficient.
Further, the determining the attention weight of the abnormal time point according to the fluctuation coefficient of the time point adjacent to the abnormal time point includes:
taking the abnormal time point as a center, and taking a time point in a preset time range as an adjacent time point of the abnormal time point;
counting the fluctuation coefficients of all adjacent time points of the abnormal time point, and taking the quantity of the fluctuation coefficients belonging to the abnormal fluctuation coefficients as the concern influence quantity of the abnormal time point;
and carrying out data processing on the attention influence quantity by using an activation function to obtain the attention weight of the abnormal time point.
Further, the data unifying processing is performed on the drilling measurement data of the low attention time points with different data types to obtain unified data corresponding to the different data types, respectively, including:
calculating the average value of the intensity data of all the low-attention time points of the same data type to obtain uniform intensity data; calculating the average value of the stress data of all the low-attention time points of the same data type to obtain uniform stress data;
and taking the unified strength data and the unified stress data as unified data.
Further, the sorting the drill measurement data of the high attention time point and the unified data of the low attention time point of the same data type according to the time sequence to obtain the sequences to be compressed of the drill measurement data of different types, including:
sorting the intensity data of the high attention time points and the unified intensity data of the low attention time points according to the time sequence to obtain a sequence to be compressed of the intensity data;
and ordering the stress data of the high attention time point and the unified stress data of the low attention time point according to the time sequence to obtain a sequence to be compressed of the stress data.
The invention has the following beneficial effects:
according to the method, the fluctuation coefficient of each time point is determined according to the fluctuation conditions of all types of drilling measurement data at all time points, the fluctuation coefficient is a coefficient representing fluctuation abnormality of the data at the time point, time sequence decomposition and data analysis are further carried out on the fluctuation coefficient, so that an abnormal time point corresponding to the abnormal fluctuation coefficient is obtained, the abnormal condition of each time point is analyzed according to a plurality of different types of drilling measurement data, and the reliability of data analysis can be improved through the time sequence decomposition and the data analysis; the method comprises the steps of determining the attention weight of each abnormal time point by combining the fluctuation coefficient of the abnormal time point and the adjacent time points, effectively screening out the abnormal time points caused by the change of the geological structure by combining the objective change rule of the drilling data when the geological structure is changed, dividing all the time points into a high attention time point and a low attention time point, carrying out different data processing according to different types of time points, carrying out data unified processing on the drilling data of the low attention time point, and reserving the drilling data of the high attention time point, so that unimportant data can be unified under the condition of reserving abnormal characteristics, and the processed sequence is compressed by using a run-length encoding compression mode, and because the run-length encoding compression mode is a lossless compression mode, namely carrying out lossless compression processing on the drilling data of the high attention time point, carrying out lossy compression processing on the drilling data of the low attention time point, thereby enhancing the compression rate of the drilling data under the condition of reserving the basic data characteristics of all the time points. In summary, the invention can combine the objective change rule of the drilling and testing data when the geological structure changes, effectively screen out the abnormal time point caused by the change of the geological structure, and facilitate timely distinguishing the abnormal data in the running state of the drilling and testing integrated equipment, thereby adopting a corresponding processing mode to perform data processing aiming at the time points under different conditions, effectively enhancing the data processing efficiency of the drilling and testing data, reducing the data transmission time and enhancing the timeliness of the data transmission in the drilling and testing process.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a drilling and testing integrated equipment data processing method according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of a specific implementation, structure, characteristics and effects of the drilling and testing integrated equipment data processing method according to the invention with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the drilling and testing integrated equipment data processing method provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for processing data of drilling and testing integrated equipment according to an embodiment of the present invention is shown, where the method includes:
s101: acquiring at least two types of drilling measurement data at different time points, and acquiring a fluctuation coefficient of each time point according to the data fluctuation condition of the drilling measurement data at all time points.
It will be appreciated that the drilling and logging integrated equipment includes a plurality of operating data tables, such as a drilling parameter table, a logging parameter table or a geological parameter table, during the detection operation, wherein the operating state table is particularly critical, and is used for recording the output data of various sensors, so that the output data of the variety can be used as drilling and logging data. In the embodiment of the invention, the drilling measurement data may specifically include, for example, the drilling measurement data including the strength data of the natural gamma logging tool and the stress data of the drill string stress sensor, and of course, the drilling measurement data may also be, for example, data corresponding to other drilling measurement integrated equipment, which is not limited.
The natural gamma logging instrument is equipment for measuring natural radioactive elements of a stratum, and generally consists of a radioactive source and a receiver, and when rays emitted by the radioactive source pass through the stratum and are received by the receiver, the natural gamma logging instrument can output corresponding intensity data of the natural gamma rays; the program needs to analyze the information of the structure, mineral composition, porosity and the like of the stratum by collecting the intensity data of the natural gamma rays; in general, intensity data generated by natural gamma logging tools does not exhibit large numerical fluctuations under normal formation conditions.
The drill string stress sensor is a device for detecting stress of the drill string, and can output stress data of the stress of the drill string.
In the embodiment of the invention, a certain time period can be set to periodically acquire the drilling measurement data, and the time period can be specifically, for example, 1 second, namely, 1 second, for acquiring the drilling measurement data once, or can be adjusted according to the actual detection requirement, so that the method is not limited.
Thus, in some embodiments of the present invention, the obtaining of the fluctuation coefficient for each time point based on the data fluctuation of different types of drilling data at all time points includes: calculating the average value of the intensity data at all time points to obtain an intensity characteristic value; calculating the average value of the stress data at all time points to obtain a stress characteristic value; and obtaining the fluctuation coefficient of the time point according to the intensity data and the stress data, the intensity characteristic value and the stress characteristic value of any time point.
In the embodiment of the invention, the average value of the intensity data at all time points can be calculated as the intensity characteristic value, namely, the intensity characteristic value represents the average level of the intensity data acquired by the natural gamma-ray logging instrument at all time points, and similarly, the stress characteristic value represents the average level of the stress data acquired by the drill string stress sensor at all time points.
Further, in the embodiment of the present invention, according to the intensity data and the stress data, the intensity characteristic value and the stress characteristic value at any time point, the obtaining the fluctuation coefficient at the time point includes: calculating a difference normalized value of the intensity data and the intensity characteristic value as an intensity influence coefficient, and calculating a difference normalized value of the stress data and the stress characteristic value as a stress influence coefficient; and taking the sum of the intensity influence coefficient and the stress influence coefficient as a fluctuation coefficient. The calculation manner of the fluctuation coefficient may specifically be, for example:
in the method, in the process of the invention,representing the fluctuation coefficient of the ith time point, < +.>Intensity data representing the ith time point, +.>Stress data indicating the ith time point, n indicates the total number of time points, j indicates the index of time points, +.>Intensity data representing the j-th time point, < +.>Stress data representing the j-th time point, < +.>Representing the intensity characteristic value, +.>Representing the stress characteristic value, < >>In one embodiment of the present invention, the normalization process may be specifically, for example, maximum and minimum normalization processes, and the normalization in the subsequent steps may be performed by using the maximum and minimum normalization processes, and in other embodiments of the present invention, other normalization methods may be selected according to a specific range of values, which will not be described herein.
In the method, in the process of the invention,representing the intensity influence coefficient, +.>The stress influence coefficient is expressed, it can be understood that when the stratum structure changes, corresponding strength data and stress data all generate the change in the same direction, corresponding strength data can be increased, stress data can also be increased, so that the strength data is larger than the integral strength characteristic value, the stress data is larger than the integral stress characteristic value, and the stress data is expressed in a formula, namely, the strength influence coefficient and the stress influence coefficient are both increased, and the fluctuation coefficient is larger, or, for example, the strength data and the force data are both decreased, namely, the fluctuation coefficient is smaller, so that the fluctuation coefficient can be an abnormal condition caused by geological change when being larger or smaller. If the abnormality at the current time point is not caused by the change of the stratum structure, the change of the two data may be non-equidirectional, that is, any one data becomes larger, the other data does not change or becomes smaller, and the fluctuation coefficient is relatively normal. Therefore, abnormal shadows caused by the influence of the non-stratum structure change can be avoided according to the intensity influence coefficient and the stress influence coefficientAnd the fluctuation coefficient can accurately represent the data fluctuation at different time points.
S102: and carrying out time sequence decomposition on the fluctuation coefficient to obtain a residual error item of the fluctuation coefficient, carrying out data analysis on the residual error item, determining an abnormal fluctuation coefficient, taking a time point corresponding to the abnormal fluctuation coefficient as an abnormal time point, and determining a concerned weight of the abnormal time point according to the fluctuation coefficient of the time point adjacent to the abnormal time point.
The time sequence decomposition in the embodiment of the present invention may specifically be, for example, a time sequence decomposition (Seasonal and Trend decomposition using Loess, STL) method using robust local weighted regression as a smoothing method, where the STL time sequence decomposition method may decompose data into a trend term, a season term and a residual term, where the STL time sequence decomposition method is a time sequence decomposition method well known in the art, which is not described in detail herein, and the time sequence decomposition is performed on the fluctuation coefficient by the STL time sequence decomposition method to obtain the residual term of the fluctuation coefficient, and then the residual term may be analyzed.
Further, in the embodiment of the present invention, performing data analysis on the residual term to determine an abnormal fluctuation coefficient includes: determining an upper limit value and a lower limit value of a residual error item based on a box diagram method; taking a range corresponding to the upper limit value and the lower limit value as a fluctuation range; and taking the fluctuation coefficient of which the residual error item does not belong to the fluctuation range as an abnormal fluctuation coefficient.
The box plot method is an analysis method capable of analyzing data to determine outliers in the data, and in the embodiment of the invention, the box plot method can be used for determining outlier data of an abnormality, namely an abnormal fluctuation coefficient.
Specifically, in the embodiment of the invention, the upper limit and the lower limit of the residual term can be determined by using a box diagram method, so that the value corresponding to the upper limit is obtained as the upper limit value, and the value corresponding to the lower limit is obtained as the lower limit value.
Further, in the embodiment of the present invention, determining the attention weight of the abnormal time point according to the fluctuation coefficient of the time point adjacent to the abnormal time point includes: taking the abnormal time point as a center, and presetting the time point in the time range as an adjacent time point of the abnormal time point; counting the fluctuation coefficients of all adjacent time points of the abnormal time point, and taking the quantity of the fluctuation coefficients belonging to the abnormal fluctuation coefficients as the concern influence quantity of the abnormal time point; and carrying out data processing on the attention influence quantity by using an activation function to obtain attention weight values of abnormal time points.
The preset time range may specifically be, for example, 10 seconds, or may be adjusted according to an actual detection requirement, which is not limited, that is, in the embodiment of the present invention, in a preset time range in which an abnormal time point is a time midpoint, a time point of data acquired in the preset time range is taken as an adjacent time point of the abnormal time point, and fluctuation coefficients of all adjacent time points of the abnormal time point are counted.
It can be understood that, when the state of the stratum structure changes during the detection operation, the natural gamma ray intensity and the output value of the drill string stress sensor are increased or decreased at the same time, and the abrupt change state is continuously maintained in a period of adjacent time nodes, that is, the abnormal condition corresponding to the change of the stratum structure state has a continuous effect in a certain time range, so that the data generating the abnormal abrupt change can be screened according to the characteristic, and the calculation formula of the corresponding attention weight is as follows:
in the method, in the process of the invention,attention weight indicating the t-th abnormality time point, t indicating the index of the abnormality time point,/->Indicating the number of influence of interest at the t-th abnormal time point,/->Representing an activation function.
The concern influence quantity is the quantity of the fluctuation coefficients belonging to the abnormal fluctuation coefficients in all adjacent time points of the abnormal time points, that is, the quantity of time points, in which the fluctuation coefficients are the abnormal fluctuation coefficients, in the adjacent time points is counted as the concern influence quantity, when the concern influence quantity is large, the corresponding abnormal situation can be represented to have a continuous effect in the adjacent time points, the abnormal situation corresponding to the abnormal time points is more likely to be the abnormal situation caused by the change of the stratum structure state, and when the concern influence quantity is small, the instantaneous fluctuation situation possibly caused by other abnormal reasons can be caused, so that the concern weight can be expressed more effectively through the sigmoid activation function, and the concern weight is more objective and accurate.
S103: dividing all time points into high attention time points and low attention time points according to attention weight values, respectively carrying out data unified processing on drilling measurement data of the low attention time points of different data types to obtain unified data corresponding to the different data types, and sequencing the drilling measurement data of the high attention time points and the unified data of the low attention time points of the same data type according to time sequence to obtain to-be-compressed sequences of the drilling measurement data of different types.
Further, in some embodiments of the present invention, dividing all time points into a high attention time point and a low attention time point according to attention weight values includes: taking an abnormal time point with the attention weight larger than a preset weight threshold as a high attention time point; all other time points except the high attention time point are taken as low attention time points.
The preset weight threshold is a threshold of the attention weight, and the preset weight threshold may specifically be, for example, 0.8, or may be set according to an actual detection requirement, which is not limited. In the embodiment of the present invention, the abnormal time point with the attention weight greater than 0.8 may be used as the high attention time point, that is, the time point with the high attention is more likely to be the time point corresponding to the change of the stratum structure state. The present invention may also take all other time points except the high attention time point as the low attention time point, where the low attention time point specifically includes a time point where the residual item belongs to the fluctuation range, and an abnormal time point where the attention weight is less than or equal to the preset weight threshold.
In the embodiment of the invention, the drilling test data of each data type at the low attention time point can be respectively subjected to data unified processing to obtain unified data respectively corresponding to different data types.
Wherein, the data unification process may be specifically expressed as unifying corresponding data into the same value.
Further, in the embodiment of the present invention, data unification processing is performed on drill measurement data with low attention time points of different data types, so as to obtain unified data corresponding to the different data types, where the method includes: calculating the average value of the intensity data of all low-attention time points of the same data type to obtain uniform intensity data; calculating the average value of the stress data of all low-attention time points of the same data type to obtain unified stress data; and taking the unified strength data and the unified stress data as unified data.
The drilling data are taken as intensity data of the natural gamma logging instrument and stress data of a drill string stress sensor are analyzed, the corresponding data types are two types, namely intensity data and stress data, the average value of the intensity data of all low-attention time points of the same data type is calculated, unified intensity data are obtained, the average value of the stress data of all low-attention time points of the same data type is calculated, unified stress data are obtained, that is, the unified intensity data are taken as unified data after being uniformly processed, and the unified stress data are taken as unified data after being uniformly processed.
Of course, in other embodiments of the present invention, a plurality of other possible ways may be used to determine the unified data of the corresponding data type, for example, the mode of the data of all the low-attention time points of the same type is taken as the unified data of the data type, or the median of the data of all the low-attention time points is taken as the unified data of the data type, which is not limited, thereby enabling the unified data to characterize the data numerical characteristics of the corresponding low-attention time points.
After unified data is determined, drill measurement data of high attention time points and unified data of low attention time points of the same data type are ordered according to time sequence, and to-be-compressed sequences of different types of drill measurement data are obtained, and the method comprises the following steps: sorting the intensity data of the high attention time points and the unified intensity data of the low attention time points according to the time sequence to obtain a sequence to be compressed of the intensity data; and ordering the stress data of the high attention time point and the unified stress data of the low attention time point according to the time sequence to obtain a sequence to be compressed of the stress data. It will be appreciated that each type of drill data corresponds to a respective sequence to be compressed.
S104: and respectively carrying out run-length coding compression processing on different types of sequences to be compressed to obtain compressed data.
The run-length encoding is a lossless statistical encoding, and the run-length encoding is a well-known encoding technique in the art, and it can be understood that the more the run-length encoding has a high data compression effect on repeatability, so that the invention unifies the data at low attention time points and the normal data by unifying the data, so that the compression effect is improved under the condition of keeping the basic data characteristics at the time points.
In the embodiment of the invention, the run-length coding compression mode is used for respectively compressing the sequences to be compressed corresponding to different types of drilling test data to obtain the corresponding types of compressed data, and all types of compressed data are used as data obtained after the drilling test integrated equipment processes the data.
According to the method, the fluctuation coefficient of each time point is determined according to the fluctuation conditions of all types of drilling measurement data at all time points, the fluctuation coefficient is a coefficient representing fluctuation abnormality of the data at the time point, time sequence decomposition and data analysis are further carried out on the fluctuation coefficient, so that an abnormal time point corresponding to the abnormal fluctuation coefficient is obtained, the abnormal condition of each time point is analyzed according to a plurality of different types of drilling measurement data, and the reliability of data analysis can be improved through the time sequence decomposition and the data analysis; the method comprises the steps of determining the attention weight of each abnormal time point by combining the fluctuation coefficient of the abnormal time point and the adjacent time points, effectively screening out the abnormal time points caused by the change of the geological structure by combining the objective change rule of the drilling data when the geological structure is changed, dividing all the time points into a high attention time point and a low attention time point, carrying out different data processing according to different types of time points, carrying out data unified processing on the drilling data of the low attention time point, and reserving the drilling data of the high attention time point, so that unimportant data can be unified under the condition of reserving abnormal characteristics, and the processed sequence is compressed by using a run-length encoding compression mode, and because the run-length encoding compression mode is an unoccupied compression mode, namely carrying out lossless compression processing on the drilling data of the high attention time point, carrying out lossy compression processing on the drilling data of the low attention time point, thereby enhancing the compression rate of the drilling data under the condition of reserving the basic data characteristics of all the time points. In summary, the invention can combine the objective change rule of the drilling and testing data when the geological structure changes, effectively screen out the abnormal time point caused by the change of the geological structure, and facilitate timely distinguishing the abnormal data in the running state of the drilling and testing integrated equipment, thereby adopting a corresponding processing mode to perform data processing aiming at the time points under different conditions, effectively enhancing the data processing efficiency of the drilling and testing data, reducing the data transmission time and enhancing the timeliness of the data transmission in the drilling and testing process.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (5)
1. A drilling and testing integrated equipment data processing method, characterized in that the method comprises the following steps:
acquiring at least two types of drilling measurement data at different time points, and acquiring a fluctuation coefficient of each time point according to the data fluctuation condition of the drilling measurement data at all the time points;
performing time sequence decomposition on the fluctuation coefficient to obtain a residual error item of the fluctuation coefficient, performing data analysis on the residual error item, determining an abnormal fluctuation coefficient, taking a time point corresponding to the abnormal fluctuation coefficient as an abnormal time point, and determining a concern weight of the abnormal time point according to the fluctuation coefficient of a time point adjacent to the abnormal time point;
dividing all time points into a high attention time point and a low attention time point according to the attention weight, respectively carrying out data unified processing on the drilling measurement data of the low attention time point of different data types to obtain unified data respectively corresponding to the different data types, and sequencing the drilling measurement data of the high attention time point and the unified data of the low attention time point of the same data type according to a time sequence to obtain a sequence to be compressed of the drilling measurement data of different types;
performing run-length coding compression processing on different types of sequences to be compressed respectively to obtain compressed data;
the drilling measurement data comprises the intensity data of a natural gamma logging instrument and the stress data of a drill string stress sensor, and the fluctuation coefficient of each time point is obtained according to the data fluctuation conditions of different types of drilling measurement data at all time points, and the method comprises the following steps:
calculating the average value of the intensity data at all time points to obtain an intensity characteristic value; calculating the average value of the stress data at all time points to obtain a stress characteristic value;
obtaining the fluctuation coefficient of any time point according to the intensity data and the stress data, the intensity characteristic value and the stress characteristic value of the time point;
the obtaining the fluctuation coefficient of the time point according to the intensity data and the stress data, the intensity characteristic value and the stress characteristic value of any time point comprises the following steps:
calculating a difference normalized value of the intensity data and the intensity characteristic value as an intensity influence coefficient, and calculating a difference normalized value of the stress data and the stress characteristic value as a stress influence coefficient;
taking the sum of the intensity influence coefficient and the stress influence coefficient as a fluctuation coefficient;
the classifying all the time points into a high attention time point and a low attention time point according to the attention weight comprises the following steps:
taking the abnormal time point with the attention weight larger than a preset weight threshold as a high attention time point;
all other time points except the high attention time point are taken as low attention time points.
2. The drilling and testing integrated equipment data processing method according to claim 1, wherein the step of performing data analysis on the residual items to determine abnormal fluctuation coefficients comprises the steps of:
determining an upper limit value and a lower limit value of a residual error item based on a box diagram method;
taking a range corresponding to the upper limit value and the lower limit value as a fluctuation range;
and taking the fluctuation coefficient of which the residual error item does not belong to the fluctuation range as an abnormal fluctuation coefficient.
3. The drilling and testing integrated equipment data processing method according to claim 2, wherein the determining the attention weight of the abnormal time point according to the fluctuation coefficient of the time point adjacent to the abnormal time point comprises:
taking the abnormal time point as a center, and taking a time point in a preset time range as an adjacent time point of the abnormal time point;
counting the fluctuation coefficients of all adjacent time points of the abnormal time point, and taking the quantity of the fluctuation coefficients belonging to the abnormal fluctuation coefficients as the concern influence quantity of the abnormal time point;
and carrying out data processing on the attention influence quantity by using an activation function to obtain the attention weight of the abnormal time point.
4. The method for processing drilling and testing integrated equipment data according to claim 1, wherein the step of performing data unified processing on the drilling and testing data of the low-attention time points with different data types to obtain unified data corresponding to the different data types respectively comprises the following steps:
calculating the average value of the intensity data of all the low-attention time points of the same data type to obtain uniform intensity data; calculating the average value of the stress data of all the low-attention time points of the same data type to obtain uniform stress data;
and taking the unified strength data and the unified stress data as unified data.
5. The drilling and testing integrated equipment data processing method according to claim 4, wherein the sorting the drilling and testing data of the high attention time point and the unified data of the low attention time point of the same data type according to the time sequence to obtain the sequences to be compressed of the drilling and testing data of different types comprises:
sorting the intensity data of the high attention time points and the unified intensity data of the low attention time points according to the time sequence to obtain a sequence to be compressed of the intensity data;
and ordering the stress data of the high attention time point and the unified stress data of the low attention time point according to the time sequence to obtain a sequence to be compressed of the stress data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310842552.6A CN116582134B (en) | 2023-07-11 | 2023-07-11 | Drilling and testing integrated equipment data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310842552.6A CN116582134B (en) | 2023-07-11 | 2023-07-11 | Drilling and testing integrated equipment data processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116582134A CN116582134A (en) | 2023-08-11 |
| CN116582134B true CN116582134B (en) | 2023-10-13 |
Family
ID=87536157
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310842552.6A Active CN116582134B (en) | 2023-07-11 | 2023-07-11 | Drilling and testing integrated equipment data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116582134B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2104287A1 (en) * | 1991-12-24 | 1993-06-25 | Jae S. Lim | Method and apparatus for encoding of data using both vector quantitization and runlength encoding and using adaptive runlength encoding |
| CN105718715A (en) * | 2015-12-23 | 2016-06-29 | 华为技术有限公司 | Anomaly detection method and device |
| CN107230150A (en) * | 2017-07-19 | 2017-10-03 | 西南大学 | A kind of method for detecting abnormality in stock market based on Non-negative Matrix Factorization |
| CN111107363A (en) * | 2018-10-26 | 2020-05-05 | 西安科锐盛创新科技有限公司 | Bandwidth compression coding method |
| CN111107362A (en) * | 2018-10-26 | 2020-05-05 | 西安科锐盛创新科技有限公司 | Video compression coding method |
| CN111459778A (en) * | 2020-03-12 | 2020-07-28 | 平安科技（深圳）有限公司 | Operation and maintenance system abnormal index detection model optimization method and device and storage medium |
| CN111510152A (en) * | 2019-01-30 | 2020-08-07 | 中国科学院声学研究所 | Compression and decompression method for acoustic logging data |
| CN112380044A (en) * | 2020-12-04 | 2021-02-19 | 腾讯科技（深圳）有限公司 | Data anomaly detection method and device, computer equipment and storage medium |
| CN112818819A (en) * | 2021-01-28 | 2021-05-18 | 青岛澎湃海洋探索技术有限公司 | AUV state monitoring method based on dynamic model and complex network theory |
| CN113284250A (en) * | 2021-06-11 | 2021-08-20 | 北京大学深圳研究生院 | Geometric encoding method and decoding method and device for point cloud |
| CN113761777A (en) * | 2021-08-26 | 2021-12-07 | 上海电力大学 | Ultra-short-term photovoltaic power prediction method based on HP-OVMD |
| CN115050210A (en) * | 2022-06-07 | 2022-09-13 | 杭州市城市大脑停车系统运营股份有限公司 | Parking lot intelligent induction method, system and device based on time sequence prediction |
| CN115061838A (en) * | 2022-03-28 | 2022-09-16 | 京东科技信息技术有限公司 | Fault detection method and system |
| CN115906310A (en) * | 2022-11-09 | 2023-04-04 | 中石化石油工程技术服务有限公司 | Drilling parameter optimization method based on variational self-encoder artificial intelligence model |
| CN115967750A (en) * | 2021-10-09 | 2023-04-14 | 中国石油化工股份有限公司 | Compression and transmission method, compression device and storage medium for while-drilling data |
| CN115994248A (en) * | 2023-03-24 | 2023-04-21 | 青岛精锐机械制造有限公司 | Data detection method and system for valve faults |
| CN116108008A (en) * | 2023-04-13 | 2023-05-12 | 山东明远生物科技有限公司 | Decorative material formaldehyde detection data processing method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7454076B2 (en) * | 2004-06-15 | 2008-11-18 | Cisco Technology, Inc. | Hybrid variable length coding method for low bit rate video coding |
-
2023
- 2023-07-11 CN CN202310842552.6A patent/CN116582134B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2104287A1 (en) * | 1991-12-24 | 1993-06-25 | Jae S. Lim | Method and apparatus for encoding of data using both vector quantitization and runlength encoding and using adaptive runlength encoding |
| CN105718715A (en) * | 2015-12-23 | 2016-06-29 | 华为技术有限公司 | Anomaly detection method and device |
| CN107230150A (en) * | 2017-07-19 | 2017-10-03 | 西南大学 | A kind of method for detecting abnormality in stock market based on Non-negative Matrix Factorization |
| CN111107363A (en) * | 2018-10-26 | 2020-05-05 | 西安科锐盛创新科技有限公司 | Bandwidth compression coding method |
| CN111107362A (en) * | 2018-10-26 | 2020-05-05 | 西安科锐盛创新科技有限公司 | Video compression coding method |
| CN111510152A (en) * | 2019-01-30 | 2020-08-07 | 中国科学院声学研究所 | Compression and decompression method for acoustic logging data |
| CN111459778A (en) * | 2020-03-12 | 2020-07-28 | 平安科技（深圳）有限公司 | Operation and maintenance system abnormal index detection model optimization method and device and storage medium |
| CN112380044A (en) * | 2020-12-04 | 2021-02-19 | 腾讯科技（深圳）有限公司 | Data anomaly detection method and device, computer equipment and storage medium |
| CN112818819A (en) * | 2021-01-28 | 2021-05-18 | 青岛澎湃海洋探索技术有限公司 | AUV state monitoring method based on dynamic model and complex network theory |
| CN113284250A (en) * | 2021-06-11 | 2021-08-20 | 北京大学深圳研究生院 | Geometric encoding method and decoding method and device for point cloud |
| CN113761777A (en) * | 2021-08-26 | 2021-12-07 | 上海电力大学 | Ultra-short-term photovoltaic power prediction method based on HP-OVMD |
| CN115967750A (en) * | 2021-10-09 | 2023-04-14 | 中国石油化工股份有限公司 | Compression and transmission method, compression device and storage medium for while-drilling data |
| CN115061838A (en) * | 2022-03-28 | 2022-09-16 | 京东科技信息技术有限公司 | Fault detection method and system |
| CN115050210A (en) * | 2022-06-07 | 2022-09-13 | 杭州市城市大脑停车系统运营股份有限公司 | Parking lot intelligent induction method, system and device based on time sequence prediction |
| CN115906310A (en) * | 2022-11-09 | 2023-04-04 | 中石化石油工程技术服务有限公司 | Drilling parameter optimization method based on variational self-encoder artificial intelligence model |
| CN115994248A (en) * | 2023-03-24 | 2023-04-21 | 青岛精锐机械制造有限公司 | Data detection method and system for valve faults |
| CN116108008A (en) * | 2023-04-13 | 2023-05-12 | 山东明远生物科技有限公司 | Decorative material formaldehyde detection data processing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116582134A (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8374974B2 (en) | Neural network training data selection using memory reduced cluster analysis for field model development | |
| CN112637132B (en) | Network anomaly detection method and device, electronic equipment and storage medium | |
| CN106130562A (en) | A kind of well logging during data real-time compression method and decompression method | |
| CN108561126B (en) | Simple method for determining organic porosity of shale gas reservoir | |
| Chen et al. | The joinpoint-jump and joinpoint-comparability ratio model for trend analysis with applications to coding changes in health statistics | |
| CN111738371B (en) | Stratum fracture number prediction method based on random forest data mining | |
| CN116582134B (en) | Drilling and testing integrated equipment data processing method | |
| CN104598705B (en) | For identifying the method and apparatus of subsurface material layer | |
| CN117112514B (en) | Recording and storing method based on p-chloromethyl styrene production data | |
| CN114186879A (en) | Method and equipment for evaluating influence of geological parameters on resource quantity calculation errors | |
| CN113806681A (en) | Rapid RQD analysis method | |
| Khondekar et al. | Nonlinearity and chaos in 8 B solar neutrino flux signals from sudbury neutrino observatory | |
| EP3258061A1 (en) | System and method for prediction of a component failure | |
| CN105653854A (en) | Method and apparatus for calculating organic carbon content of carbonate source rock | |
| CN110414755A (en) | The method and apparatus that a kind of pair of evaluation object is evaluated | |
| CN114991757A (en) | Formation pressure measurement and recording integrated monitoring method and system while drilling | |
| US9921329B2 (en) | Automated method for selecting positions within formations from which to extract samples thereof | |
| Velis | Statistical segmentation of geophysical log data | |
| RU2782505C2 (en) | Method and computer system for processing borehole data | |
| CN117473351B (en) | Power supply information remote transmission system based on Internet of things | |
| CN107944749B (en) | Shale gas block development potential evaluation method based on relative preference index | |
| CN117150207B (en) | Method, equipment and storage medium for evaluating associated helium resource quantity | |
| Li et al. | Downhole Signal Compression and Surface Reconstruction Based on Dictionary Machine Learning | |
| CN117648590B (en) | Omnibearing gamma logging data optimization processing method | |
| CN114183134B (en) | Shale gas horizontal well ground stress prediction method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |