Method for measuring oil-water two-phase flow parameters of oil well based on multivariate time sequence prediction model of cross-dimension dependency

Abstract

The invention discloses an oil well oil-water two-phase flow parameter measurement method based on a multivariate time sequence prediction model of cross-dimension dependency, and the oil well oil-water two-phase flow parameter measurement method realizes high-precision prediction of the water content of the oil well oil-water two-phase flow through the multivariate time sequence prediction model of the cross-dimension dependency. The multivariate time series prediction model based on the cross-dimension dependency comprises a dimension segmentation embedding module, a cross-time attention calculation module, a routing mechanism module, a cross-dimension attention calculation module and a feedforward neural network which are connected in sequence, and the dimension segmentation embedding module is used for performing patch segmentation, linear projection and patch enhancement in sequence. The cross-time attention calculation module is used for obtaining cross-time patch embedding features, the routing mechanism module is used for reducing calculation complexity, the cross-dimension attention calculation module is used for capturing potential association of different routers, and the feedforward neural network is used for outputting a water content prediction value of oil-water two-phase flow of an oil well.

Description

Technical Field

[0001] The present invention belongs to the field of dynamic monitoring of oil well exploitation, and specifically relates to a method for measuring oil-water two-phase flow parameters in an oil well based on a multivariate time series prediction model with cross-dimensional dependence. Background Art

[0002] Oil-water two-phase flow is widely present in the development and production process of oil fields, and is closely related to economic development and scientific and technological progress. Accurately measuring the parameters of oil-water two-phase flow, especially the precise measurement of water content, is crucial to improving mining efficiency and saving resources. In recent years, many methods for measuring water content have been developed, and the conductivity method and capacitance method are currently widely used. Conductivity sensors and capacitance sensors usually use low-frequency signals as excitation sources, which leads to a close relationship between the electric field distribution of the sensor and its structure, that is, the sensitivity is higher in the area near the electrode, but as the total flow rate of the two phases increases, the measurement resolution decreases. The microwave method has been widely studied and applied to the fields of oil-water two-phase flow phase content and flow parameter measurement due to its non-contact, sensitivity to water molecules, wide measurement range, and good reliability.

[0003] Due to the long-term water injection development of my country's oil fields, some oil wells show the production characteristics of low flow rate and high water content. The oil-water two-phase flow at low flow rate is affected by the slip effect, and the flow rate of the oil-water medium shows nonlinear characteristics and complex flow morphology, which increases the difficulty of measuring water content. Further in-depth research on the measurement of water content of oil-water two-phase flow in oil wells can optimize the production process of oil wells, reduce operating costs and efficiently manage oilfield resources, which is of great significance.

[0004] With the introduction of soft measurement methods, two-phase flow measurement technology has been greatly promoted, especially the continuous progress in the field of deep learning, which has further expanded the application of multiphase flow soft measurement models. Measuring the water content of oil-water two-phase flow with low flow rate and high water content is essentially a complex nonlinear solution process, so it is particularly necessary to introduce a neural network-based algorithm to solve this problem. Through soft measurement technology, the multi-dimensional data obtained by the sensor can be fused, so as to extract the characteristic information of the multiphase flow more accurately and efficiently. Summary of the invention

[0005] In view of the shortcomings of the prior art, an object of the present invention is to provide a multivariate time series prediction model with cross-dimensional dependence. Another object of the present invention is to provide a method for measuring oil-water two-phase flow parameters in oil wells based on the multivariate time series prediction model with cross-dimensional dependence.

[0006] The purpose of the present invention is achieved through the following technical solutions.

[0007] A multivariate time series prediction model based on cross-dimensional dependency, comprising: a dimensional segmentation embedding module, a cross-time attention calculation module, a routing mechanism module, a cross-dimensional attention calculation module and a feedforward neural network connected in sequence, wherein the input of the dimensional segmentation embedding module is a sample and the output is a patch embedding feature, and the dimensional segmentation embedding module is used to perform patch segmentation, linear projection and patch enhancement in sequence;

[0008] Among them, patch segmentation is to use the sliding window method to perform non-overlapping segmentation on the sample to obtain N = T / P patches of length P, and N patches form a vector array X, where T is the sample length, P is the patch length, and N is the number of patches;

[0009] Linear projection is to linearly project each patch in the vector array X into a unified feature space to obtain N transformed patches and form a vector array Y;

[0010] Patch enhancement is used to add position encoding to each transformed patch in the vector array Y, obtaining N patch embedding features and forming a vector array Z;

[0011] The samples include a normalized amplitude voltage signal and a normalized phase voltage signal. The normalized amplitude voltage signal is obtained by normalizing the amplitude voltage signal, and the normalized phase voltage signal is obtained by normalizing the phase voltage signal. The amplitude voltage signal and the phase voltage signal are obtained by collecting the oil-water two-phase fluid in the oil well in the same time period.

[0012] The input of the cross-temporal attention calculation module is the vector array Z, and the output is the vector array Z′. The cross-temporal attention calculation module uses the self-attention mechanism to perform attention calculation on the different patch embedding features in the vector array Z, obtains the cross-temporal patch embedding features and forms the vector array Z′;

[0013] The input of the routing mechanism module is the vector array Z′, and the output is three routers. The routing mechanism module selects the Sth cross-time patch embedding feature, the 2Sth cross-time patch embedding feature, and the 3Sth cross-time patch embedding feature in the vector array Z′, and uses each of the three cross-time patch embedding features selected by the routing mechanism module as a router;

[0014] The input of the cross-dimensional attention calculation module is three routers and a vector array Z′, and the output is three router features that form a vector array Z″. The cross-dimensional attention calculation module uses a self-attention mechanism to perform attention calculation on the three routers and the vector array Z′.

[0015] The input of the feedforward neural network is the vector array Z″, and the output is the predicted value of the water content of the oil-water two-phase flow in the oil well. The feedforward neural network includes: an input layer, a Dropout layer, a hidden layer, a Dropout layer, and an output layer.

[0016] In the above multivariate time series prediction model based on cross-dimensional dependency, N=30 and P=100.

[0017] In the above multivariate time series prediction model based on cross-dimensional dependency, the dimension of the vector array Z′ is 30×256.

[0018] In the above multivariate time series prediction model based on cross-dimensional dependency, the dimension of each router is 1×256, 1≤S <N。

[0019] In the above multivariate time series prediction model based on cross-dimensional dependency, the dimension of the vector array Z″ is 3×256.

[0020] In the above-mentioned multivariate time series prediction model based on cross-dimensional dependency, the number of neurons in the input layer of the feedforward neural network is 768, the number of neurons in the hidden layer is 128, the number of neurons in the output layer is 1, the discard rate of the Dropout layer is 0.2, and the activation function of the feedforward neural network is ReLU.

[0021] A method for measuring oil-water two-phase flow parameters in an oil well based on a multivariate time series prediction model with cross-dimensional dependencies, comprising:

[0022] The test set is input into the trained multivariate time series prediction model based on cross-dimensional dependency to obtain the moisture content prediction value corresponding to each sample in the test set.

[0023] In the above-mentioned oil-water two-phase flow parameter measurement method of an oil well, a method for obtaining a trained multivariate time series prediction model based on cross-dimensional dependency includes: inputting the training set into the multivariate time series prediction model based on cross-dimensional dependency for training, calculating the loss function value according to the water cut prediction value and the true value of the water cut, training each batch of samples of the training set, and after each training round, inputting the verification set into the multivariate time series prediction model based on cross-dimensional dependency for water cut prediction, and calculating whether the loss function value decreases: if the loss function value of the verification set does not improve within 10 consecutive rounds, the early stopping mechanism is triggered, the training is terminated, and the best performing parameters of the verification set are saved as the trained multivariate time series prediction model based on cross-dimensional dependency.

[0024] In the above-mentioned oil-water two-phase flow parameter measurement method of oil wells, the maximum training round is 200, the loss function value is the mean square error function, the initial learning rate is 0.0001, and the learning rate scheduling uses the cosine annealing scheduler.

[0025] The present invention has the following advantages due to the adoption of the above technical solution:

[0026] 1. The oil-water two-phase flow parameter measurement method of the oil well of the present invention constructs a multivariate time series prediction model based on cross-dimensional dependence according to the response rules of the amplitude voltage signal and phase voltage signal of the microwave sensor under different working conditions, thereby realizing the prediction of the water content of the oil-water two-phase flow in the oil well.

[0027] 2. The routing mechanism module in the multivariate time series prediction model of the present invention reduces the amount of calculation and greatly reduces the complexity.

[0028] 3. The multivariate time series prediction model of the present invention obtains aggregate information through a cross-time attention calculation module and a cross-dimensional attention calculation module, thereby improving the prediction accuracy of the multivariate time series prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a schematic diagram of the structure of the multivariate time series prediction model based on cross-dimensional dependency of the present invention. DETAILED DESCRIPTION

[0030] The method for measuring oil-water two-phase flow parameters in an oil well using a multivariate time series prediction model with cross-dimensional dependence of the present invention is described in detail below in conjunction with the accompanying drawings.

[0031] Example 1

[0032] like Figure 1 As shown, a multivariate time series prediction model based on cross-dimensional dependency includes: a dimensional segmented embedding module, a cross-time attention calculation module, a routing mechanism module, a cross-dimensional attention calculation module and a feedforward neural network connected in sequence, wherein the input of the dimensional segmented embedding module is a sample and the output is a patch embedding feature, and the dimensional segmented embedding module is used to perform patch segmentation, linear projection and patch enhancement in sequence, wherein the sample includes a normalized amplitude voltage signal and a normalized phase voltage signal, the normalized amplitude voltage signal is obtained after normalizing the amplitude voltage signal, the normalized phase voltage signal is obtained after normalizing the phase voltage signal, and the amplitude voltage signal and the phase voltage signal are obtained by collecting oil-water two-phase fluid in the oil well in the same time period.

[0033] Among them, patch segmentation is to use the sliding window method to perform non-overlapping segmentation on the sample, and obtain N = T / P patches of length P, N patches form a vector array X, T is the sample length;

[0034] Linear projection is to linearly project each patch in the vector array X into a unified feature space to obtain N transformed patches and form a vector array Y, where the dimension of the feature space is D, and in this embodiment D=256;

[0035] Patch enhancement is used to add positional encoding to each transformed patch in the vector array Y, that is, to provide information about the position of each transformed patch in the sample, obtaining N patch embedding features and forming a vector array Z. Each patch embedding feature retains the local dynamic changes of the sample and the temporal order information of the patch embedding feature;

[0036] Among them, the dimension of the sample is T×C, the sample length is T = 3000, the feature dimension C = 2, that is, two dimensions of the normalized phase voltage signal and the normalized amplitude voltage signal. The dimension of the vector array X is N×(C×P), N = 30 is the number of patches, P is the patch length, P = 100, the dimension of the vector array Y is 30×256, and the dimension of the vector array Z is 30×256.

[0037] The input of the cross - temporal attention calculation module is the vector array Z, and the output is the vector array Z'. The cross - temporal attention calculation module uses the self - attention mechanism (Vaswani A. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017.) to calculate the attention of different patch embedding features in the vector array Z, obtaining cross - temporal patch embedding features and forming the vector array Z'. The dimension of the vector array Z' is 30×D.

[0038] Among them, the cross - temporal attention calculation module is used to measure the correlation and weights between different patches, strengthen the transmission of time information, and capture the long - term dependence relationship in the sample. The cross - temporal attention calculation module effectively aggregates the time information of different patch embedding features through the self - attention mechanism, strengthens the long - term time - dependence features of different patch embedding features, and enables the multivariate time - series prediction model to better learn the dynamic changes and trends in the sample.

[0039] The input of the routing mechanism module is the vector array Z', and the output is three routers. The routing mechanism module is used to reduce the computational complexity. The routing mechanism module selects the S - th cross - temporal patch embedding feature, the 2S - th cross - temporal patch embedding feature, and the 3S - th cross - temporal patch embedding feature in the vector array Z', and makes each of the three selected cross - temporal patch embedding features serve as a router. The three routers are all learnable, and the dimension of each router is 1×256. The routing mechanism module reduces the computational complexity of the following cross - dimensional attention calculation module, where 1≤S < N. In this embodiment, S = 10.

[0040] The input of the cross-dimensional attention calculation module is three routers and a vector array Z′, and the output is three router features that form a vector array Z″. The cross-dimensional attention calculation module uses the self-attention mechanism (Vaswani A. Attention is all you need [J]. Advances in Neural Information Processing Systems, 2017.) to perform attention calculations on the three routers and the vector array Z′ to obtain three router features, so that each router feature contains independent features of each dimension and cross-dimensional interaction features. The vector array Z″ contains dynamic information between different time steps and interaction characteristics between dimensions. Among them, the dimension of the vector array Z″ is 3×256. The cross-dimensional attention calculation module aggregates the feature information of different routers through the self-attention mechanism, thereby capturing the potential associations between different routers. The router acts as an "information filter", allowing the cross-dimensional attention calculation module to adaptively focus on the most important features for the task in different dimensions and ignore irrelevant or redundant information.

[0041] The input of the feedforward neural network is a vector array Z″, and the output is a predicted value of the water content of the oil-water two-phase flow in the oil well. The feedforward neural network includes an input layer, a Dropout layer, a hidden layer, a Dropout layer, and an output layer connected in sequence, wherein the number of neurons in the input layer is 768, the number of neurons in the hidden layer is 128, and the number of neurons in the output layer is 1; the dropout rate of the Dropout layer is 0.2; the activation function of the feedforward neural network is ReLU (Agarap A F. Deep learning using rectified linear units (relu) [J]. arXiv preprint arXiv: 1803.08375, 2018.). Among them, the feedforward neural network is used to enhance the nonlinear modeling capability, the output layer is used to output the predicted value of the water content of the oil-water two-phase flow in the oil well, and the Dropout layer is used to prevent overfitting.

[0042] Example 2

[0043] A method for obtaining a fluid data set, comprising:

[0044] The amplitude voltage signal and the phase voltage signal are obtained by a microwave sensor installed in the oil well pipeline. The operating frequency of the microwave sensor is set to 1.2 GHz, wherein the microwave sensor can use a corresponding microwave sensor, for example, the microwave sensor can use the double-helix microwave sensor in CN202311628606.5.

[0045] The sampling frequency of the microwave sensor is 1 kHz. The amplitude voltage signal and the phase voltage signal within 1 hour are collected every 12 hours, and the amplitude voltage signal and the phase voltage signal within 12 hours in total are collected.

[0046] The amplitude voltage signal and the phase voltage signal within 12 hours are normalized to obtain the normalized amplitude voltage signal and the normalized phase voltage signal. The normalized amplitude voltage signal and the normalized phase voltage signal are segmented without overlap using a sliding window with a sliding window length of 3000. 14400 samples are obtained to form a fluid data set.

[0047] When the microwave sensor collects the amplitude voltage signal and the phase voltage signal, the oil-water two-phase flow of the oil well is manually sampled and manually tested, and the test value obtained is used as the true value of the water content corresponding to the sample, where the length of each sample in the fluid data set is T = 3000, the dimension of each sample is T × C, and the feature dimension C = 2, that is, the two dimensions of the normalized amplitude voltage signal and the normalized phase voltage signal;

[0048] The fluid dataset is divided into training set, validation set and test set in a ratio of 7:2:1.

[0049] Example 3

[0050] A training method for a multivariate time series prediction model based on cross-dimensional dependencies, comprising:

[0051] The training set in Example 2 is input into the multivariate time series prediction model based on cross-dimensional dependency in Example 1 for training, and the loss function value is calculated according to the prediction results. 200 rounds of training are performed on 32 samples in each batch of training sets. After each round of training, the verification set in Example 2 is input into the multivariate time series prediction model for moisture content prediction, and it is calculated whether the loss function value decreases: if the loss function value of the verification set does not improve within 10 consecutive rounds, the early stopping mechanism is triggered, the training is terminated, and the best performing parameters of the verification set are saved as the trained multivariate time series prediction model.

[0052] Among them, the loss function value is calculated using the mean square error function MSE.

[0053] The hyperparameters are set as follows: initial learning rate: 0.0001, learning rate scheduling: using cosine annealing scheduler (Liu Guoquan, Chen Shangliang, Li Yuezhong, et al. Improved YOLOv3 high-voltage power equipment target detection method based on SGD and cosine annealing algorithm [J]. Journal of East China University of Technology (Natural Science Edition), 2024, 47(03): 294-300.), and gradually reducing the learning rate according to the training rounds.

[0054] Example 4

[0055] A method for measuring oil-water two-phase flow parameters in an oil well based on a multivariate time series prediction model with cross-dimensional dependencies, comprising:

[0056] The test set in Example 2 is input into the multivariate time series prediction model based on cross-dimensional dependency trained in Example 3 to obtain the moisture content prediction value corresponding to each sample in the test set, and the mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and determination coefficient (R) are calculated. 2 , to comprehensively evaluate the performance of trained multivariate time series forecasting models based on cross-dimensional dependencies.

[0057] Example 5

[0058] A method for measuring the water content of oil-water two-phase flow in an oil well is basically the same as that of Example 4, with the only difference being that the patch length is set to 50.

[0059] Example 6

[0060] A method for measuring the water content of oil-water two-phase flow in an oil well is basically the same as that of Example 4, with the only difference being that the patch length is set to 300.

[0061] Example 7

[0062] A method for measuring the water content of oil-water two-phase flow in an oil well is basically the same as Example 4, with the only difference being that the routing mechanism module is deleted, the vector array Z′ output by the cross-time attention calculation module is used as the input of the feedforward neural network, and the number of neurons in the input layer of the feedforward neural network is replaced with 7680.

[0063] The mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient of determination (R) are used to calculate the 2 Four statistical indicators are used to evaluate the performance of the trained multivariate time series prediction model based on cross-dimensional dependencies. The results are as follows:

[0064] Table 1

[0065] Model MSE MAE MAPE R Example 7 0.00312 0.0655 3.09％ 92.9％ Example 6 0.00409 0.0583 2.65％ 94.3％ Example 5 0.00368 0.0687 5.29％ 90.5％ Example 4 0.00257 0.0416 1.63％ 96.6％

[0066] As can be seen from Table 1, the oil-water two-phase flow water cut measurement method of oil wells based on the multivariate time series prediction model of cross-dimensional dependency improves the reliability and accuracy of water cut prediction through the multivariate time series prediction model based on cross-dimensional dependency. The multivariate time series prediction model based on cross-dimensional dependency uses the cross-time attention calculation module and the cross-dimensional attention calculation module to efficiently obtain the two dependencies of cross-time and cross-dimensional, and introduces the routing mechanism module, which enhances the model's modeling ability for complex time series data, avoids excessive complexity, and reduces the amount of calculation.

[0067] The present invention is described above by way of example. It should be noted that, without departing from the core of the present invention, any simple deformation, modification or other equivalent replacement that can be made by those skilled in the art without inventive effort falls within the protection scope of the present invention.

Claims

1. A multivariate time series prediction model based on cross-dimensional dependencies, characterized in that: include: A dimensional segmentation embedding module, a cross-temporal attention calculation module, a routing mechanism module, a cross-dimensional attention calculation module and a feedforward neural network are connected in sequence, wherein the input of the dimensional segmentation embedding module is a sample and the output is a patch embedding feature, and the dimensional segmentation embedding module is used to perform patch segmentation, linear projection and patch enhancement in sequence; Among them, patch segmentation is to use the sliding window method to perform non-overlapping segmentation on the sample to obtain N = T / P patches of length P, and N patches form a vector array X, where T is the sample length, P is the patch length, and N is the number of patches; Linear projection is to linearly project each patch in the vector array X into a unified feature space to obtain N transformed patches and form a vector array Y; Patch enhancement is used to add position encoding to each transformed patch in the vector array Y, obtaining N patch embedding features and forming a vector array Z; The samples include a normalized amplitude voltage signal and a normalized phase voltage signal. The normalized amplitude voltage signal is obtained by normalizing the amplitude voltage signal, and the normalized phase voltage signal is obtained by normalizing the phase voltage signal. The amplitude voltage signal and the phase voltage signal are obtained by collecting the oil-water two-phase fluid in the oil well in the same time period. The input of the cross-temporal attention calculation module is the vector array Z, and the output is the vector array Z′. The cross-temporal attention calculation module uses the self-attention mechanism to perform attention calculation on the different patch embedding features in the vector array Z, obtains the cross-temporal patch embedding features and forms the vector array Z′; The input of the routing mechanism module is the vector array Z′, and the output is three routers. The routing mechanism module selects the Sth cross-time patch embedding feature, the 2Sth cross-time patch embedding feature, and the 3Sth cross-time patch embedding feature in the vector array Z′, and uses each of the three cross-time patch embedding features selected by the routing mechanism module as a router; The input of the cross-dimensional attention calculation module is three routers and a vector array Z′, and the output is three router features that form a vector array Z″. The cross-dimensional attention calculation module uses a self-attention mechanism to perform attention calculation on the three routers and the vector array Z′. The input of the feedforward neural network is the vector array Z″, and the output is the predicted value of the water content of the oil-water two-phase flow in the oil well. The feedforward neural network includes: an input layer, a Dropout layer, a hidden layer, a Dropout layer, and an output layer.

2. The multivariate time series prediction model according to claim 1, characterized in that: N=30, P=100.

3. The multivariate time series prediction model according to claim 1, characterized in that: The dimension of the vector array Z' is 30×256.

4. The multivariate time series prediction model according to claim 1, characterized in that: The dimension of each router is 1×256, 1≤S <N。 5. The multivariate time series prediction model according to claim 1, characterized in that: The dimension of the vector array Z″ is 3×256.

6. The multivariate time series prediction model according to claim 1, characterized in that: The number of neurons in the input layer of the feedforward neural network is 768, the number of neurons in the hidden layer is 128, the number of neurons in the output layer is 1, the discard rate of the Dropout layer is 0.2, and the activation function of the feedforward neural network is ReLU.

7. A method for measuring oil-water two-phase flow parameters in oil wells based on a multivariate time series prediction model with cross-dimensional dependence, characterized in that: include: The test set is input into the trained multivariate time series prediction model based on cross-dimensional dependency as described in any one of claims 1 to 6 to obtain the moisture content prediction value corresponding to each sample in the test set.

8. The method for measuring oil-water two-phase flow parameters in an oil well according to claim 7, characterized in that: The method for obtaining a trained multivariate time series prediction model based on cross-dimensional dependency includes: inputting a training set into the multivariate time series prediction model based on cross-dimensional dependency for training, calculating a loss function value according to a moisture content prediction value and a moisture content true value, training samples of each batch of training sets, and after each training round, inputting a validation set into the multivariate time series prediction model based on cross-dimensional dependency for moisture content prediction, and calculating whether the loss function value decreases: if the loss function value of the validation set does not improve within 10 consecutive rounds, an early stopping mechanism is triggered to terminate the training, and the best performing parameters of the validation set are saved as the trained multivariate time series prediction model based on cross-dimensional dependency.

9. The method for measuring oil-water two-phase flow parameters in an oil well according to claim 8, characterized in that: The maximum number of training rounds is 200, and the loss function value is the mean square error function.

10. The method for measuring oil-water two-phase flow parameters in an oil well according to claim 8, characterized in that: The initial learning rate is 0.0001, and the learning rate scheduler uses the cosine annealing scheduler.

Images