Multi-parameter underground intelligent processing and preferential uploading method and device for underground engineering while drilling

Abstract

The invention provides a multi-parameter underground intelligent processing and preferential uploading method and device for underground engineering while drilling, and the method comprises the steps: collecting underground data in real time, and storing the underground data into a first data table; performing preprocessing according to the underground data in the first data table, and storing the preprocessed underground data into a second data table; on the basis of underground data of the second data table, a datum line and / or a neural network model are / is adopted for feature analysis, change features of parameters are described, and feature data are stored in a third data table; performing underground condition identification on the feature data of the third data table, and storing an identification result into a fourth data table; the underground conditions at least comprise unclean well holes, drilling leakage of a drilling tool and blockage of water holes; according to the identification result of the fourth data table, determining the uploaded normal and abnormal engineering measurement parameters and storing the parameters in a fifth data table; and uploading the parameter data of the fifth data table to a ground early warning unit, and performing alarm analysis by the ground early warning unit in combination with the logging parameters.

Description

Technical Field

[0001] The present invention relates to the technical field of drilling exploration, and particularly to a method and device for intelligent processing and selective uploading of multi-parameters during downhole drilling operations. Background Art

[0002] This section aims to provide background or context for the embodiments of the present invention described in the claims. The description herein is not admitted to be prior art merely by virtue of being included in this section.

[0003] Real-time measurement of downhole drilling engineering parameters is one of the core technologies for safe and rapid drilling. By uploading the measured downhole engineering parameters during drilling to the ground, it can provide data support for drilling engineers to understand the downhole drilling state.

[0004] Currently, the research on real-time measurement instruments for downhole drilling engineering parameters mainly focuses on the downhole measurement methods and instruments for each parameter. For example: a downhole multi-parameter measurement sub-section (Patent Application No. 201510817995.5), a near-bit multi-parameter measurement system and method based on fiber Bragg grating (Patent Application No. 201911321507.6) proposed a sub-section using a fiber Bragg grating group to measure axial force, torque, temperature, and pressure. A near-bit multi-parameter downhole measurement and control system during drilling (Patent Application No. 202111230883.1), a multi-parameter measurement device during drilling (Patent Application No. 201811478487.9), a multi-parameter logging-while-drilling tool (Patent Application No. 201510946063.0), and an oilfield downhole multi-parameter measurement system (Patent Application No. 201220090224.2) each proposed different measurement methods and tools. A method and system for real-time measurement and transmission of multi-parameters during drilling in the entire well section (Patent Application No. 201410232679.7) proposed a method and system for realizing multi-parameter measurement while drilling at multiple points along the drill string in the wellbore and real-time transmission to the ground based on acoustic wave information transmission, all of which adopted acoustic wave information transmission. The above methods are currently the most commonly used in drilling operations. However, in the actual application process, due to the large amount and variety of downhole measurement data during drilling, the pulse transmission is too slow, often resulting in incomplete data received on the ground and a serious time lag, unable to reflect the actual downhole state at the current moment, unable to achieve real-time monitoring, and having little guiding significance for the drilling site.

[0005] In summary, there is an urgent need for a technical solution that can overcome the above defects and can perform intelligent processing and selective uploading of downhole drilling engineering parameters. Summary of the Invention

[0006] To solve the problems existing in the prior art, the present invention proposes a method and device for intelligent processing and optimized uploading of multi-parameters during downhole drilling. The present invention can realize intelligent processing and optimized and rapid uploading of multi-parameters during downhole drilling. After processing a large amount of different collected data downhole, combined with engineering, the downhole working conditions and effective abnormal data are preferentially uploaded to the ground, and combined with the surface logging data, the downhole state is judged in a timely and accurate manner, and then the engineer takes reasonable measures to avoid downhole risks in drilling and improve drilling efficiency.

[0007] In the first aspect of the embodiments of the present invention, a method for intelligent processing and optimized uploading of multi-parameters during downhole drilling is proposed, including:

[0008] Collect downhole data in real time and store the downhole data in a first data table, where the downhole data at least includes weight on bit, torque, internal pressure of drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration and rotational speed;

[0009] Preprocess the downhole data according to the downhole data in the first data table and store the preprocessed downhole data in a second data table;

[0010] Based on the downhole data in the second data table, perform feature analysis using a baseline and / or a neural network model to describe the change characteristics of the parameters, and store the feature data in a third data table;

[0011] Identify the downhole conditions for the feature data in the third data table and store the identification results in a fourth data table; the downhole conditions at least include un-clean wellbore, drill string leakage, and nozzle blockage;

[0012] Determine the normal and abnormal engineering measurement parameters to be uploaded according to the identification results in the fourth data table and store them in a fifth data table;

[0013] Upload the parameter data in the fifth data table to a ground warning unit, and perform warning analysis by the ground warning unit in combination with logging parameters.

[0014] In the second aspect of the embodiments of the present invention, a device for intelligent processing and optimized uploading of multi-parameters during downhole drilling is proposed, including:

[0015] A data acquisition module for collecting downhole data in real time and storing the downhole data in a first data table, where the downhole data at least includes weight on bit, torque, internal pressure of drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration and rotational speed;

[0016] A preprocessing module for preprocessing the downhole data according to the downhole data in the first data table and storing the preprocessed downhole data in a second data table;

[0017] A feature analysis module, used to perform feature analysis based on the downhole data in the second data table using a baseline and / or a neural network model to describe the variation characteristics of the parameters and store the feature data in a third data table;

[0018] A downhole analysis module, used to identify downhole conditions based on the characteristic data in the third data table, and store the identification results in a fourth data table; the downhole conditions at least include unclean wellbore, drilling tool leakage, and water hole blockage;

[0019] A data classification module, used to determine the uploaded normal and abnormal engineering measurement parameters according to the recognition result of the fourth data table and store them in a fifth data table;

[0020] The uploading module is used to upload the parameter data of the fifth data table to the ground early warning unit, and the ground early warning unit performs alarm analysis in combination with the logging parameters.

[0021] In the third aspect of an embodiment of the present invention, a computer device is proposed, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a method for intelligent downhole processing and optimal uploading of multiple parameters of downhole drilling engineering is implemented.

[0022] In a fourth aspect of an embodiment of the present invention, a computer-readable storage medium is proposed, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for downhole intelligent processing and optimal uploading of multiple parameters of downhole drilling engineering is implemented.

[0023] In a fifth aspect of an embodiment of the present invention, a computer program product is proposed, which includes a computer program. When the computer program is executed by a processor, a method for downhole intelligent processing and optimal uploading of multiple parameters of downhole drilling engineering is implemented.

[0024] The method and device for downhole intelligent processing and preferential uploading of multiple parameters of downhole drilling engineering proposed in the present invention can analyze and process the data collected downhole, select data that can reflect the real-time status of drilling conditions for uploading, reduce the amount of data transmission, and improve data transmission efficiency, so that the ground can obtain downhole data in time, implement targeted adjustments to the drilling plan, and improve drilling operation efficiency; the downhole data is uploaded after processing, and only key data and abnormal working condition characteristics are obtained on the ground, which can effectively solve the problem of single uploaded data, and the information is more accurate and reliable, so that drilling engineers can clearly grasp the actual changes in downhole working conditions and make accurate judgments, providing strong data support for drilling scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0026] Figure 1 It is a schematic flow chart of a method for intelligent downhole processing and optimized uploading of multiple downhole engineering parameters while drilling in an embodiment of the present invention.

[0027] Figure 2A It is a schematic diagram of a downhole multi-parameter measurement system while drilling in an embodiment of the present invention.

[0028] Figure 2B It is a schematic diagram of downhole multi-parameter acquisition and processing in an embodiment of the present invention.

[0029] Figure 3 It is a flow chart of downhole processing and optimized uploading of multiple downhole parameters in an embodiment of the present invention.

[0030] Figure 4 It is a flow chart of downhole working condition identification of multiple downhole parameters in an embodiment of the present invention.

[0031] Figure 5 It is a flow chart of establishing a downhole reference line for multiple downhole parameters in an embodiment of the present invention.

[0032] Figure 6 It is a schematic diagram of downhole complex judgment in an embodiment of the present invention.

[0033] Figure 7 It is a schematic diagram of the architecture of a device for intelligent downhole processing and optimized uploading of multiple downhole engineering parameters while drilling in an embodiment of the present invention.

[0034] Figure 8 It is a schematic diagram of the structure of a computer device in an embodiment of the present invention. Specific embodiments

[0035] The following will describe the principles and spirit of the present invention with reference to several exemplary embodiments. It should be understood that these embodiments are only provided to enable those skilled in the art to better understand and implement the present invention, and do not limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to be able to fully convey the scope of the present disclosure to those skilled in the art.

[0036] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, a device, equipment, a method, or a computer program product. Therefore, the present disclosure can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0037] According to an embodiment of the present invention, there is provided a method and device for intelligent downhole processing and optimized uploading of multi-parameters in downhole engineering while drilling, which relates to the technical field of drilling exploration. After processing a large amount of different data collected downhole in the present invention, combined with engineering, the downhole working conditions and effective abnormal data are preferentially uploaded to the ground, and combined with the surface logging data, the downhole state is judged timely and accurately. The drilling engineer can use the uploaded data to timely detect the precursors of downhole complexity, adjust the drilling parameters, and take reasonable measures to avoid downhole risks and improve the drilling efficiency.

[0038] Next, with reference to several representative embodiments of the present invention, the principles and spirit of the present invention will be elaborated in detail.

[0039] Figure 1 It is a schematic flowchart of the method for intelligent downhole processing and optimized uploading of multi-parameters in downhole engineering while drilling according to an embodiment of the present invention. As Figure 1 shown, the method includes:

[0040] S101, collect downhole data in real time and store the downhole data in a first data table, where the downhole data at least includes weight on bit, torque, internal pressure of drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration, and rotational speed;

[0041] S102, preprocess the downhole data according to the downhole data in the first data table, and store the preprocessed downhole data in a second data table;

[0042] S103, based on the downhole data in the second data table, perform feature analysis using a baseline and / or a neural network model to describe the change characteristics of the parameters, and store the feature data in a third data table;

[0043] S104, identify the downhole conditions for the feature data in the third data table, and store the identification results in a fourth data table; the downhole conditions at least include unclean wellbore, drill string leakage, and water eye blockage;

[0044] S105, determine the normal and abnormal engineering measurement parameters to be uploaded according to the identification results in the fourth data table, and store them in a fifth data table;

[0045] S106, upload the parameter data in the fifth data table to the ground warning unit, and the ground warning unit performs warning analysis in combination with the logging parameters.

[0046] In order to explain more clearly the multi-parameter downhole intelligent processing and optimal uploading method of the downhole drilling engineering, each step is described in detail below.

[0047] S101:

[0048] The downhole data are collected in real time and stored in a first data table, wherein the downhole data at least includes drilling pressure, torque, drilling tool internal pressure, annular space pressure, annular space temperature, longitudinal vibration, lateral vibration, axial vibration and rotation speed.

[0049] In one embodiment, downhole data is collected in real time through a sensor group; the sensor group includes at least a stress strain gauge, a temperature and pressure sensor, a triaxial acceleration sensor and a gyroscope;

[0050] Among them, the stress strain gauge measures drilling pressure, torque and internal pressure of the drill bit; the temperature and pressure sensor measures the annular space pressure and annular space temperature; the three-axial acceleration sensor measures longitudinal vibration, lateral vibration and axial vibration; and the gyroscope measures the rotation speed of the drill bit.

[0051] S102:

[0052] Preprocessing is performed on the downhole data in the first data table, and the preprocessed downhole data is stored in the second data table.

[0053] In one embodiment, the downhole data is filtered and validity identified, erroneous data and invalid data are eliminated, and the pre-processed downhole data is stored in the second data table.

[0054] Downhole data filtering and validity identification is to process the data collected from the downhole to remove noise and interference, while identifying and retaining valid information. This step is very important in geophysical exploration scenarios, which can improve the quality and reliability of data and provide a more reliable basis for subsequent analysis and decision-making.

[0055] Filtering is the process of processing data to remove noise and interference. Common filtering methods include low-pass filtering, high-pass filtering, band-pass filtering, etc. You can choose the appropriate filtering method for processing according to the characteristics and needs of the data.

[0056] Validity identification refers to analyzing and judging the data after filtering to determine the valid information in it. This includes analyzing the spectral characteristics and time domain characteristics of the data to determine the valid signals and information in the data.

[0057] In practical applications, the filtering and validity identification methods can be combined to comprehensively process downhole data to improve the quality and reliability of the data, which is of great significance for subsequent data analysis, imaging and interpretation.

[0058] Further, the method includes:

[0059] At every set period interval, collect the average data of N data curves underground. After data validity processing, insert it into the in-memory data buffer.

[0060] For example, N = 8. Collect the average data of 8 curves underground every 5 seconds. After data validity processing, insert it into the in-memory data buffer.

[0061] Judge whether the cached data is an integer multiple of M. If not, continue to collect underground data in the next set period. If so, calculate the average value and working condition, and insert them into the baseline parameter calculation table.

[0062] For example, M = 6. Judge whether the number of cached data is an integer multiple of 6, that is, cached quantity % 6 = 0.

[0063] Judge whether the number of data groups in the baseline parameter calculation table is P. If so, establish a baseline and continue to collect underground data. If not, continue to collect underground data. N, M, and P are positive integers.

[0064] For example, P = 5. Judge whether the number of data groups in the baseline parameter calculation table is 5.

[0065] Among them, when calculating the working condition, for rotary drilling and compound drilling, the parameter characteristics of the drilling working condition meet the following conditions: weight on bit > 0, rotary speed > 0, internal pressure of drill string > external pressure of drill string, axial vibration > 0. For sliding drilling, the parameter characteristics of the drilling working condition meet the following conditions: weight on bit > 0, internal pressure of drill string > external pressure of drill string, axial vibration > 0.

[0066] S103:

[0067] Based on the underground data in the second data table, perform feature analysis using the baseline and / or neural network model, describe the change characteristics of the parameters, and store the feature data in the third data table.

[0068] In one embodiment, perform feature analysis in the way of the baseline. The specific method is:

[0069] Group the underground data collected within a set time duration and fill it into the baseline parameter calculation table. Among them, the baseline parameter calculation table contains 5 data groups. Each data group contains weight on bit, torque, internal pressure of drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration, and rotary speed.

[0070] Judge whether the baseline is in a stable state. The judgment conditions for the stable state are:

[0071]

[0072] WOB represents the weight on bit, TRQ represents the torque, PA represents the annulus pressure, PT represents the internal pressure, TMP represents the temperature, ACCX represents the lateral vibration, ACCZ represents the axial vibration, n is the data serial number, and the subscripts n and n - 1 represent the data at the nth moment and the data at the previous moment respectively; represents rounding down;

[0073] After the newly established baseline, the subsequent newly measured data are respectively compared with the baseline. If there are no abnormal features, they are updated and a new baseline is re-established; if there are abnormalities, the baseline features remain unchanged.

[0074] The updated data are the data after 30 s.

[0075] In one embodiment, the specific method for judging the working condition is as follows:

[0076] Read the number of data in the baseline parameter calculation table, and judge whether the number of the baseline parameter calculation table is 5. If not, it is determined that the working condition is non-drilling, and after sleeping for a certain period of time, read the number of data in the baseline parameter calculation table again;

[0077] For example, sleeping for a certain period of time is sleeping for 1 s.

[0078] If so, judge whether the working condition of the latest two points of data is drilling. If so, it is determined that the working condition is drilling; if not, it is determined that the working condition is non-drilling. After the determination, sleep for a certain period of time and read the number of data in the baseline parameter calculation table again.

[0079] In one embodiment, for feature analysis using a neural network model, the data can be input into the neural network for training to learn the features and patterns in the data. When describing the change characteristics of parameters, the following steps are implemented through the neural network model:

[0080] Data preparation: First, the data set for training needs to be prepared, including the input data and the corresponding labels or outputs. These data can be various parameters collected from the wellbore, such as geological structures, formation characteristics, seismic data, etc.

[0081] Feature extraction: After the data are input into the neural network, the neural network will automatically extract the features in the data. During the training process, the neural network will continuously adjust the weights and biases to accurately predict the output results to the greatest extent. In this way, the neural network can learn the features and patterns in the data.

[0082] Description of parameter change characteristics: By analyzing the trained neural network, the description of the parameter change characteristics can be obtained. This can include the change situations of parameters such as weights, biases, and activation functions in the neural network, as well as the output change situations of the neural network under different input conditions.

[0083] Data prediction and classification: The trained neural network model can be used to predict and classify new data. By inputting new data, the neural network can predict and classify the data based on the learned features and patterns, thereby describing the change characteristics of parameters.

[0084] Using a neural network model for feature analysis can help identify important features and patterns in the data, thereby describing the change characteristics of parameters. This method has broad application prospects in downhole data analysis.

[0085] S104:

[0086] Identify the downhole conditions for the characteristic data of the third data table and store the identification results in the fourth data table.

[0087] In one embodiment, a big data artificial intelligence analysis method or a logical judgment method is used to identify the downhole conditions; among them, the downhole working conditions include abnormal working conditions and normal working conditions, and the abnormal working conditions at least include, according to the degree of importance: precursors of stuck pipe, water eye blockage, annulus blockage, severe drill string vibration, stick-slip, and increase in cuttings bed.

[0088] Specifically, the detailed process of identifying the downhole conditions by the logical judgment method is as follows:

[0089] Convert the change of characteristic parameters of abnormal working conditions into mathematical descriptions and make judgments in sequence according to the degree of importance of abnormal working conditions;

[0090] First, update the data at a set time interval, read the data in the baseline parameter calculation table, and judge whether it is empty. If it is empty, there are unprocessed abnormal working conditions; if it is not empty, continue to judge whether there are abnormal working conditions;

[0091] For example, update the data every 30s.

[0092] When judging the precursors of stuck pipe, if the ratio of the weight on bit / torque value at this moment to the weight on bit / torque value at the previous moment exceeds a 10% fluctuation, it is judged as a precursor of stuck pipe, and the continuous time is 5 groups;

[0093] When judging water eye blockage, if the value of the drill string internal pressure - annulus pressure at this moment is greater than the value of the drill string internal pressure - annulus pressure at the next moment by 1MPa, it is judged as water eye blockage, and the continuous time is 5 groups;

[0094] When judging annulus blockage, if the value of the drill string internal pressure - annulus pressure at this moment is less than the value of the drill string internal pressure - annulus pressure at the next moment by 1MPa, it is judged as annulus blockage, and the continuous time is 5 groups;

[0095] When judging severe drill string vibration, classify the three-axis vibration data of the horizontal axis, vertical axis, and axial direction collected downhole. If it exceeds 5g, it is judged as severe drill string vibration;

[0096] When judging stick-slip, if the rotational speed at this moment / the rotational speed at the previous moment is greater than 20%, it is judged as stick-slip;

[0097] When judging the increase of the cuttings bed, the ratio of the weight on bit / torque value at this moment to the weight on bit / torque value at the previous moment exceeds 10% fluctuation; the value of the drill string internal pressure - annulus pressure at this moment is greater than the value of the drill string internal pressure - annulus pressure at the next moment by 0.5 MPa; if the above two conditions are met, it is judged that the cuttings bed has increased;

[0098] Classify the identified abnormal working conditions and upload the abnormal working conditions and abnormal feature data;

[0099] If the above abnormal working conditions are not judged, it is determined as a normal working condition.

[0100] S105:

[0101] According to the recognition results of the fourth data table, determine the uploaded normal and abnormal engineering measurement parameters and store them in the fifth data table;

[0102] In one embodiment, compared with the prior art of uploading all downhole acquisition parameters to the downhole for display, which has problems such as large data transmission volume, slow transmission speed, low real-time performance, and inability to provide targeted help to drilling engineers, etc., through steps S101 to S105 of this application, real-time processing and analysis can be carried out when downhole data is acquired, and the data is preferentially selected and uploaded to the ground.

[0103] S106:

[0104] Upload the parameter data of the fifth data table to the ground warning unit, and the ground warning unit performs alarm analysis in combination with the logging parameters.

[0105] In one embodiment, uploading the abnormal working conditions to the ground warning unit and performing alarm analysis in combination with the logging parameters can help monitor and warn of downhole abnormal conditions, so as to take measures in time to avoid accidents.

[0106] Through the previous steps S101 to S105 of processing downhole data (one of the themes of this application, downhole data processing), further select representative data and upload it to the ground (one of the themes of this application, preferential upload), provide it to the drilling engineer to understand the downhole situation, timely discover the precursors of downhole complexity, timely adjust the drilling parameters, and achieve the purpose of avoiding downhole risks and improving drilling efficiency.

[0107] During data transmission, abnormal working condition data and / or normal working condition data are transmitted to the ground warning unit through wireless or wired networks. The ground warning unit receives and stores the data from the underground. This unit is usually equipped with specialized software and algorithms for real-time analysis and processing of data. During warning analysis, the ground warning unit performs warning analysis on the received abnormal working condition data. In addition to the abnormal working condition data, the ground warning unit also conducts comprehensive analysis by combining logging parameters such as geological structure, formation characteristics, seismic data, etc. Through pre-set rules and algorithms, the ground warning unit can automatically identify abnormal situations and issue alarms.

[0108] Once the ground warning unit identifies an abnormal situation, it will immediately issue an alarm and notify relevant personnel for handling. This can include measures such as stopping the drilling operation, adjusting drilling parameters, checking equipment, etc.

[0109] In this way, the ground warning unit can conduct real-time monitoring and warning of underground abnormal working conditions, which helps to avoid accidents and ensure the safe and efficient progress of drilling operations. Conducting warning analysis by combining logging parameters can improve the accuracy and timeliness of warnings and ensure that abnormal situations are handled in a timely manner.

[0110] It should be noted that although the operations of the method of the present invention are described in a specific order in the above embodiments and accompanying drawings, however, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution.

[0111] The following describes the downhole intelligent processing and optimal uploading method for multi-parameters during drilling of the present invention in combination with a specific embodiment. The present invention can perform downhole intelligent processing on multi-parameters during downhole drilling and upload them optimally and quickly, which belongs to a key technology for downhole multi-parameter measurement while drilling. After the downhole data is acquired in real time, it is pre-processed downhole, and then the processed data is compressed and quickly uploaded to the ground to provide technical support for the drilling project.

[0112] 1. For the downhole multi-parameter measurement while drilling system:

[0113] Refer to Figure 2A and Figure 2B , a set of downhole multi-parameter measurement while drilling system is set up at the drilling site. This system consists of a downhole unit and a ground unit.

[0114] The downhole unit is composed of a sensor group, digital signals, downhole power supply, downhole pre-processing center, and signal sending device (continuous wave or MWD pulse).

[0115] The sensor group includes stress and strain gauges, temperature and pressure sensors, three-axis acceleration sensors, and gyroscopes. The stress and strain gauges measure the weight on bit and torque, and can also measure the internal pressure and external pressure of the drill string; the temperature and pressure sensors measure the downhole temperature and downhole pressure; the three-axis acceleration sensors measure the longitudinal vibration (vibration Y), lateral vibration (vibration X), and axial vibration (vibration Z); the gyroscope measures the rotational speed of the drill string.

[0116] The power supply of the sensor group is provided by the downhole power supply. The data measured by the sensors are converted into digital signals through filtering, amplification, and ADC, and then enter the downhole preprocessing center.

[0117] After being processed by the downhole preprocessing center, the working condition identification results and characteristic parameters are transmitted to the signal sending device in real time, and then uploaded to the ground warning unit. The ground warning unit makes a comprehensive judgment based on the uploaded information combined with the logging data to determine the downhole state, and at the same time gives early warnings and alarms for drilling complications.

[0118] 2. For downhole multi-parameter downhole processing and optimal uploading:

[0119] Downhole multi-parameter downhole processing and optimal uploading is the key technology for downhole multi-parameter measurement while drilling. Refer to Figure 3 , which is the flowchart of downhole multi-parameter downhole processing and optimal uploading in an embodiment of the present invention.

[0120] As Figure 3 shown, the nine parameters measured by the sensor group enter the downhole preprocessing center in the form of digital signals.

[0121] The downhole preprocessing center is a CPU chip, which consists of five data tables and can perform independent operations.

[0122] The first data table is based on the downhole data real-time acquisition module, and stores the weight on bit, torque, rotational speed, internal pressure of the drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, and axial vibration data collected in real time according to the measurement frequency, and aligns them by time;

[0123] The second data table is based on the filtering and validity identification module, and eliminates the error data by operating on the data in the first data table and stores them;

[0124] The third data table is based on the data processing module, and establishes a baseline or constructs new working condition data using a neural network model for the data in the second data table to describe the change characteristics of each parameter;

[0125] The fourth data table is based on the complex identification and judgment module, and creates a new table by operating, identifies downhole complications for the data in the third data table and creates a new table. Downhole complications include abnormal working conditions such as unclean wellbore, drill string leakage, and water eye blockage, and stores the normal and abnormal engineering measurement parameters that need to be uploaded.

[0126] 3. For determining the drilling operation conditions:

[0127] When real-time acquisition of multiple downhole parameters is carried out and downhole operations are performed, first determine the drilling operation conditions (as shown in the flowchart of downhole multi-parameter downhole operation condition identification). Figure 4 shown in the flowchart of downhole multi-parameter downhole operation condition identification).

[0128] When rotary drilling and compound drilling, determine the parameter characteristics of the drilling operation conditions: WOB > 0; RPM > 0; internal pressure of the drill string > external pressure of the drill string; vibration Z > 0.

[0129] When sliding drilling, determine the parameter characteristics of the drilling operation conditions: WOB > 0; internal pressure of the drill string > external pressure of the drill string; vibration Z > 0.

[0130] 4. For feature analysis using the reference line:

[0131] When drilling starts, the measured data of multiple downhole parameters enter the CPU for calculation (as shown in the flowchart of establishing the downhole reference line for multiple downhole parameters). Figure 5 shown in the flowchart of establishing the downhole reference line for multiple downhole parameters).

[0132] Within 150 s, after filtering and validity identification of 9 parameters such as WOB and torque, for the 30 pieces of collected data, they are divided into 6 groups and filled into the reference line parameter calculation table as shown in Table 1 below.

[0133] Table 1

[0134]

[0135]

[0136] Calculate the reference line, obtain and update the reference line M0 {WOB, TRQ, PA, PT, TMP, ACCX, ACCZ}. Only when the data from 30 s to 150 s is stable can the reference line for each data be established.

[0137] The conditions for judging stability are:

[0138]

[0139] After the newly established reference line, subsequent newly measured data are respectively compared with the reference line. If there are no abnormal features, then update and re-establish the reference line. If there are abnormalities, then do not change the reference line features.

[0140] Update the reference line parameter calculation table for 30 s, as shown in Table 2, with the time from 60 s to 180 s.

[0141] Table 2

[0142]

[0143] 5. Analysis of abnormal working conditions:

[0144] The judgment of abnormal working conditions is graded according to the degree of importance (such as Figure 6 As shown in the figure, a schematic diagram of complex judgment in the well): Precursor of stuck drill ≥ Water eye blockage ≥ Annulus blockage ≥ Severe vibration of drilling tool ≥ Stick-slip ≥ Increased cuttings bed ≥ Normal drilling. In actual application scenarios, abnormal working conditions are not limited to this, but may also include other abnormal working conditions, and each abnormal working condition can be classified according to its importance.

[0145] There are two methods to judge abnormal working conditions: 1. Big data artificial intelligence; 2. Judgement based on logical rules.

[0146] 1. Big Data and Artificial Intelligence

[0147] By using big data artificial intelligence technology to judge abnormal operating conditions, the ability to identify and warn of abnormal situations can be improved.

[0148] Downhole sensors can collect various data such as drilling parameters, geological structure data, seismic data, etc. in real time. These data can be stored, managed and analyzed through big data technology. Then artificial intelligence algorithms, such as machine learning and deep learning, can be used to analyze and model the collected data. Through learning and pattern recognition of historical data, artificial intelligence algorithms can identify the characteristics and laws of abnormal working conditions.

[0149] Big data artificial intelligence technology can provide more accurate and timely monitoring and early warning of abnormal conditions in underground wells. Artificial intelligence algorithms can identify the characteristics of abnormal conditions and improve the accuracy and timeliness of early warnings by learning and analyzing massive amounts of data. This approach can help drilling operations be carried out more safely and efficiently.

[0150] 2. Logical rule judgment

[0151] The changes of characteristic parameters of abnormal working conditions are mathematically described.

[0152] 1) Premonition of drill sticking

[0153] If the ratio of the bit pressure / torque value at this moment to the bit pressure / torque value at the previous moment exceeds a fluctuation of 10%, it is judged as a precursor of pipe sticking, and the continuous time is 5 groups.

[0154] 2) Water hole is blocked

[0155] The drill bit internal pressure - annulus pressure value at this moment is greater than the drill bit internal pressure - annulus pressure value at the next moment by 1MPa, which is judged as water eye blockage, and the continuous time is 5 groups.

[0156] 3) Annular space blockage

[0157] The internal pressure - annulus pressure value in the drill string at this moment is less than the internal pressure - annulus pressure value in the drill string at the next moment by 1 MPa, which is judged as annulus blockage, and the continuous time is 5 groups.

[0158] 4) Severe vibration of the drill string

[0159] Severe vibration of the drill string can cause damage to the downhole drill string, and in severe cases, it can lead to drill string fracture. Therefore, the XYZ three - axis vibration data collected downhole is classified, and if it exceeds 5g, it is uploaded.

[0160] 5) Stick - slip

[0161] Stick - slip has a great impact on drilling speed increase and can also cause damage to the drill string. The characteristic parameter of stick - slip is the rotational speed. If the rotational speed at this moment / the rotational speed at the previous moment is greater than 20%, it is judged as stick - slip.

[0162] 6) Increase in the cuttings bed

[0163] An increase in the cuttings bed will cause hazards such as pipe sticking and a slowdown in the mechanical drilling speed. Therefore, if the ratio of the weight - on - bit / torque value at this moment to the weight - on - bit / torque value at the previous moment exceeds a 10% fluctuation; and the internal pressure - annulus pressure value in the drill string at this moment is greater than the internal pressure - annulus pressure value in the drill string at the next moment by 0.5 MPa; when the above two conditions are met, it is judged that the cuttings bed has increased.

[0164] Classify the identified abnormal working conditions, upload the abnormal working conditions and abnormal characteristic data to improve the transmission rate. As shown in Table 3, it is the working condition data table.

[0165] Table 3

[0166]

[0167] Since the data collected downhole is of many types and large in quantity, if it is uploaded in real - time, it will probably take 3 - 5 minutes, and the information obtained on the ground cannot reflect the current drilling working conditions, seriously affecting the decision - making of drilling operations. After implementing the present invention, due to the substantial reduction in the transmission volume, it can be obtained 1 - 2 minutes in advance. The ground can timely obtain the downhole data, and adjust the drilling plan in a targeted manner to improve the drilling operation efficiency; in addition, after the downhole data is processed and uploaded, the ground only obtains the key data and abnormal working condition characteristics, which can effectively solve the problem of single - data upload, and the information is more accurate and reliable. The drilling engineer can also clearly master the actual changes in the downhole working conditions and make accurate judgments.

[0168] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 7 to introduce the downhole intelligent processing and optimal upload device for multi - parameter downhole engineering while drilling of the exemplary embodiment of the present invention.

[0169] The implementation of the downhole intelligent processing and optimized uploading device for multi-parameters during drilling can refer to the implementation of the above method, and the repeated parts will not be described again. The term "module" or "unit" used hereinafter can be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0170] Based on the same inventive concept, the present invention also proposes a downhole intelligent processing and optimized uploading device for multi-parameters during drilling, as Figure 7 shown. The device includes:

[0171] A data acquisition module, configured to collect downhole data in real time and store the downhole data in a first data table. Among them, the downhole data at least includes weight on bit, torque, internal pressure of drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration and rotational speed;

[0172] A preprocessing module, configured to perform preprocessing on the downhole data in the first data table and store the preprocessed downhole data in a second data table;

[0173] A feature analysis module, configured to perform feature analysis on the downhole data in the second data table by using a baseline and / or a neural network model, describe the change characteristics of parameters, and store the feature data in a third data table;

[0174] A downhole analysis module, configured to identify downhole conditions for the feature data in the third data table and store the identification results in a fourth data table; the downhole conditions at least include unclean wellbore, drill string leakage, and nozzle blockage;

[0175] A data classification module, configured to determine the normal and abnormal engineering measurement parameters to be uploaded according to the identification results in the fourth data table and store them in a fifth data table;

[0176] An uploading module, configured to upload the parameter data in the fifth data table to a ground warning unit, and the ground warning unit performs warning analysis in combination with mud logging parameters.

[0177] In one embodiment, the data acquisition module, which collects downhole data in real time and stores the downhole data in a first data table, includes:

[0178] Collect downhole data in real time through a sensor group; the sensor group at least includes stress and strain gauges, temperature and pressure sensors, triaxial acceleration sensors and gyroscopes;

[0179] Among them, the stress and strain gauge measures the weight on bit, torque and internal pressure of the drill string; the temperature and pressure sensor measures the annulus pressure and annulus temperature; the three-axis acceleration sensor measures the longitudinal vibration, lateral vibration and axial vibration; and the gyroscope measures the rotational speed of the drill string.

[0180] In one embodiment, the preprocessing module preprocesses the downhole data according to the downhole data in the first data table and stores the preprocessed downhole data in the second data table, including:

[0181] Filter and identify the validity of the downhole data, eliminate the error data and invalid data, and store the preprocessed downhole data in the second data table.

[0182] In one embodiment, the device includes: a reference line processing module;

[0183] Among them, the reference line processing module is used for:

[0184] Insert the target data into the memory data buffer; the target data is obtained by collecting the average data of N downhole data curves every set period and obtaining the target data after data validity processing;

[0185] Judge whether the cached data is an integer multiple of M; if not, continue to collect downhole data in the next set period; if so, calculate the average value and working condition, and insert them into the reference line parameter calculation table;

[0186] Judge whether the number of data groups in the reference line parameter calculation table is P; if so, establish a reference line and continue to collect downhole data; if not, continue to collect downhole data; N, M, and P are positive integers;

[0187] Among them, when calculating the working condition, for rotary drilling and compound drilling, the parameter characteristics of the drilling working condition meet the following conditions: weight on bit > 0, rotational speed > 0, internal pressure of the drill string is greater than the external pressure of the drill string, and axial vibration > 0; for sliding drilling, the parameter characteristics of the drilling working condition meet the following conditions: weight on bit > 0, internal pressure of the drill string is greater than the external pressure of the drill string, and axial vibration > 0.

[0188] In one embodiment, the feature analysis module performs feature analysis based on the downhole data in the second data table using a reference line and / or a neural network model, describes the change characteristics of the parameters, and stores the feature data in the third data table, including:

[0189] Group the downhole data collected within a set time duration and fill it into the reference line parameter calculation table; among them, the reference line parameter calculation table contains 5 data groups; each data group contains weight on bit, torque, internal pressure of the drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration and rotational speed;

[0190] Judge whether the reference line is in a stable state, and the judgment condition for the stable state is:

[0191]

[0192] WOB represents the weight on bit, TRQ represents the torque, PA represents the annulus pressure, PT represents the internal pressure, TMP represents the temperature, ACCX represents the lateral vibration, ACCZ represents the axial vibration, n is the data sequence number, and the subscripts n and n - 1 represent the data at the nth moment and the data at the previous moment; represents rounding down;

[0193] After the newly established baseline, the subsequent newly measured data are respectively compared with the baseline. If there are no abnormal features, they are updated and a new baseline is re - established; if there are abnormalities, the baseline features remain unchanged.

[0194] In one embodiment, the feature analysis module performs feature analysis based on the downhole data in the second data table, using a baseline and / or a neural network model to describe the variation characteristics of parameters, and stores the feature data in the third data table, including:

[0195] Read the number of data in the baseline parameter calculation table, and determine whether the number of the baseline parameter calculation table is 5. If not, determine that the working condition is non - drilling, and sleep for a certain period of time and then re - read the number of data in the baseline parameter calculation table;

[0196] If so, determine whether the working condition of the latest two - point data is drilling. If so, determine that the working condition is drilling; if not, determine that the working condition is non - drilling. After the determination, sleep for a certain period of time and then re - read the number of data in the baseline parameter calculation table.

[0197] In one embodiment, the downhole analysis module identifies the downhole situation for the feature data in the third data table and stores the identification result in the fourth data table, including:

[0198] Adopt big data artificial intelligence analysis method or logical judgment method to identify the downhole situation; among them, the downhole working conditions include abnormal working conditions and normal working conditions. The abnormal working conditions at least include, according to the degree of importance: precursors of sticking, water - eye blockage, annulus blockage, severe drill string vibration, stick - slip, and increase of cuttings bed.

[0199] In one embodiment, the downhole analysis module identifies the downhole situation according to the logical judgment method, including:

[0200] Convert the change of characteristic parameters of abnormal working conditions into mathematical descriptions and judge them in turn according to the degree of importance of abnormal working conditions;

[0201] Update the data according to a set time period, read the data in the baseline parameter calculation table, and determine whether it is empty. If it is empty, there are unprocessed abnormal working conditions; if it is not empty, continue to determine whether there are abnormal working conditions;

[0202] When judging the precursor of stuck pipe, if the ratio of the weight-on-bit / torque value at this moment to the weight-on-bit / torque value at the previous moment exceeds a 10% fluctuation, it is judged as a precursor of stuck pipe, and the continuous time is 5 groups;

[0203] When judging the blockage of the nozzle, if the value of the drill string internal pressure - annulus pressure at this moment is greater than the value of the drill string internal pressure - annulus pressure at the next moment by 1 MPa, it is judged as a blockage of the nozzle, and the continuous time is 5 groups;

[0204] When judging the annulus blockage, if the value of the drill string internal pressure - annulus pressure at this moment is less than the value of the drill string internal pressure - annulus pressure at the next moment by 1 MPa, it is judged as an annulus blockage, and the continuous time is 5 groups;

[0205] When judging the severe vibration of the drill string, the three - axis vibration data of the horizontal axis, vertical axis, and axial direction collected downhole are classified, and when it exceeds 5g, it is judged that the drill string vibrates severely;

[0206] When judging stick - slip, if the rotational speed at this moment / the rotational speed at the previous moment is greater than 20%, it is judged as stick - slip;

[0207] When judging the increase of the cuttings bed, the ratio of the weight-on-bit / torque value at this moment to the weight-on-bit / torque value at the previous moment exceeds a 10% fluctuation; the value of the drill string internal pressure - annulus pressure at this moment is greater than the value of the drill string internal pressure - annulus pressure at the next moment by 0.5 MPa; when the above two conditions are met, it is judged that the cuttings bed increases;

[0208] Classify the identified abnormal working conditions and upload the abnormal working conditions and abnormal feature data;

[0209] If the above abnormal working conditions are not judged, it is determined as a normal working condition.

[0210] It should be noted that although several modules of the downhole intelligent processing and optimized uploading device for multi - parameter downhole engineering while drilling are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of the two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0211] Based on the foregoing inventive concept, as Figure 8 shown, the present invention also proposes a computer device 800, including a memory 810, a processor 820, and a computer program 830 stored on the memory 810 and executable on the processor 820. When the processor 820 executes the computer program 830, the foregoing method for downhole intelligent processing and optimized uploading of multi - parameter downhole engineering while drilling is implemented.

[0212] Based on the foregoing inventive concept, the present invention provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the foregoing method for intelligent processing and optimal uploading of multi-parameters during downhole drilling operations.

[0213] Based on the foregoing inventive concept, the present invention provides a computer program product including a computer program, which when executed by a processor implements the method for intelligent processing and optimal uploading of multi-parameters during downhole drilling operations.

[0214] The method and device for intelligent processing and optimal uploading of multi-parameters during downhole drilling operations proposed by the present invention can analyze and process the data collected downhole, select the data that can reflect the real-time state of the drilling conditions for uploading, reduce the data transmission volume, improve the data transmission efficiency, enable the ground to obtain downhole data in a timely manner, and adjust the drilling plan targeted, thereby improving the drilling operation efficiency; after the downhole data is processed and uploaded, the ground only obtains the key data and the characteristics of abnormal working conditions, which can effectively solve the problem of single uploaded data, and the information is more accurate and reliable, enabling the drilling engineer to clearly master the actual changes in the downhole conditions and make accurate judgments, providing strong data support for the drilling scenario.

[0215] In the technical solution of the present application, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of laws and regulations.

[0216] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a device, or a computer program product. Therefore, the present invention can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can be implemented in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0217] The present invention is described with reference to the flowcharts and / or block diagrams of methods and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0218] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction device that implements the function specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0219] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the function specified in one or more of the processes and / or blocks Figure 1 in one or more of the processes and / or blocks Figure 1 specified in the block or blocks.

[0220] Finally, it should be noted that the above-described embodiments are only specific embodiments of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions described in the foregoing embodiments, or can easily conceive of changes, or make equivalent replacements for some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the protection scope of the claims.

Claims

1. A method for intelligent processing and optimal uploading of multiple parameters in downhole drilling engineering. It is characterized in that include: Collect downhole data in real time and store the downhole data in a first data table, wherein the downhole data at least includes drilling pressure, torque, internal pressure of drilling tool, annular pressure, annular temperature, longitudinal vibration, lateral vibration, axial vibration and rotation speed; Preprocessing the downhole data in the first data table and storing the preprocessed downhole data in a second data table; Based on the downhole data in the second data table, a baseline and / or a neural network model is used to perform feature analysis to describe the variation characteristics of the parameters, and the feature data is stored in a third data table; Identify the downhole conditions on the characteristic data in the third data table, and store the identification results in a fourth data table; the downhole conditions at least include unclean wellbore, drilling tool leakage, and water hole blockage; According to the recognition result of the fourth data table, determine the uploaded normal and abnormal engineering measurement parameters and store them in a fifth data table; The parameter data of the fifth data table is uploaded to the ground early warning unit, and the ground early warning unit performs alarm analysis in combination with the logging parameters.

2. The method according to claim 1, It is characterized in that Collect downhole data in real time and store the downhole data in a first data table, including: Collect downhole data in real time through a sensor group; the sensor group includes at least a stress strain gauge, a temperature and pressure sensor, a triaxial acceleration sensor and a gyroscope; Among them, the stress strain gauge measures drilling pressure, torque and internal pressure of the drill bit; the temperature and pressure sensor measures the annular space pressure and annular space temperature; the three-axial acceleration sensor measures longitudinal vibration, lateral vibration and axial vibration; and the gyroscope measures the rotation speed of the drill bit.

3. The method according to claim 1, It is characterized in that Preprocessing the downhole data in the first data table and storing the preprocessed downhole data in the second data table includes: The downhole data is filtered and validity identified, erroneous data and invalid data are eliminated, and the pre-processed downhole data is stored in the second data table.

4. The method according to claim 1, It is characterized in that The method includes: At each set interval, the average data of N data curves in the well is collected, and after data validity processing, it is inserted into the memory data buffer area; Determine whether the cached data is an integer multiple of M; if not, continue to collect downhole data in the next set period; if so, calculate the average value and working condition, and insert them into the baseline parameter calculation table; Determine whether the number of data groups in the baseline parameter calculation table is P. If so, establish the baseline and continue to collect downhole data; if not, continue to collect downhole data; N, M, P are positive integers; Among them, when calculating the working conditions, for rotary drill and compound drill, the parameter characteristics of the drilling conditions meet the following conditions: drilling pressure>0, speed>0, the internal pressure of the drill bit is greater than the external pressure of the drill bit, and the axial vibration>0; for sliding drilling, the parameter characteristics of the drilling conditions meet the following conditions: drilling pressure>0, the internal pressure of the drill bit is greater than the external pressure of the drill bit, and the axial vibration>0.

5. The method according to claim 4, It is characterized in that Based on the downhole data in the second data table, perform feature analysis using a baseline and / or a neural network model to describe the variation characteristics of parameters, and store the feature data in a third data table, including: Group the downhole data collected within a set time period and fill it into a baseline parameter calculation table; among them, the baseline parameter calculation table contains 5 data groups; each data group includes weight on bit, torque, drill string internal pressure, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration, and rotational speed. Judge whether the baseline is in a stable state. The judgment conditions for the stable state are: WOB represents the weight on bit, TRQ represents the torque, PA represents the annulus pressure, PT represents the internal pressure, TMP represents the temperature, ACCX represents the lateral vibration, ACCZ represents the axial vibration, n is the data serial number, and the subscripts n and n - 1 represent the data at the nth moment and the data at the previous moment; represents rounding down; After a newly established baseline, compare the subsequent newly measured data with the baseline respectively. If there are no abnormal features, update and re-establish the baseline; if there are abnormalities, do not change the baseline features.

6. The method according to claim 5, wherein, Based on the downhole data in the second data table, perform feature analysis using a baseline and / or a neural network model to describe the variation characteristics of parameters, and store the feature data in a third data table, including: Read the number of data in the baseline parameter calculation table, and judge whether the number of the baseline parameter calculation table is 5. If not, determine that the working condition is non-drilling, and sleep for a certain period of time and then re-read the number of data in the baseline parameter calculation table. If so, judge whether the working condition of the latest two data points is drilling. If so, determine that the working condition is drilling; if not, determine that the working condition is non-drilling. After the determination, sleep for a certain period of time and then re-read the number of data in the baseline parameter calculation table.

7. The method according to claim 1, wherein, Identify the downhole situation for the feature data in the third data table, and store the identification result in a fourth data table, including: Use big data artificial intelligence analysis or logical judgment to identify the downhole situation; among them, the downhole working conditions include abnormal working conditions and normal working conditions. The abnormal working conditions at least include, according to the degree of importance: precursors of stuck pipe, water eye blockage, annulus blockage, severe drill string vibration, stick-slip, and increase of cuttings bed.

8. The method according to claim 7, wherein, Use logical judgment to identify the downhole situation, including: Convert the change of characteristic parameters of abnormal working conditions into mathematical descriptions, and judge them in turn according to the degree of importance of abnormal working conditions; Update the data at a set time period, read the data in the baseline parameter calculation table, and judge whether it is empty. If it is empty, there are unprocessed abnormal working conditions; if it is not empty, continue to judge whether there are abnormal working conditions; When judging the precursors of stuck pipe, if the ratio of the weight on bit / torque value at this moment to the weight on bit / torque value at the previous moment exceeds 10% fluctuation, it is judged as the precursors of stuck pipe, and the continuous time is 5 groups; When judging water eye blockage, if the value of drill string internal pressure - annulus pressure at this moment is greater than the value of drill string internal pressure - annulus pressure at the next moment by 1 MPa, it is judged as water eye blockage, and the continuous time is 5 groups; When judging annulus blockage, if the value of drill string internal pressure - annulus pressure at this moment is less than the value of drill string internal pressure - annulus pressure at the next moment by 1 MPa, it is judged as annulus blockage, and the continuous time is 5 groups; When judging that the drilling tool vibration is severe, the triaxial vibration data of the horizontal axis, vertical axis and axial axis collected downhole are classified, and the drilling tool vibration is judged to be severe if it exceeds 5g; When judging stick-slip, if the speed at this moment / the speed at the previous moment is greater than 20%, it is judged as stick-slip; When judging the increase of the cuttings bed, the ratio of the drilling pressure / torque value at this moment to the drilling pressure / torque value at the previous moment exceeds a fluctuation of 10%; the drilling tool internal pressure-annular pressure value at this moment is greater than the drilling tool internal pressure-annular pressure value at the next moment by 0.5MPa; if the above two conditions are met, it is judged that the cuttings bed is increased; Classify the identified abnormal working conditions and upload the abnormal working conditions and abnormal characteristic data; If the above abnormal operating conditions are not determined, it is determined to be a normal operating condition.

9. A device for intelligent processing and optimal uploading of multiple parameters in downhole drilling engineering. It is characterized in that include: A data acquisition module, used for real-time acquisition of downhole data, and storing the downhole data in a first data table, wherein the downhole data at least includes drilling pressure, torque, internal pressure of drilling tool, annular pressure, annular temperature, longitudinal vibration, lateral vibration, axial vibration and rotation speed; A preprocessing module, used for preprocessing the downhole data in the first data table, and storing the preprocessed downhole data in a second data table; A feature analysis module, used to perform feature analysis based on the downhole data in the second data table using a baseline and / or a neural network model to describe the variation characteristics of the parameters and store the feature data in a third data table; A downhole analysis module, used to identify downhole conditions based on the characteristic data in the third data table, and store the identification results in a fourth data table; the downhole conditions at least include unclean wellbore, drilling tool leakage, and water hole blockage; A data classification module, used to determine the uploaded normal and abnormal engineering measurement parameters according to the recognition result of the fourth data table and store them in a fifth data table; The uploading module is used to upload the parameter data of the fifth data table to the ground early warning unit, and the ground early warning unit performs alarm analysis in combination with the logging parameters.

10. The device according to claim 9, It is characterized in that The data acquisition module collects downhole data in real time and stores the downhole data in a first data table, including: Collect downhole data in real time through a sensor group; the sensor group includes at least a stress strain gauge, a temperature and pressure sensor, a triaxial acceleration sensor and a gyroscope; Among them, the stress strain gauge measures drilling pressure, torque and internal pressure of the drill bit; the temperature and pressure sensor measures the annular space pressure and annular space temperature; the three-axial acceleration sensor measures longitudinal vibration, lateral vibration and axial vibration; and the gyroscope measures the rotation speed of the drill bit.

11. The device according to claim 9, It is characterized in that The preprocessing module performs preprocessing according to the downhole data in the first data table and stores the preprocessed downhole data in the second data table, including: The downhole data is filtered and validity identified, erroneous data and invalid data are eliminated, and the pre-processed downhole data is stored in the second data table.

12. The device according to claim 9, It is characterized in that The device comprises: a baseline processing module; The baseline processing module is used to: Insert the target data into the memory data buffer; the target data is obtained by collecting the average data of N downhole data curves every set period and then performing data validity processing on the collected data. Determine whether the cached data is an integer multiple of M; if not, continue to collect downhole data in the next set period; if so, calculate the average value and working condition, and insert them into the baseline parameter calculation table. Determine whether the number of data groups in the baseline parameter calculation table is P; if so, establish a baseline and continue to collect downhole data; if not, continue to collect downhole data; N, M, and P are positive integers. Among them, when calculating the working condition, for rotary drilling and compound drilling, the parameter characteristics of the drilling working condition meet the following conditions: weight on bit > 0, rotary speed > 0, internal pressure of the drill string > external pressure of the drill string, axial vibration > 0; for sliding drilling, the parameter characteristics of the drilling working condition meet the following conditions: weight on bit > 0, internal pressure of the drill string > external pressure of the drill string, axial vibration > 0.

13. The device according to claim 12, wherein, the feature analysis module performs feature analysis on the downhole data of the second data table by using a baseline and / or a neural network model to describe the change characteristics of the parameters, and stores the feature data in the third data table, including: Group the downhole data collected within a set time period and fill it into the baseline parameter calculation table; wherein, the baseline parameter calculation table contains 5 data groups; each data group contains weight on bit, torque, internal pressure of the drill string, annulus pressure, annulus temperature, longitudinal vibration, lateral vibration, axial vibration, and rotary speed. Determine whether the baseline is in a stable state, and the judgment conditions for the stable state are: WOB represents the weight on bit, TRQ represents the torque, PA represents the annulus pressure, PT represents the internal pressure, TMP represents the temperature, ACCX represents the lateral vibration, ACCZ represents the axial vibration, n is the data sequence number, and the subscripts n and n - 1 represent the data at the nth moment and the data at the previous moment; represents rounding down; After the newly established baseline, the subsequent newly measured data are compared with the baseline respectively. If there are no abnormal features, update and re - establish the baseline; if there are abnormalities, do not change the baseline features.

14. The device according to claim 13, wherein, the feature analysis module performs feature analysis on the downhole data of the second data table by using a baseline and / or a neural network model to describe the change characteristics of the parameters, and stores the feature data in the third data table, including: Read the number of data in the baseline parameter calculation table, and determine whether the number of the baseline parameter calculation table is 5. If not, determine that the working condition is non - drilling, and sleep for a certain period of time and then re - read the number of data in the baseline parameter calculation table. If so, determine whether the working condition of the latest two data points is drilling. If so, determine that the working condition is drilling; if not, determine that the working condition is non - drilling. After the determination, sleep for a certain period of time and then re - read the number of data in the baseline parameter calculation table.

15. The device according to claim 9, wherein, the downhole analysis module identifies the downhole situation for the feature data in the third data table and stores the identification result in the fourth data table, including: Use big data artificial intelligence analysis method or logical judgment method to identify the downhole situation; wherein, the downhole working conditions include abnormal working conditions and normal working conditions. The abnormal working conditions at least include, according to the degree of importance: precursors of stuck pipe, water eye blockage, annulus blockage, severe drill string vibration, stick - slip, and increase of cuttings bed.

16. The device according to claim 15, It is characterized in that the downhole analysis module identifies the downhole conditions in a logical judgment manner, including: converting the change of characteristic parameters of abnormal working conditions into mathematical descriptions, and judging them in order of importance according to the abnormal working conditions; updating data at a set time interval, reading the data in the baseline parameter calculation table, and judging whether it is empty. If it is empty, there are unprocessed abnormal working conditions; if it is not empty, continue to judge whether there are abnormal working conditions; when judging the precursor of sticking, if the ratio of the weight on bit / torque value at this moment to the weight on bit / torque value at the previous moment exceeds 10% fluctuation, it is judged as the precursor of sticking, and the continuous time is 5 groups; when judging the nozzle blockage, if the value of the drill string internal pressure - annulus pressure at this moment is greater than the value of the drill string internal pressure - annulus pressure at the next moment by 1 MPa, it is judged as nozzle blockage, and the continuous time is 5 groups; when judging the annulus blockage, if the value of the drill string internal pressure - annulus pressure at this moment is less than the value of the drill string internal pressure - annulus pressure at the next moment by 1 MPa, it is judged as annulus blockage, and the continuous time is 5 groups; when judging the severe drill string vibration, grading the three - axis vibration data of the horizontal axis, vertical axis, and axial direction collected downhole, and if it exceeds 5g, it is judged that the drill string vibrates severely; when judging stick - slip, if the rotational speed at this moment / the rotational speed at the previous moment is greater than 20%, it is judged as stick - slip; when judging the increase of cuttings bed, the ratio of the weight on bit / torque value at this moment to the weight on bit / torque value at the previous moment exceeds 10% fluctuation; the value of the drill string internal pressure - annulus pressure at this moment is greater than the value of the drill string internal pressure - annulus pressure at the next moment by 0.5 MPa; if the above two conditions are met, it is judged that the cuttings bed increases; classify the identified abnormal working conditions, and upload the abnormal working conditions and abnormal characteristic data; if the above abnormal working conditions are not judged, it is determined as a normal working condition.

17. A computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, It is characterized in that when the processor executes the computer program, it implements the method according to any one of claims 1 to 8.

18. A computer - readable storage medium, It is characterized in that the computer - readable storage medium stores a computer program, and when the computer program is executed by the processor, it implements the method according to any one of claims 1 to 8.

19. A computer program product, It is characterized in that the computer program product includes a computer program, and when the computer program is executed by the processor, it implements the method according to any one of claims 1 to 8.

Images