CN113445991B - Artificial intelligence single-machine multi-well oil pumping machine monitoring method, system and storage medium - Google Patents
Artificial intelligence single-machine multi-well oil pumping machine monitoring method, system and storage medium Download PDFInfo
- Publication number
- CN113445991B CN113445991B CN202110702990.3A CN202110702990A CN113445991B CN 113445991 B CN113445991 B CN 113445991B CN 202110702990 A CN202110702990 A CN 202110702990A CN 113445991 B CN113445991 B CN 113445991B
- Authority
- CN
- China
- Prior art keywords
- well
- pumping unit
- data
- oil
- artificial intelligence
- 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.)
- Active
Links
Images
Classifications
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B47/00—Survey of boreholes or wells
- E21B47/008—Monitoring of down-hole pump systems, e.g. for the detection of "pumped-off" conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH DRILLING; MINING
- E21B—EARTH DRILLING, e.g. DEEP DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- E21B2200/00—Special features related to earth drilling for obtaining oil, gas or water
- E21B2200/22—Fuzzy logic, artificial intelligence, neural networks or the like
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention provides a method, a system and a storage medium for monitoring a single-machine multi-well pumping unit based on artificial intelligence, which relate to the field of oilfield development and comprise the following steps: acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and/or reading data of an oil field database to acquire the electrical parameter data of the oil pumping unit; calculating the active power, the reactive power or the system efficiency data of the pumping unit according to the electrical parameter data of the pumping unit; according to an energy mechanics balance principle, combining the active power, the reactive power or the system efficiency data to perform stress analysis on the oil pumping unit; when the pumping unit drives all power output flexible ropes to work, calculating total load data, stopping a certain group of power output flexible ropes, entering a single-well shutdown state, calculating single-well shutdown load data, and subtracting the single-well shutdown load data from the total load data to obtain single-well load data of a shutdown pumping well; and judging the pumping well with abnormal work according to the stress analysis and the distribution structure of the multiple groups of power output flexible ropes of the pumping unit.
Description
Technical Field
The invention relates to the technical field of oilfield development, in particular to a method and a system for monitoring an artificial intelligent single-machine multi-well pumping unit and a storage medium.
Background
In recent years, the oil price is low, the oil field exploitation benefits are worsened year by year, more than 200 thousands of pumping wells are available in oil fields at home and abroad, most of pumping wells at 40-50 thousands of mouths at home are oil pumping units, and as the pumping units develop for nearly one hundred years, no major technical breakthrough exists, and the oil pumping units have large energy consumption, large volume and large weight. The oil pumping efficiency is low, and the oil pumping device is not suitable for high-efficiency exploitation in a low-oil-price environment. In recent years, the development of artificial intelligence technology is rapid, the application of the field of oilfield field development is relatively backward, a large number of lifting processes of an oilfield, particularly the technology of internet of things matched with a beam-pumping well, develop the technical application and practice of a digital oilfield, and the time rate of the oilfield is improved, and the workload intensity is simplified. But oil field intellectualization and intelligent oil field research tests are just started. The matching technology that a single pumping unit drives a plurality of pumping wells simultaneously is not complete, and the problem of energy conservation and investment reduction of oil field exploitation engineering needs to be solved urgently; in addition, the development and application of the intelligent technology of single pump and multiple wells are not reported at present.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art or the related technology, and discloses a single-machine multi-well pumping unit monitoring method, a system and a storage medium based on artificial intelligence.
The invention discloses a single-machine multi-well pumping unit monitoring method based on artificial intelligence.A speed reducer of the single-machine multi-well pumping unit is connected with a double-crank power output mechanism, a first crank and a second crank are symmetrically arranged at two ends of a power output shaft of the speed reducer, a flexible rope led out from the first crank and a flexible rope led out from the second crank form a group of power output flexible ropes together, each group of power output flexible ropes drives one pumping well, and the single-machine multi-well pumping unit is provided with a plurality of groups of power output flexible ropes with homogeneous phase distribution; the method comprises the following steps: acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and/or reading data of an oil field database to acquire the electrical parameter data of the oil pumping unit; calculating the active power, the reactive power or the system efficiency data of the oil pumping unit according to the electrical parameter data of the oil pumping unit; according to the energy mechanics balance principle, the stress analysis is carried out on the pumping unit by combining active power, reactive power or system efficiency data, and one or more of the following analysis data are calculated: moment data, stress data, a moment variation value and a stress variation value; when the pumping unit drives all power output flexible ropes to work, calculating total load data, stopping a certain group of power output flexible ropes, entering a single-well shutdown state, calculating single-well shutdown load data, and subtracting the single-well shutdown load data from the total load data to obtain single-well load data of a shutdown pumping well; and judging the pumping well with abnormal work according to the stress analysis and the distribution structure of the multiple groups of power output flexible ropes of the pumping unit.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, the method further comprises the following steps: and acquiring a field monitoring video of the pumping unit and/or acquiring linkage data of the mobile terminal and a manager so as to implement full-time monitoring on the pumping unit and the oil well.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, the step of acquiring the electrical parameter data of the pumping unit by using an internet-of-things device acquisition system specifically comprises the following steps: and acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and uploading the electrical parameter data to an oil field cloud platform.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, the method further comprises the following steps: and making a single well indicator diagram and an oil well pump indicator diagram according to the single well load data, and quantitatively calculating the liquid production data and the flowing pressure data of the oil well.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, the method further comprises the following steps: and sharing the single well indicator diagram, the oil pump indicator diagram, the liquid production data and the flow pressure data to the oil field cloud platform so as to establish or communicate an information sharing database among the well layer, the well group, the block and the oil-water well of the oil field.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, the method further comprises the following steps: establishing a fault diagnosis database based on artificial intelligence and big data, wherein multiple kinds of abnormal working condition data of the oil well are preset in the fault diagnosis database; and diagnosing the abnormal working condition of the oil pumping unit according to the matching degree of the indicator diagram, the electrical parameter data, the active power, the reactive power, the system efficiency data or the analysis data and the oil well abnormal working condition data.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, a single-group power output flexible rope is subjected to tension test, and the load calculation accuracy is calibrated by using a parallel pressure meter.
According to the single-machine multi-well pumping unit monitoring method based on artificial intelligence disclosed by the invention, preferably, the method further comprises the following steps: according to the oil-water well layer, well group, block and dynamic change of oil field, the stroke and frequency setting of pumping well and/or working parameters of pumping unit and oil pump can be regulated.
The second aspect of the invention discloses a single-machine multi-well pumping unit monitoring system based on artificial intelligence, which comprises: a memory for storing program instructions; and the processor is used for calling the program instructions stored in the memory to realize the artificial intelligence-based single-machine multi-well pumping unit monitoring method according to any technical scheme.
In a third aspect of the present invention, a computer-readable storage medium is disclosed, wherein the computer-readable storage medium stores program codes for implementing the method for monitoring a single-machine multi-well pumping unit based on artificial intelligence according to any one of the above technical solutions.
The beneficial effects of the invention at least comprise: the load data of each single well can be obtained only by monitoring the main engine of the oil pumping unit, and the working state of each well head can be diagnosed. Specifically, the method comprises the following steps: the single-motor driven speed reducer single-shaft double-output oil pumping unit is used for driving a 3-25-port oil pumping well with uniformly distributed phases to perform oil pumping operation through a plurality of flexible ropes and universal fixed pulleys. The system collects electrical parameters through the Internet of things, calculates the related power of the system, and intelligently diagnoses whether any one of the multiple wells has a problem. Aiming at the problem well, the stress change data and the stress change condition of the single well can be accurately calculated by adopting a successive subtraction method, and a single well indicator diagram is made; dozens of working conditions of the pump can be analyzed, and meanwhile, the liquid flow pressure of a single well can be calculated. On the basis, an oil field database is combined and shared, oil-water well layers, well groups, blocks and oil field dynamic changes are analyzed, an optimization measure scheme is provided, the system stroke frequency host is guided to optimize and control, and working parameters of a machine and a pump are adjusted. The method is beneficial to realizing energy conservation and efficiency improvement of oil field exploitation engineering and reducing investment.
Drawings
Fig. 1 shows a schematic flow diagram of a single-machine multi-well pumping unit monitoring method based on artificial intelligence according to an embodiment of the invention.
Fig. 2 shows a load change curve of an artificial intelligence based single-machine multi-well pumping unit monitoring system according to an embodiment of the present invention.
Fig. 3 shows a graph comparing normal single well loading to abnormal single well loading for an artificial intelligence based single-machine multi-well pumping unit monitoring system according to an embodiment of the present invention.
Fig. 4 shows a schematic diagram of single well load curve calculation for an artificial intelligence based single-machine multi-well pumping unit monitoring system, according to an embodiment of the present invention.
Fig. 5 shows a schematic diagram of a stand-alone multi-well pumping unit configuration of an artificial intelligence based stand-alone multi-well pumping unit monitoring system according to an embodiment of the present invention.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention, taken in conjunction with the accompanying drawings and detailed description, is set forth below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and thus the present invention is not limited to the specific embodiments disclosed below.
Example one
One embodiment of the invention discloses a single-machine multi-well pumping unit monitoring method based on artificial intelligence, which comprises the following steps: acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and/or reading data of an oil field database to acquire the electrical parameter data of the oil pumping unit; calculating the active power, the reactive power or the system efficiency data of the pumping unit according to the electrical parameter data of the pumping unit; according to the energy mechanics balance principle, the stress analysis is carried out on the pumping unit by combining active power, reactive power or system efficiency data, and one or more of the following analysis data are calculated: moment data, stress data, a moment variation value and a stress variation value; when the pumping unit drives all power output flexible ropes to work, calculating total load data, stopping a certain group of power output flexible ropes, entering a single-well shutdown state, calculating single-well shutdown load data, and subtracting the single-well shutdown load data from the total load data to obtain single-well load data of a shutdown pumping well; and judging the pumping well with abnormal work according to the stress analysis and the distribution structure of the multiple groups of power output flexible ropes of the pumping unit.
As shown in fig. 5, a speed reducer 501 of the single-unit multi-well pumping unit is connected with a double-crank power output mechanism, a first crank 502 and a second crank 503 are symmetrically arranged at two ends of a power output shaft of the speed reducer, a first flexible rope 504 led out from the first crank and a second flexible rope 505 led out from the second crank jointly form a group of power output flexible ropes, each group of power output flexible ropes drives one pumping well, and a plurality of groups of power output flexible ropes are distributed on an annular power output frame 506 of the single-unit multi-well pumping unit in a phase manner. The speed reducer is configured to be single-shaft double-output, namely two cranks are fixed at two ends of the rotating shaft, and the cranks do circular motion around the rotating shaft; the first crank and the second crank drive a plurality of flexible ropes to output power respectively, the two flexible ropes which move synchronously drive one pumping well together, the flexible ropes are restrained by a guide assembly 507 (such as a universal fixed pulley) in the power output direction, a plurality of groups of flexible ropes are respectively guided to different directions by the guide assemblies with uniformly distributed phases, so that the power output is distributed in uniform phases, and 3-25 wells or even more wells can be driven.
According to the above embodiment, preferably, the method further comprises: and acquiring a field monitoring video of the pumping unit and/or acquiring linkage data of the mobile terminal and a manager so as to implement full-time monitoring on the pumping unit and the oil well.
According to the above embodiment, preferably, the step of acquiring the electrical parameter data of the pumping unit by using the internet of things device acquisition system specifically includes: and acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and uploading the electrical parameter data to an oil field cloud platform.
According to the above embodiment, preferably, the method further comprises: and making a single well indicator diagram and an oil well pump indicator diagram according to the single well load data, and quantitatively calculating the liquid production data and the flowing pressure data of the oil well.
According to the above embodiment, preferably, the method further comprises: and sharing the single well indicator diagram, the oil pump indicator diagram, the liquid production data and the flow pressure data to the oil field cloud platform so as to establish or communicate an information sharing database among the well layer, the well group, the block and the oil-water well of the oil field.
According to the above embodiment, preferably, the method further comprises: establishing a fault diagnosis database based on artificial intelligence and big data, wherein multiple kinds of abnormal working condition data of the oil well are preset in the fault diagnosis database; and diagnosing the abnormal working condition of the oil pumping unit according to the matching degree of the indicator diagram, the electrical parameter data, the active power, the reactive power, the system efficiency data or the analysis data and the oil well abnormal working condition data.
According to the above embodiment, preferably, the single group of power output flexible ropes are subjected to tension test, and the load calculation accuracy is calibrated by using the parallel pressure gauge.
According to the above embodiment, preferably, the method further comprises: according to the oil-water well layer, well group, block and dynamic change of oil field, the stroke and stroke frequency setting of pumping well and/or working parameters of pumping unit and oil pump are regulated.
Example two
As shown in fig. 1, in the oilfield exploitation operation, the practical application scheme corresponding to the single-machine multi-well pumping unit monitoring method based on artificial intelligence provided by the invention comprises the following steps:
1. the Internet of things collects current, voltage and electric parameters and shares the current, voltage and electric parameters with an oil field database;
2. calculating data such as active power energy consumption, reactive power energy consumption and system efficiency, and processing dynamic data and static data of the oil field;
3. calculating the torque and stress conditions of the multi-well system according to an energy mechanics balance principle;
4. monitoring the oil well in all time and linking with the mobile terminal to realize monitoring of management personnel;
5. quantitatively calculating the liquid production amount and the bottom hole flow pressure according to the indicator diagram, and qualitatively diagnosing the working condition of the oil well pump;
6. converting a working diagram of the underground oil well pump according to the big data artificial intelligence wave equation;
7. generating a single-well working diagram according to an energy mechanical balance principle and an oil extraction lifting principle;
8. carrying out online test according to the system load subtraction method and calculating the periodic load of the single well;
9. analyzing the oil-water well to obtain dynamic parameters;
10. the intelligent management platform of the oil-water well comprehensively covers the oil field production system so as to facilitate the implementation and management;
11. the oil reservoir oil extraction ground engineering technology deepens multi-factor linkage analysis;
12. and the overall optimization of the whole system is realized through technical measures and scheme planning of the oil field.
In the embodiment, an intelligent oil field platform is used for sharing an oil field dynamic database, a static database and an internet of things acquisition device, electric parameters such as current and voltage are acquired on a balanced multi-well pumping unit and uploaded to the intelligent oil field platform, the oil field dynamic and static databases are shared, active power is calculated through processing, and then the torque, the stress and the change value of the multi-well pumping unit are converted through an energy mechanics balance principle; according to the structural geometric shape characteristics of the multi-well machine, a well with large load change of a single well can be judged to be used as a key analysis target well; the load of the single well can be accurately calculated by using the load decreasing method for the target well. The oil well problem can be preliminarily analyzed and diagnosed by accurately calculating the load of a single well, and the oil well liquid production quantity and the flowing pressure can be quantitatively calculated by making a working diagram of an oil well pump. Analyzing the characteristics of the pump or diagnosing dozens of problems of the well pump; by combining the diagnosis result with the shared oil field database, well layers, well groups, blocks and oil field oil-water wells can be established or communicated. The dynamic change and the change influence factors of the oil field are intelligently analyzed, and corresponding optimization technical measures and oil field adjustment schemes are provided.
EXAMPLE III
As shown in fig. 2, a plurality of well machines simultaneously drive 8 pumping wells to work, physical numerical modeling of the system is utilized, load change curves of all the wells are drawn by combining data measured by the acquisition device, load curves of one well, two wells, three wells, four wells, five wells, six wells, seven wells, eight wells, normal total load and abnormal total load can be obtained, the load curve of the normal total load and the load curve of the abnormal total load are analyzed, the load curve of the eight wells is known to be abnormal, and fig. 3 shows the comparison condition of the normal load curve and the abnormal oil well load curve of the oil well.
In this embodiment, the single well problem can be judged by model analysis by using the physical numerical modeling of the system and combining the data measured by the acquisition device: the problem well with large load change in the system can be judged through the active power of the motor, and the well head with the problem can be judged through the change of the total load (the load of the fault well is greatly reduced).
Example four
The process of calculating the single well load by a subtractive method comprises the following steps:
collecting electrical parameters of the oil pumping unit through an internet-of-things data acquisition device, calculating the cycle load of all oil wells (such as 8 oil wells) working together, and generating a load curve 1;
after the eighth well is stopped, calculating the periodic load when the other 7 wells work together to generate a load curve 2;
as shown in fig. 4, the load curve 2 is subtracted from the load curve 1 to obtain a load curve (load curve 3) of the eighth well;
and so on:
calculating the periodic load of the joint work of all oil wells (such as 8 oil wells) to generate a load curve 1; after the seventh well is stopped, calculating the periodic load when the other 7 wells work together to generate a load curve 2; and subtracting the load curve 2 from the load curve 1 to obtain a load curve of the seventh well.
Calculating the periodic load of the joint work of all oil wells (such as 8 oil wells) to generate a load curve 1; after the sixth well is stopped, calculating the periodic load when the other 7 wells work together to generate a load curve 2; and subtracting the load curve 2 from the load curve 1 to obtain a load curve of the sixth well.
Until the load curve of each single well is calculated, the load change curve of each well head is drawn, and the load change curve is shown in figure 2.
In addition, can also be through the mode that sets up the tensiometer on the power flexible rope of each well, measure the pulling force change data of each well to drawing well head load change curve, when carrying out single well tensile test, implementing the parallel tensile test method of single well load flexible rope to the single well, correcting single well data, in order to realize accurate calculation: and the load calculation accuracy is calibrated by using the parallel pressure gauges, so that the calculation prediction accuracy of the system is ensured.
EXAMPLE five
According to one of the embodiments of the invention, the invention also discloses a single-machine multi-well pumping unit monitoring system based on artificial intelligence, which comprises: a memory for storing program instructions; a processor for invoking the program instructions stored in the memory to implement the monitoring method as follows: acquiring electrical parameter data of the pumping unit and/or reading data of an oil field database to acquire the electrical parameter data of the pumping unit; calculating the active power, the reactive power or the system efficiency data of the pumping unit according to the electrical parameter data of the pumping unit; according to the energy mechanics balance principle, the stress analysis is carried out on the pumping unit by combining active power, reactive power or system efficiency data, and one or more of the following analysis data are calculated: moment data, stress data, a moment variation value and a stress variation value; when the pumping unit drives all power output flexible ropes to work, calculating total load data, stopping a certain group of power output flexible ropes, entering a single-well shutdown state, calculating single-well shutdown load data, and subtracting the single-well shutdown load data from the total load data to obtain single-well load data of a shutdown pumping well; and judging the pumping well with abnormal work according to the stress analysis and the distribution structure of the multiple groups of power output flexible ropes of the pumping unit.
According to the single-machine multi-well pumping unit monitoring system based on artificial intelligence disclosed in the above embodiment, preferably, the monitoring method implemented by the processor calling the program instructions stored in the memory further includes: and acquiring a field monitoring video of the pumping unit and/or acquiring linkage data of the mobile terminal and a manager so as to implement full-time monitoring on the pumping unit and the oil well.
Preferably, the step of acquiring the electrical parameter data of the pumping unit specifically comprises: and acquiring electrical parameter data of the pumping unit and uploading the electrical parameter data to the oil field cloud platform.
According to the single-machine multi-well pumping unit monitoring system based on artificial intelligence disclosed in the above embodiment, preferably, the monitoring method implemented by the processor calling the program instructions stored in the memory further includes: and making a single well indicator diagram and an oil well pump indicator diagram according to the single well load data, and quantitatively calculating the liquid production data and the flowing pressure data of the oil well.
According to the single-machine multi-well pumping unit monitoring system based on artificial intelligence disclosed in the above embodiment, preferably, the monitoring method implemented by the processor calling the program instructions stored in the memory further includes: and sharing the single well indicator diagram, the oil pump indicator diagram, the liquid production data and the flow pressure data to the oil field cloud platform so as to establish or communicate an information sharing database among the well layer, the well group, the block and the oil-water well of the oil field.
According to the single-machine multi-well pumping unit monitoring system based on artificial intelligence disclosed in the above embodiment, preferably, the monitoring method implemented by the processor calling the program instructions stored in the memory further includes: establishing a fault diagnosis database based on artificial intelligence and big data, wherein multiple kinds of abnormal working condition data of the oil well are preset in the fault diagnosis database; and diagnosing the abnormal working condition of the oil pumping unit according to the matching degree of the indicator diagram, the electrical parameter data, the active power, the reactive power, the system efficiency data or the analysis data and the oil well abnormal working condition data.
According to the single-machine multi-well pumping unit monitoring system based on artificial intelligence disclosed in the above embodiment, preferably, the monitoring method implemented by the processor calling the program instructions stored in the memory further includes: and (4) carrying out tension test on the single-group power output flexible rope, and calibrating load calculation accuracy by using a parallel pressure meter.
According to the single-machine multi-well pumping unit monitoring system based on artificial intelligence disclosed in the above embodiment, preferably, the monitoring method implemented by the processor calling the program instructions stored in the memory further includes: according to the oil-water well layer, well group, block and dynamic change of oil field, the stroke and stroke frequency setting of pumping well and/or working parameters of pumping unit and oil pump are regulated.
EXAMPLE six
According to one embodiment of the invention, the invention further discloses a computer-readable storage medium, wherein the computer-readable storage medium stores program codes, and the program codes are used for realizing the monitoring method of the single-machine multi-well pumping unit based on the artificial intelligence disclosed in the first embodiment.
According to the embodiment of the invention, the load data of each single well can be obtained only by monitoring the main engine of the oil pumping unit, and the working state of each wellhead can be diagnosed. Specifically, the method comprises the following steps: the single-motor driven speed reducer single-shaft double-output of the oil pumping unit main machine drives 3-10 oil pumping wells with uniformly distributed phases through a plurality of flexible ropes and universal fixed pulleys to perform oil pumping operation. The system collects electrical parameters through the Internet of things, calculates the related power of the system, and intelligently diagnoses whether any one of the multiple wells has a problem. Aiming at the problem well, the stress change data and the stress change condition of the single well can be accurately calculated by adopting a successive subtraction method, and a single well indicator diagram is made; dozens of working conditions of the pump can be analyzed, and meanwhile, the liquid flow pressure of a single well can be calculated. On the basis, an oil field database is combined and shared, oil-water well layers, well groups, blocks and oil field dynamic changes are analyzed, an optimization measure scheme is provided, the system stroke frequency host is guided to optimize and control, and working parameters of a machine and a pump are adjusted. The method is beneficial to realizing energy conservation and efficiency improvement of oil field exploitation engineering and reducing investment.
All or part of the steps in the methods of the above embodiments may be implemented by controlling the related hardware through a program, the program may be stored in a readable storage medium, which includes Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically Erasable rewritable Read-Only Memory (EEPROM), compact disc Read-Only Memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other medium capable of being Read by a user to carry or store data.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A single-machine multi-well pumping unit monitoring method based on artificial intelligence is characterized in that a speed reducer of the single-machine multi-well pumping unit is connected with a double-crank power output mechanism, a first crank and a second crank are symmetrically arranged at two ends of a power output shaft of the speed reducer, a flexible rope led out from the first crank and a flexible rope led out from the second crank form a group of power output flexible ropes together, each group of power output flexible ropes drives one pumping well, and the single-machine multi-well pumping unit is provided with a plurality of groups of power output flexible ropes with homogeneous phase distribution; the method comprises the following steps:
acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and/or reading data of an oil field database to acquire the electrical parameter data of the oil pumping unit;
calculating the active power, the reactive power or the system efficiency data of the pumping unit according to the electrical parameter data of the pumping unit;
and (2) performing stress analysis on the pumping unit according to an energy mechanics balance principle by combining the active power, the reactive power or the system efficiency data, and calculating one or more of the following analysis data: moment data, stress data, a moment variation value and a stress variation value;
when the pumping unit drives all power output flexible ropes to work, calculating total load data, stopping a certain group of power output flexible ropes, entering a single-well shutdown state, calculating single-well shutdown load data, and subtracting the single-well shutdown load data from the total load data to obtain single-well load data of a shutdown pumping well;
and judging the pumping well with abnormal work according to the stress analysis and the distribution structure of the multiple groups of power output flexible ropes of the pumping unit.
2. The artificial intelligence-based single-machine multi-well pumping unit monitoring method according to claim 1, further comprising:
and acquiring a field monitoring video of the pumping unit and/or acquiring linkage data of the mobile terminal and a manager so as to implement full-time monitoring on the pumping unit and the oil well.
3. The single-machine multi-well pumping unit monitoring method based on artificial intelligence of claim 1, wherein the step of acquiring the pumping unit electrical parameter data by using the internet of things device acquisition system specifically comprises:
and acquiring electrical parameter data of the oil pumping unit by using an internet of things device acquisition system and uploading the electrical parameter data to an oil field cloud platform.
4. The artificial intelligence-based single-machine multi-well pumping unit monitoring method according to claim 1, further comprising:
and making a single well indicator diagram and an oil well pump indicator diagram according to the single well load data, and quantitatively calculating the liquid production data and the flowing pressure data of the oil well.
5. The artificial intelligence based single-machine multi-well pumping unit monitoring method according to claim 4, further comprising:
and sharing the single-well indicator diagram, the oil-well pump indicator diagram, the liquid production data and the flow pressure data to an oil field cloud platform so as to establish or communicate an information sharing database among well layers, well groups, blocks and oil-water wells of the oil field.
6. The artificial intelligence based single-machine multi-well pumping unit monitoring method according to any one of claims 1 to 5, further comprising:
establishing a fault diagnosis database based on artificial intelligence and big data, wherein multiple kinds of abnormal working condition data of the oil well are preset in the fault diagnosis database;
and diagnosing the abnormal working conditions of the pumping unit according to the matching degree of the indicator diagram, the electric parameter data, the active power, the reactive power, the system efficiency data or the analysis data and the abnormal working condition data of the oil well.
7. The artificial intelligence based single-machine multi-well pumping unit monitoring method according to any one of claims 1-5, wherein a single group of power output flexible ropes is subjected to a tension test, and load calculation accuracy is calibrated by using a parallel pressure gauge.
8. The artificial intelligence based single-machine multi-well pumping unit monitoring method according to any one of claims 1 to 5, further comprising:
and adjusting the working parameters of the oil pumping unit and the oil pumping pump according to the dynamic changes of the oil-water well layer, the well group, the block and the oil field.
9. The utility model provides a unit multiwell beam-pumping unit monitoring system based on artificial intelligence which characterized in that includes:
a memory for storing program instructions;
a processor for invoking the program instructions stored in the memory to implement the artificial intelligence based single-machine multi-well pumping unit monitoring method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores program code for implementing the artificial intelligence based single-machine multi-well pumping unit monitoring method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110702990.3A CN113445991B (en) | 2021-06-24 | 2021-06-24 | Artificial intelligence single-machine multi-well oil pumping machine monitoring method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110702990.3A CN113445991B (en) | 2021-06-24 | 2021-06-24 | Artificial intelligence single-machine multi-well oil pumping machine monitoring method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113445991A CN113445991A (en) | 2021-09-28 |
| CN113445991B true CN113445991B (en) | 2022-09-16 |
Family
ID=77812565
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110702990.3A Active CN113445991B (en) | 2021-06-24 | 2021-06-24 | Artificial intelligence single-machine multi-well oil pumping machine monitoring method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113445991B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113153227B (en) * | 2021-04-01 | 2022-07-15 | 中油智采(天津)科技有限公司 | Multiphase regulation and control multi-well pumping unit |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4413676A (en) * | 1981-09-04 | 1983-11-08 | Well Research, Inc. | Oil well monitoring device |
| US20080066901A1 (en) * | 2006-09-19 | 2008-03-20 | Weatherford/Lamb, Inc. | Box end sucker rod shear coupling |
| US8073665B2 (en) * | 2008-03-07 | 2011-12-06 | Schlumberger Technology Corporation | Analyzing an oilfield network for oilfield production |
| CN101545364B (en) * | 2009-04-24 | 2012-06-20 | 唐建宇 | Single machine multi-well horizontal type flexible energy-saving oil pumping unit |
| CN201818288U (en) * | 2010-10-28 | 2011-05-04 | 张启金 | Combined oil pumping unit for plurality of oil wells |
| CN202520288U (en) * | 2012-04-18 | 2012-11-07 | 王洪亮 | Working condition parameter remote monitoring pre-diagnosing device for oil pumping unit |
| CN103422851B (en) * | 2012-05-21 | 2016-08-03 | 王双全 | Oil well pump dynamic degree of filling well testing determines interval pumping system method |
| CN204060636U (en) * | 2014-09-14 | 2014-12-31 | 哈尔滨理工大学 | Dive oily multistage lifting type oil pumping system in down-hole |
| US10540594B2 (en) * | 2015-09-18 | 2020-01-21 | International Business Machines Corporation | Identifying abnormal pumpjack conditions |
| CN107288617B (en) * | 2016-07-21 | 2020-10-02 | 中国石油大学(北京) | Method and system for improving oil measuring precision of indicator diagram of pumping well |
| US10844854B2 (en) * | 2017-01-23 | 2020-11-24 | Caterpillar Inc. | Pump failure differentiation system |
| CN109255134B (en) * | 2017-07-12 | 2021-08-31 | 中国石油天然气股份有限公司 | Method for acquiring fault condition of pumping well |
| CN109098691A (en) * | 2018-08-01 | 2018-12-28 | 张洪源 | A kind of hydraulic oil pumping system and its application method |
| US11408271B2 (en) * | 2019-06-11 | 2022-08-09 | Noven, Inc. | Well pump diagnostics using multi-physics sensor data |
| CN112031748B (en) * | 2020-09-14 | 2023-09-01 | 南京富岛信息工程有限公司 | Oil pumping well abnormal condition diagnosis method based on indicator diagram characteristics |
| CN112502669A (en) * | 2020-10-01 | 2021-03-16 | 潍坊晨昊机械有限公司 | Double-drum non-beam pumping unit and control method |
| CN112861912A (en) * | 2021-01-08 | 2021-05-28 | 中国石油大学(北京) | Deep learning-based method and system for identifying indicator diagram of complex working condition of pumping well |
-
2021
- 2021-06-24 CN CN202110702990.3A patent/CN113445991B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113445991A (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101305187B (en) | System and method for optimizing down-hole fluid yield | |
| CN103161430B (en) | Beam-pumping unit jig frequency, balance real-time intelligent method of adjustment | |
| CN111105063A (en) | Fault prediction method, fault prediction device, model construction method, fault prediction device, processor and readable storage medium | |
| CN111896244B (en) | Fully mechanized mining equipment PHM system | |
| CN113445991B (en) | Artificial intelligence single-machine multi-well oil pumping machine monitoring method, system and storage medium | |
| CN202391390U (en) | Device for regulating stroke frequency and balance of pumping unit in real time | |
| CN110046409B (en) | ResNet-based steam turbine component health state evaluation method | |
| CN104405365A (en) | Pumping unit indicator diagram liquid production capacity measurement technology | |
| CN104265247A (en) | Automatic beam pumper balance adjustment device and automatic control method | |
| CN102268989A (en) | Method and system for acquiring online real-time data of working fluid level of pumping well | |
| CN111896254A (en) | Fault prediction system and method for variable-speed variable-load large rolling bearing | |
| CN107103425B (en) | Intelligent energy evaluation system for power generation equipment running state computer | |
| CN112257224A (en) | Method, system and terminal for overhauling state of steam turbine generator | |
| CN104373113A (en) | Diagnostic method for measuring annular working fluid level and working conditions of rod-pumped well by electric parameters | |
| CN116680607A (en) | On-line monitoring method for motor state of drilling pump based on LSTM neural network | |
| CN114483561B (en) | Method and device for displaying parameter signals through angle domain | |
| Zyuzev et al. | SRPU balance monitoring by wattmeter card | |
| CN115750304B (en) | Intelligent control system of green energy pumping unit | |
| CN114412447A (en) | Fault detection method and device for screw pump well | |
| CN102359368A (en) | Working fluid level prediction method for submersible reciprocating-type oil pumping unit based on support vector machine | |
| CN106066845B (en) | A kind of study estimation method of pumping-unit workdone graphic | |
| CN110617038A (en) | Oil pumping drive control and detection analysis device based on self-adaptive analysis | |
| CN116362078A (en) | Method and system for acquiring real state of gantry crane structure | |
| CN114109313B (en) | Digital oil pumping unit intelligent control method and system based on double stepping method | |
| CN110439537B (en) | Method for inverting ground indicator diagram by using electric indicator diagram of pumping unit |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |