CN115874993A - Shale gas well production control method, equipment and system based on artificial intelligence - Google Patents
Shale gas well production control method, equipment and system based on artificial intelligence Download PDFInfo
- Publication number
- CN115874993A CN115874993A CN202310138674.7A CN202310138674A CN115874993A CN 115874993 A CN115874993 A CN 115874993A CN 202310138674 A CN202310138674 A CN 202310138674A CN 115874993 A CN115874993 A CN 115874993A
- Authority
- CN
- China
- Prior art keywords
- shale gas
- yield
- dynamic
- production control
- production
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000000195 production control method Methods 0.000 title claims abstract description 14
- 238000004519 manufacturing process Methods 0.000 claims abstract description 97
- 230000002159 abnormal effect Effects 0.000 claims abstract description 69
- 239000004576 sand Substances 0.000 claims abstract description 14
- 230000003068 static effect Effects 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 27
- 238000013145 classification model Methods 0.000 claims description 17
- 238000012806 monitoring device Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000004891 communication Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 13
- 239000007788 liquid Substances 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 229910052799 carbon Inorganic materials 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 239000012530 fluid Substances 0.000 claims description 3
- 230000035699 permeability Effects 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 12
- 238000003860 storage Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 108010076504 Protein Sorting Signals Proteins 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention discloses a shale gas well production control method, equipment and a system based on artificial intelligence, which belong to the technical field of shale gas production, can realize remote unmanned control production of shale gas wells, realize real-time yield prediction by using a shale gas well head yield dynamic prediction module and upload prediction results to a control module, realize real-time recognition of working conditions such as shaft effusion, shaft sand production, pipeline leakage, pipeline blockage and the like by using an abnormal working condition early warning module, upload the recognition results to the control module, make a control decision by using the control module and issue a control instruction, and improve the accuracy and reliability of production control of the shale gas wells.
Description
Technical Field
The invention belongs to the technical field of shale gas exploitation, and particularly relates to a shale gas well production control method, equipment and system based on artificial intelligence.
Background
The successful development of shale gas effectively promotes the optimization of the energy structure in China, but in the aspects of shale gas well production rule, reasonable production system, field management and the like, the traditional manual and computer mode cannot meet the requirements of synchronous tracking analysis and fine gas reservoir management, and mature theories, technologies and experiences are not available at home and abroad for reference. In shale gas field production management, there are 2 main aspects of the problem that restrict the high-efficient management of gas reservoir: (1) the rapid production prediction method is lack, and the identification of influencing factors is difficult. The shale gas exploration and development difficulty is large, the basic theory research is insufficient, and the production rule is not deeply known. How to select the optimal production mode, formulate reasonable working schedule, effective control is decreased progressively and the problem such as the single well recoverable reserve is improved, need to optimize and improve continuously. (2) The abnormality identification and treatment are not timely and accurate. Shale gas well degressive fast, the law change is fast, the existing software can not carry out production analysis and prediction fast and accurately, the identification of influencing factors is difficult, the establishment of the optimal countermeasure of the gas well is restricted, and the control degressive measure is relatively lagged.
For yield prediction, the current yield prediction technologies mainly include: patent zl201910041520.x predicts shale gas yield by combining static parameters with a seepage mathematical model; patent ZL201710212048.2 predicts the yield by using a plate through constructing a yield regularization simulated pressure function of a well to be analyzed; the shale gas multi-section fracturing well yield prediction based on the random forest algorithm predicts the yield of the shale gas well by using static parameters such as depth measurement, vertical depth, extension pressure, brittleness index, density log value, total liquid amount and the like; the yield prediction technology of the shale GAs horizontal well in the Changning region based on the GA-BP neural network predicts the yield by using geological and engineering parameters such as organic carbon content, GAs content, effective porosity, brittle mineral content and the like. However, the yield prediction technology mainly utilizes static parameters related to yield to establish a theoretical model or a big data model, and dynamic parameters such as oil jacket pressure, output pressure and the like change in real time in the shale gas production process, which also has great influence on yield, so that the existing yield prediction technology has low prediction accuracy and reliability.
Aiming at the early warning of abnormal working conditions, the existing abnormal working condition early warning technology mainly comprises the following steps: the research and application of the multi-parameter combined early warning model of the gas well calculate corresponding parameter values through corresponding algorithms to carry out early warning on abnormal working conditions, and pushes abnormal conditions and treatment suggestions according to preset values; according to a plunger gas lift dynamic model, whether liquid is accumulated at the bottom of a well or whether a pipeline is blocked is judged through theoretical models such as oil casing pressure and the like. However, the above abnormal working condition early warning technology is mainly based on a theoretical model, and the model itself has many assumed conditions, and cannot restore the most real working conditions, and the early warning accuracy is low, and the abnormal working condition of prediction is single, and cannot simultaneously identify working conditions such as shaft effusion, shaft sand production, pipeline puncture, pipeline blockage.
Aiming at an artificial intelligent shale gas well production control system and an intelligent production optimization method for a low-pressure low-yield shale gas well, the intelligent production optimization method applicable to the low-pressure low-yield shale gas well is provided, and the automatic production and operation monitoring of the gas well are realized by taking an artificial intelligent algorithm as a center. Predicting the yield by combining dynamic parameters with artificial intelligence, and predicting the bottom hole accumulated liquid according to a Turner critical liquid carrying flow model; the development of an intelligent system of an intermittent production gas well pattern takes gas well pattern control as a starting point, and aims at intermittent gas production and low-yield gas wells as main research objects, the intelligent system of the intermittent production gas well pattern based on Mitsubishi PLC is developed, the volume of fluid in a well shaft after the well is closed is predicted, and optimal control parameters are determined; an application effect evaluation of an intelligent shale gas field production aid decision system introduces a production aid decision system, early warning research is carried out from the directions of low pressure, effusion, production system change and the like, and short-term, medium-term and long-term analysis and prediction are carried out on the production rule change of a single well. However, in the current artificial intelligent shale gas well production control system, production is mainly predicted by using static or dynamic parameters, and meanwhile, accumulated liquid at the bottom of a well is predicted by using a theoretical model, so that the error of a yield prediction result is large, and the prediction of abnormal working conditions is single, thereby influencing the control precision and accuracy.
Disclosure of Invention
The invention provides a shale gas well production control method, equipment and system based on artificial intelligence, and aims to solve the problems that shale gas well production control accuracy and accuracy are poor (yield prediction accuracy is low, abnormal working condition prediction is single and the like) in the prior art. The invention can realize the remote unmanned control production of the shale gas well, realizes the real-time yield prediction by using the shale gas well mouth yield dynamic prediction module and uploads the prediction result to the control module, and simultaneously realizes the real-time recognition of the working conditions such as the accumulated liquid in the shaft, the sand production in the shaft, the pipeline leakage, the pipeline blockage and the like by using the abnormal working condition early warning module, and uploads the recognition result to the control module, and the control module makes a control decision and issues a control instruction, thereby improving the accuracy and the reliability of the production control of the shale gas well.
The invention is realized by the following technical scheme:
a shale gas well production control method based on artificial intelligence comprises the following steps:
acquiring dynamic and static parameters of a target well, realizing the real-time prediction of the shale gas yield of the target well by using a dynamic yield prediction model, and uploading the prediction result to a remote control module to assist in generating a production control instruction;
acquiring sound information in real time during production of the wellhead of the target well, and preprocessing and extracting characteristics of the acquired sound information;
matching the extracted characteristic vectors by using an abnormal working condition classification model, determining the type of the abnormal working condition, and transmitting the abnormal working condition type to the remote control module for early warning and/or auxiliary generation of a production control instruction;
and receiving a production control instruction issued by the remote control module, and adjusting the opening of the electric valve and/or the electric oil nozzle according to the production control instruction so as to control whether production and/or yield are carried out.
As a preferred embodiment, the dynamic prediction model construction process of the present invention specifically includes:
acquiring static parameters and dynamic parameters of a target well, wherein the static parameters comprise geological parameters and fracturing construction parameters of the target well, and the dynamic parameters are wellhead parameters acquired through a wellhead monitoring device;
performing correlation analysis on the obtained static parameters and dynamic parameters by using a correlation coefficient calculation method to determine yield master control factors;
and inputting the yield master control factor into a neural network algorithm for training to obtain a dynamic yield prediction model.
As a preferred embodiment, the static parameters of the present invention include: organic carbon content, porosity, permeability, layer thickness, well depth, discharge capacity, slick water amount, total liquid amount, total sand amount, average sand ratio, fracture pressure, pump stop pressure, number of stages, number of clusters and the like; dynamic parameters include, but are not limited to, wellhead oil pressure, back pressure, casing pressure, and flow;
the dynamic parameters comprise wellhead oil pressure, back pressure, casing pressure and flow.
As a preferred embodiment, the correlation analysis process of the present invention specifically includes:
performing correlation calculation on the obtained dynamic and static parameters by adopting a Pearson correlation coefficient calculation method to obtain the correlation degree of each dynamic and static parameter;
and determining yield main control factors according to the correlation degree and the strength requirement.
As a preferred embodiment, the abnormal condition classification model construction process specifically includes:
acquiring training sample data, wherein the training sample data consists of sound information acquired by a sound receiver during well head production under various abnormal working conditions;
preprocessing the training sample data and extracting characteristics;
and classifying the extracted feature vectors into corresponding abnormal working condition types to obtain various abnormal working condition classification models.
As a preferred embodiment, the types of abnormal conditions of the present invention include wellbore fluid loading, wellbore sand production, pipeline leaks and pipeline plugging.
In a second aspect, the present invention proposes a computer device comprising a memory storing a computer program and a processor implementing the steps of the above-mentioned method of the present invention when the processor executes the computer program.
In a third aspect, the invention provides a shale gas well production control system based on artificial intelligence, which comprises the computer equipment, a communication module and a remote control module, wherein the computer equipment is used for providing a control signal for the shale gas well production control system;
the computer equipment comprises a yield dynamic prediction module, an abnormal working condition early warning module and a wellhead control module;
the yield dynamic prediction module is used for acquiring dynamic and static parameters of a target well, realizing the real-time prediction of shale gas yield by using a dynamic yield prediction model and uploading a prediction result to the remote control module through the communication module to assist in generating a production control instruction;
the abnormal working condition early warning module is used for collecting sound information during the production of a target well wellhead, preprocessing and extracting characteristics of the collected sound information, matching the extracted characteristic vectors by using an abnormal working condition classification model, determining the type of an abnormal working condition and uploading the abnormal working condition type to the remote control module through the communication module to perform early warning and/or assist in generating a production control command;
the wellhead control module receives a production control instruction issued by the remote control module through the communication module, and adjusts the opening degree of the electric valve and/or the electric oil nozzle according to the production control instruction, so as to control whether to produce and/or output.
As a preferred embodiment, the system of the present invention further includes a power supply device, which provides power for each component of the system to ensure normal operation of the system.
In a preferred embodiment, the system of the present invention further comprises a monitoring device for monitoring wellhead information and uploading it to the computer device for processing.
The invention has the following advantages and beneficial effects:
1. according to the method, the shale gas yield is predicted in real time by using the wellhead dynamic prediction model, the influence of static parameters such as geological parameters and construction parameters on the yield is considered, the influence of dynamic data such as wellhead parameters on the yield is also considered, the considered influence factors are more comprehensive, the shale gas yield is predicted more accurately, and the method is more suitable for field practice.
2. According to the invention, the abnormal working condition early warning model is utilized, and the sound recognition technology is adopted to early warn the abnormal working conditions such as shaft effusion, shaft sand production, pipeline puncture, pipeline blockage and the like, so that the advance rate and the accuracy rate are greatly improved compared with the traditional theoretical model for early warning the abnormal working conditions.
3. According to the invention, the yield predicted value and the abnormal working condition identification result are only required to be uploaded to the remote production control end to assist the production control instruction, a large amount of data is not required to be uploaded to the remote production control end for processing, the data transmission quantity is greatly reduced, and the real-time performance of early warning is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a flow chart of yield dynamics prediction according to the present invention;
FIG. 3 is a flow chart of the abnormal operating condition recognition of the present invention;
fig. 4 is a schematic block diagram of the system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
The embodiment is as follows:
in the existing shale gas well production control technology, the yield is mainly predicted by using static or dynamic parameters, and the error of a yield prediction result is large; the theoretical model is used for early warning of accumulated liquid at the bottom of the well, the early warning of abnormal working conditions is single, the early warning has hysteresis, and the accuracy is low. Based on this, the embodiment provides a shale gas well production control method based on artificial intelligence. According to the method, the yield can be predicted in real time by using the wellhead yield dynamic prediction model, and meanwhile, the prediction result is transmitted to the remote production control end for reference of a decision maker, so that the prediction accuracy and reliability are improved, and the data transmission quantity is reduced. The method provided by the embodiment also utilizes the abnormal working condition classification model, can realize real-time identification of abnormal working conditions such as shaft liquid accumulation, shaft sand production, pipeline leakage, pipeline blockage and the like, and transmits the identification result to the remote production control end for reference of a decision maker, so that the early warning accuracy and the real-time performance are improved.
As shown in fig. 1, the method proposed in this embodiment specifically includes the following steps:
step 1, obtaining dynamic and static parameters of a target well, utilizing a dynamic yield prediction model to realize real-time prediction of shale gas yield of the target well, and uploading a prediction result to a remote control module to assist in generating a production control instruction.
And 2, acquiring sound information in real time during production of a wellhead of the target well, and preprocessing and extracting characteristics of the acquired sound information.
And 3, matching the extracted characteristic vectors by using the abnormal working condition classification model, determining the type of the abnormal working condition, and uploading the type of the abnormal working condition to a remote control module for early warning and/or auxiliary generation of a production control instruction.
And 4, receiving a production control instruction issued by the remote control module, and adjusting the opening of the electric valve and/or the electric oil nozzle according to the production control instruction so as to control whether production and/or yield are/is performed.
The method provided by the embodiment can realize remote unmanned control production of the shale gas well, the real-time yield prediction is realized by utilizing a wellhead yield dynamic prediction model, and meanwhile, the wellhead yield dynamic prediction model is uploaded to a remote control module for reference of a decision maker; by using the abnormal working condition classification model, the real-time identification of various abnormal working conditions can be realized, the abnormal working conditions are uploaded to the remote control module for early warning, and an operator can issue a control instruction according to the uploaded information. Compared with the existing shale gas production control technology which needs manual assistance, the control accuracy and the real-time performance are improved.
As an alternative embodiment, as shown in fig. 2, the dynamic production prediction model building process includes the following sub-steps:
and 11, acquiring static parameters and dynamic parameters of the target well, wherein the dynamic parameters are historical wellhead parameters acquired by a wellhead monitoring device.
Specifically, the static parameters obtained in this embodiment include geological parameters and fracturing construction parameters of the target well, including but not limited to: organic carbon content (TOC), porosity, permeability, layer thickness, well depth, discharge capacity, slip water amount, total liquid amount, total sand amount, average sand ratio, burst pressure, pump stop pressure, number of stages, number of clusters, and the like; dynamic parameters include, but are not limited to, wellhead oil pressure, back pressure, casing pressure, flow rate, and the like. Static parameters can be directly obtained from a remote control module, and dynamic parameters are acquired by using an oil pressure monitoring device, a back pressure monitoring device, a casing pressure monitoring device, a flow monitoring device and the like which are installed at the wellhead of a target well.
And step 12, performing correlation analysis on the obtained static parameters and dynamic parameters by using a correlation coefficient calculation method, and determining yield main control factors.
Specifically, in this embodiment, correlation analysis is performed on the acquired data by using a Pearson correlation coefficient calculation method, the main calculation method is shown as the following formula, the calculation result interval is [ -1,1], and the main determination standard is shown in table 1.
In the formula: cov (a, b) -the covariance matrix of the variables a, b; sigma a ，σ b -the standard deviation of each of the variables a, b; a is i ，b i -the ith variable value in the variable a, b dataset;
，/>
-the average of the variables a, b; n-the data set size of the variables a, b.
The variable a is the yield, and the variable b is the parameters affecting the yield, such as static parameters and dynamic parameters.
Table 1:
pearson correlation coefficient ranking
As can be seen from table 1, according to actual requirements, parameters with more than strong correlation can be selected as the main control factors.
And step 13, inputting the yield master control factors into a neural network algorithm for training to obtain a dynamic yield prediction model. The specific training process is as follows:
(1) Initialization of the network, assuming the number of nodes of the input layer isnThe number of nodes of the hidden layers (A1, A2, A3 are neurons of the hidden layers) is l, and the number of nodes of the output layer ism. Input layer to hidden layer weightsW ij The weight from hidden layer to output layer isW jk The bias of the input layer to the hidden layer isa j The bias from the hidden layer to the output layer isb k . The learning rate is, the excitation function isg(x) In that respect Wherein the excitation functiong(x) Take Sigmoid function. The form is:
(2) The output of the hidden layer, as shown in the above three-layer BP network, is:
(3) Output of the output layer:
(4) And (3) calculating an error:
the error formula is:
wherein
Is the desired output. />
Then E can be expressed as:
in the above formula, the first and second light sources are,
。
(5) Updating the weight value, wherein the updating formula of the weight value is as follows:
(6) Updating the bias, wherein the updating formula of the bias is as follows:
hidden layer to output layer bias update
The update formula for the bias is:
bias update of input layer to hidden layer:
wherein:
the update formula for the bias is:
(7) And judging whether the iteration of the algorithm is finished or not, and obtaining the shale gas yield dynamic prediction model after the iteration is finished.
As an optional implementation manner, in step 2, sound information generated during production of the wellhead of the target well may be collected in real time by using a sound receiver, and then denoising processing is performed on the collected sound information first. In the present case, a spectral subtraction and denoising method is selectediThe frame-clean sound signal sequence isx i (m) 1iSequence of frame-band noise signalsy i (m) the estimated 1-frame noise signal sequence isd i (m), where m is the sampling point number, the denoising formula is as follows:
in the formula (I), the compound is shown in the specification,Y i (w) Is composed ofy i (m) the Fourier transformed values,D(w) Is composed ofd i (m) The value after the fourier transform is performed,X i (w) Is composed ofx i (m) The value after the fourier transform is performed,αin order to over-reduce the factor(s),βis a gain compensation factor.
And then extracting characteristic frequency from the abnormal working condition classification model, and matching the extracted characteristic frequency with the abnormal working condition classification model so as to determine the type of the abnormal working condition.
As an optional implementation manner, as shown in fig. 3, the abnormal condition classification model building process specifically includes the following sub-steps:
and step 31, acquiring training sample data, wherein the training sample data is sound information acquired by a sound receiver during the production of the well head under various abnormal working conditions.
And step 32, preprocessing and feature extraction are carried out on the training sample data. The pretreatment process comprises the following steps: firstly, denoising training sample data; the background noise is then removed by fourier transform. The specific process is the same as the pretreatment process in step 2, and is not described herein again. The extracted features are the feature frequencies.
And step 33, classifying the extracted feature vectors into corresponding abnormal working condition types, so as to obtain a plurality of abnormal working condition classification models. The abnormal operating condition types include but are not limited to operating conditions such as wellbore effusion, wellbore sand production, pipeline puncture, pipeline blockage and the like.
The abnormal working condition classification model is used for identifying the sample to be detected, so that the type of the abnormal working condition can be determined, the real-time identification of various abnormal working conditions can be realized, and the early warning accuracy is improved. The sample to be tested is the sound information collected by the sound receiver during the production of the wellhead of the target well.
As an optional implementation manner, step 4 specifically includes the following cases:
and controlling the opening and closing of the electric valve and/or the opening size of the electric oil nozzle according to an instruction issued by the remote control module, so as to realize the adjustment of production and/or yield size. For example, when the issued command is a shut-in command, a closing command is issued to the electric valve, and the electric valve is closed; if the issued command is well opening, an opening command is issued to the electric valve, and the electric valve is opened; if the issued instruction is a shale gas output regulating instruction, the opening size of the electric oil nozzle is adjusted to realize different output control, meanwhile, the flow monitoring device uploads the collected data to the remote control module to confirm whether the current output is the current production task, and if the current output is not the current production task, the opening size of the electric oil nozzle is continuously adjusted.
And controlling the opening and closing of the electric valve and/or the opening of the electric nozzle according to the predicted yield value and the production plan, so as to realize the adjustment of production and/or yield. For example, the predicted yield value does not match the production schedule, and the yield can be controlled by adjusting the opening size of the electric nozzle.
And controlling the opening and closing of the electric valve and/or the opening of the electric oil nozzle according to the type of the abnormal working condition, so as to realize the adjustment of production and/or yield. When the abnormal working condition can not be solved through remote control, a remote operator can send early warning information to a well site operator to perform manual adjustment. For example, when the abnormal condition is serious, the electric valve needs to be controlled to close, so that the well is shut down for maintenance.
According to the embodiment, the shale gas yield is predicted through dynamic and static parameters, the parameters are considered more comprehensively, the prediction result is more accurate, meanwhile, the yield dynamic prediction result is only required to be uploaded to a remote control module, and the transmission quantity of data is greatly reduced.
The embodiment adopts the sound recognition technology to carry out the early warning to unusual operating mode, compares the unusual operating mode of traditional theoretical model early warning, and the rate of accuracy will promote by a wide margin, has greatly improved the real-time of early warning.
The embodiment also provides a computer device for executing the method of the embodiment.
The computer equipment comprises a processor, an internal memory and a system bus; various device components including internal memory and processors are connected to the system bus. A processor is hardware used to execute computer program instructions through basic arithmetic and logical operations in a computer system. An internal memory is a physical device used to temporarily or permanently store computing programs or data (e.g., program state information). The system bus may be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus. The processor and the internal memory may be in data communication via a system bus. Including read-only memory (ROM) or flash memory, and Random Access Memory (RAM), which typically refers to main memory loaded with an operating system and computer programs.
Computer devices typically include an external storage device. The external storage device may be selected from a variety of computer readable media, which refers to any available media that can be accessed by the computer device, including both removable and non-removable media. For example, computer-readable media includes, but is not limited to, flash memory (micro SD cards), CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer device.
A computer device may be logically connected in a network environment to one or more network terminals. The network terminal may be a personal computer, a server, a router, a smart phone, a tablet, or other common network node. The computer apparatus is connected to the network terminal through a network interface (local area network LAN interface). A Local Area Network (LAN) refers to a computer network formed by interconnecting within a limited area, such as a home, a school, a computer lab, or an office building using a network medium. WiFi and twisted pair wiring ethernet are the two most commonly used technologies to build local area networks.
It should be noted that other computer systems including more or less subsystems than computer devices can also be suitable for use with the invention.
As described in detail above, a computer apparatus suitable for use in the present embodiments is capable of performing the designated operations of the shale gas well production control method. The computer device performs these operations in the form of software instructions executed by a processor in a computer-readable medium. These software instructions may be read into memory from a storage device or from another device via a local area network interface. The software instructions stored in the memory cause the processor to perform the method of processing group membership information described above. Furthermore, the invention can be implemented by hardware circuitry or by a combination of hardware circuitry and software instructions. Thus, implementation of the present embodiments is not limited to any specific combination of hardware circuitry and software.
The embodiment provides a shale gas well production control system based on artificial intelligence, and particularly relates to a shale gas well production control system based on artificial intelligence, which is shown in fig. 4 and comprises the computer equipment, a communication module and a remote control module.
The computer equipment comprises a yield dynamic prediction module, an abnormal working condition early warning module and a wellhead control module.
The yield dynamic prediction module is used for acquiring dynamic and static parameters of a target well, realizing shale gas yield real-time prediction by using the dynamic yield prediction model and uploading the prediction result to the remote control module through the communication module to assist in generating a production control instruction;
the abnormal working condition early warning module is used for collecting sound information during production of a target well wellhead, preprocessing and feature extraction are carried out on the collected sound information, extracted feature vectors are matched through the abnormal working condition classification model, the type of the abnormal working condition is determined, and the abnormal working condition type is uploaded to the remote control module through the communication module to carry out early warning and/or auxiliary production control instructions.
The wellhead control module receives a production control instruction issued by the remote control module through the communication module, and adjusts the opening degree of the electric valve and/or the electric oil nozzle according to the production control instruction, so that whether production and/or yield are/is controlled.
As an optional embodiment, the system further includes a power supply device, the power supply device provides power for the components of the system, and ensures that the system operates normally, and the power supply device may be, but is not limited to, a storage battery, and the storage battery may be charged through the photovoltaic wind power generation system.
As an alternative embodiment, the system further comprises monitoring devices including, but not limited to, an oil pressure monitoring device, a back pressure monitoring device, a casing pressure monitoring device, a flow monitoring device, and a sound receiver.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A shale gas well production control method based on artificial intelligence is characterized by comprising the following steps:
acquiring dynamic and static parameters of a target well, realizing real-time prediction of shale gas yield of the target well by using a dynamic yield prediction model, and uploading a prediction result to a remote control module to assist in generating a production control instruction;
acquiring sound information in real time during production of the wellhead of the target well, and preprocessing and extracting characteristics of the acquired sound information;
matching the extracted characteristic vectors by using an abnormal working condition classification model, determining the type of the abnormal working condition, and transmitting the abnormal working condition type to the remote control module for early warning and/or auxiliary generation of a production control instruction;
and receiving a production control instruction issued by the remote control module, and adjusting the opening of the electric valve and/or the electric oil nozzle according to the production control instruction so as to control whether production and/or yield are carried out.
2. The artificial intelligence based shale gas well production control method as claimed in claim 1, wherein the dynamic prediction model construction process specifically comprises:
acquiring static parameters and dynamic parameters of a target well, wherein the static parameters comprise geological parameters and fracturing construction parameters of the target well, and the dynamic parameters are wellhead parameters acquired through a wellhead monitoring device;
performing correlation analysis on the obtained static parameters and dynamic parameters by using a correlation coefficient calculation method to determine yield master control factors;
and inputting the yield master control factor into a neural network algorithm for training to obtain a dynamic yield prediction model.
3. The artificial intelligence based shale gas well production control method as claimed in claim 2, wherein the static parameters comprise: organic carbon content, porosity, permeability, layer thickness, well depth, discharge capacity, slick water quantity, total liquid quantity, total sand quantity, average sand ratio, fracture pressure, pump stop pressure, stage number, cluster number and the like; dynamic parameters include, but are not limited to, wellhead oil pressure, back pressure, casing pressure, and flow;
the dynamic parameters comprise wellhead oil pressure, back pressure, casing pressure and flow.
4. The artificial intelligence based shale gas well production control method as claimed in claim 2, wherein the correlation analysis process specifically comprises:
performing correlation calculation on the obtained dynamic and static parameters by adopting a Pearson correlation coefficient calculation method to obtain the correlation degree of each dynamic and static parameter;
and determining yield main control factors according to the correlation degree and the strength requirement.
5. The artificial intelligence based shale gas well production control method as claimed in any one of claims 1-4, wherein the abnormal operating condition classification model construction process specifically comprises:
acquiring training sample data, wherein the training sample data is composed of sound information acquired by a sound receiver during wellhead production under various abnormal working conditions;
preprocessing and feature extracting are carried out on the training sample data;
and classifying the extracted feature vectors into corresponding abnormal working condition types, thereby obtaining various abnormal working condition classification models.
6. The artificial intelligence based shale gas well production control method as claimed in claim 5 wherein the abnormal operating condition types include wellbore fluid loading, wellbore sand production, pipeline breakthrough and pipeline plugging.
7. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor realizes the steps of the method according to any of claims 1-6 when executing the computer program.
8. An artificial intelligence based shale gas well production control system, characterized in that the system comprises the computer device, the communication module and the remote control module of claim 7;
the computer equipment comprises a yield dynamic prediction module, an abnormal working condition early warning module and a wellhead control module;
the yield dynamic prediction module is used for acquiring dynamic and static parameters of a target well, realizing the real-time prediction of shale gas yield by using a dynamic yield prediction model and uploading a prediction result to the remote control module through the communication module to assist in generating a production control instruction;
the abnormal working condition early warning module is used for collecting sound information during production of a target well wellhead, preprocessing and extracting characteristics of the collected sound information, matching the extracted characteristic vectors by using an abnormal working condition classification model, determining the type of an abnormal working condition and uploading the abnormal working condition type to the remote control module through the communication module for early warning and/or assisting to generate a production control instruction;
the wellhead control module receives a production control instruction issued by the remote control module through the communication module, and adjusts the opening degree of the electric valve and/or the electric oil nozzle according to the production control instruction, so as to control whether to produce and/or output.
9. The artificial intelligence based shale gas well production control system as claimed in claim 8 further comprising power supply equipment, wherein the power supply equipment provides power for the system components to ensure the system operates normally.
10. An artificial intelligence based shale gas well production control system as claimed in claim 8 further comprising monitoring equipment for monitoring wellhead information and uploading it to the computer equipment for processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310138674.7A CN115874993A (en) | 2023-02-21 | 2023-02-21 | Shale gas well production control method, equipment and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310138674.7A CN115874993A (en) | 2023-02-21 | 2023-02-21 | Shale gas well production control method, equipment and system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115874993A true CN115874993A (en) | 2023-03-31 |
Family
ID=85761367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310138674.7A Pending CN115874993A (en) | 2023-02-21 | 2023-02-21 | Shale gas well production control method, equipment and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115874993A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432975A (en) * | 2023-04-23 | 2023-07-14 | 重庆万普隆能源股份有限公司北京分公司 | Exploitation management method, device, equipment and medium of shale gas multi-station platform |
| CN117454294A (en) * | 2023-11-02 | 2024-01-26 | 西南石油大学 | Shale gas well plunger process well abnormal condition judging method |
| CN117973589A (en) * | 2024-01-26 | 2024-05-03 | 四川华飞能源科技有限公司 | Horizontal well effusion prediction method based on gas well production data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NO960517D0 (en) * | 1995-02-09 | 1996-02-08 | Baker Hughes Inc | Method and system for controlling and monitoring a number of zones in a well |
| US6012015A (en) * | 1995-02-09 | 2000-01-04 | Baker Hughes Incorporated | Control model for production wells |
| CN108595803A (en) * | 2018-04-13 | 2018-09-28 | 重庆科技学院 | Shale gas well liquid loading pressure prediction method based on recurrent neural network |
| CN109214026A (en) * | 2017-07-07 | 2019-01-15 | 中国石油天然气股份有限公司 | Shale gas horizontal well initial-stage productivity prediction method |
| CN112943181A (en) * | 2021-02-07 | 2021-06-11 | 北京爱新能智科技有限公司 | Intelligent gas well valve adjusting system |
-
2023
- 2023-02-21 CN CN202310138674.7A patent/CN115874993A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| NO960517D0 (en) * | 1995-02-09 | 1996-02-08 | Baker Hughes Inc | Method and system for controlling and monitoring a number of zones in a well |
| US6012015A (en) * | 1995-02-09 | 2000-01-04 | Baker Hughes Incorporated | Control model for production wells |
| CN109214026A (en) * | 2017-07-07 | 2019-01-15 | 中国石油天然气股份有限公司 | Shale gas horizontal well initial-stage productivity prediction method |
| CN108595803A (en) * | 2018-04-13 | 2018-09-28 | 重庆科技学院 | Shale gas well liquid loading pressure prediction method based on recurrent neural network |
| CN112943181A (en) * | 2021-02-07 | 2021-06-11 | 北京爱新能智科技有限公司 | Intelligent gas well valve adjusting system |
Non-Patent Citations (2)
| Title |
|---|
| 杜奉屏: "机械设备的故障诊断与工况监视", 东南大学出版社 * |
| 陈中普;于相东;陶青龙;赵聪会;魏佳强;万康;刘秋豹;: "气田生产物联网系统构建与应用", 录井工程 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116432975A (en) * | 2023-04-23 | 2023-07-14 | 重庆万普隆能源股份有限公司北京分公司 | Exploitation management method, device, equipment and medium of shale gas multi-station platform |
| CN116432975B (en) * | 2023-04-23 | 2023-09-19 | 重庆万普隆能源股份有限公司北京分公司 | Exploitation management method, device, equipment and medium of shale gas multi-station platform |
| CN117454294A (en) * | 2023-11-02 | 2024-01-26 | 西南石油大学 | Shale gas well plunger process well abnormal condition judging method |
| CN117454294B (en) * | 2023-11-02 | 2024-06-04 | 西南石油大学 | Shale gas well plunger process well abnormal condition judging method |
| CN117973589A (en) * | 2024-01-26 | 2024-05-03 | 四川华飞能源科技有限公司 | Horizontal well effusion prediction method based on gas well production data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115874993A (en) | Shale gas well production control method, equipment and system based on artificial intelligence | |
| CN111651312B (en) | Three-level bidirectional early warning method and system for equipment fault based on edge calculation | |
| CN109508827B (en) | Drilling accident early warning method based on time recursion neural network | |
| CN110807557B (en) | BP neural network-based drilling rate prediction method and BP neural network-based particle swarm optimization method | |
| CN107122860B (en) | Rock burst danger level prediction method based on grid search and extreme learning machine | |
| CN114896903A (en) | Forced learning-based decision optimization method for oil field production system | |
| CN114777192B (en) | Secondary network heat supply autonomous optimization regulation and control method based on data association and deep learning | |
| US11905817B2 (en) | Method and system for managing carbon dioxide supplies using machine learning | |
| CN116384554A (en) | Method and device for predicting mechanical drilling speed, electronic equipment and computer storage medium | |
| US20230193791A1 (en) | Method and system for managing carbon dioxide supplies and supercritical turbines using machine learning | |
| CN111030299A (en) | Side channel-based power grid embedded terminal safety monitoring method and system | |
| CN113156492B (en) | Real-time intelligent early warning method applied to TBM tunnel rockburst disasters | |
| CN114357887A (en) | BP neural network-based method for predicting slurry leakage before drilling under complex well conditions | |
| CN116307010A (en) | Drilling condition identification method based on random forest algorithm | |
| Zhou et al. | Application of BP neural network in efficiency prediction of oilfield mechanized mining system | |
| Isik et al. | Importance of data preprocessing for neural networks modeling: The case of estimating the compaction parameters of soils | |
| CN116822352A (en) | GRNN neural network-based underground waterproof sealing wall working condition prediction method and system | |
| CN112149255A (en) | Coal face hydraulic support working resistance prediction method based on LSTM neural network | |
| CN110188439A (en) | The subway work ground settlement method for early warning of case-based reasioning and system dynamics | |
| CN116644844A (en) | Stratum pressure prediction method based on neural network time sequence | |
| CN110674868A (en) | Stratum lithology identification system and method based on high-dimensional drilling parameter information | |
| CN112733076A (en) | System identification method based on neural network ordinary differential equation under non-continuous excitation | |
| CN116906025B (en) | Oil extraction engineering production abnormality diagnosis device | |
| Liu et al. | Prediction of hydraulic pumps remaining useful life based on LSTM and Transform with dual self-attention | |
| CN118114812B (en) | Shale gas yield prediction method, computer equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230331 |
|
| RJ01 | Rejection of invention patent application after publication |