CN114386272A - Multi-working-condition bottom hole pressure prediction method and device, computer equipment and storage medium - Google Patents
Multi-working-condition bottom hole pressure prediction method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114386272A CN114386272A CN202210025698.7A CN202210025698A CN114386272A CN 114386272 A CN114386272 A CN 114386272A CN 202210025698 A CN202210025698 A CN 202210025698A CN 114386272 A CN114386272 A CN 114386272A
- Authority
- CN
- China
- Prior art keywords
- working condition
- bottom hole
- hole pressure
- historical
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Abstract
The invention relates to the field of oil and gas exploration, in particular to a multi-working-condition bottom hole pressure prediction method, a multi-working-condition bottom hole pressure prediction device, computer equipment and a storage medium. The method comprises the steps of obtaining real-time working conditions according to real-time logging data; determining a bottom hole pressure prediction model of the real-time working condition, wherein the bottom hole pressure prediction model of each working condition is obtained by training based on historical input characteristic data related to pressure of each working condition, historical bottom hole pressure data of each working condition and constraint conditions of each working condition, and the constraint conditions of each working condition are established according to the correlation between the historical input characteristic data of each working condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism; determining input characteristic data of the real-time working condition according to the real-time logging data; and inputting the input characteristic data of the real-time working condition into a bottom hole pressure prediction model of the real-time working condition, and predicting to obtain the bottom hole pressure.
Description
Technical Field
The invention relates to the field of oil and gas exploration, in particular to a multi-working-condition bottom hole pressure prediction method, a multi-working-condition bottom hole pressure prediction device, computer equipment and a storage medium.
Background
Along with the continuous deepening of oil and gas exploration and development, the oil and gas exploration and development gradually and rapidly extend to unconventional oil and gas resources such as deep layers, ultra-deep layers, low permeability and the like.
The existing shaft pressure prediction is based on an annular multi-phase flow mechanism model, the model complexity is high, the calculation time consumption is long, and the precision is insufficient under complex geological and engineering conditions, and on the other hand, the shaft bottom pressure is measured by an underground measuring device under the working environment of high temperature and high pressure, so that the measurement cost is high.
Most of the existing intelligent prediction models for wellbore pressure are machine learning or deep learning models which are built by directly combining an intelligent algorithm with a large amount of geological and engineering big data, the models are greatly influenced by the quality of training data, although the average accuracy of the prediction of the wellbore pressure can be improved to a certain degree, the fluctuation of the prediction result is large, the abnormal value is more, and the stability and the generalization performance of the models still need to be improved.
Aiming at the problems of large fluctuation of a shaft pressure prediction result and high measurement cost in the prior art, a multi-working-condition shaft bottom pressure prediction method is urgently needed to be researched.
Disclosure of Invention
To address the above-described problems of the prior art, embodiments herein provide a multi-regime bottom hole pressure prediction method. By adding a mechanism constraint method, the deep fusion of an algorithm and a mechanism can be realized, the prediction precision of the neural network model is ensured, meanwhile, the prediction result can better accord with the change mechanism of a prediction target, the abnormal value and the fluctuation value of the prediction result are reduced, and the stability and the generalization capability of the neural network model are effectively improved. And technical support and important reference are provided for efficient prediction and fine regulation of the bottom pressure under the deep high-temperature high-pressure drilling gas invasion condition.
Embodiments herein provide a multi-regime bottom hole pressure prediction method, comprising: acquiring real-time working conditions according to the real-time logging data; determining a bottom hole pressure prediction model of the real-time working condition, wherein the bottom hole pressure prediction model of each working condition is obtained by training based on historical input characteristic data related to pressure of each working condition, historical bottom hole pressure data of each working condition and constraint conditions of each working condition, and the constraint conditions of each working condition are established according to the correlation between the historical input characteristic data of each working condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism; determining input characteristic data of the real-time working condition according to the real-time logging data; and inputting the input characteristic data of the real-time working condition into a bottom hole pressure prediction model of the real-time working condition, and predicting to obtain the bottom hole pressure.
According to one aspect of the embodiments herein, the bottom hole pressure prediction model training process for each operating condition comprises: acquiring a historical sample data set of each working condition, wherein the historical sample data set of each working condition comprises a plurality of sample data, and each sample data comprises historical input characteristic data and historical bottom hole pressure data; establishing equality constraint conditions of all working conditions according to the annular air-liquid-solid three-phase flow mechanism; establishing inequality constraint conditions of all working conditions according to the correlation between the historical input characteristic data of all working conditions and the corresponding historical bottom hole pressure data; constructing a loss function of each working condition according to the historical sample data set of each working condition, the equality constraint condition and the inequality constraint condition of each working condition; and training parameters in the neural network model by using the loss function of each working condition, and taking the neural network model obtained by training each working condition as a bottom hole pressure prediction model of each working condition.
According to one aspect of embodiments herein, establishing an inequality constraint for each operating condition based on a correlation of historical input characteristic data for each operating condition with corresponding historical bottom hole pressure data comprises: for each working condition, calculating the correlation between each input characteristic data in the historical input characteristic data under the working condition and the historical bottom hole pressure data under the corresponding working condition; taking the input characteristic data with the correlation lower than a first preset threshold value as a non-sensitive parameter of the working condition, and taking the input characteristic data with the correlation higher than the first preset threshold value as a sensitive parameter of the working condition; and establishing an inequality constraint condition of the working condition according to the sensitive parameters and the non-sensitive parameters of the working condition.
According to an aspect of the embodiments herein, after determining the sensitive parameters under each operating condition, the method further includes: taking any two sensitive parameters under the working condition as a sensitive parameter group, and calculating the correlation of the sensitive parameters in each sensitive parameter group; screening out a sensitive parameter group with the correlation larger than a second preset threshold value; and deleting one sensitive parameter from each screened sensitive parameter group.
According to one aspect of embodiments herein, obtaining the historical bottom hole pressure data set for each operating condition comprises: estimating the bottom hole pressure range of each working condition according to an annular pressure calculation formula; and deleting the sample data which do not meet the bottom hole pressure range in the historical sample data set of each working condition.
According to one aspect of the embodiments herein, establishing an inequality constraint for each operating condition according to the sensitive parameter and the non-sensitive parameter of each operating condition comprises:
the inequality constraints are established using the following formula:
wherein x represents a sensitive parameter and a non-sensitive parameter of each working condition, P and F (x, w, b) both represent output bottom hole pressure expressions of the neural network model, w represents the weight of each layer in the neural network, and b represents the bias of each layer in the neural network.
According to one aspect of embodiments herein, establishing the equality constraints for each operating regime according to the toroidal air-liquid-solid three-phase flow mechanism comprises:
the equality constraints are established using the following formula:
so that A is Atheory(ii) a Wherein A istheoryThe method is characterized in that a momentum conservation equation in annular gas-liquid-solid flow mechanism is adopted, z represents the fixed point vertical depth of each working condition, and P and F (x, w, b) both represent bottom hole pressure expressions predicted by a neural network model; t represents time; m represents one of three components of gas, liquid and solid; rhomRepresents the density; alpha is alphamRepresents the average flow rate; vmRepresenting the volume fraction of gas, liquid, solid; cos θ represents the well angle; g represents the gravitational acceleration; ffThe friction force between the annulus and the drilling fluid is represented, w represents the weight of each layer in the neural network, and b represents the offset of each layer in the neural network.
Embodiments herein also provide a multi-regime bottom hole pressure prediction apparatus, comprising: the working condition acquisition unit is used for acquiring real-time working conditions according to the real-time logging data;
the bottom hole pressure prediction model determining unit is used for determining a bottom hole pressure prediction model of the real-time working condition, wherein the bottom hole pressure prediction model of each working condition is obtained by training based on historical input characteristic data related to pressure of each working condition, historical bottom hole pressure data of each working condition and constraint conditions of each working condition, and the constraint conditions of each working condition are established according to the correlation between the historical input characteristic data of each working condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism; and the bottom hole pressure prediction unit is used for inputting the input characteristics of the real-time working condition into the bottom hole pressure prediction model of the real-time working condition and predicting to obtain the bottom hole pressure.
Embodiments herein also provide a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the above-mentioned method when executing the computer program.
Embodiments herein also provide a computer-readable storage medium having stored thereon computer instructions, which when executed by a processor, implement the above-described method.
By utilizing the embodiment, the deep fusion of the algorithm and the mechanism can be realized by adding a mechanism constraint method, the prediction precision of the neural network model is ensured, meanwhile, the prediction result can better accord with the change mechanism of the prediction target, the abnormal value and the fluctuation value of the prediction result are reduced, and the stability and the generalization capability of the neural network model are effectively improved. And technical support and important reference are provided for efficient prediction and fine regulation of the bottom pressure under the deep high-temperature high-pressure drilling gas invasion condition.
Drawings
In order to more clearly illustrate the embodiments or technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating a multi-regime bottom hole pressure prediction method according to an embodiment of the disclosure;
FIG. 2 is a flow chart illustrating a method for training a bottom hole pressure prediction model for various operating conditions according to an embodiment of the present disclosure;
FIG. 3 is a flow chart illustrating a method for establishing inequality constraints according to an embodiment of the present disclosure;
FIG. 4 is a flow chart illustrating a method for processing sensitive parameters according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram illustrating a multi-regime bottom hole pressure prediction apparatus according to an embodiment of the disclosure;
FIG. 6 is a schematic diagram showing the detailed structure of the multi-condition bottom hole pressure prediction device;
FIG. 7 is a diagram illustrating a neural network model according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a computer device according to an embodiment of the present disclosure.
Description of the symbols of the drawings:
501. a working condition obtaining unit;
5011. a working condition identification rule determining module;
502. a bottom hole pressure prediction model determination unit;
5021. a historical sample data set acquisition module;
5022. a historical sample data set screening module;
5023. an equality constraint establishing module;
5024. an inequality constraint establishing module;
5025. a loss function establishing module;
503. an input feature data determination unit;
5031. a correlation calculation module;
5032. a sensitive parameter determination module;
5033. a non-sensitive parameter determination module;
5034. a sensitive parameter group screening module;
5035. a sensitive parameter deleting module;
504. a bottom hole pressure prediction unit;
802. a computer device;
804. a processor;
806. a memory;
808. a drive mechanism;
810. an input/output module;
812. an input device;
814. an output device;
816. a presentation device;
818. a graphical user interface;
820. a network interface;
822. a communication link;
824. a communication bus.
Detailed Description
In order to make the technical solutions in the present specification better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments, but not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments herein without making any creative effort, shall fall within the scope of protection.
It should be noted that the terms "first," "second," and the like in the description and claims herein and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments herein described are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or device.
The present specification provides method steps as described in the examples or flowcharts, but may include more or fewer steps based on routine or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual system or apparatus product executes, it can execute sequentially or in parallel according to the method shown in the embodiment or the figures.
It should be noted that the multi-operating-condition bottom hole pressure prediction method and device can be used in the field of oil and gas exploration, and the application field of the multi-operating-condition bottom hole pressure prediction method and device is not limited.
Fig. 1 is a flow chart of a multi-operating-mode bottom hole pressure prediction method according to an embodiment of the present disclosure, which specifically includes the following steps:
In some embodiments of the present description, logging data includes various types of parameters including well depth, sag, bit depth, bit sag, time on bit, weight on bit, catenary, rotational speed, torque, square in, hook position, hook speed, vertical pressure, casing pressure, pump stroke 1, pump stroke 2, pump stroke 3, total pit volume late time, mud spillage, inlet/outlet flow, inlet/outlet density, inlet/temperature, total hydrocarbons, H2S content, C1/C2 content, displacement volume, kick-up depth, and the like. The real-time logging data are obtained by measuring equipment such as a field logging instrument, an underground sensor and a broken drill measuring device. Different real-time logging data correspond to different real-time working conditions. The logging data of different working conditions may show different variation trends as the logging number changes with time or the drilling process progresses. For example, it exhibits an increasing trend with time, a decreasing trend with time, or a steady, no significant change with time, etc. Therefore, the real-time working condition can be determined according to the change condition of the real-time logging data. Specifically, according to theoretical analysis and actual field experience, change laws such as wellhead pressure, tubular column movement, hook load, drilling disk torque and the like under different working conditions are summarized, a recognition rule of drilling working conditions is formed, and a working condition recognition program is further formed. The operation condition recognition program can be described with reference to table 1.
TABLE 1 drilling Condition identification rules
Table 1 illustrates an identification rule of drilling conditions according to an embodiment of the present disclosure. Table 1 shows the correspondence between the operating conditions and the input characteristic data determined from the variation tendency of the input characteristic data under different operating conditions.
Table 1 shows 7 operating conditions, including drilling, tripping, reaming, backreaming, circulation, drilling, and stopping drilling, where the corresponding input characteristic data includes: suspended weight, weight on bit, rotational speed, torque, pump pressure, bit depth variation, well depth variation, etc. Wherein, the numbers >0 and <0 in the table represent the variation trend of the input characteristic data. For example, under drilling conditions, a catenary weight >0 indicates that under such conditions, the catenary weight exhibits an increasing trend. For example, under the back-reaming condition, the data corresponding to the bit depth variable is <0, which indicates that under the condition, the bit depth variable shows a decreasing trend. For another example, in the drill stop condition, the data corresponding to the bit pressure is 0, which means that the bit pressure is substantially unchanged in the drill stop condition.
Based on the change trend of the input characteristic data and a large amount of change trends under different working conditions, the identification rule of each working condition can be formed. According to the change trend of the plurality of input characteristic data, the working condition corresponding to the current input characteristic data can be judged, so that the working condition identification is realized.
In practical application, real-time logging data obtained by field real-time measurement is input into a determined working condition identification program, and a corresponding real-time working condition can be determined. In some embodiments of the present disclosure, a real-time working condition corresponding to a plurality of real-time logging data, such as a hanging weight, a weight on bit, a rotation speed, a torque, a pump pressure, a bit depth variable, a well depth variable, and the like, may be determined as a drilling working condition according to a condition that the real-time logging data shows an increasing trend along with an increase of time.
And 102, determining a bottom hole pressure prediction model of the real-time working condition, wherein the bottom hole pressure prediction model of each working condition is obtained by training based on historical input characteristic data related to pressure of each working condition, historical bottom hole pressure data of each working condition and constraint conditions of each working condition, and the constraint conditions of each working condition are established according to the correlation between the historical input characteristic data of each working condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism.
In some embodiments of the present description, different operating conditions have respective bottom hole pressure prediction models, and the bottom hole pressure prediction models for each operating condition are stored in a database. When step 102 is implemented, according to the implementation working condition determined in step 101, a bottom hole pressure prediction model corresponding to the real-time working condition is searched from a database.
The logging data of each working condition comprises historical input characteristic data and historical bottom hole pressure data related to pressure, and after the data in the logging data are screened, a bottom hole pressure prediction model of each working condition can be obtained through training further according to the constraint conditions of each working condition. Wherein, the initial model of the bottom hole pressure prediction model is a neural network model.
The constraint conditions of all working conditions comprise equality constraint conditions and inequality constraint conditions, and parameters of the model are constrained in the model training process according to the change rule of the logging data along with the drilling process. The inequality constraint is established according to the correlation between historical input characteristic data and historical bottom hole pressure data of all working conditions, and the equality constraint is established according to an annular air-liquid-solid three-phase flow mechanism.
And 103, determining input characteristic data of the real-time working condition according to the real-time logging data.
In this step, noise may exist in the real-time logging data acquired in real time by using the measurement devices such as the downhole sensor, that is, errors may exist in the acquired real-time logging data of each working condition. After the historical log data is filtered, historical input characteristic data related to pressure in each working condition can be determined, as shown in step 201. Similarly, after the logging data is screened, the historical input characteristics related to the real-time working condition and the pressure can be determined. The real-time logging data is specifically screened in step 201.
And 104, inputting the input characteristic data of the real-time working condition into a bottom hole pressure prediction model of the real-time working condition, and predicting to obtain bottom hole pressure. Each real-time operating condition corresponds to a respective bottom hole pressure prediction model, and the method for training the bottom hole pressure prediction model is described in detail in figure 2. By adding a mechanism constraint method, the method can realize deep fusion of an algorithm and a mechanism, ensure the prediction precision of the neural network model, enable the prediction result to better conform to the change mechanism of the prediction target, reduce the abnormal value and fluctuation value of the prediction result, and effectively improve the stability and generalization capability of the neural network model.
FIG. 2 is a flow chart of a method for training a bottom hole pressure prediction model for various operating conditions according to an embodiment of the present disclosure. The method specifically comprises the following steps:
Taking the drilling condition as an example, the historical sample data set of the drilling condition comprises a plurality of historical input characteristic data and corresponding historical bottom hole pressure data. Wherein the historical input feature data comprises: historical input characteristic data such as fixed point vertical depth, drilling fluid discharge capacity, drilling fluid density, return pressure pump flow, funnel viscosity, drill bit depth, rotating speed, vertical pressure, outlet flow, outlet density, sand content and the like, and the historical bottom hole pressure data of the drilling working condition is bottom hole pressure values corresponding to the historical input characteristic data.
In some further embodiments of the present description, the operating conditions include, but are not limited to: the method comprises the following working conditions of sand washing and well washing, overflow well killing, back reaming, drill stopping, drill pulling, drill running and the like.
As described above, the historical bottom hole pressure data obtained by using the measurement device such as the downhole sensor may have noise corresponding to each working condition, that is, the historical bottom hole pressure data of each working condition may have an error. Thus, in some further embodiments of the present description, after obtaining the historical bottom hole pressure data set for each operating condition, the method further comprises: estimating the bottom hole pressure range of each working condition according to an annular pressure calculation formula; and deleting the sample data which do not meet the bottom hole pressure range in the historical sample data set of each working condition. Wherein sample data not satisfying the bottom hole pressure range comprises: the historical input feature data set historical bottom hole pressure data. This step may be considered as data processing of the historical bottom hole pressure data set. After the approximate bottom hole pressure range of each working condition is estimated according to the annular pressure calculation formula, historical bottom hole pressure data which do not meet the bottom hole pressure range in the historical sample data set can be deleted according to the bottom hole pressure range estimated by the annular pressure calculation formula, and historical input characteristic data which do not meet the bottom hole pressure range can also be deleted.
In the step, the annular gas-liquid-solid three-phase flow mechanism represents the flow rule of gas, liquid and solid in the well bore annular space. In a drilling scene, a gas-liquid-solid coexisting state is underground. Wherein the gas includes, but is not limited to, air, natural gas from a formation, etc.; liquids include, but are not limited to, formation fluids, petroleum, drilling fluids, and the like; solids include, but are not limited to, drilling fluid solids particles, rock debris, and the like. Furthermore, the annular gas-liquid-solid three-phase flow mechanism comprises equations such as a mass conservation equation and a mass conservation equation. The momentum conservation equation has the partial derivative of input characteristic data of bottom hole pressure to fixed point vertical depth, so that the equation is carried out on each working condition according to the formula in the annular air-liquid-solid three-phase flow mechanism. Specifically, the neural network is used for predicting the bottom hole pressure, a deviation equation of the bottom hole pressure and the well depth predicted by the neural network is obtained, then a momentum conservation equation in the annular air-liquid-solid three-phase flow mechanism is used for solving the deviation equation of the well depth, and the two equations are made to be the same, so that equation constraint on each working condition is realized.
Specifically, the equality constraint is established using the following formula:
so that A is Atheory(ii) a Wherein A istheoryThe method is characterized in that a momentum conservation equation in annular gas-liquid-solid flow mechanism is adopted, z represents the fixed point vertical depth of each working condition, and P and F (x, w, b) both represent bottom hole pressure expressions predicted by a neural network; t represents time; m represents one of three components of gas, liquid and solid; rhomRepresents the density; alpha is alphamRepresents the average flow rate; vmRepresenting the volume fraction of gas, liquid, solid; cos θ represents the well angle; g represents the gravitational acceleration; ffThe friction force between the annulus and the drilling fluid is represented, w represents the weight of each layer in the neural network, and b represents the offset of each layer in the neural network.
As previously described, P is the downhole pressure expression predicted by the neural network. Conservation of momentum in three-phase flow mechanics by using annular air-liquid-solidtheoryCarrying out equality constraint on the bottom hole pressure expression predicted by the neural network and the deviation derivative (formula A) of the bottom hole pressure to the well depth, and enabling the formulas A and AtheoryAre equal. And further establishing equality constraint conditions of all working conditions. Further variation of the above equation yields:
and step 203, establishing inequality constraint conditions of all working conditions according to the correlation between the historical input characteristic data of all working conditions and the corresponding historical bottom hole pressure data. In some embodiments of the present description, the historical input characteristic data for each operating condition has some correlation with its historical bottom hole pressure data. Specifically, when a part of the historical input characteristic data changes, the bottom hole pressure also changes, so that the historical input characteristic data has a certain correlation with the corresponding historical bottom hole pressure data. Different historical input characteristic data have different correlations with historical bottom hole pressure data. For example, variations in the drilling fluid displacement from the historical input signature data during drilling conditions may cause large variations in the bottom hole pressure, and variations in the depth of the drill bit from the historical input signature data may cause small variations in the bottom hole pressure.
The changing relationship of the historical characteristic input data to the historical bottom hole pressure data can be mathematically expressed as a bottom hole pressure to historical input characteristic data partial derivative of greater than 0. The description of establishing inequality constraints based on the correlation of historical input characteristic data and historical bottom hole pressure data for each operating condition is described below and in detail in FIG. 3.
And 204, constructing a loss function of each working condition according to the historical sample data set of each working condition, the equality constraint condition and the inequality constraint condition of each working condition.
In some embodiments, the loss function for each condition is used to evaluate the difference between the predicted value of the bottom hole pressure for the bottom hole pressure prediction model being trained and the actual value of the bottom hole pressure actually measured by the measurement device. The bottom hole pressure prediction value of the bottom hole pressure prediction model is obtained by inputting historical input characteristic data of all working conditions into a neural network. The model training ends when the loss function of the trained bottom hole pressure prediction model is minimized.
In this step, the loss function for each condition includes: the difference between the predicted value of the neural network model to the bottom hole pressure and the true value of the bottom hole pressure, the difference between the predicted value of the neural network model to the bottom hole pressure and the momentum conservation equation, inequality constraint conditions, and the loss function are related to the weight and the bias of the neural network and penalty factors of the inequality constraint conditions. And continuously adjusting the weight, bias and penalty factors of the loss function through model training until the loss function obtains the minimum value.
In some embodiments of the present description, the bottom hole pressure prediction model is an equality, inequality under dual constraints, when an equality constraint based on a toroidal air-liquid-solid three-phase flow mechanism is applied to the model simultaneously with an inequality constraint based on a correlation of historical characteristic input data and bottom hole pressure data. Constructing the objective function and the constraint as a penalty using a penalty function methodA function to convert a constrained nonlinear programming problem to an unconstrained nonlinear programming problem. The following formula is a difference expression between the predicted value of the bottom hole pressure and the true value of the bottom hole pressure by the neural network:
wherein P ispreBottom hole pressure value, P, representing neural network model predictiontrueRepresenting the actual measured bottom hole pressure value. For example, the inequality constraint is established using 1 sensitive parameter and 3 non-sensitive parameters, so the inequality constraint condition includes 4 inequality constraint equations. Considering that the action strengths of the 4 inequality constraints on the final bottom hole pressure prediction result are different, in addition to calculating the weight and the bias of the neural network by using the particle swarm algorithm, 4 penalty factors of the inequality constraints need to be solved, so that the model has different responses when facing the constraints of different degrees. Wherein, the corresponding function is as follows:
wherein λ is1，λ2，λ3，λ4I.e. 4 penalty factors for the inequality constraint. And solving the weight, the bias and the penalty factor lambda of the constraint condition of the neural network by using a particle swarm algorithm, and further determining a loss function.
And step 205, training parameters in the neural network model by using the loss function of each working condition, and taking the neural network model obtained by training each working condition as a bottom hole pressure prediction model of each working condition. After solving the weight and bias of the neural network and the penalty factor in the objective function, the intelligent prediction model of the bottom hole pressure is successfully solved and established, and the intelligent prediction method of the bottom hole pressure under the mechanism constraint is formed.
In some embodiments of the present description, real-time logging data is judged in real time according to a working condition identification rule, drilling working conditions corresponding to the number of real-time logs are distinguished, different constraint conditions are selected for different drilling working conditions according to the constraint conditions, so that a constrained neural network is established and solved, and a bottom hole pressure prediction model for different working conditions can be obtained.
Fig. 3 is a flow chart illustrating a method for establishing inequality constraints according to an embodiment of the present disclosure. The method specifically comprises the following steps:
For example, taking a drilling condition as an example, setting a first preset threshold value to be 0.5, and taking input characteristic data (such as rotating speed, sand content, vertical pressure and the like) with correlation lower than 0.5 as non-sensitive parameters of the drilling condition; and taking input characteristic data (such as drilling fluid density, drilling fluid discharge capacity, drill bit depth and the like) with the correlation higher than 0.5 as sensitive parameters of the drilling working condition. The first preset threshold value can be preset, and can also be adjusted on site according to the real-time logging data and the real-time working condition. The present application does not limit the value of the first predetermined threshold.
In some embodiments of the present description, establishing inequality constraints for the operating conditions includes: the inequality constraints are established using the following formula:
In this step, in some embodiments of the present description, F (x, w, b) may be represented as:
wherein f is1For the first activation function in the neural network model, f2For the second activation function in the neural network model, f3As a third activation function in the neural network model, w[1]Weights, w, representing the first layer of the neural network[2]Weight, w, representing the second layer of the neural network[3]Representing weights of the third layer of the neural network, b[1]Representing the bias of the first layer of the neural network, b[2]Representing the bias of the second layer of the neural network, b[3]Representing the bias of the third layer of the neural network. In order to ensure the regression performance of the neural network model, in the embodiment of the present specification, a 4-layer neural network is provided, which includes: 1 input layer, 2 hidden layers and 1 output layer. Wherein the activation function from the input layer to the 1 st hidden layer is f1(Relu), the activation function between the 1 st hidden layer and the 2 nd hidden layer is f2(Relu), the almost function between the 2 nd hidden layer to the output layer is f3(Linear). Fig. 7 is a schematic structural diagram of a neural network model according to an embodiment of the present disclosure. The number of neurons in the hidden layer is reasonably set by a grid search method, so that the prediction accuracy of the model is ensured, overfitting of the model is avoided, and the neural network model with the topological structure as shown in the figure of 12-32-16-1 is established. In the figure, wij [k]Representing a weight coefficient between the ith neuron of the kth layer and the jth neuron of the previous layer; zi [k]A value representing that the ith neuron of the kth layer has not undergone an activation function; f. ofi(x) Representing an activation function; a. thei [k]Represents the value of the ith neuron of the k layer after the activation function.
Through calculation of the neural network, the mathematical expression P, F (x, w, b) ═ F of the neural network of the bottom hole pressure can be obtained3(w[3]×f2(w[2]×f1(w[1]×X+b[1])+b[2])+b[3]). Therefore, the training process of the neural network becomes a constrained nonlinear programming solving problem, namely, the optimal network weight and bias are found, so that the objective function is realized
And minimum. In other embodiments of the present disclosure, the number of layers of the neural network may be 3, 5, or any other number of layers, and correspondingly, the number of activation functions in the neural network may be 2, 4, or any other number, and the number of layers of the neural network and the number of activation functions are not limited herein. Therefore, the specific representation of F (x, w, b) is not limited.
Fig. 4 is a flow chart illustrating a method for processing sensitive parameters according to an embodiment of the present disclosure.
At least one sensitive parameter may be determined based on the correlation of the historical input characteristic data with the bottom hole pressure, as depicted at step 302. When more than two sensitive parameters under a certain working condition are obtained, any two sensitive parameters are used as a group, and the correlation between the two sensitive parameters in the group is calculated. For example, the sensitive parameters of the drilling condition obtained in step 302 include drilling fluid density, drilling fluid displacement, and drill bit depth. The correlation between two sensitive parameters of the drilling fluid density and the drilling fluid discharge can be calculated by taking the drilling fluid density and the drilling fluid discharge as a group.
And step 402, screening out a sensitive parameter group with the correlation larger than a second preset threshold value.
In this step, by screening the set of two sensitive parameters for sensitive parameters, if the correlation between the two sensitive parameters is greater than a second preset threshold, it can be considered that the two sensitive parameters may have a similar effect on the bottom hole pressure. For example, setting the second preset threshold value to 0.9, the correlation between the drilling fluid density and the drilling fluid displacement in the group of sensitive parameters calculated in step 401 is 0.95, and the second preset threshold value is exceeded. The effect of drilling fluid density and drilling fluid displacement on bottom hole pressure is therefore considered to be the same. For another example, if the correlation between the drilling fluid density and the bit depth calculated in step 401 is 0.6, then the drilling fluid density and the bit depth are considered to have different effects on the bottom hole pressure. The second preset threshold value can be preset and can also be adjusted according to the real-time situation on site.
In step 403, one of the sensitive parameters is deleted from each of the screened sets of sensitive parameters.
When the correlation between the two sensitive parameters in each sensitive parameter set is greater than the second preset threshold, that is, the two sensitive parameters have the same influence with the bottom hole pressure. Any one sensitive parameter in the set of sensitive parameters is deleted and the remaining one sensitive parameter is retained. Based on the above, in the subsequent steps, the inequality constraint is established by using the remaining sensitive parameter, and further model training is performed, so that redundant data can be reduced, the calculated amount of model training is reduced, and the model training efficiency is improved.
Fig. 5 is a schematic structural diagram of a multi-condition bottom hole pressure prediction apparatus according to an embodiment of the present disclosure, and this diagram describes a basic structure of the multi-condition bottom hole pressure prediction apparatus, where functional units and modules may be implemented in a software manner, or implemented by a general chip or a specific chip, and the apparatus specifically includes:
a working condition obtaining unit 501, configured to obtain a real-time working condition according to the real-time logging data;
a bottom hole pressure prediction model determining unit 502, configured to determine a bottom hole pressure prediction model associated with the real-time operating condition, where the bottom hole pressure prediction model associated with each operating condition is obtained by training based on historical input characteristic data related to each operating condition and pressure, historical bottom hole pressure data of each operating condition, and constraint conditions of each operating condition, where the constraint conditions of each operating condition are established according to a correlation between the historical input characteristic data of each operating condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism;
an input characteristic data determining unit 503, configured to determine input characteristic data of the real-time working condition according to the real-time logging data;
and a bottom hole pressure prediction unit 504, configured to input the input characteristic of the real-time operating condition into a bottom hole pressure prediction model of the real-time operating condition, and predict to obtain a bottom hole pressure.
By adding mechanism constraint, the device can realize deep fusion of algorithm and mechanism, ensure the prediction precision of the neural network model, simultaneously ensure that the prediction result more conforms to the change mechanism of the prediction target, reduce the abnormal value and fluctuation value of the prediction result, and effectively improve the stability and generalization capability of the neural network model. And technical support and important reference are provided for efficient prediction and fine regulation of the bottom pressure under the deep high-temperature high-pressure drilling gas invasion condition.
As an embodiment herein, referring to a specific structural diagram of a multi-operating-condition bottom hole pressure prediction apparatus as shown in fig. 6, the operating condition obtaining unit 501 is further configured to determine an operating condition identification rule.
As an embodiment herein, the operating condition obtaining unit 501 further includes:
and the working condition identification rule determining module 5011 is used for determining a working condition identification rule according to the logging data.
As an embodiment herein, the bottom hole pressure prediction model determining unit 502 is further configured to obtain historical sample data sets of each operating condition, and establish an equality constraint condition of each operating condition according to a circular air-liquid-solid three-phase flow mechanism; and establishing inequality constraint conditions and loss functions of all working conditions according to the correlation between the historical input characteristic data of all working conditions and the corresponding historical bottom hole pressure data. The bottom hole pressure prediction model determination unit 502 further includes:
a historical sample data set obtaining module 5021, configured to obtain historical sample data sets of various operating conditions;
the historical sample data set screening module 5022 is used for deleting partial sample data according to an annular pressure calculation formula;
the equation constraint establishing module 5023 is used for establishing equal-input constraint conditions according to a circular air-liquid-solid three-phase flow mechanism;
the inequality constraint establishing module 5024 is used for establishing inequality constraints according to the correlation between the historical input characteristic data of all working conditions and the historical bottom hole pressure data;
a loss function building module 5025 is used to build the loss function.
As an embodiment herein, the input feature data determination unit 503 further includes:
a correlation calculation module 5031 for calculating a correlation of the historical input signature data with the bottom hole pressure data;
a sensitive parameter determining module 5032, configured to use data with a correlation greater than a first preset threshold as a sensitive parameter;
a non-sensitive parameter determining module 5033, configured to use data with a correlation smaller than a first preset threshold as a non-sensitive parameter;
a sensitive parameter group screening module 5034, configured to screen out a sensitive parameter group whose correlation is greater than a second preset threshold;
a sensitive parameter deleting module 5035, configured to delete one of the screened sets of sensitive parameters.
As shown in fig. 8, for a computer device provided for embodiments herein, the computer device 802 may include one or more processors 804, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The computer device 802 may also include any memory 806 for storing any kind of information, such as code, settings, data, etc. For example, and without limitation, memory 806 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may use any technology to store information. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 802. In one case, when the processor 804 executes the associated instructions, which are stored in any memory or combination of memories, the computer device 802 can perform any of the operations of the associated instructions. The computer device 802 also includes one or more drive mechanisms 808, such as a hard disk drive mechanism, an optical disk drive mechanism, etc., for interacting with any memory.
Corresponding to the methods in fig. 1-4, the embodiments herein also provide a computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, performs the steps of the above-described method.
Embodiments herein also provide computer readable instructions, wherein when executed by a processor, a program thereof causes the processor to perform the method as shown in fig. 1-4.
It should be understood that, in various embodiments herein, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments herein.
It should also be understood that, in the embodiments herein, the term "and/or" is only one kind of association relation describing an associated object, meaning that three kinds of relations may exist. For example, a and/or B, may represent: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided herein, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments herein.
In addition, functional units in the embodiments herein may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present invention may be implemented in a form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The principles and embodiments of this document are explained herein using specific examples, which are presented only to aid in understanding the methods and their core concepts; meanwhile, for the general technical personnel in the field, according to the idea of this document, there may be changes in the concrete implementation and the application scope, in summary, this description should not be understood as the limitation of this document.
Claims (10)
1. A method of multi-regime bottom hole pressure prediction, the method comprising:
acquiring real-time working conditions according to the real-time logging data;
determining a bottom hole pressure prediction model of the real-time working condition, wherein the bottom hole pressure prediction model of each working condition is obtained by training based on historical input characteristic data related to pressure of each working condition, historical bottom hole pressure data of each working condition and constraint conditions of each working condition, and the constraint conditions of each working condition are established according to the correlation between the historical input characteristic data of each working condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism;
determining input characteristic data of the real-time working condition according to the real-time logging data;
and inputting the input characteristic data of the real-time working condition into a bottom hole pressure prediction model of the real-time working condition, and predicting to obtain the bottom hole pressure.
2. The multi-regime bottom hole pressure prediction method of claim 1, wherein the bottom hole pressure prediction model training process for each regime comprises:
acquiring a historical sample data set of each working condition, wherein the historical sample data set of each working condition comprises a plurality of sample data, and each sample data comprises historical input characteristic data and historical bottom hole pressure data;
establishing equality constraint conditions of all working conditions according to the annular air-liquid-solid three-phase flow mechanism;
establishing inequality constraint conditions of all working conditions according to the correlation between the historical input characteristic data of all working conditions and the corresponding historical bottom hole pressure data;
constructing a loss function of each working condition according to the historical sample data set of each working condition, the equality constraint condition and the inequality constraint condition of each working condition;
and training parameters in the neural network model by using the loss function of each working condition, and taking the neural network model obtained by training each working condition as a bottom hole pressure prediction model of each working condition.
3. The method of claim 2, wherein establishing an inequality constraint for each operating condition based on a correlation of historical input characteristic data for each operating condition with corresponding historical bottom hole pressure data comprises:
for each working condition, calculating the correlation between each input characteristic data in the historical input characteristic data under the working condition and the historical bottom hole pressure data under the corresponding working condition;
taking the input characteristic data with the correlation lower than a first preset threshold value as a non-sensitive parameter of the working condition, and taking the input characteristic data with the correlation higher than the first preset threshold value as a sensitive parameter of the working condition;
and establishing an inequality constraint condition of the working condition according to the sensitive parameters and the non-sensitive parameters of the working condition.
4. The multi-regime bottom hole pressure prediction method of claim 3, wherein for each regime after determining the sensitive parameters for that regime, further comprising:
taking any two sensitive parameters under the working condition as a sensitive parameter group, and calculating the correlation of the sensitive parameters in each sensitive parameter group;
screening out a sensitive parameter group with the correlation larger than a second preset threshold value;
and deleting one sensitive parameter from each screened sensitive parameter group.
5. The multi-regime bottom hole pressure prediction method of claim 2, wherein obtaining the historical bottom hole pressure data set for each regime comprises:
estimating the bottom hole pressure range of each working condition according to an annular pressure calculation formula;
and deleting the sample data which do not meet the bottom hole pressure range in the historical sample data set of each working condition.
6. The method of claim 3, wherein establishing the inequality constraints for each operating condition based on the sensitive parameters and the non-sensitive parameters for each operating condition comprises:
the inequality constraints are established using the following formula:
wherein x represents a sensitive parameter and a non-sensitive parameter of each working condition, P and F (x, w, b) both represent bottom hole pressure expressions output by the neural network model, w represents the weight of each layer in the neural network, and b represents the bias of each layer in the neural network.
7. The method of claim 2, wherein establishing the equality constraints for each operating regime based on the annular air-liquid-solid three-phase flow mechanism comprises:
the equality constraints are established using the following formula:
so that A is Atheory(ii) a Wherein A istheoryThe method is characterized in that a momentum conservation equation in annular gas-liquid-solid flow mechanism is adopted, z represents the fixed point vertical depth of each working condition, and P and F (x, w, b) both represent bottom hole pressure expressions predicted by a neural network; t represents time; m represents one of three components of gas, liquid and solid; rhomRepresents the density; alpha is alphamRepresents the average flow rate; vmRepresenting the volume fraction of gas, liquid, solid; cos θ represents the well angle; g represents the gravitational acceleration; ffThe friction force between the annulus and the drilling fluid is represented, w represents the weight of each layer in the neural network, and b represents the offset of each layer in the neural network.
8. A multi-regime bottom hole pressure prediction apparatus, the apparatus comprising:
the working condition acquisition unit is used for acquiring real-time working conditions according to the real-time logging data;
the bottom hole pressure prediction model determining unit is used for determining a bottom hole pressure prediction model of the real-time working condition, wherein the bottom hole pressure prediction model of each working condition is obtained by training based on historical input characteristic data related to each working condition and pressure, historical bottom hole pressure data of each working condition and constraint conditions of each working condition, and the constraint conditions of each working condition are established according to the response relation between the historical input characteristic data of each working condition and the historical bottom hole pressure data and/or an annular gas-liquid-solid three-phase flow mechanism;
the input characteristic data determining unit is used for determining the input characteristic data of the real-time working condition according to the real-time logging data;
and the bottom hole pressure prediction unit is used for inputting the input characteristics of the real-time working condition into the bottom hole pressure prediction model of the real-time working condition and predicting to obtain the bottom hole pressure.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1-7 when executing the computer program.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210025698.7A CN114386272A (en) | 2022-01-11 | 2022-01-11 | Multi-working-condition bottom hole pressure prediction method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210025698.7A CN114386272A (en) | 2022-01-11 | 2022-01-11 | Multi-working-condition bottom hole pressure prediction method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114386272A true CN114386272A (en) | 2022-04-22 |
Family
ID=81201626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210025698.7A Pending CN114386272A (en) | 2022-01-11 | 2022-01-11 | Multi-working-condition bottom hole pressure prediction method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114386272A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114775611A (en) * | 2022-04-24 | 2022-07-22 | 贵州强胜基础工程技术有限公司 | Construction method for sediment treatment and reinforcement of building pile foundation bottom |
-
2022
- 2022-01-11 CN CN202210025698.7A patent/CN114386272A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114775611A (en) * | 2022-04-24 | 2022-07-22 | 贵州强胜基础工程技术有限公司 | Construction method for sediment treatment and reinforcement of building pile foundation bottom |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2007211294B2 (en) | Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator | |
| CA2640725C (en) | Methods, systems, and computer-readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| Bello et al. | Application of artificial intelligence methods in drilling system design and operations: a review of the state of the art | |
| EP2912493B1 (en) | System and method for well data analysis | |
| US8504341B2 (en) | Methods, systems, and computer readable media for fast updating of oil and gas field production models with physical and proxy simulators | |
| US8229880B2 (en) | Evaluation of acid fracturing treatments in an oilfield | |
| Abdelgawad et al. | New approach to evaluate the equivalent circulating density (ECD) using artificial intelligence techniques | |
| US10282496B2 (en) | Graph partitioning to distribute wells in parallel reservoir simulation | |
| Fruhwirth et al. | Hybrid simulation using neural networks to predict drilling hydraulics in real time | |
| Zanjani et al. | Data-driven hydrocarbon production forecasting using machine learning techniques | |
| CN114386272A (en) | Multi-working-condition bottom hole pressure prediction method and device, computer equipment and storage medium | |
| Løken et al. | Data-driven approaches tests on a laboratory drilling system | |
| US20180004234A1 (en) | Fuzzy logic flow regime identification and control | |
| Mendez et al. | Applications of Machine Learning Methods to Predict Hole Cleaning in Horizontal and Highly Deviated Wells | |
| US11803678B2 (en) | Disentanglement for inference on seismic data and generation of seismic data | |
| Aljubran et al. | Surrogate-Based Prediction and Optimization of Multilateral Inflow Control Valve Flow Performance with Production Data | |
| CN116362143B (en) | Drill string friction analysis method and device | |
| Thabet et al. | Application of Machine Learning and Deep Learning to Predict Production Rate of Sucker Rod Pump Wells | |
| Serapião et al. | Classification of petroleum well drilling operations with a hybrid particle swarm/ant colony algorithm | |
| WO2024030598A1 (en) | Optimal bottom hole assembly configuration | |
| WO2024044111A1 (en) | Method and system for generating predictive logic and query reasoning in knowledge graphs for petroleum systems | |
| MX2008009776A (en) | Methods, systems, and computer-readable media for real-time oil and gas field production optimization using a proxy simulator |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |