Real-time prediction method and device for oil-based drilling fluid filtrate contamination

Abstract

The present invention discloses a real-time prediction method and device for the contamination degree of oil-based drilling fluid filtrate, the method comprising: extracting formation fluid by using a sampling instrument to obtain a first spectral absorbance of the formation fluid; the formation fluid comprises drilling fluid filtrate and original formation oil and gas; determining a second spectral absorbance corresponding to the drilling fluid filtrate; inputting the first spectral absorbance and the extraction factor into a trained absorbance prediction model to predict the predicted third spectral absorbance of original formation oil and gas; the absorbance prediction model is obtained based on radial basis function network training; the contamination degree of the drilling fluid filtrate is calculated based on the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions. The predicted third spectral absorbance is obtained based on the extraction factor through the absorbance prediction model, and then the contamination degree of the drilling fluid filtrate is accurately calculated to determine the timing of extracting formation oil and gas that meets the requirements.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of well logging technology, and in particular to a method and device for real-time prediction of oil-based drilling fluid filtrate contamination. Background Art

[0002] During oilfield exploration and production, oilfield workers are often concerned about the composition of formation oil and gas. The most intuitive method is to use a pressure sampling instrument to lower it to the target depth downhole to obtain samples. However, due to the drilling fluid in the instrument wellbore and the permeability of the formation, the drilling fluid filtrate will continue to infiltrate into the formation during drilling. If the drilling fluid invades the formation too deeply, it will cause serious formation pollution. The fluid extracted by the downhole instrument includes a mixture of original formation oil and gas and drilling fluid filtrate. The acquisition of original formation oil and gas samples depends largely on the determination of the degree of contamination during the logging process. When extracting formation oil and gas samples, the first thing extracted is the drilling fluid filtrate, followed by a mixture of drilling fluid filtrate and formation oil and gas. Only when the extraction time is long can the percentage of the original formation oil and gas content in the extracted formation oil and gas samples reach the required level. However, long-term extraction will lead to excessively high costs. Therefore, there is an urgent need for a real-time prediction method for oil-based drilling fluid filtrate contamination, so as to predict the contamination in real time and determine the best extraction time to extract the formation oil and gas that meets the demand. Summary of the invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a method and device for real-time prediction of oil-based drilling fluid filtrate contamination that overcomes the above problems or at least partially solves the above problems.

[0004] According to one aspect of an embodiment of the present invention, a method for real-time prediction of oil-based drilling fluid filtrate contamination is provided, the method comprising:

[0005] Extracting formation fluid using a sampling instrument to obtain a first spectral absorbance of the formation fluid; the formation fluid includes drilling fluid filtrate and original formation oil and gas;

[0006] determining a second spectral absorbance corresponding to the drilling fluid filtrate;

[0007] The first spectral absorbance and the extraction factor are input into the trained absorbance prediction model to predict the third spectral absorbance of the original formation oil and gas; the absorbance prediction model is obtained based on radial basis function network training; the extraction factor includes extraction volume or extraction time;

[0008] The contamination degree of the drilling fluid filtrate is calculated according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions.

[0009] According to another aspect of an embodiment of the present invention, a real-time prediction device for oil-based drilling fluid filtrate contamination is provided, comprising:

[0010] The first module is adapted to extract formation fluid using a sampling instrument to obtain a first spectral absorbance of the formation fluid; the formation fluid includes drilling fluid filtrate and original formation oil and gas;

[0011] A second module, adapted to determine a second spectral absorbance corresponding to the drilling fluid filtrate;

[0012] The prediction module is adapted to input the first spectral absorbance and the extraction factor into the trained absorbance prediction model to predict the predicted third spectral absorbance of the original formation oil and gas; the absorbance prediction model is obtained based on radial basis function network training; the extraction factor includes extraction volume or extraction time;

[0013] The calculation module is adapted to calculate the contamination degree of the drilling fluid filtrate according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions.

[0014] According to another aspect of an embodiment of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0015] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned method for real-time prediction of oil-based drilling fluid filtrate contamination.

[0016] According to another aspect of an embodiment of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the above-mentioned method for real-time prediction of oil-based drilling fluid filtrate contamination.

[0017] According to another aspect of an embodiment of the present invention, a computer program product is provided, comprising at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the above-mentioned method for real-time prediction of oil-based drilling fluid filtrate contamination.

[0018] According to the real-time prediction method and device for the contamination degree of oil-based drilling fluid filtrate provided by the embodiments of the present invention, the third spectral absorbance can be predicted based on the extraction factor through the absorbance prediction model, and then the contamination degree of the drilling fluid filtrate can be accurately calculated according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance, so as to determine the timing of extracting formation oil and gas that meets the extraction requirements, reducing the existing extraction time and extraction costs.

[0019] The above description is only an overview of the technical solution of the embodiment of the present invention. In order to more clearly understand the technical means of the embodiment of the present invention, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present invention more obvious and easy to understand, the specific implementation method of the embodiment of the present invention is specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the embodiments of the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0021] Figure 1 A flowchart of a method for real-time prediction of oil-based drilling fluid filtrate contamination according to an embodiment of the present invention is shown;

[0022] Figure 2 A schematic diagram of the EFDT tool extracting formation fluid is shown;

[0023] Figure 3 It shows a schematic diagram of IFSA sampling while drilling instrument extracting formation fluid;

[0024] Figure 4 A schematic diagram of the spectra of white oil and oil is shown;

[0025] Figure 5 A schematic diagram showing the time-varying spectral absorbance of formation oil and gas;

[0026] Figure 6 A schematic diagram of filtrate contamination over time is shown;

[0027] Figure 7 It shows a schematic structural diagram of a device for real-time prediction of oil-based drilling fluid filtrate contamination according to one embodiment of the present invention;

[0028] Figure 8 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0029] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0030] Figure 1FIG. 4 is a flow chart showing a method for real-time prediction of oil-based drilling fluid filtrate contamination according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0031] Step S101: extracting formation fluid using a sampling instrument to obtain a first spectral absorbance of the formation fluid.

[0032] When extracting oil and gas from the original formation, a sampling instrument can be used to extract the drilling fluid filtrate first, followed by the formation fluid containing a mixture of the drilling fluid filtrate and the original formation oil and gas. Figure 2 or Figure 3 As shown, Figure 2 200 is an EFDT instrument (formation pressure sampling instrument), including a piston pump 201, a spectrum measuring device 202 and a probe 203. The EFDT instrument is placed at the target depth in the well, and the well wall is surrounded by the formation 220. The probe 203 is sealed on the well wall. After the sealing is successful, the piston pump 201 is started, and the formation fluid enters the pipeline through the suction port, passes through the spectrum measuring device 202, and generates a spectrum signal value (i.e., the near-infrared spectrum absorbance of the fluid measured in real time). The data is transmitted remotely through the cable and uploaded to the ground logging system 210 in real time. Figure 3 300 is an IFSA sampling while drilling instrument, which includes a piston pump 301, a spectrum measuring device 302 and a probe 303. The IFSA sampling while drilling instrument 300 is placed at the target depth downhole, and the surrounding of the well wall is the formation 320. The surface logging system 310 communicates with the downhole mud transmission device 340 through the mud transmission device 330, and the downhole mud transmission device 340 sends the surface command to the IFSA sampling while drilling instrument 300. The IFSA sampling while drilling instrument 300 seals the probe 303 on the well wall. After the sealing is successful, the piston pump 301 is started, and the formation fluid enters the pipeline through the suction port, passes through the spectrum measuring device 302, and generates a spectrum signal value (i.e., the near-infrared spectrum absorbance of the fluid measured in real time). The data is uploaded to the surface logging system 310 in real time through the downhole mud transmission device 340 and the mud transmission device 330. The above piston pump can be a suction pump, and the spectrum measuring device can be a spectrometer.

[0033] use Figure 2 or Figure 3 The sampling instrument shown can extract formation fluid in real time, and the first spectral absorbance of the currently extracted formation fluid can be obtained via the spectral measurement device therein.

[0034] Furthermore, based on the given temperature and pressure, the near infrared spectra of drilling fluid filtrate and oil and gas in different formations are different, e.g. Figure 4In the spectrogram shown, the horizontal axis is wavelength, the vertical axis is absorbance, the blue line is the absorbance of white oil (drilling fluid filtrate) at different wavelengths, and the red line is the absorbance of oil (formation oil and gas) at different wavelengths. At certain wavelengths, there is a significant difference in absorbance between the drilling fluid filtrate and the formation oil and gas. The measurement accuracy of absorbance can reach 0.005, that is, when the absorbance difference between the drilling fluid filtrate and the formation oil and gas is much greater than 0.005, the absorbance of the drilling fluid filtrate and the formation oil and gas can be accurately distinguished, and then the contamination degree of the drilling fluid filtrate can be determined. Therefore, when determining the first spectral absorbance of the formation fluid, the second spectral absorbance of the drilling fluid filtrate, and the predicted third spectral absorbance of the original formation oil and gas in this embodiment, the premise is to first determine the target wavelength. The target wavelength can select the wavelength where the absorbance difference between the drilling fluid filtrate and the formation oil and gas is much greater than 0.005 as the target wavelength. The specific target wavelength is set according to the implementation situation and is not limited here. After determining the target wavelength, the first spectral absorbance of the formation fluid, the second spectral absorbance of the drilling fluid filtrate, and the predicted third spectral absorbance of the original formation oil and gas can be determined based on the target wavelength. The first spectral absorbance, the second spectral absorbance, and the predicted third spectral absorbance correspond to the target wavelength.

[0035] Step S102, determining the second spectral absorbance corresponding to the drilling fluid filtrate.

[0036] The second spectral absorbance of the drilling fluid filtrate can be obtained in the following ways: for example, the drilling fluid filter cake is obtained from the well to the surface, the filtrate is squeezed out, and its near-infrared spectrum is directly measured with an EFDT instrument or an IFSA downhole sampling instrument, and the absorbance is corrected to the temperature and pressure of the formation to obtain the second spectral absorbance; or, when the EFDT instrument or the IFSA downhole sampling instrument is used for pumping, the initial extraction is the drilling fluid filtrate, and the spectral absorbance measured at this time is the second spectral absorbance of the drilling fluid filtrate; or, by pre-measuring and determining the corresponding relationship between the spectral absorbance of various oil-based drilling fluid filtrates and the temperature and pressure, the second spectral absorbance of the drilling fluid filtrate is calculated according to the type, temperature and pressure of the drilling fluid filtrate during logging. The above is an example, which is set according to the implementation situation and is not limited here.

[0037] Step S103, inputting the first spectral absorbance and the extraction factor into the trained absorbance prediction model to predict the third spectral absorbance of the original formation oil and gas.

[0038] The predicted third spectral absorbance of undisturbed formation oil and gas can be predicted using an absorbance prediction model.

[0039] The absorbance prediction model can be obtained based on RBF network (Radial basis function network, radial basis function neural network) training. When constructing the absorbance prediction model, the absorbance prediction model is constructed based on the connection weight, the radial basis function of the sample extraction factor and the absorbance of the first sample spectrum, and the mapping relationship between the absorbance of the third sample spectrum and the radial basis function of the sample extraction factor is obtained. When the sample extraction factor is the sample extraction time, the following method is used:

[0040]

[0041] When the sample extraction factor is the sample extraction volume, the following method is used:

[0042]

[0043] Among them, D k is the spectral absorbance of the third sample, D fw is the spectral absorbance of the first sample, t is the sample extraction time, V is the sample extraction volume, w jk is the connection weight, j is the jth neuron in the hidden layer, and its value is 1-m, where m can be 6, etc., k is the kth neuron in the output layer, and its value can be set to 1. The connection weight is the connection weight between the hidden layer neuron and the output layer neuron. The initial value of the connection weight can be determined based on a random point with a Gaussian distribution with a standard deviation of 1, and has no direct relationship with j and k. When training the absorbance prediction model, the connection weight can be adjusted by using methods such as gradient descent or Newton's method. j (V), h j (t) is the action function of the jth neuron in the hidden layer, which has a nonlinear mapping relationship with the sample extraction factor, such as the sample extraction volume or the sample extraction time, as shown below:

[0044]

[0045]

[0046] Among them, j is the jth neuron in the hidden layer, the value is 1-m, t is the sample extraction time, V is the sample extraction volume, C j is the center of the jth basis function, a vector with the same dimension as V or t, σ jis the width of the jth basis function. The center of the basis function is the cluster center, and clustering is performed according to the sample extraction factor. The cluster center can be obtained by randomly selecting a sample from the sample extraction volume or the sample extraction time as the initial cluster center, and iterating through K-means clustering until the cluster center no longer changes, thereby determining the corresponding cluster center. The center of the jth basis function, that is, the jth randomly selected sample, is used as the initial cluster center. K-means clustering is iterated to obtain the jth cluster center as the center of the jth basis function. According to the center of the jth basis function, the maximum distance from the center is determined, and the variance calculated is the width of the jth basis function. The radial basis function is constructed according to the center of the radial basis function obtained above and the width of the radial basis function.

[0047] Obtain the first sample spectral absorbance, sample extraction factor and third sample spectral absorbance, input the first sample spectral absorbance, sample extraction factor and third sample spectral absorbance into the absorbance prediction model for training, determine the basis function center of the absorbance prediction model, adjust the connection weight, and thus obtain the trained absorbance prediction model. fw =[D1, D2, ..., Dn], which changes with the sample extraction volume V=[V1, V2, ..., Vn] or the sample extraction time t=[t1, t2, ..., tn]. Collect the first sample spectral absorbance, the sample extraction factor, and the measured third sample spectral absorbance D k , input into the absorbance prediction model, train the absorbance prediction model, adjust the basis function center and connection weight according to the training results, and obtain the trained absorbance prediction model.

[0048] This embodiment is based on the trained absorbance prediction model. When extracting the well, the first spectral absorbance and the extraction factor are input into the trained absorbance prediction model to predict the third spectral absorbance of the original formation oil and gas. The extraction factor includes an extraction volume factor or an extraction time factor. The extraction volume factor is the volume of the pumped formation fluid, and the extraction time factor is the extraction time of the sampling instrument. One of the extraction factors can be selected and input into the absorbance prediction model to obtain the predicted third spectral absorbance of the original formation oil and gas.

[0049] Figure 5 is the time-varying spectral absorbance of formation oil and gas, such as Figure 5 As shown, the horizontal axis is time, and the vertical axis is oil peak absorbance (absorbance measured at the peak). Green represents the absorbance measured at the peak based on the EFDT instrument, and red represents the absorbance measured at the peak by the absorbance prediction model. Figure 6 is the pollution degree that changes with time, such as Figure 6As shown, the horizontal axis is time, and the vertical axis is the filtrate contamination. The green represents the filtrate contamination calculated based on the peak absorbance after extraction by the EFDT instrument, and the red represents the filtrate contamination calculated based on the absorbance prediction model according to the peak absorbance prediction. Figure 5 and Figure 6 It can be seen that the absorbance prediction model has a high prediction accuracy.

[0050] Step S104, calculating the contamination degree of the drilling fluid filtrate according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions.

[0051] After obtaining the first spectral absorbance Dmix, the second spectral absorbance Dm and the predicted third spectral absorbance Dr, the first difference between the first spectral absorbance Dmix and the predicted third spectral absorbance Dr can be calculated first, and then the second difference between the second spectral absorbance Dm and the predicted third spectral absorbance Dr can be calculated. According to the ratio of the first difference to the second difference, the contamination degree C=(Dmix-Dr) / (Dm-Dr) of the drilling fluid filtrate can be obtained.

[0052] For the contamination degree of the drilling fluid filtrate, a preset contamination degree threshold value, such as 10%, can be set according to the specific implementation situation. When the contamination degree is judged to be less than the preset contamination degree threshold value, it means that the purity of the original formation oil and gas in the formation fluid currently extracted is relatively high, which meets the extraction conditions and can meet the demand. At this time, the extraction time of the predicted third spectral absorbance is determined to be the target extraction time to reach the preset contamination degree threshold value. The target extraction time can be determined according to the extraction time of the extraction factor or the time corresponding to the extraction volume. For example, when the absorbance prediction model is used for prediction, when the input extraction factor is the extraction time, the target extraction time is the extraction time; when the input extraction factor is the extraction volume, the time corresponding to the extraction volume is determined according to the single extraction amount and the extraction volume to obtain the target extraction time. Furthermore, for example, based on the historical data of drilling, multiple first spectral absorbances and corresponding multiple extraction volumes or multiple extraction times can be obtained, and multiple first spectral absorbances and corresponding multiple extraction volumes or multiple extraction times can be input into the absorbance prediction model to obtain multiple predicted third spectral absorbances, and different contamination levels of drilling fluid filtrates can be calculated to make judgments, and the target extraction time corresponding to the contamination level that meets the extraction conditions can be obtained. Alternatively, for new drilling, formation fluid can be extracted in real time, and the predicted third spectral absorbance can be obtained based on the first spectral absorbance of the extracted formation fluid and the corresponding extraction volume or extraction time, and the contamination level of the drilling fluid filtrate can be calculated to make judgments. If the contamination level is judged to be not less than the preset contamination level threshold, the formation fluid can continue to be extracted, and the new predicted third spectral absorbance can be predicted based on the absorbance prediction model according to the first spectral absorbance of the new formation fluid and the new extraction volume or extraction time, and the contamination level of the new drilling fluid filtrate can be calculated to make judgments, until the contamination level is judged to be less than the preset contamination level threshold, and the target extraction time can be obtained.

[0053] According to the real-time prediction method for the contamination of oil-based drilling fluid filtrate provided by an embodiment of the present invention, the third spectral absorbance can be predicted based on the extraction factor through the absorbance prediction model, and then the contamination of the drilling fluid filtrate can be accurately calculated according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance, so as to determine the timing of extracting formation oil and gas that meets the extraction requirements, reducing the existing extraction time and extraction costs.

[0054] Figure 7 The structure diagram of the real-time prediction device for the contamination degree of oil-based drilling fluid filtrate provided by the embodiment of the present invention is shown. Figure 7 As shown, the device comprises:

[0055] The first module 710 is adapted to extract formation fluid using a sampling instrument to obtain a first spectral absorbance of the formation fluid; the formation fluid includes drilling fluid filtrate and original formation oil and gas;

[0056] A second module 720, adapted to determine a second spectral absorbance corresponding to the drilling fluid filtrate;

[0057] The prediction module 730 is adapted to input the first spectral absorbance and the extraction factor into the trained absorbance prediction model to predict the predicted third spectral absorbance of the original formation oil and gas; the absorbance prediction model is obtained based on radial basis function network training; the extraction factor includes extraction volume or extraction time;

[0058] The calculation module 740 is adapted to calculate the contamination degree of the drilling fluid filtrate according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions.

[0059] Optionally, the device further comprises: a wavelength determination module 750, adapted to determine a target wavelength; wherein the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance correspond to the target wavelength.

[0060] Optionally, the device also includes: a training module 760, suitable for obtaining the first sample spectral absorbance, a sample extraction factor and a third sample spectral absorbance, the sample extraction factor including the sample extraction volume or the sample extraction time; constructing an absorbance prediction model; wherein the absorbance prediction model is constructed based on connection weights, radial basis functions of the sample extraction factor and the first sample spectral absorbance, and a mapping relationship between the third sample spectral absorbance and the radial basis function of the sample extraction factor is obtained; the connection weights are the connection weights between the hidden layer neurons and the output layer neurons, and the initial values ​​of the connection weights are determined according to random points of the Gaussian distribution; the radial basis function of the sample extraction factor constructs a nonlinear mapping relationship according to the sample extraction factor; the first sample spectral absorbance, the sample extraction factor and the third sample spectral absorbance are input into the absorbance prediction model for training, the connection weights are adjusted, and the trained absorbance prediction model is obtained.

[0061] Optionally, the training module 760 is further adapted to: clustering according to the sample extraction factor to obtain the cluster center as the center of the radial basis function; calculating the variance according to the cluster center as the width of the radial basis function; and constructing the radial basis function of the sample extraction factor according to the center of the radial basis function and the width of the radial basis function.

[0062] Optionally, the calculation module 740 is further adapted to:

[0063] Calculating a first difference between the first spectral absorbance and the predicted third spectral absorbance;

[0064] Calculating a second difference between the second spectral absorbance and the predicted third spectral absorbance;

[0065] The contamination degree of the drilling fluid filtrate is obtained according to the ratio of the first difference to the second difference.

[0066] Optionally, the calculation module 740 is further adapted to:

[0067] Determine whether the pollution level is less than a preset pollution level threshold;

[0068] If so, determine that the extraction time corresponding to the predicted third spectral absorbance is the target extraction time for reaching the preset contamination threshold; the target extraction time is determined according to the extraction time or the time corresponding to the extraction volume.

[0069] The description of each module above refers to the corresponding description in the method embodiment and will not be repeated here.

[0070] An embodiment of the present invention further provides a non-volatile computer storage medium storing at least one executable instruction, which can execute operations corresponding to the method for real-time prediction of oil-based drilling fluid filtrate contamination in any of the above method embodiments.

[0071] An embodiment of the present application provides a computer program product, which includes at least one executable instruction or computer program, which enables a processor to execute operations corresponding to the real-time prediction method for oil-based drilling fluid filtrate contamination in any of the above-mentioned method embodiments.

[0072] Figure 8 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown, and the specific implementation of the embodiment of the present invention does not limit the specific implementation of the computing device.

[0073] like Figure 8 As shown, the computing device may include: a processor 802 , a communication interface 804 , a memory 806 , and a communication bus 808 .

[0074] in:

[0075] The processor 802 , the communication interface 804 , and the memory 806 communicate with each other via a communication bus 808 .

[0076] The communication interface 804 is used to communicate with other devices such as clients or other servers.

[0077] The processor 802 is used to execute the program 810, and specifically can execute the relevant steps in the above-mentioned embodiment of the method for real-time prediction of the contamination degree of oil-based drilling fluid filtrate.

[0078] Specifically, the program 810 may include program codes, which include computer operation instructions.

[0079] The processor 802 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0080] The memory 806 is used to store the program 810. The memory 806 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0081] Program 810 can be specifically used to enable processor 802 to execute the real-time prediction method for oil-based drilling fluid filtrate contamination in any of the above-mentioned method embodiments. The specific implementation of each step in program 810 can refer to the corresponding descriptions in the corresponding steps and units in the above-mentioned oil-based drilling fluid filtrate contamination real-time prediction embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described equipment and modules can refer to the corresponding process description in the above-mentioned method embodiment, which will not be repeated here.

[0082] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other device. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious that the structure required for constructing such systems. In addition, the embodiment of the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the embodiment of the present invention described herein, and the description of the above specific language is to disclose the preferred implementation of the embodiment of the present invention.

[0083] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0084] Similarly, it should be understood that in order to streamline the embodiments of the present invention and to aid in understanding one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, the disclosed method should not be interpreted as reflecting the following intention: that the claimed embodiments of the present invention require more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, the inventive aspects lie in less than all the features of the single embodiment disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, wherein each claim itself serves as a separate embodiment of the present invention.

[0085] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and further may be divided into a plurality of submodules or subunits or subcomponents. All features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device so disclosed may be combined in any combination, except that at least some of such features and / or processes or units are mutually exclusive. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0086] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0087] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components according to the embodiments of the present invention. The embodiments of the present invention may also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing part or all of the methods described herein. Such a program for implementing an embodiment of the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0088] It should be noted that the above embodiments illustrate rather than limit the present invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim listing a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A real-time prediction method for the contamination degree of oil-based drilling fluid filtrate, characterized in that the method include: Extracting formation fluid using a sampling instrument to obtain a first spectral absorbance of the formation fluid; the formation fluid includes drilling fluid filtrate and original formation oil and gas; determining a second spectral absorbance corresponding to the drilling fluid filtrate; The first spectral absorbance and the extraction factor are input into the trained absorbance prediction model to predict the third spectral absorbance of the original formation oil and gas; the absorbance prediction model is obtained based on radial basis function network training; the extraction factor includes extraction volume or extraction time; the absorbance prediction model is constructed based on connection weights, radial basis functions of sample extraction factors and the first sample spectral absorbance to obtain a mapping relationship between the third sample spectral absorbance and the radial basis function of the sample extraction factor; the connection weight is the connection weight between the hidden layer neurons and the output layer neurons, and the initial value of the connection weight is determined according to the random points of the Gaussian distribution; the sample extraction factor includes the sample extraction volume or the sample extraction time; When the sample extraction factor is the sample extraction time, the following method is used: When the sample extraction factor is the sample extraction volume, the following method is used: Among them, D k is the spectral absorbance of the third sample, D fw is the spectral absorbance of the first sample, t is the sample extraction time, V is the sample extraction volume, w jk is the connection weight, j is the jth neuron in the hidden layer, and its value is 1-m, k is the kth neuron in the output layer, and h j (V), h j (t) is the action function of the jth neuron in the hidden layer, h j (V) and sample extraction volume, h j (t) has a nonlinear mapping relationship with the sample extraction time; The contamination degree of the drilling fluid filtrate is calculated based on the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions; wherein, the first difference between the first spectral absorbance and the predicted third spectral absorbance is calculated; the second difference between the second spectral absorbance and the predicted third spectral absorbance is calculated; and the contamination degree of the drilling fluid filtrate is obtained according to the ratio of the first difference to the second difference.

2. The method according to claim 1, characterized in that The method further comprises: Determine a target wavelength; wherein the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance correspond to the target wavelength.

3. The method according to claim 1, characterized in that The method further comprises: Obtaining the first sample spectral absorbance, the sample extraction factor, and the third sample spectral absorbance; Constructing an absorbance prediction model; wherein the radial basis function of the sample extraction factor constructs a nonlinear mapping relationship according to the sample extraction factor; The first sample spectral absorbance, the sample extraction factor and the third sample spectral absorbance are input into the absorbance prediction model for training, and the connection weight is adjusted to obtain the trained absorbance prediction model.

4. The method according to claim 3, characterized in that The radial basis function of the sample extraction factor constructs a nonlinear mapping relationship according to the sample extraction factor: Clustering is performed according to the sample extraction factor to obtain a cluster center as the center of the radial basis function; Calculating the variance according to the cluster center as the width of the radial basis function; A radial basis function of the sample decimation factor is constructed according to the center of the radial basis function and the width of the radial basis function.

5. The method according to any one of claims 1 to 4, characterized in that Determining the degree of contamination that meets the extraction conditions further includes: Determining whether the pollution level is less than a preset pollution level threshold; If so, determine that the extraction time corresponding to the predicted third spectral absorbance is the target extraction time for reaching the preset contamination threshold; the target extraction time is determined according to the extraction time of the extraction factor or the time corresponding to the extraction volume of the extraction factor.

6. A real-time prediction device for oil-based drilling fluid filtrate contamination, characterized in that: The device includes: The first module is adapted to extract formation fluid using a sampling instrument to obtain a first spectral absorbance of the formation fluid; the formation fluid includes drilling fluid filtrate and original formation oil and gas; A second module, adapted to determine a second spectral absorbance corresponding to the drilling fluid filtrate; A prediction module, adapted to input the first spectral absorbance and extraction factor into the trained absorbance prediction model, and predict the predicted third spectral absorbance of the original formation oil and gas; the absorbance prediction model is obtained based on radial basis function network training; the extraction factor includes extraction volume or extraction time; the absorbance prediction model is constructed based on connection weights, radial basis functions of sample extraction factors, and the first sample spectral absorbance, and obtains a mapping relationship between the third sample spectral absorbance and the radial basis function of the sample extraction factor; the connection weight is the connection weight between the hidden layer neurons and the output layer neurons, and the initial value of the connection weight is determined according to the random points of the Gaussian distribution; the sample extraction factor includes the sample extraction volume or the sample extraction time; When the sample extraction factor is the sample extraction time, the following method is used: When the sample extraction factor is the sample extraction volume, the following method is used: Among them, D k is the spectral absorbance of the third sample, D fw is the spectral absorbance of the first sample, t is the sample extraction time, V is the sample extraction volume, w jk is the connection weight, j is the jth neuron in the hidden layer, and its value is 1-m, k is the kth neuron in the output layer, and h j (V), h j (t) is the action function of the jth neuron in the hidden layer, h j (V) and sample extraction volume, h j (t) has a nonlinear mapping relationship with the sample extraction time; A calculation module is suitable for calculating the contamination degree of the drilling fluid filtrate according to the first spectral absorbance, the second spectral absorbance and the predicted third spectral absorbance to determine the contamination degree that meets the extraction conditions; wherein, a first difference between the first spectral absorbance and the predicted third spectral absorbance is calculated; a second difference between the second spectral absorbance and the predicted third spectral absorbance is calculated; and the contamination degree of the drilling fluid filtrate is obtained according to the ratio of the first difference to the second difference.

7. A computing device, characterized in that include: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform operations corresponding to the real-time prediction method for oil-based drilling fluid filtrate contamination according to any one of claims 1-6.

8. A computer storage medium, characterized in that The storage medium stores at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the real-time prediction method for oil-based drilling fluid filtrate contamination as described in any one of claims 1-5.

9. A computer program product, characterized in that It comprises at least one executable instruction, wherein the executable instruction enables the processor to execute operations corresponding to the method for real-time prediction of oil-based drilling fluid filtrate contamination as described in any one of claims 1-5.

Images