Underground fluid measurement method and system based on optical fiber sensing technology and medium

Abstract

The invention discloses an underground fluid measurement method and system based on an optical fiber sensing technology and a medium. Relates to the technical field of underground fluid measurement. The method comprises the following steps: periodically collecting demodulation signals from an optical fiber sensor; acquiring a first intermediate flow velocity corresponding to the demodulation signal at the current moment according to a corresponding relation between the demodulation signal and the flow velocity under the first frequency; at a second frequency, based on the constructed neural network model, obtaining a second intermediate flow rate corresponding to the demodulation signal at the current moment; wherein the first frequency is a preset multiple of the second frequency; calculating a difference value between the first intermediate flow velocity and the second intermediate flow velocity, and determining an actual flow velocity corresponding to the demodulation signal at the current moment according to the difference value; by means of the method, the accuracy and efficiency of underground fluid measurement can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of underground fluid measurement, and in particular to an underground fluid measurement method, system and medium based on optical fiber sensing technology. Background Art

[0002] How to accurately measure the liquid flow at different depths in the oil well to construct a liquid production profile, so as to accurately grasp the oil and gas production of each production layer, is crucial for obtaining dynamic data of oil reservoirs in the later stage of oil field development. The fluid in the oil well is located underground and needs to be collected and transported using oil pipelines. The flow meters used in traditional industries have problems such as low reliability, poor resistance to high temperature and high pressure, and poor corrosion resistance, making them difficult to use normally in complex underground environments. Therefore, an underground fluid measurement system is established. By monitoring the flow rate of the fluid in the pipeline, it is possible to promptly perceive the occurrence of events such as blockage and leakage in the pipeline, thereby reducing safety accidents and reducing adverse effects.

[0003] As a new type of monitoring technology, distributed fiber acoustic sensing technology can well meet the monitoring needs in oil and gas production and other fields with its anti-electromagnetic interference, high temperature and high pressure resistance and corrosion resistance. As a frontier field in the development of distributed fiber optic sensing technology, distributed fiber acoustic sensing (DAS) technology based on backward Rayleigh scattering can correspond in real time according to the changes in external sound waves and the phase changes of scattered signals.

[0004] In current distributed flow monitoring, how to improve the accuracy and efficiency of measuring fluid flow changes is an urgent problem that those skilled in the art need to solve. Summary of the invention

[0005] The technical problem to be solved by the present invention is: there are problems of low accuracy and efficiency in the current distributed flow monitoring. The purpose of the present invention is to provide an underground fluid measurement method, system and medium based on optical fiber sensing technology. By judging the difference in the intermediate flow velocities of the demodulated signal at different frequencies, the actual flow velocity corresponding to the demodulated signal is determined, thereby solving the problems of low accuracy and efficiency in the distributed flow monitoring process.

[0006] The present invention is achieved through the following technical solutions:

[0007] This solution provides an underground fluid measurement method based on optical fiber sensing technology, including:

[0008] Periodically collecting demodulated signals from the optical fiber sensor;

[0009] At the first frequency, according to the corresponding relationship between the demodulated signal and the flow velocity, obtaining a first intermediate flow velocity corresponding to the demodulated signal at the current moment;

[0010] At the second frequency, based on the constructed neural network model, a second intermediate flow rate corresponding to the demodulated signal at the current moment is obtained; wherein the first frequency is a preset multiple of the second frequency;

[0011] The difference between the first intermediate flow rate and the second intermediate flow rate is calculated, and the actual flow rate corresponding to the demodulated signal at the current moment is determined according to the difference.

[0012] Working principle of this scheme: There are problems of low accuracy and efficiency in the current distributed flow monitoring. This scheme combines the two methods of calculating fluid flow rate, conventional calculation and neural network model, by calculating the difference between the first intermediate flow rate and the second intermediate flow rate, and determining the actual flow rate corresponding to the demodulated signal at the current moment based on the difference, which can reduce the impact of abnormal values ​​and improve the accuracy of monitoring.

[0013] A further optimization scheme is that the corresponding relationship between the demodulated signal and the flow velocity includes:

[0014] Demodulated signal S(t) and flow rate The square of is linearly related:

[0015]

[0016] in, Indicates the average flow velocity parallel to the axial direction of the pipe, u i (t) represents the instantaneous flow velocity parallel to the axial direction of the pipeline; n represents the number of samples when solving the instantaneous flow velocity (divided into certain depth intervals, generally 10m intervals); k represents the slope; y∝x means that y is proportional to x.

[0017] A further optimization scheme is that, based on the constructed neural network model, a second intermediate flow rate corresponding to the demodulated signal at the current moment is obtained; including the method:

[0018] Extracting features of the demodulated signal at the current moment to obtain signal features, wherein the signal features include amplitude features, main lobe peak, zero crossing rate, and peak side lobe level;

[0019] The signal feature is input into the constructed neural network model to obtain the second intermediate flow rate corresponding to the demodulated signal.

[0020] A further optimization scheme is that the method for constructing the neural network model includes:

[0021] The sample data is labeled to obtain a data set; the sample data includes: amplitude characteristics, main lobe peak, zero crossing rate and peak side lobe level of the demodulated signal;

[0022] Divide the data into training set, validation set and test set according to the preset ratio;

[0023] The training set is input into the initial neural network model to train the neural network model, and the neural network model is updated based on the validation set: the mean square error MSE is used as the loss function, the difference between the output result and the label is calculated, and the weights and biases in the neural network are continuously updated until the performance of the model on the validation set no longer improves or the predetermined number of iterations is reached.

[0024] A further optimization scheme is that the initial neural network model includes a long short-term memory network LSTM.

[0025] A further optimization scheme is that the demodulated signal is obtained based on a PGC demodulation algorithm or a 3×3 coupler phase demodulation algorithm.

[0026] A further optimization scheme is that the actual flow rate corresponding to the demodulated signal at the current moment is determined according to the difference; including the method:

[0027] Presetting a first threshold and a second threshold;

[0028] When the difference is less than or equal to the first threshold, taking the first intermediate flow rate corresponding to the demodulated signal at the current moment as the actual flow rate corresponding to the demodulated signal at the current moment;

[0029] When the difference is greater than the first threshold and less than or equal to the second threshold, taking the average of the first intermediate flow rate and the second intermediate flow rate corresponding to the demodulated signal at the current moment as the actual flow rate corresponding to the demodulated signal at the current moment;

[0030] When the difference is greater than the second threshold, obtain N adjacent demodulated signals collected at the moment closest to the current moment, perform sliding average processing on the N adjacent demodulated signals to obtain N-M+1 adjacent signals, where M is the sliding window size; obtain the second intermediate flow velocities corresponding to the N-M+1 adjacent signals based on the constructed neural network model; and take the average value of the second intermediate flow velocities corresponding to the N-M+1 adjacent signals as the actual flow velocity corresponding to the demodulated signal at the current moment.

[0031] A further optimization scheme is that the actual flow rate corresponding to the demodulated signal at the current moment is determined according to the difference; and the method also includes: presetting a number threshold;

[0032] When the difference is continuously greater than the second threshold for a number of times greater than the number threshold, the second frequency is increased; when the difference is continuously less than or equal to the first threshold for a number of times greater than the number threshold, the second frequency is decreased.

[0033] This solution also provides an underground fluid measurement system based on optical fiber sensing technology, which is used to implement the above-mentioned underground fluid measurement method based on optical fiber sensing technology; the system includes:

[0034] An acquisition module, used for periodically acquiring demodulated signals from the optical fiber sensor;

[0035] A first calculation module is used to obtain a first intermediate flow rate corresponding to the demodulated signal at a current moment according to a correspondence between the demodulated signal and the flow rate at a first frequency;

[0036] A second calculation module is used to obtain a second intermediate flow rate corresponding to the demodulated signal at the current moment based on the constructed neural network model at a second frequency; wherein the first frequency is a preset multiple of the second frequency;

[0037] The output module is used to calculate the difference between the first intermediate flow rate and the second intermediate flow rate, and determine the actual flow rate corresponding to the demodulated signal at the current moment according to the difference.

[0038] The present solution also provides a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the underground fluid measurement method based on optical fiber sensing technology as described above.

[0039] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0040] 1. The present invention provides an underground fluid measurement method, system and medium based on optical fiber sensing technology; combining conventional calculation and neural network model, two methods for calculating fluid flow rate, by calculating the difference between the first intermediate flow rate and the second intermediate flow rate, and determining the actual flow rate based on the comparison result of the difference with a threshold, it is possible to reduce the influence of abnormal values ​​and improve the accuracy of measurement.

[0041] 2. The present invention provides an underground fluid measurement method, system and medium based on optical fiber sensing technology; by dynamically adjusting the frequency of calculating the flow velocity using a neural network model, it is possible to reduce the amount of calculation while meeting the measurement accuracy.

[0042] 3. The present invention provides an underground fluid measurement method, system and medium based on optical fiber sensing technology; by acquiring demodulated signals in real time, real-time monitoring of underground fluids can be achieved, providing continuous dynamic data for oil and gas field development. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without creative work. In the drawings:

[0044] Figure 1It is a schematic diagram of the process of underground fluid measurement method based on optical fiber sensing technology;

[0045] Figure 2 It is a schematic diagram of the structure of a distributed optical fiber acoustic wave sensing system;

[0046] Figure 3 This is a schematic diagram of the structure of an underground fluid measurement system based on optical fiber sensing technology;

[0047] Figure 4 A schematic diagram of the electronic device structure. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0049] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0050] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0051] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0052] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0053] Regarding underground fluid measurement methods based on fiber optic sensing technology, there are currently a variety of methods for calculation, and there are two common methods: calculation based on the mathematical relationship between the vibration signal and the fluid velocity in the pipe; calculation based on the neural network model method. However, the two methods currently have their own advantages and disadvantages: when calculating based on mathematical relationships, the calculation speed is fast and the efficiency is high, but the measurement results are greatly affected by the noise in the signal, and the accuracy needs to be improved. When calculating based on the neural network model, it can be identified according to the internal characteristics of the vibration signal, and the measurement accuracy is high, but the calculation amount is large and the efficiency is low. In view of this, this embodiment provides the following embodiments to solve the above-mentioned technical problems.

[0054] Embodiment 1: This embodiment provides a method for measuring underground fluid based on optical fiber sensing technology, such as Figure 1 As shown, including:

[0055] Step 1: periodically collect demodulated signals from the optical fiber sensor; specifically, the distributed optical acoustic sensor (DAS) system is mainly composed of a high-coherence pulse laser source, an optical signal amplifier, an optical detector (demodulator), a single-mode (or multi-mode) optical fiber, and a data processing and analysis device. The system structure is as follows: Figure 2 After the coherent light pulse enters the optical fiber, changes in the external environment (such as pressure, vibration, etc.) will cause the refractive index or length of the optical fiber to change, thereby causing the phase of the backward Rayleigh scattered light in the optical fiber to change.

[0056] In the data processing process, we cannot directly detect the phase of the optical signal, but can only detect the light intensity. Since there is a nonlinear relationship between light intensity and phase, we need to use a light detector to demodulate the required demodulation signal S(t) from the light intensity signal. This embodiment obtains the demodulation signal based on the PGC demodulation algorithm or the 3×3 coupler phase demodulation algorithm.

[0057] In this embodiment, the demodulated signal is obtained based on a PGC demodulation algorithm or a 3×3 coupler phase demodulation algorithm.

[0058] Step 2: Under the first frequency, according to the corresponding relationship between the demodulated signal and the flow velocity, obtain the first intermediate flow velocity corresponding to the demodulated signal at the current moment; the corresponding relationship between the demodulated signal and the flow velocity includes:

[0059] Demodulated signal S(t) and flow rate The square of is linearly related:

[0060]

[0061] in, Indicates the average flow velocity parallel to the axial direction of the pipe, u i (t) represents the instantaneous flow velocity parallel to the axial direction of the pipeline; n represents the number of samples when solving the instantaneous flow velocity (divided into certain depth intervals, generally 10m intervals); k represents the slope; y∝x means that y is proportional to x.

[0062] Step 3, at the second frequency, based on the constructed neural network model, obtaining the second intermediate flow rate corresponding to the demodulated signal at the current moment; wherein the first frequency is a preset multiple of the second frequency; the method of obtaining the second intermediate flow rate corresponding to the demodulated signal at the current moment based on the constructed neural network model includes:

[0063] Extracting features of the demodulated signal at the current moment to obtain signal features, wherein the signal features include amplitude features, main lobe peak, zero crossing rate, and peak side lobe level;

[0064] The signal feature is input into the constructed neural network model to obtain the second intermediate flow rate corresponding to the demodulated signal.

[0065] The method for constructing the neural network model includes:

[0066] The sample data is labeled to obtain a data set; the sample data includes: amplitude characteristics, main lobe peak, zero crossing rate and peak side lobe level of the demodulated signal;

[0067] Divide the data into training set, validation set and test set according to the preset ratio;

[0068] The training set is input into the initial neural network model to train the neural network model, and the neural network model is updated based on the validation set: the mean square error MSE is used as the loss function, the difference between the output result and the label is calculated, and the weights and biases in the neural network are continuously updated until the performance of the model on the validation set is no longer improved or the predetermined number of iterations is reached. The initial neural network model includes a long short-term memory network LSTM.

[0069] Specifically, in the process of collecting and processing Rayleigh backscattering, it is inevitable to be interfered by various random noises, which will cause the deviation of the recognition results, making the difference between the results of the two different recognition methods larger. In order to reduce the influence of the noise on the recognition results, multiple collected signals can be superimposed, and then the average amplitude of the superimposed signals can be calculated, so that the random changes of the noise will offset or average each other, and the useful signal will be enhanced, making the acquired backscattering curve clearer and more reliable.

[0070] Set the averaging window, and the number of signals in the averaging window remains unchanged. After the averaging window is set, the signals entering the averaging window will be averaged, and then deferred in sequence according to the data sequence number until the data with the largest sequence number ends the process. Specifically, obtain the demodulated signals s = {s1, s2, ...s N}, if the number of averaging windows is set to M, the averaged demodulated signal is S = {S1, S2, ... S K}, where K = N-M+1, and

[0071]

[0072] For example, if there are 10 demodulated signals originally, when M is set to 5, N-M+1=6 demodulated signals are obtained after processing. The values ​​of N and M can be adjusted according to experience.

[0073] Step 4: Calculate the difference between the first intermediate flow rate and the second intermediate flow rate, and determine the actual flow rate corresponding to the demodulated signal at the current moment according to the difference. In this step, the actual flow rate corresponding to the demodulated signal at the current moment is determined according to the difference; including the method:

[0074] Presetting a first threshold and a second threshold;

[0075] When the difference is less than or equal to the first threshold, taking the first intermediate flow rate corresponding to the demodulated signal at the current moment as the actual flow rate corresponding to the demodulated signal at the current moment;

[0076] When the difference is greater than the first threshold and less than or equal to the second threshold, taking the average of the first intermediate flow rate and the second intermediate flow rate corresponding to the demodulated signal at the current moment as the actual flow rate corresponding to the demodulated signal at the current moment;

[0077] When the difference is greater than the second threshold, obtain N adjacent demodulated signals collected at the moment closest to the current moment, perform sliding average processing on the N adjacent demodulated signals to obtain N-M+1 adjacent signals, where M is the sliding window size; obtain the second intermediate flow velocities corresponding to the N-M+1 adjacent signals based on the constructed neural network model; and take the average value of the second intermediate flow velocities corresponding to the N-M+1 adjacent signals as the actual flow velocity corresponding to the demodulated signal at the current moment.

[0078] Also included is a method of: presetting a number threshold;

[0079] When the difference is continuously greater than the second threshold for a number of times greater than the number threshold, the second frequency is increased; when the difference is continuously less than or equal to the first threshold for a number of times greater than the number threshold, the second frequency is decreased.

[0080] For example: Assume that a demodulated signal from an optical fiber sensor is collected once per second, and the first intermediate flow velocity corresponding to the demodulated signal is obtained every second according to the corresponding relationship between the demodulated signal and the flow velocity. Every 10 seconds (for illustration only, the actual frequency can be set as needed, such as every minute, every hour, every day, etc.), the neural network model is used to obtain the second intermediate flow velocity corresponding to the demodulated signal. Assume that 10 demodulated signals s = {s1, s2, ...s 10}, then the demodulated signals s1, s2, ...s are calculated. 10 The first intermediate flow velocities u1, u2, ...u 10 , and the signal s 10 The corresponding second intermediate flow rate v 10 After obtaining the second intermediate flow rate v 10 Calculate the current u 10 and v 10 The difference Δ.

[0081] Preset a first threshold value th1 and a second threshold value th2;

[0082] When Δ≤th1, the actual flow rate of the fluid at the current moment is u 10 ;

[0083] When th1<Δ≤th2, the actual flow rate of the fluid at the current moment is (u 10 +v 10 ) / 2;

[0084] When Δ>th2, the demodulated signals s={s1, s2, ...s N}, if the number of averaging windows is set to M, the averaged demodulated signal is S = {S1, S2, ... S K Based on the neural network model, the second intermediate flow velocities v1, v2, ... v corresponding to the N-M+1 demodulated signals are obtained. K , the average value of the second intermediate flow rate corresponding to the N-M+1 demodulated signals The actual flow rate corresponding to the demodulated signal collected at the current moment.

[0085] The method of this embodiment also includes dynamically adjusting the second frequency: when the difference is greater than the second threshold for a long time, it means that some sudden noise may be encountered at this time, and the use of mathematical methods to calculate is not enough to meet the system accuracy requirements. By increasing the second frequency, the frequency of calculation using the neural network model is increased, and the measurement accuracy can be improved; when the difference is less than or equal to the first threshold for a long time, it means that the use of mathematical methods to calculate is sufficient to meet the system accuracy requirements. By reducing the second frequency, the frequency of calculation using the neural network model is reduced, the amount of calculation is reduced, and the recognition efficiency is improved.

[0086] This solution combines conventional calculation and neural network model, two methods for calculating fluid flow rate. By calculating the difference between the first intermediate flow rate and the second intermediate flow rate, and determining the actual flow rate based on the comparison result of the difference and the threshold, it can reduce the influence of abnormal values ​​and improve the accuracy of measurement. This method can reduce the amount of calculation while meeting the measurement accuracy by dynamically adjusting the frequency of calculating the flow rate using the neural network model. By acquiring the demodulated signal in real time, real-time monitoring of underground fluids can be achieved, providing continuous dynamic data for oil and gas field development.

[0087] Embodiment 2: This embodiment provides an underground fluid measurement system based on optical fiber sensing technology, such as Figure 2 As shown, a method for measuring underground fluid based on optical fiber sensing technology according to embodiment 1 is implemented; the system comprises:

[0088] An acquisition module, used for periodically acquiring demodulated signals from the optical fiber sensor;

[0089] A first calculation module is used to obtain a first intermediate flow rate corresponding to the demodulated signal at a current moment according to a correspondence between the demodulated signal and the flow rate at a first frequency;

[0090] A second calculation module is used to obtain a second intermediate flow rate corresponding to the demodulated signal at the current moment based on the constructed neural network model at a second frequency; wherein the first frequency is a preset multiple of the second frequency;

[0091] The output module is used to calculate the difference between the first intermediate flow rate and the second intermediate flow rate, and determine the actual flow rate corresponding to the demodulated signal at the current moment according to the difference.

[0092] The output module includes: a difference acquisition module, an actual flow rate acquisition module and a frequency adjustment module;

[0093] The difference acquisition module is used to calculate the difference between the first intermediate flow rate and the second intermediate flow rate at the current moment when the second intermediate flow rate is acquired;

[0094] The actual flow rate acquisition module is used to determine the actual flow rate corresponding to the demodulated signal according to the difference between the first intermediate flow rate and the second intermediate flow rate at the current moment; specifically includes:

[0095] When the difference is less than or equal to a first threshold, taking the first intermediate flow rate at the current moment as the actual flow rate corresponding to the demodulated signal;

[0096] When the difference is greater than the first threshold and less than or equal to the second threshold, taking the average of the first intermediate flow rate and the second intermediate flow rate at the current moment as the actual flow rate corresponding to the demodulated signal;

[0097] When the difference is greater than the second threshold, the N demodulated signals collected closest to the current moment are obtained, and the N demodulated signals are subjected to sliding average to obtain N-M+1 signals, where M is the sliding window size, and the second intermediate flow velocities corresponding to the N-M+1 demodulated signals are obtained based on the neural network model, and the average value of the second intermediate flow velocities corresponding to the N-M+1 demodulated signals is used as the actual flow velocity corresponding to the demodulated signal collected at the current moment;

[0098] The frequency adjustment module is used to increase the second frequency when the difference is continuously greater than the second threshold for a number of times greater than a preset value; and to reduce the second frequency when the difference is continuously less than or equal to the first threshold for a number of times greater than a preset value.

[0099] Embodiment 3: This embodiment provides a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement a method for measuring underground fluid based on optical fiber sensing technology as described in Embodiment 1. Specifically, the following steps are performed:

[0100] Step 1: Periodically collect the demodulated signal from the optical fiber sensor;

[0101] Step 2: Under the first frequency, according to the corresponding relationship between the demodulated signal and the flow velocity, obtain the first intermediate flow velocity corresponding to the demodulated signal at the current moment;

[0102] Step 3: Under the second frequency, based on the constructed neural network model, obtain the second intermediate flow rate corresponding to the demodulated signal at the current moment; wherein the first frequency is a preset multiple of the second frequency;

[0103] Step 4: Calculate the difference between the first intermediate flow rate and the second intermediate flow rate, and determine the actual flow rate corresponding to the demodulated signal at the current moment according to the difference.

[0104] Embodiment 4: This embodiment provides an electronic device, such as Figure 4 As shown, the electronic device includes: a memory and a processor, the memory and the processor are coupled; the memory stores program instructions, and when the program instructions are executed by the processor, the electronic device executes the method as described in Example 1. The processor is coupled to the memory via an internal bus.

[0105] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not limitation, and the above details do not limit the present application to be implemented by adopting the above specific details.

[0106] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0107] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0108] The method and apparatus of the present application may be implemented in many ways. For example, the method and apparatus of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present application may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers a recording medium storing a program for executing the method according to the present application.

[0109] It should also be noted that in the apparatus, equipment and method of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present application. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present application. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown here, but according to the widest scope consistent with the principles disclosed here and novel features.

[0110] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for measuring underground fluid based on optical fiber sensing technology, characterized in that: include: Periodically collecting demodulated signals from the optical fiber sensor; At the first frequency, according to the corresponding relationship between the demodulated signal and the flow velocity, obtaining a first intermediate flow velocity corresponding to the demodulated signal at the current moment; At the second frequency, based on the constructed neural network model, a second intermediate flow rate corresponding to the demodulated signal at the current moment is obtained; wherein the first frequency is a preset multiple of the second frequency; The difference between the first intermediate flow rate and the second intermediate flow rate is calculated, and the actual flow rate corresponding to the demodulated signal at the current moment is determined according to the difference.

2. The underground fluid measurement method based on optical fiber sensing technology according to claim 1 is characterized in that: The corresponding relationship between the demodulated signal and the flow velocity includes: Demodulated signal S(t) and flow rate The square of is linearly related: in, Indicates the average flow velocity parallel to the axial direction of the pipe, u i (t) represents the instantaneous flow velocity parallel to the axial direction of the pipe; n represents the number of samples when solving the instantaneous flow velocity; k represents the slope; y∝x means that y is proportional to x.

3. The underground fluid measurement method based on optical fiber sensing technology according to claim 2 is characterized in that: The method comprises obtaining a second intermediate flow rate corresponding to the demodulated signal at the current moment based on the constructed neural network model; Included methods: Extracting features of the demodulated signal at the current moment to obtain signal features, wherein the signal features include amplitude features, main lobe peak, zero crossing rate, and peak side lobe level; The signal feature is input into the constructed neural network model to obtain the second intermediate flow rate corresponding to the demodulated signal.

4. The underground fluid measurement method based on optical fiber sensing technology according to claim 3 is characterized in that: The method for constructing the neural network model includes: The sample data is labeled to obtain a data set; the sample data includes: amplitude characteristics, main lobe peak, zero crossing rate and peak side lobe level of the demodulated signal; Divide the data into training set, validation set and test set according to the preset ratio; The training set is input into the initial neural network model to train the neural network model, and the neural network model is updated based on the validation set: the mean square error MSE is used as the loss function, the difference between the output result and the label is calculated, and the weights and biases in the neural network are continuously updated until the performance of the model on the validation set no longer improves or the predetermined number of iterations is reached.

5. The underground fluid measurement method based on optical fiber sensing technology according to claim 4 is characterized in that: The initial neural network model includes a long short-term memory network LSTM.

6. The underground fluid measurement method based on optical fiber sensing technology according to claim 1 is characterized in that: The demodulated signal is obtained based on a PGC demodulation algorithm or a 3×3 coupler phase demodulation algorithm.

7. The underground fluid measurement method based on optical fiber sensing technology according to claim 1 is characterized in that: Determining the actual flow rate corresponding to the demodulated signal at the current moment according to the difference; Included methods: Presetting a first threshold and a second threshold; When the difference is less than or equal to the first threshold, taking the first intermediate flow rate corresponding to the demodulated signal at the current moment as the actual flow rate corresponding to the demodulated signal at the current moment; When the difference is greater than the first threshold and less than or equal to the second threshold, taking the average of the first intermediate flow rate and the second intermediate flow rate corresponding to the demodulated signal at the current moment as the actual flow rate corresponding to the demodulated signal at the current moment; When the difference is greater than the second threshold, obtain N adjacent demodulated signals collected at the moment closest to the current moment, perform sliding average processing on the N adjacent demodulated signals to obtain N-M+1 adjacent signals, where M is the sliding window size; obtain the second intermediate flow velocities corresponding to the N-M+1 adjacent signals based on the constructed neural network model; and take the average value of the second intermediate flow velocities corresponding to the N-M+1 adjacent signals as the actual flow velocity corresponding to the demodulated signal at the current moment.

8. The underground fluid measurement method based on optical fiber sensing technology according to claim 7 is characterized in that: The actual flow rate corresponding to the demodulated signal at the current moment is determined according to the difference; and the method further includes: presetting a number threshold; When the difference is continuously greater than the second threshold for a number of times greater than the number threshold, the second frequency is increased; when the difference is continuously less than or equal to the first threshold for a number of times greater than the number threshold, the second frequency is decreased.

9. An underground fluid measurement system based on optical fiber sensing technology, characterized in that: Used to implement a method for measuring underground fluid based on optical fiber sensing technology as described in any one of claims 1 to 8; the system comprises: An acquisition module, used for periodically acquiring demodulated signals from the optical fiber sensor; A first calculation module is used to obtain a first intermediate flow rate corresponding to the demodulated signal at a current moment according to a correspondence between the demodulated signal and the flow rate at a first frequency; A second calculation module is used to obtain a second intermediate flow rate corresponding to the demodulated signal at the current moment based on the constructed neural network model at a second frequency; wherein the first frequency is a preset multiple of the second frequency; The output module is used to calculate the difference between the first intermediate flow rate and the second intermediate flow rate, and determine the actual flow rate corresponding to the demodulated signal at the current moment according to the difference.

10. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement an underground fluid measurement method based on optical fiber sensing technology as described in any one of claims 1 to 8.

Images