Trace substance tracer agent monitoring method based on intelligent algorithm

Abstract

The invention discloses a trace substance tracer monitoring method based on an intelligent algorithm, and the method comprises the following steps: screening a plurality of trace substance tracers according to the characteristics of a multilayer loose sandstone geological reservoir; calculating the dosage of the trace substance tracer according to the monitoring time and the release rate of the tracer; according to the difference of different engineering parameters, different types of tracer patches are placed in all layers and sections of the directional producing well; meanwhile, multiple rounds of collection and detection analysis are conducted on the oil-water mixed sample, and a segmented water-soluble trace substance tracer agent output concentration curve and an oil-soluble trace substance tracer agent output concentration curve are obtained; according to the corrected tracer agent concentration data, a machine learning algorithm is utilized to consider the influence of multiple factors to calculate the output contribution rates of different layer sections, and therefore the output condition of each layer section of the directional oil production well is obtained. According to the method, the output layer sections of the directional producing well are monitored by adopting various trace tracers in combination with an intelligent algorithm, so that the interlayer output change can be accurately mastered, and a reliable basis is provided for next development and adjustment.

Description

Technical Field

[0001] The present invention belongs to the technical field of offshore oil and gas field development, and particularly relates to a monitoring method for trace substance tracers based on intelligent algorithms. Background Technique

[0002] In recent years, most offshore water injection developed oilfields have entered the high water cut stage. Due to the differences in geological reservoir characteristics such as structure, reservoir, and well pattern layer systems, the three major contradictions of reservoir plane, intra-layer, and inter-layer are prominent. At present, offshore oilfields mainly use directional wells for development. In view of the problems such as the rapid increase in water cut of directional oil production wells and uneven production of intervals, how to optimize and adjust the interval production of directional oil production wells to improve the economic benefits of the oilfield is the key point for the adjustment and potential tapping of high water cut oilfields. Currently, commonly used measures include: profile control and flooding adjustment at the water injection well end, optimized water injection at the water injection well end, and layer plugging and water shutoff at the oil well end. Whether the above measures are effective depends on the understanding of the reservoir.

[0003] At present, during the oilfield production and development process, tracer monitoring technology is widely used in aspects such as injection-production well connectivity analysis, calculation of injected water advance velocity, analysis of oil well response, and analysis of formation stimulation effect. In recent years, this technology has undergone four generations of evolution, namely: chemical tracer monitoring technology, radioactive isotope tracer monitoring technology, stable isotope tracer monitoring technology, and trace substance tracer monitoring technology. Currently, trace substance tracer technology is the main development direction of inter-well monitoring technology.

[0004] In the prior art, trace substance tracers are mostly produced from the wellhead with the fluid, and after detection and analysis, a relatively complete tracer production concentration curve is obtained, so as to invert the reservoir dynamic information. However, the tracer production concentration is affected by multiple inter-layer interference factors such as erosion rate, flow-through liquid volume, reservoir physical properties, well spacing, and fluid properties, and it is not possible to simply convert the sampling concentration into interval production. Therefore, improving the accuracy of monitoring results can provide a basis for the adjustment of injection-production wells in the later stage. Summary of the Invention

[0005] The problem to be solved by the present invention is to provide a monitoring method for trace substance tracers based on intelligent algorithms. This method is simple and easy to implement, the monitoring results are accurate and reliable, and the interpretation method is more reasonable, and it is suitable for the production monitoring of directional oil production wells in offshore multi-layer sandstone reservoirs.

[0006] To solve the above technical problems, the technical solution adopted by the present invention is: a monitoring method for trace substance tracers based on intelligent algorithms, including the following steps,

[0007] S1: According to the geological characteristics of offshore multi-layer unconsolidated sandstone and the reservoir characteristics of high underground salinity, screen a variety of trace substance tracers;

[0008] S2: Calculate the dosage of the trace substance tracer in different intervals based on the monitoring time of the trace substance tracer and the release rate of the trace substance tracer;

[0009] S3: Place trace substance tracer patches of different types in each interval of the directional oil production well according to the differences in reservoir data of different perforated intervals and engineering parameters of the sand control interval span;

[0010] S4: Collect the oil well mixed oil-water samples in multiple rounds according to the on-site sampling principle, and detect and analyze the on-site samples to obtain the production concentration curve of the trace substance tracer in different segments;

[0011] S5: Based on the corrected tracer concentration data, use machine learning algorithms to calculate the oil production and water production contribution rates of different intervals considering the influence of various factors, so as to obtain the production conditions of each interval of the directional oil production well.

[0012] Further, in the S1, in combination with the analysis of the compatibility of the trace substance tracer with formation water, solubility in crude oil, anti-adsorption property, thermal stability, acid and alkali resistance, and temperature and salt resistance, water-soluble trace substance tracers and oil-soluble trace substance tracers are screened.

[0013] Further, in the S2, the dosage of the trace substance tracer is calculated by the following formula,

[0014] A = μ[R0+(T - 1)R a V

[0015] In the formula, A is the dosage of the trace substance tracer, g; μ is the guarantee coefficient, the purpose of which is to eliminate the influence of various natural and artificial adverse factors and ensure that the injected tracer can be detected; R0 is the initial release rate of the slow-release tracer, g / m 3 / d; R a is the average release rate of the slow-release tracer, g / m 3 / d; T is the required monitoring time, d; V is the predicted maximum daily liquid production of a single well, m 3 / d.

[0016] Further, the S3 includes the following steps,

[0017] S31: According to the monitoring target and design requirements, use the specified trace substance tracer in different monitoring intervals and install it on the corresponding tracer nipple on the ground;

[0018] S32: All the trace substance tracers are vacuum packaged and installed at the specified positions of the tubing or screen pipe through the tracer carrier sleeve and lowered into the well along with the oil casing.

[0019] Further, the S4 includes the following steps,

[0020] S41: Follow the principle of collecting mixed oil-water samples irregularly after opening the well at the site, take samples at the wellhead to detect the concentrations of various tracers. In the first stage, which lasted for 15 days in total, 19 mixed oil-water samples were collected.

[0021] S42: In the second stage, which lasted for 5 days in total, 5 mixed oil-water samples were collected.

[0022] S43: In the third stage, which lasted for 5 days in total, 5 mixed oil-water samples were collected. A total of 29 oil-water mixed samples were collected and sent to the laboratory in batches.

[0023] S44: After oil-water separation, use a liquid chromatography-mass spectrometry (LC-MS) instrument to detect the water samples and a gas chromatography-mass spectrometry (GC-MS) instrument to detect the oil samples, and obtain the production concentration curves of water-soluble trace substance tracers and oil-soluble trace substance tracers in segments.

[0024] Furthermore, the above-mentioned S5 includes the following steps.

[0025] S51: Establish a corresponding model to calculate the tracer flux and correct the tracer concentration.

[0026] S52: Using machine learning algorithms, considering various factors such as reservoir physical properties, well spacing, and fluid properties, establish an algorithm model for training, solve the relationship between the corrected concentration of the trace substance tracer and the oil and water production contribution rates of each layer section, and obtain the production profiles of directional oil production wells at different production stages.

[0027] Furthermore, the corrected formula for the tracer concentration is as follows:

[0028] C (t) =C s +C0·e -ZQt

[0029] In the formula, C (t) is the tracer concentration as a function of time, μg / L; C s is the constant concentration (steady state) released when the tracer contacts the liquid, μg / L; C0 is the initial concentration, μg / L; Q is the flow rate of the target fluid, m 3 / d; Z is a constant; t is the time, d.

[0030] Furthermore, the present invention provides a device for running the above data processing method.

[0031] Furthermore, the present invention provides a device including a memory, a processor, and an algorithm stored in the memory and executable on the processor. When the processor executes the computer program, the above data processing method is implemented.

[0032] Further, the present invention provides a computer-readable storage medium storing a computer algorithm, and when the computer algorithm is executed by a processor, the above data processing is implemented.

[0033] The advantages and positive effects of the present invention are as follows:

[0034] 1. In order to compensate for the influence of flow velocity and flow rate on the effective release concentration value of the tracer at the wellhead end, the present invention establishes a corresponding model to calculate the tracer flux and correct the measured tracer concentration. Considering various factors such as the physical properties of the underground reservoir, well spacing, and fluid properties, an intelligent algorithm model is established for training to solve the complex relationship between the corrected concentration of the trace substance tracer and the oil and water production contribution rates of each layer section, so as to obtain the production profile of the directional oil production well at different production stages, providing a basis for the adjustment of injection-production wells in the later stage of the area.

[0035] 2. The method of the present invention is simple and easy to implement, the monitoring results are accurate and reliable, and the interpretation method is more reasonable, which is suitable for the production monitoring of directional oil production wells in offshore multi-layer sandstone oil reservoirs. Brief Description of the Drawings

[0036] Figure 1 is the overall flow schematic diagram of the embodiment of the present invention.

[0037] Figure 2 is the schematic diagram of the solid slow-release trace substance tracer spline of the embodiment of the present invention.

[0038] Figure 3 is the graph of the corrected sectional water-soluble trace tracer production concentration of Well D at different stages in the embodiment of the present invention.

[0039] Figure 4 is the graph of the corrected sectional oil-soluble trace tracer production concentration of Well D at different stages in the embodiment of the present invention.

[0040] Figure 5 is the sectional water production profile of Well D under the intelligent optimization algorithm at different monitoring stages in the embodiment of the present invention.

[0041] Figure 6 is the sectional oil production profile of Well D under the intelligent optimization algorithm at different monitoring stages in the embodiment of the present invention.

[0042] Figure 7 is the sectional liquid production profile of Well D under the intelligent optimization algorithm at different monitoring stages in the embodiment of the present invention.

[0043] Figure 8 is the sectional water production ratio profile of Well D at different monitoring stages in the embodiment of the present invention.

[0044] Figure 9It is the sectional oil production ratio profile of Well D in different monitoring stages of the embodiment of the present invention.

[0045] Figure 10 It is the sectional liquid production ratio profile of Well D in different monitoring stages of the embodiment of the present invention.

[0046] Figure 11 It is the sectional water cut profile of Well D in different monitoring stages of the embodiment of the present invention. Detailed implementation manners

[0047] Next, the technical solutions of the present invention will be clearly and completely described in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0048] The following further describes the embodiments of the present invention in conjunction with the accompanying drawings:

[0049] As Figure 1 shown, a trace substance tracer monitoring method based on an intelligent algorithm includes the following steps.

[0050] S1: According to the geological characteristics of offshore multi-layer unconsolidated sandstone and the reservoir characteristics of high salinity underground, a variety of trace substance tracers are screened. Specifically, by combining the analysis of the compatibility of trace substance tracers with formation water, the solubility in crude oil, the anti-adsorption property, the thermal stability, the acid and alkali resistance, and the temperature and salt resistance, water-soluble trace substance tracers and oil-soluble trace substance tracers are screened.

[0051] Preferably, the tracers used in this embodiment are all trace element tracers, and the water-soluble trace substance tracers and oil-soluble trace substance tracers are complexes of one or several trace elements among lutetium, samarium, zirconium, indium, scandium, terbium, dysprosium, rubidium, europium, ytterbium, praseodymium, gallium, erbium, gadolinium, yttrium, cesium, titanium, cerium, thulium, neodymium, lanthanum, and holmium.

[0052] S2: Calculate the dosage of the trace substance tracer according to the monitoring time of the trace substance tracer and the release rate of the trace substance tracer. Specifically, the dosages of both the water-soluble trace substance tracer and the oil-soluble trace substance tracer are calculated by the following formula,

[0053] A = μ[R0 + (T - 1)R a V

[0054] In the formula, A is the dosage of the trace substance tracer, g; μ is the guarantee coefficient, the purpose of which is to eliminate the influence of various natural and artificial adverse factors and ensure that the injected tracer can be detected; R0 is the initial release rate of the slow-release tracer, g / m 3 / d; Ra is the average release rate of the sustained-release tracer, g / m 3 / d; T is the required monitoring time, d; V is the maximum daily liquid production of the predicted single well, m 3 / d.

[0055] S3: According to the differences in reservoir data of different perforation intervals and engineering parameters of the sand control section span, different types of trace substance tracer patches are placed in each interval of the directional oil production well. Specifically, S3 includes the following steps,

[0056] S31: According to the monitoring objectives and design requirements, specified trace substance tracers are used in different monitoring intervals, and they are installed on the corresponding tracer nipples on the ground. Preferably, the tracer nipples in this embodiment are placed as high as possible in each sand control section, and the setting depth is determined in combination with the physical properties of the reservoir to ensure the accuracy of the test for each sand control section; if the span of each sand control section is large and there are many main layers, several types of tracers can be considered to be placed in this sand control section to detect the contribution degree of the main layers.

[0057] S32: All trace substance tracer products are vacuum packaged after being manufactured. To avoid moisture absorption during transportation and storage, they are then installed at the specified positions of the tubing or screen pipe through special tracer carriers and lowered into the well along with the oil and casing pipes.

[0058] Preferably, to ensure the test accuracy, it is better to separate the intervals to be tested. The separation method can be a packer or a blank pipe. And it is better to use annulus filling to reduce axial crossflow. In this embodiment, the distance between the detection intervals should be greater than 10 m to reduce errors.

[0059] S4: The oil well mixed oil and water samples are collected in multiple rounds according to the on-site sampling principle, and the on-site samples are detected and analyzed to obtain the sectional trace substance tracer production concentration curve. Specifically, S4 includes the following steps,

[0060] S41: The trace substance tracer can slowly diffuse into the solvent through the pores in the framework. On-site, following the sampling principle of collecting the mixed oil and water samples irregularly after the well is opened, the concentrations of various tracers are detected by sampling at the wellhead. In the first stage, a total of 19 mixed oil and water samples are collected in 15 days;

[0061] S42: In the second stage, a total of 5 days, 5 mixed oil and water samples are collected;

[0062] S43: In the third stage, a total of 5 days, 5 mixed oil and water samples are collected, and a total of 29 oil and water mixed samples are collected and sent to the laboratory in batches. Specifically, the treatment process of the oil and water samples in this embodiment includes: filtration, digestion, acid dilution and constant volume, and finally the samples to be tested are obtained.

[0063] S44: According to the internal work standard SY / T 5925-2012 "Selection Method of Chemical Tracer for Oilfield Water Injection", after oil-water separation, use a liquid chromatography-mass spectrometry (LC-MS) instrument to detect the water sample and a gas chromatography-mass spectrometry (GC-MS) instrument to detect the oil sample, and obtain the production concentration curves of water-soluble trace substance tracers and oil-soluble trace substance tracers in segments.

[0064] S5: Based on the corrected tracer concentration data, use a machine learning algorithm to consider the influence of various factors and calculate the oil production and water production contribution rates of different intervals, so as to obtain the production situation of each interval of the directional oil production well. Specifically, S5 includes the following steps.

[0065] S51: The effective release concentration of the tracer is affected by multiple factors, including the flushing rate, the amount of flowing liquid, etc. In order to compensate for the influence of flow velocity and flow rate on its value, a corresponding model is established to calculate the tracer flux. The corrected formula for the tracer concentration is as follows:

[0066] C (t) =C s +C0·e -ZQt

[0067] In the formula, C (t) is the tracer concentration as a function of time, μg / L; C s is the constant concentration (steady state) released when the tracer contacts the liquid, μg / L; C0 is the initial concentration, μg / L; Q is the target fluid flow rate, m 3 / d; Z is a constant; t is the time, d.

[0068] S52: Use a machine learning algorithm, consider the influence of various factors such as reservoir physical properties, well spacing, and fluid properties, establish an algorithm model for training, solve the relationship between the corrected concentration of the trace substance tracer and the oil production and water production contribution rates of each interval, and obtain the production profile of the directional oil production well at different production stages.

[0069] The following specifically describes the present invention in conjunction with specific embodiments:

[0070] S1: Combining with the geological reservoir conditions of the offshore multi-layer unconsolidated sandstone oil reservoir, 6 water-soluble trace substance tracers and 6 oil-soluble trace substance tracers are selected, namely WS-01, WS-02, WS-03, WS-04, WS-05, WS-06, OS-01, OS-02, OS-03, OS-4, OS-05, OS-6, which respectively represent one or several trace elements in trace elements such as lutetium, samarium, zirconium, indium, scandium, terbium, dysprosium, rubidium, europium, ytterbium, praseodymium, gallium, erbium, gadolinium, yttrium, cesium, titanium, cerium, thulium, neodymium, lanthanum, and holmium. Production monitoring is carried out on the L50 to L104 small layers of Well D in Oilfield P.

[0071] S2: Design the dosage of the tracer based on the micro-tracer monitoring time and the tracer release rate. The designed dosages of the water-soluble micro-substance tracer and the oil-soluble micro-substance tracer include:

[0072] A = μ[R0+(T - 1)R a V

[0073] Where: A is the dosage of the micro-tracer, g; μ is the safeguard coefficient, whose purpose is to eliminate the influence of various natural and artificial adverse factors and ensure that the injected tracer can be detected; R0 is the initial release rate of the slow-release tracer, g / m 3 / d; R a is the average release rate of the slow-release tracer, g / m 3 / d; T is the required monitoring time, d; V is the predicted maximum daily liquid production of a single well, m 3 / d.

[0074] S3: Mix the water-soluble tracer and the oil-soluble tracer for well-to-well monitoring with a polymer substance and solidify them into a solid slow-release micro-substance tracer spline, as Figure 2 shown. Place different types of tracer patches according to the differences in engineering parameters such as reservoir data of different perforated intervals and the span of the sand control section. In the L54, L64, L72 - L74, L82, L88 - L94, and L100 - L102 sub-layers, the oil-soluble micro-substance tracers for each section are, in sequence: OS-5, OS-4, OS-3, OS-2, OS-1, OS-6, OS-3; the water-soluble micro-substance tracers for each section are, in sequence: WS-5, WS-4, WS-3, WS-2, WS-1, WS-6, WS-3.

[0075] S4: Collect the oil well mixed oil-water samples in multiple rounds according to the on-site sampling principle. In the first stage, it lasts for 15 days and 19 mixed oil-water samples are collected; in the second stage, it lasts for 5 days and 5 mixed oil-water samples are collected; in the third stage, it lasts for 5 days and 5 mixed oil-water samples are collected. A total of 29 oil-water mixed samples are collected and sent to the laboratory in batches.

[0076] S5: Since the effective release concentration of the tracer is affected by multiple factors, including the scouring rate, the flow rate of the flowing liquid, etc., in order to compensate for the influence of the flow rate and the flow volume on its value, establish a corresponding model to calculate the tracer flux. The optimized tracer concentration includes:

[0077] C (t) = C s + C0·e -ZQt

[0078] Where: C (t) is the tracer concentration as a function of time, μg / L; C sC is the constant concentration (steady state) released when the tracer contacts the liquid, μg / L; C0 is the initial concentration, μg / L; Q is the flow rate of the target fluid, m 3 / d; Z is a constant; t is time, d.

[0079] Through the fine detection and analysis of on-site samples, the corrected sectional water-soluble tracer and oil-soluble tracer production concentration curves are obtained as Figure 3 、 Figure 4 shown.

[0080] According to the corrected tracer concentration data, using machine learning algorithms to consider various factors such as reservoir physical properties, well spacing, and fluid properties, an algorithm model is established for training to solve the oil production and water production contribution rates of each layer section, so as to quantitatively calculate the formation water production, formation oil production, formation fluid production, and the production contribution degree of each layer section under the open-hole completion method of offshore multi-layer unconsolidated sandstone reservoirs, etc. as Figures 5 - 10 shown.

[0081] According to the production profile obtained from the test samples, the production conditions of each layer section and the main water production positions can be clarified, so as to accurately and reliably obtain the production profile of the directional oil production well, and by combining the reservoir characteristics and the production dynamics of surrounding wells, provide a reliable basis for the optimization and adjustment of this well and the well group in the next step.

[0082] The results are analyzed as follows:

[0083] According to Figure 3 and Figure 4 it can be seen that there are obvious water-soluble trace substance tracers and oil-soluble trace substance tracers produced in each sand control layer section, and there is no obvious difference in the overall production concentration curves of water-soluble trace substance tracers and oil-soluble trace substance tracers between samples.

[0084] On the basis of the above divided stages, according to Figure 7 and Figure 11 it can be seen that the production profile of Well D06S2 in the first stage was sampled from September 21 to October 5, 2023 (the first batch), with a water cut of about 80%; the production profile of the second stage was sampled from November 26 to November 30, 2023 (the second batch), with a water cut of about 30%; the production profile of the third stage was sampled from March 9 to March 13, 2024 (the laboratory failed to separate enough water samples from the mixed samples for detection and analysis), the stage liquid volume decreased significantly, the water cuts of each layer were less different, and the water cuts of each layer in the second batch decreased significantly compared with the first batch.

[0085] On the basis of the above divided stages, according to Figure 4 、 Figure 6 、 Figure 7 、 Figure 9It can be seen that the 1st, 2nd, 4th, and 6th test intervals are the main water production contributing intervals, and the 3rd and 5th test intervals are the low water production contributing intervals. Among them, the water production ratios of the 1st and 2nd test intervals have increased, while the other intervals have all decreased to a certain extent.

[0086] Based on the above divided stages, according to Figure 5 and Figure 8 It can be seen that in the second stage, the 1st and 6th test intervals are the main oil production contributing intervals, the 2nd and 4th test intervals are the medium oil production contributing intervals, and the 3rd and 5th test intervals are the low oil production contributing intervals. In the second stage, the 1st, 2nd, and 6th test intervals are the main oil production contributing intervals, the 3rd and 4th test intervals are the medium oil production contributing intervals, and the 5th test interval is the low oil production contributing interval. In the third stage, the 2nd test interval is the main oil production contributing interval, the 1st, 3rd, 4th, and 6th test intervals are the medium oil production contributing intervals, and the 5th test interval is the low oil production contributing interval.

[0087] Generally speaking, the change in the concentration of water-soluble trace substance tracers is similar to the daily water production ratio, and the change in the concentration of oil-soluble trace substance tracers is similar to the daily oil production ratio.

[0088] According to the above analysis, it can be seen that the production ratios of each interval in different stages are relatively stable, the differences in the concentrations of test tracers are not significant, and the obtained liquid production profiles can be used for the analysis and evaluation of the production conditions of each test interval; at the current stage, the 2nd test interval is the main oil production contributing interval, the 1st test interval and the 2nd test interval are the main water production contributing intervals and the main liquid production contributing intervals, and the production data of the 5th test interval show a downward trend; affected by the mutual interference between intervals and open-hole completion, the decline amplitudes of the daily water production and water cut of each interval are basically the same.

[0089] The advantages and positive effects of the present invention are as follows:

[0090] 1. In order to compensate for the influence of flow velocity and flow rate on the effective release concentration value of tracers at the wellhead end, the present invention establishes a corresponding model to calculate the tracer flux and corrects the test tracer concentration. Considering various factors such as the physical properties of underground reservoirs, well spacing, and fluid properties, an intelligent algorithm model is established for training to solve the complex relationship between the corrected concentration of trace substance tracers and the oil and water production contribution rates of each interval, so as to obtain the production profiles of directional oil production wells in different production stages, providing a basis for the adjustment of injection-production wells in the later stage of the area.

[0091] 2. The method of the present invention is simple and easy to implement, the monitoring results are accurate and reliable, the interpretation method is more reasonable, and it is suitable for the production monitoring of directional oil production wells in offshore multi-layer sandstone oil reservoirs.

[0092] The above has described in detail an embodiment of the present invention, but the above content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made in accordance with the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. A trace substance tracer monitoring method based on intelligent algorithm, characterized in that: The following steps are included: S1: Screening a variety of trace material tracers based on the geological characteristics of offshore multi-layer loose sandstone and underground high-mineralization oil reservoir characteristics; S2: Calculating the amount of the trace substance tracer in different layers according to the monitoring time of the trace substance tracer and the release rate of the trace substance tracer; S3: According to the differences in reservoir data of different perforated layers and engineering parameters of sand control span, different types of trace material tracer patches are placed in each layer of the directional oil production well; S4: collecting mixed oil and water samples of the oil well in multiple rounds according to the field sampling principle, and testing and analyzing the field samples to obtain the output concentration curve of the trace substance tracer in the segment; S5: Based on the corrected tracer concentration data, the machine learning algorithm is used to calculate the contribution rates of oil and water production in different layers by considering multiple factors, so as to obtain the production status of each layer in the directional oil production well.

2. The method for monitoring trace substances based on an intelligent algorithm according to claim 1, characterized in that: In S1, water-soluble trace substance tracers and oil-soluble trace substance tracers are screened in combination with analysis of the trace substance tracer's compatibility with formation water, crude oil solubility, adsorption resistance, thermal stability, acid and alkali resistance, and temperature and salt resistance.

3. A trace substance tracer monitoring method based on intelligent algorithm according to claim 1 or 2, characterized in that: In S2, the amount of the trace substance tracer is calculated by the following formula: A=μ[R0+(T-1)R a ]V Where A is the amount of tracer used, g; μ is the security factor, which aims to eliminate the influence of various natural and artificial adverse factors and ensure that the injected tracer is detected; R0 is the initial release rate of the slow-release tracer, g / m 3 / d;R a is the average release rate of the sustained-release tracer, g / m 3 / d; T is the required monitoring time, d; V is the predicted maximum daily fluid production of a single well, m 3 / d.

4. A trace substance tracer monitoring method based on intelligent algorithm according to claim 1 or 2, characterized in that: The S3 comprises the following steps, S31: According to the monitoring objectives and design requirements, designated trace substance tracers are used in different monitoring layers and installed on the corresponding tracer short sections on the ground; S32: All the trace material tracers are vacuum packaged, installed at the designated position of the oil pipe or screen pipe through the tracer carrier sleeve, and lowered into the well along the oil casing.

5. The method for monitoring trace substances based on an intelligent algorithm according to claim 1 or 2, characterized in that: The S4 comprises the following steps, S41: The site follows the principle of collecting mixed oil and water samples irregularly after well opening, and samples are taken at the wellhead to test the concentration of various tracers. In the first stage, a total of fifteen days, 19 mixed oil and water samples were collected; S42: The second phase lasted five days, during which five mixed oil and water samples were collected; S43: The third phase lasted five days, during which five mixed oil-water samples were collected, and a total of 29 mixed oil-water samples were collected and sent to the laboratory in batches; S44: After oil-water separation, the water sample is tested using a liquid chromatography-mass spectrometer, and the oil sample is tested using a gas chromatography-mass spectrometer to obtain a segmented water-soluble trace substance tracer output concentration curve and an oil-soluble trace substance tracer output concentration curve.

6. A trace substance tracer monitoring method based on intelligent algorithm according to claim 1 or 2, characterized in that: The S5 comprises the following steps: S51: Establish a corresponding model to calculate the tracer flux and correct the tracer concentration; S52: Using machine learning algorithms, considering the influence of multiple factors such as reservoir physical properties, well spacing, and fluid properties, an algorithm model is established for training to solve the relationship between the corrected trace substance tracer concentration and the contribution rate of oil and water production in each layer, and obtain the production profile of directional oil wells in different production stages.

7. The method for monitoring trace substances based on an intelligent algorithm according to claim 6, characterized in that: The corrected formula for the tracer concentration is as follows: C (t) =C s +C0·e -ZQt In the formula, C (t) is the tracer concentration as a function of time, μg / L; C s is the constant concentration (steady state) released when the tracer contacts the liquid, μg / L; C0 is the initial concentration, μg / L; Q is the target fluid flow rate, m 3 / d; Z is a constant; t is time, d.

8. A device, characterized in that: Run the data processing method according to any one of claims 1 to 7.

9. A device comprising a memory, a processor, and an algorithm stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the data processing method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer algorithm, characterized in that: When the computer algorithm is executed by a processor, the data processing according to any one of claims 1 to 7 is implemented.

Images