CN113128734A - Method and device for predicting oil field yield - Google Patents
Method and device for predicting oil field yield Download PDFInfo
- Publication number
- CN113128734A CN113128734A CN201911394142.XA CN201911394142A CN113128734A CN 113128734 A CN113128734 A CN 113128734A CN 201911394142 A CN201911394142 A CN 201911394142A CN 113128734 A CN113128734 A CN 113128734A
- Authority
- CN
- China
- Prior art keywords
- oil field
- operator
- operators
- target
- prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 110
- 238000012216 screening Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000004519 manufacturing process Methods 0.000 claims description 98
- 238000012549 training Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 17
- 230000036961 partial effect Effects 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 19
- 238000004422 calculation algorithm Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Animal Husbandry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Mining & Mineral Resources (AREA)
- General Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for predicting oil field yield, which relate to the technical field of machine learning, utilize a machine learning algorithm to automatically find a better model suitable for predicting the yield of a target oil field from a plurality of known oil field yield prediction models, and also ensure the accuracy of the yield of the predicted oil field, and the main technical scheme of the invention is as follows: receiving an oil field yield prediction instruction, wherein the prediction instruction carries a target oil field identifier and current yield data of a target oil field; acquiring historical yield data corresponding to the target oil field according to the target oil field identification; obtaining a plurality of oil field yield prediction models, wherein each oil field yield prediction model is packaged into an independent operator; screening the operators by using historical yield data, and screening the operators matched with the target oil field from the operators; and processing the current yield data by calling an operator matched with the target oil field, executing the operation of predicting the future yield of the target oil field, and outputting a prediction result.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a method and a device for predicting oil field yield.
Background
The yield change of the oil field is very important for one oil field and is an important factor influencing the development and production process of the oil field and investment decision. The method is very important for oil field development by accurately predicting the decreasing rule of the oil field yield and the residual oil, and is a basis for scientifically managing the oil field and making an economic and feasible development scheme. If the yield of the oil field can be accurately predicted, the produced oil field can be better managed, the yield of the oil field can be reasonably controlled and optimized, more oil can be extracted from the underground, and the recovery efficiency and the development effect of the oil field can be improved.
At present, each oil field in China has its own oil field production management system, and the daily oil production, water production, liquid production and other data of each oil field, each oil production plant and each well are recorded in a production management system library. As a result, oil fields have accumulated a large amount of production data from which hundreds of oil field production prediction techniques and methods have been proposed since the 20 th century.
However, although there are many methods for predicting oil field production, each method has its limitations, and neither method nor technique is applicable to accurate prediction of all oil field production. At present, after a target oil field to be detected is determined, a prediction method and a model suitable for the target oil field need to be found manually from a large number of known prediction methods, so that the difficulty and the workload are high, the calculation is complex, and the realization is difficult.
Disclosure of Invention
In view of the above, the present invention provides a method and an apparatus for predicting oil field production, and the main objective of the present invention is to automatically find a better model suitable for the prediction of target oil field production from known oil field production prediction models by using a machine learning algorithm, so as to predict the future production of an oil field by using the better model to ensure the accuracy of the prediction result.
In order to achieve the above purpose, the present invention mainly provides the following technical solutions:
in one aspect, the invention provides a method for predicting oilfield production, comprising:
receiving an oil field yield prediction instruction, wherein the prediction instruction carries a target oil field identifier and current yield data of a target oil field;
acquiring historical yield data corresponding to the target oil field according to the target oil field identification;
obtaining a plurality of oilfield production prediction models, each of which is encapsulated into an independent operator;
screening the operators by utilizing the historical yield data, and screening out the operator matched with the target oilfield from the operators;
and processing the current yield data by calling an operator matched with the target oil field, executing the operation of predicting the future yield of the target oil field, and outputting a prediction result.
Optionally, the screening the plurality of operators by using the historical production data, and screening out an operator matched with the target oilfield from the plurality of operators, includes:
respectively training a plurality of operators by using historical yield data to obtain an optimal parameter corresponding to each operator;
and adjusting the corresponding operator according to the optimal parameter to obtain an operator matched with the target oilfield yield.
Optionally, after the operator matched with the target oilfield is screened from the plurality of operators, if the number of operators matched with the target oilfield is multiple, the method further includes:
if the number of operators matched with the target oil field is multiple, determining the operators matched with the target oil field as to-be-selected operators;
dividing the historical yield data into partial yield data corresponding to each preset time unit according to the preset time unit;
processing the partial yield data by using each operator to be selected to obtain a prediction result corresponding to each time unit;
searching a historical actual result corresponding to each time unit;
calculating the average error percentage obtained by processing the historical yield data by each operator to be selected according to the corresponding prediction result and the historical actual result of each time unit;
and selecting the operator with the average error percentage meeting a preset condition as a target operator, wherein the preset condition is the first N operators with the minimum average error percentage, or the operators with the minimum average error percentage, namely the first M%, and the N is a positive integer, and the M is a positive number.
Optionally, the processing the current production data by calling an operator matched with the target oilfield, executing an operation of predicting future production of the target oilfield, and outputting a prediction result includes:
calling the target operators to process the current yield data, and outputting a prediction result corresponding to each target operator;
forming a prediction result set by the prediction results respectively corresponding to each target operator;
and feeding back the prediction result set to a user.
Optionally, before the screening the plurality of operators by using the historical production data and screening out an operator matching the target oilfield from the plurality of operators, the method further includes:
analyzing the parameter dimension contained in the historical yield data;
judging whether the parameter dimension is matched with the parameter dimension which needs to be processed by the operator;
and if not, discarding the operator.
Optionally, before the screening the plurality of operators by using the historical production data and screening out an operator matching the target oilfield from the plurality of operators, the method further includes:
outputting the prediction result of each operator on the future production of the target oil field by adapting the historical production data to each operator;
acquiring historical actual results corresponding to the target oil field in the same time interval according to the time interval corresponding to the prediction result;
comparing the prediction result calculated by each operator with the historical actual result to judge whether the prediction error reaches a preset threshold value;
and if so, discarding the operator.
In another aspect, the present invention further provides an oilfield production prediction apparatus, including:
the system comprises a receiving unit, a judging unit and a judging unit, wherein the receiving unit is used for receiving an oil field yield prediction instruction, and the prediction instruction carries a target oil field identifier and current yield data of a target oil field;
the acquisition unit is used for searching historical yield data corresponding to the target oil field according to the target oil field identification received by the receiving unit;
the obtaining unit is further configured to obtain a plurality of oilfield production prediction models, and each oilfield production prediction model is packaged into an independent operator;
the screening unit is used for screening the operators acquired by the acquisition units by using the historical yield data received by the receiving unit, and screening the operators matched with the target oil field from the operators;
and the execution unit is used for processing the current yield data by calling the operator which is screened by the screening unit and matched with the target oil field, executing the operation of predicting the future yield of the target oil field and outputting a prediction result.
Optionally, the screening unit includes:
the training module is used for respectively training a plurality of operators by utilizing historical yield data to obtain the optimal parameters corresponding to each operator;
and the determining module is used for adjusting the corresponding operator according to the optimal parameters obtained by the training of the training module and determining the operator matched with the target oilfield yield.
Optionally, the apparatus further comprises:
the determining unit is further used for determining the operator matched with the target oil field as the operator to be selected if the operator matched with the target oil field is multiple after the operator matched with the target oil field is screened from the multiple operators;
the dividing unit is used for dividing the historical yield data into partial yield data corresponding to each preset time unit according to the preset time unit;
the processing unit is used for processing the partial yield data by utilizing each operator to be selected to obtain a prediction result corresponding to each time unit;
the searching unit is used for acquiring a historical actual result corresponding to each time unit;
the calculation unit is used for calculating the average error percentage obtained by processing the historical yield data by each operator to be selected according to the prediction result obtained by the processing unit corresponding to each time unit and the historical actual result obtained by the acquisition unit;
and the selecting unit is used for selecting the operator with the average error percentage which is calculated by the calculating unit and meets a preset condition as a target operator, wherein the preset condition is the first N operators with the minimum average error percentage, or the first M% operators with the minimum average error percentage, the N is a positive integer, and the M is a positive number.
Optionally, the execution unit includes:
the calling module is used for calling the target operator to process the current yield data;
the output module is used for outputting a prediction result corresponding to each target operator;
the composition module is used for composing the prediction results corresponding to each target operator into a prediction result set;
and the feedback module is used for feeding the prediction result set back to the user.
Optionally, the apparatus further comprises:
the analysis unit is used for analyzing the parameter dimensionality contained in the historical yield data before the operators are screened by using the historical yield data and the operators matched with the target oilfield are screened from the operators;
the judging unit is used for comparing the parameter dimension obtained by the analyzing unit with the parameter dimension required to be processed by the operator to judge whether the parameter dimension is matched with the operator;
and the abandoning unit is used for abandoning the operator when the judging unit judges that the parameter dimension obtained by the analyzing unit is matched with the parameter dimension which needs to be processed by the operator.
Optionally, the apparatus further comprises:
the forecasting unit is used for outputting forecasting results of each operator on the future production of the target oilfield by adapting the historical production data to each operator before screening the operators by using the historical production data and screening out the operators matched with the target oilfield from the operators;
the searching unit is further used for acquiring historical actual results corresponding to the target oil field in the same time interval according to the time interval corresponding to the prediction result;
the judging unit is further configured to judge whether a prediction error reaches a preset threshold value by comparing the prediction result predicted by each operator with the historical actual result obtained by the obtaining unit;
the abandoning unit is further used for abandoning the operator when the judging unit judges that the prediction error reaches a preset threshold value.
In still another aspect, the present invention further provides a storage medium, where the storage medium includes a stored program, where the program is executed to control a device where the storage medium is located to perform the method for predicting oilfield production as described above.
In yet another aspect, the present invention also provides an electronic device comprising at least one processor, and at least one memory, a bus connected to the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to invoke program instructions in the memory to perform the method for predicting oilfield production as described above.
By the technical scheme, the technical scheme provided by the invention at least has the following advantages:
the invention provides a method and a device for predicting oil field yield, which automatically find a better model suitable for predicting the target oil field yield from a plurality of known oil field yield prediction models by utilizing a machine learning algorithm. Compared with the prior art, the method solves the problems of large difficulty and workload, complex calculation and difficult reality caused by manually searching a prediction method and a model suitable for the target oil field. According to the method provided by the invention, for each target oil field to be measured, when the current yield data of the target oil field uploaded by a user is received, a better model for executing the prediction of the oil field yield is automatically and efficiently searched, and the better model is called to predict the future yield of the target oil field, so that the accuracy of the oil field yield prediction is ensured.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for predicting oilfield production according to an embodiment of the present invention;
FIG. 2 is a flow chart of another method for predicting oilfield production provided by an embodiment of the present invention;
FIG. 3 is a block diagram of an oilfield production prediction device according to an embodiment of the present invention;
FIG. 4 is a block diagram of another oilfield production prediction device according to an embodiment of the present invention;
fig. 5 is an electronic device for predicting oilfield production provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
The embodiment of the invention provides a method for predicting oil field yield, as shown in fig. 1, the method automatically finds a better model suitable for predicting the target oil field yield from a plurality of known oil field yield prediction models by using a machine learning algorithm, and the embodiment of the invention provides the following specific steps:
101. and receiving an oil field yield prediction instruction, wherein the prediction instruction carries a target oil field identifier and current yield data of the target oil field.
Wherein, the target oil field refers to the oil field to be executed with the prediction of the future production of the oil field.
In the embodiment of the invention, a man-machine interaction interface can be constructed in advance, the interface is used for receiving the issued future production instruction of the predicted specified oil field, after the target oil field identification carried by the predicted instruction and the current production data of the target oil field are analyzed, the background can directly call the relevant prediction method/model to automatically execute the prediction operation according to the data information carried by the predicted instruction, and the automatically executed prediction operation is the content recorded in the step 102 and the step 105.
It should be noted that, in the embodiment of the present invention, rather than building a platform for performing prediction of future oil field production, for a user, only a prediction instruction is issued, and the data information includes: the method comprises the steps of determining a target oil field to be predicted and inputting current yield data of the target oil field, automatically executing prediction by the built platform and feeding back a prediction result, so that the obtained oilfield yield prediction operation is simple and efficient, a user does not need to have professional computer knowledge, the user can call an optimized operator to predict the yield without writing codes, and the threshold for oilfield yield prediction is reduced.
102. And searching historical yield data corresponding to the target oil field according to the target oil field identification.
In the embodiment of the invention, after the target oilfield identifier is determined, historical production data can be searched from the production management system corresponding to the target oilfield.
The collected historical production data of the target oil field can be obtained according to the following steps of 8: 2 into training and test sets, if the historical production data is less than 5 points (i.e., 5 time units of data), such as: and 5 years and 5 days of history yield data, all the data are divided into training sets. For the embodiment of the invention, a machine learning model for searching operators suitable for executing yield prediction on a target oil field from a plurality of operators is constructed by utilizing a training set, and a test set is used for testing whether the quality of the constructed machine learning model reaches the standard or not.
103. A plurality of oilfield production prediction models are obtained, and each oilfield production prediction model is packaged into an independent operator.
Hundreds of oilfield production prediction techniques and methods are now being proposed. Generally speaking, the field prediction method can be divided into three categories: statistical model-based methods, mechanism model-based methods, and system function-based prediction methods. Specific exemplary statements are as follows:
the method based on the statistical model is to use mathematical statistics and analysis methods to fit historical data of historical oil production and water production of an oil field, a block or a single well from the angle of mathematical statistics to obtain formulas and models of various yield changes and predict future yield of the oil field. At present, a plurality of statistical prediction methods are available, mainly including a water flooding characteristic curve method, an empirical formula method, an Arps decreasing curve method, a generalized Weng's prediction model method, an HCZ method and the like.
The method based on the mechanism model is mainly based on the engineering mechanism of the oil field production, and the future yield of the oil field is predicted by utilizing the technologies and methods of numerical reservoir simulation, material balance, seepage mechanics and the like.
The prediction method based on the system function mainly predicts the yield of the oil field from the perspective of a system theory and a control theory.
In the embodiment of the invention, the oil field yield prediction method is packaged into an independent operator and stored into a machine learning library, so that after the target oil field to be predicted is determined, a better operator suitable for predicting the future yield of the target oil field is screened from the machine learning library.
Further, in the embodiment of the present invention, step 103 is in parallel relationship with step 101, and the two steps are not limited in sequence.
104. And screening the operators by using historical yield data, and screening the operators matched with the target oil field from the operators.
In the embodiment of the invention, historical yield data are adapted to the operators one by one, and the machine learning algorithm in the operators is a regression algorithm, such as: one of HuberRegener, Lasso, Ridge, SGDRegresorsor, LinearSVR, SVR, Desision TreeRegenerator, AdaBoostRegenerator, BaggingRegenerator, GradientBoostRegenerator and RandomForest Regenerator is continuously adjusted to enable the error of the predicted oil field yield of the operator after parameter adjustment to be closer to the minimum direction and to approach the minimum error as much as possible, the operator after parameter adjustment is obtained, and a better operator suitable for predicting the future yield of the target oil field is further screened out from the operator.
105. And processing the current yield data by calling an operator matched with the target oil field, executing the operation of predicting the future yield of the target oil field, and outputting a prediction result.
In the embodiment of the invention, after the better operator matched with the target oil field is determined, according to step 101, in the built platform for executing the prediction of the future yield of the oil field, the background calls the operator matched with the target oil field to process the current yield data, the prediction operation is executed to obtain the prediction result, and the prediction result is output through the human-computer interaction interface and fed back to the user.
Or, the better operator can be issued into an API by combining the established platform in a microservice mode for being directly called by business user operation, the user selects the designated operator, and the prediction operation is executed according to the prediction instruction issued by the user. No matter which mode, the operation of predicting the future yield of the oil field is simple, efficient, convenient and flexible.
The embodiment of the invention provides a method for predicting oil field yield. Compared with the prior art, the method solves the problems of large difficulty and workload, complex calculation and difficult reality caused by the fact that a prediction method and a model suitable for a target oil field need to be found out manually from a large number of known prediction methods. According to the method provided by the embodiment of the invention, for each target oil field to be measured, when the current yield data of the target oil field uploaded by a user is received, the better model for executing the prediction of the oil field yield is automatically and efficiently searched, the better model is called to predict the future yield of the target oil field, and the accuracy of the predicted oil field yield is also ensured.
In order to explain the above embodiments in more detail, another oilfield production prediction method is further provided in the embodiments of the present invention, as shown in fig. 2, the method adds a pre-screening step on operators, so as to reduce the workload of subsequently using machine learning to tune operators and select better operators, and for this embodiment of the present invention, the following specific steps are provided:
201. and receiving an oil field yield prediction instruction, wherein the prediction instruction carries a target oil field identifier and current yield data of the target oil field.
202. And searching historical yield data corresponding to the target oil field according to the target oil field identification.
203. A plurality of oilfield production prediction models are obtained, and each oilfield production prediction model is packaged into an independent operator.
In the embodiment of the present invention, please refer to steps 101 and 103 for the statements in steps 201 and 203, which are not described herein again.
204. And preliminarily filtering out operators which are not suitable for predicting the future production of the target oil field from a plurality of operators.
In the embodiment of the invention, a pre-screening step for operator execution is added, so that the method comprises the following steps: and operators which are obviously not suitable for predicting the future yield of the target oil field are filtered, so that the workload of subsequently utilizing machine learning to tune the operators and selecting better operators is reduced, and the efficiency of screening the better operators is improved. Specifically, the following two preliminary filtering methods can be included:
one way of preliminary filtration is: based on training data, that is, data used for training a machine learning model in historical yield data, multiple existing operators are preliminarily screened, and the specific steps may be as follows:
firstly, analyzing parameter dimensions contained in historical yield data; secondly, comparing the parameter dimension with the parameter dimension which needs to be processed by the operator to judge whether the parameter dimension is matched, and if the parameter dimension is not matched, directly discarding the operator.
For example: the parameter dimensions that the operator needs to process are: temperature, pressure, saturation, monthly oil production and daily gas production, but the historical production data only contain 3 parameter dimensions, so that the obvious data dimensions do not accord with each other, and the operator cannot be used for predicting the oil field production.
Another primary filtering method is as follows: based on a Bayesian network method, a network is constructed according to historical prediction results of operators, operators which are large in future yield error and obviously incapable of meeting the requirements in accuracy are filtered, and the following concrete statements are provided:
the historical yield data are adapted to each operator, the prediction result of each operator on the future yield of the target oil field is output, the historical actual result corresponding to the target oil field in the same time interval is obtained according to the time interval corresponding to the prediction result, the prediction result calculated by each operator is compared with the historical actual result, whether the prediction error reaches a preset threshold value is judged, and if yes, the operator is abandoned.
It should be noted that, in the embodiment of the present invention, one of the two filtering manners may be selected optionally, or may be used in combination, and after the encapsulated operators are primarily screened and those operators obviously unsuitable for target oilfield production prediction are removed, modeling is performed on the remaining operators, so as to form a group of machine learning and business mechanism models suitable for current oilfield production data.
205. And training a plurality of operators respectively by using historical yield data to obtain an optimal parameter corresponding to each operator, and adjusting the corresponding operator according to the optimal parameter to obtain an operator matched with the target oilfield yield.
In the embodiment of the present invention, a machine learning algorithm is used to perform an automatic parameter adjusting operation on each operator to obtain an optimal parameter corresponding to each operator, and specifically, the process of performing parameter adjusting on each operator may include: after each operator processes historical yield data to obtain a prediction result, comparing the prediction result with a historical actual result in the same time interval, automatically adjusting parameters of the operators by machine learning according to the difference between the prediction result and the historical actual result, and executing the prediction operation by the adjusted operators, repeating the steps until the difference between the prediction result and the historical actual result tends to be minimum, so that the automatic parameter adjusting process is equivalent to the process that the operators continuously execute the prediction operation and try for mistakes. Therefore, the automatic parameter adjustment is used for replacing the traditional manual parameter adjustment, the system automatically adjusts and optimizes the parameters of a single operator, and the best prediction effect of the single operator is automatically realized.
Further, for the embodiment of the present invention, if a plurality of operators matched with the target oilfield are obtained, a better operator can be further extracted from the target oilfield, so as to calculate the prediction result by using the better operator, instead of feeding the prediction result calculated by each matched operator back to the user, so as to reduce the amount of data fed back, make the feedback prediction result more targeted, and improve the accuracy of the feedback predicted oilfield output, specifically, the step of optimally selecting the better operator may include the following steps:
firstly, if a plurality of operators matched with the target oil field exist, the operators matched with the target oil field are obtained as the operators to be selected. According to the preset time unit, dividing the historical yield data into partial yield data corresponding to each preset time unit, and processing the partial yield data by using each operator to be selected to obtain a prediction result corresponding to each time unit.
For example: the historical yield data is multidimensional index data of the oil field with 5 years, so that the historical yield data is divided into corresponding historical yield data every year by selecting a preset time unit as a year.
Further, historical actual results corresponding to each time unit are obtained. For example, after the preset time unit is determined to be year, in the embodiment of the present invention, the actual historical results of each year are known data, so that the actual results can be directly obtained from the production management system corresponding to the current oil field.
And secondly, calculating the average error percentage obtained by processing the historical yield data by each operator to be selected according to the corresponding prediction result and the historical actual result of each time unit.
Next, according to the average error percentage obtained by processing the historical yield data by each operator to be selected, selecting an operator with the average error percentage meeting a preset condition as a target operator, where the preset condition is the first N operators with the minimum average error percentage, or the first M% operators with the minimum average error percentage, where N is a positive integer, and M is a positive number, and the specific statement is as follows:
for example: sorting the average error percentages corresponding to each operator to be selected according to the sequence of percentage values from small to large to obtain a value queue, and selecting the average error percentages with preset number according to the sequence from the first position to the last position in the value data queue, namely selecting the first N operators with the minimum average error percentage.
For another example: after obtaining the average error percentage value queue, according to the number of values included in the value queue, an operator of the top M% with the smallest average error percentage is selected, that is, a smaller value is selected from the value queue, but the selected number may be M% of the total number.
206. And processing the current yield data by calling an operator matched with the target oil field, executing the operation of predicting the future yield of the target oil field, and outputting a prediction result.
In the embodiment of the present invention, after obtaining a better target operator based on step 205, the target operator is called to process the current yield data, the prediction results corresponding to each target operator are output, the prediction results corresponding to each target operator are formed into a prediction result set, and the prediction result set is pushed to the user.
It should be noted that, in the embodiment of the present invention, it is more preferable to predict the target oil field yield by using multiple better operators, so as to feed back multiple prediction results to the user, where the prediction results are inevitably different, but the difference is already controllable and tends to the minimum error as much as possible, and since the prediction results are reference data of the predicted oil field yield for the user and are not equal to the future actual result, feeding back multiple prediction results to the user is equivalent to feeding back three results of high, medium, and low grades to the user, so that the user can more fully understand and analyze the prediction of the future oil field yield.
Further, as an implementation of the methods shown in fig. 1 and fig. 2, an embodiment of the present invention provides a device for predicting oilfield production. The embodiment of the apparatus corresponds to the embodiment of the method, and for convenience of reading, details in the embodiment of the apparatus are not repeated one by one, but it should be clear that the apparatus in the embodiment can correspondingly implement all the contents in the embodiment of the method. The device is applied to automatically find a better model suitable for the yield prediction of a target oil field from a plurality of known oil field yield prediction models, and particularly as shown in figure 3, the device comprises:
a receiving unit 301, configured to receive an oilfield yield prediction instruction, where the prediction instruction carries a target oilfield identifier and current yield data of a target oilfield;
an obtaining unit 302, configured to obtain historical yield data corresponding to the target oil field according to the target oil field identifier received by the receiving unit 301;
the obtaining unit 302 is further configured to obtain a plurality of oilfield production prediction models, where each oilfield production prediction model is packaged into an independent operator;
a screening unit 303, configured to screen the operators acquired by the acquiring unit 302 by using the historical yield data received by the receiving unit 301, and screen out an operator matched with the target oilfield from the operators;
and the execution unit 304 is configured to execute the operation of predicting the future yield of the target oilfield by calling the operator matched with the target oilfield and screened by the screening unit 303 to process the current yield data, and output a prediction result.
Further, as shown in fig. 4, the screening unit 303 includes:
a training module 3031, configured to train multiple operators respectively by using historical yield data, so as to obtain an optimal parameter corresponding to each operator;
a determining module 3032, configured to adjust a corresponding operator according to the optimal parameter obtained through training by the training module 3031, and determine an operator matched with the target oilfield yield.
Further, as shown in fig. 4, the apparatus further includes:
the determining unit 305 is further configured to, after an operator matched with the target oilfield is screened from the multiple operators, determine, if the operators matched with the target oilfield are multiple, the operator matched with the target oilfield as an operator to be selected;
a dividing unit 306, configured to divide the historical yield data into partial yield data corresponding to each preset time unit according to preset time units;
the processing unit 307 is configured to process the partial yield data by using each operator to be selected, so as to obtain a prediction result corresponding to each time unit;
the searching unit 308 is configured to search a historical actual result corresponding to each time unit;
a calculating unit 309, configured to calculate an average error percentage obtained by processing the historical yield data by each operator to be selected according to the prediction result obtained by the processing unit 307 corresponding to each time unit and the historical actual result found by the searching unit 308;
a selecting unit 310, configured to select, as a target operator, an operator whose average error percentage calculated by the calculating unit 309 meets a preset condition, where the preset condition is the first N operators with the smallest average error percentage, or the operator with the smallest average error percentage, which is the first M%, where N is a positive integer, and M is a positive number.
Further, as shown in fig. 4, the execution unit 304 includes:
a calling module 3041, configured to call the target operator to process the current yield data;
an output module 3042, configured to output a prediction result corresponding to each target operator;
a composition module 3043, configured to combine the prediction results corresponding to each target operator into a prediction result set;
a feedback module 3044, configured to feed back the prediction result set to the user.
Further, as shown in fig. 4, the apparatus further includes:
the analyzing unit 311 is configured to analyze a parameter dimension included in the historical yield data before the historical yield data is used to screen the plurality of operators and an operator matched with the target oilfield is screened from the plurality of operators;
a judging unit 312, configured to compare the parameter dimension obtained by the analyzing unit 311 with the parameter dimension that needs to be processed by the operator, and judge whether the parameter dimensions match;
a discarding unit 313, configured to discard the operator when the determining unit 312 determines that the parameter dimension obtained by the analyzing unit 311 matches the parameter dimension that needs to be processed by the operator.
Further, as shown in fig. 4, the apparatus further includes:
a prediction unit 314, configured to, before the screening of the plurality of operators by using the historical production data and the screening of the operator matching the target oilfield from the plurality of operators, output a prediction result of each operator on the future production of the target oilfield by adapting the historical production data to each operator;
the searching unit 308 is further configured to search, according to a time interval corresponding to the prediction result, a historical actual result corresponding to the target oilfield in the same time interval;
the determining unit 312 is further configured to determine whether a prediction error reaches a preset threshold value by comparing the prediction result predicted by each operator with the historical actual result found by the searching unit 308;
the discarding unit 313 is further configured to discard the operator when the determining unit 312 determines that the prediction error reaches the preset threshold.
In summary, embodiments of the present invention provide a method and an apparatus for predicting oilfield production, and the embodiments of the present invention automatically find a better model suitable for predicting the target oilfield production from known oilfield production prediction models by using a machine learning algorithm. Compared with the prior art, the method solves the problems of large difficulty and workload, complex calculation and difficult reality caused by the fact that a prediction method and a model suitable for a target oil field need to be found out manually from a large number of known prediction methods. According to the method provided by the embodiment of the invention, for each target oil field to be measured, when the current yield data of the target oil field uploaded by a user is received, the better model for executing the prediction of the oil field yield is automatically and efficiently searched, the better model is called to predict the future yield of the target oil field, and the accuracy of the predicted oil field yield is also ensured.
The device for predicting the oilfield production comprises a processor and a memory, wherein the receiving unit, the acquiring unit, the screening unit, the executing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. The kernel can be set to be one or more than one, a better model suitable for the prediction of the yield of the target oil field is automatically found from a plurality of known oil field yield prediction models by adjusting kernel parameters through a machine learning algorithm, and the accuracy of the yield of the predicted oil field is also ensured.
An embodiment of the present invention provides a storage medium on which a program is stored, the program implementing the method for predicting oilfield production when executed by a processor.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute the prediction method of the oilfield production.
An embodiment of the present invention provides an electronic device 40, as shown in fig. 5, the device includes at least one processor 401, and at least one memory 402 and a bus 403 connected to the processor 401; the processor 401 and the memory 402 complete communication with each other through the bus 403; processor 401 is configured to call program instructions in memory 402 to perform the field production prediction method described above.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device:
a method of predicting oilfield production, the method comprising: receiving an oil field yield prediction instruction, wherein the prediction instruction carries a target oil field identifier and current yield data of a target oil field; acquiring historical yield data corresponding to the target oil field according to the target oil field identification; obtaining a plurality of oilfield production prediction models, each of which is encapsulated into an independent operator; screening the operators by utilizing the historical yield data, and screening out the operator matched with the target oilfield from the operators; and processing the current yield data by calling an operator matched with the target oil field, executing the operation of predicting the future yield of the target oil field, and outputting a prediction result.
Further, the screening the operators by using the historical production data to screen out the operator matched with the target oilfield from the operators comprises: respectively training a plurality of operators by using historical yield data to obtain an optimal parameter corresponding to each operator; and adjusting the corresponding operator according to the optimal parameter to obtain an operator matched with the target oilfield yield.
Further, after the operator matched with the target oilfield is screened out from the plurality of operators, if the operator matched with the target oilfield is multiple, the method further includes: if the number of operators matched with the target oil field is multiple, determining the operators matched with the target oil field as to-be-selected operators; dividing the historical yield data into partial yield data corresponding to each preset time unit according to the preset time unit; processing the partial yield data by using each operator to be selected to obtain a prediction result corresponding to each time unit; searching a historical actual result corresponding to each time unit; calculating the average error percentage obtained by processing the historical yield data by each operator to be selected according to the corresponding prediction result and the historical actual result of each time unit; and selecting the operator with the average error percentage meeting a preset condition as a target operator, wherein the preset condition is the first N operators with the minimum average error percentage, or the operators with the minimum average error percentage, namely the first M%, and the N is a positive integer, and the M is a positive number.
Further, the processing the current production data by calling an operator matched with the target oil field, executing an operation of predicting future production of the target oil field, and outputting a prediction result includes: calling the target operators to process the current yield data, and outputting a prediction result corresponding to each target operator; forming a prediction result set by the prediction results respectively corresponding to each target operator; and feeding back the prediction result set to a user.
Further, before the screening the plurality of operators by using the historical production data and screening out the operator matched with the target oilfield from the plurality of operators, the method further comprises: analyzing the parameter dimension contained in the historical yield data; judging whether the parameter dimension is matched with the parameter dimension which needs to be processed by the operator; and if not, discarding the operator.
Further, before the screening the plurality of operators by using the historical production data and screening out the operator matched with the target oilfield from the plurality of operators, the method further comprises: outputting the prediction result of each operator on the future production of the target oil field by adapting the historical production data to each operator; acquiring historical actual results corresponding to the target oil field in the same time interval according to the time interval corresponding to the prediction result; comparing the prediction result calculated by each operator with the historical actual result to judge whether the prediction error reaches a preset threshold value; and if so, discarding the operator.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. The device may also include input/output interfaces, network interfaces, and the like.
The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip. The memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for predicting oilfield production, the method comprising:
receiving an oil field yield prediction instruction, wherein the prediction instruction carries a target oil field identifier and current yield data of a target oil field;
acquiring historical yield data corresponding to the target oil field according to the target oil field identification;
obtaining a plurality of oilfield production prediction models, each of which is encapsulated into an independent operator;
screening the operators by utilizing the historical yield data, and screening out the operator matched with the target oilfield from the operators;
and processing the current yield data by calling an operator matched with the target oil field, executing the operation of predicting the future yield of the target oil field, and outputting a prediction result.
2. The method of claim 1, wherein the using the historical production data to screen the plurality of operators to screen out operators from the plurality of operators that match the target field comprises:
respectively training a plurality of operators by using historical yield data to obtain an optimal parameter corresponding to each operator;
and adjusting the corresponding operator according to the optimal parameter to obtain an operator matched with the target oilfield yield.
3. The method of claim 1, wherein after screening out the operators matching the target field from the plurality of operators, if the operators matching the target field are a plurality of operators, the method further comprises:
if the number of operators matched with the target oil field is multiple, determining the operators matched with the target oil field as to-be-selected operators;
dividing the historical yield data into partial yield data corresponding to each preset time unit according to the preset time unit;
processing the partial yield data by using each operator to be selected to obtain a prediction result corresponding to each time unit;
searching a historical actual result corresponding to each time unit;
calculating the average error percentage obtained by processing the historical yield data by each operator to be selected according to the corresponding prediction result and the historical actual result of each time unit;
and selecting the operator with the average error percentage meeting a preset condition as a target operator, wherein the preset condition is the first N operators with the minimum average error percentage, or the operators with the minimum average error percentage, namely the first M%, and the N is a positive integer, and the M is a positive number.
4. The method of claim 3, wherein the processing the current production data by calling an operator matched to the target field, performing operations to predict future production from the target field, and outputting the prediction comprises:
calling the target operators to process the current yield data, and outputting a prediction result corresponding to each target operator;
forming a prediction result set by the prediction results respectively corresponding to each target operator;
and feeding back the prediction result set to a user.
5. The method of claim 1, wherein prior to said screening a plurality of said operators using said historical production data to screen an operator from said plurality of operators that matches said target field, said method further comprises:
analyzing the parameter dimension contained in the historical yield data;
judging whether the parameter dimension is matched with the parameter dimension which needs to be processed by the operator;
and if not, discarding the operator.
6. The method of claim 1, wherein prior to said screening a plurality of said operators using said historical production data to screen an operator from said plurality of operators that matches said target field, said method further comprises:
outputting the prediction result of each operator on the future production of the target oil field by adapting the historical production data to each operator;
acquiring historical actual results corresponding to the target oil field in the same time interval according to the time interval corresponding to the prediction result;
comparing the prediction result calculated by each operator with the historical actual result to judge whether the prediction error reaches a preset threshold value;
and if so, discarding the operator.
7. An apparatus for predicting oilfield production, the apparatus comprising:
the system comprises a receiving unit, a judging unit and a judging unit, wherein the receiving unit is used for receiving an oil field yield prediction instruction, and the prediction instruction carries a target oil field identifier and current yield data of a target oil field;
the acquisition unit is used for searching historical yield data corresponding to the target oil field according to the target oil field identification received by the receiving unit;
the obtaining unit is further configured to obtain a plurality of oilfield production prediction models, and each oilfield production prediction model is packaged into an independent operator;
the screening unit is used for screening the operators acquired by the acquisition units by using the historical yield data received by the receiving unit, and screening the operators matched with the target oil field from the operators;
and the execution unit is used for processing the current yield data by calling the operator which is screened by the screening unit and matched with the target oil field, executing the operation of predicting the future yield of the target oil field and outputting a prediction result.
8. The apparatus of claim 7, wherein the screening unit comprises:
the training module is used for respectively training a plurality of operators by utilizing historical yield data to obtain the optimal parameters corresponding to each operator;
and the determining module is used for adjusting the corresponding operator according to the optimal parameters obtained by the training of the training module and determining the operator matched with the target oilfield yield.
9. A storage medium comprising a stored program, wherein the program, when executed, controls a device on which the storage medium is located to perform the method of predicting oilfield production as defined in any one of claims 1 to 6.
10. An electronic device, comprising at least one processor, and at least one memory, bus connected to the processor;
the processor and the memory complete mutual communication through the bus;
the processor is configured to invoke program instructions in the memory to perform the method of predicting oilfield production as defined in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911394142.XA CN113128734A (en) | 2019-12-30 | 2019-12-30 | Method and device for predicting oil field yield |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911394142.XA CN113128734A (en) | 2019-12-30 | 2019-12-30 | Method and device for predicting oil field yield |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113128734A true CN113128734A (en) | 2021-07-16 |
Family
ID=76767693
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911394142.XA Pending CN113128734A (en) | 2019-12-30 | 2019-12-30 | Method and device for predicting oil field yield |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128734A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759363A (en) * | 2022-11-01 | 2023-03-07 | 昆仑数智科技有限责任公司 | Model training method and device, and recovery ratio determining method, device and equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104238545A (en) * | 2014-07-10 | 2014-12-24 | 中国石油大学(北京) | Fault diagnosis and pre-warning system in oil refining production process and establishment method thereof |
| US20160208582A1 (en) * | 2015-01-19 | 2016-07-21 | International Business Machines Corporation | Resource identification using historic well data |
| CN109740661A (en) * | 2018-12-28 | 2019-05-10 | 沈阳工业大学 | A kind of well fluid level adaptive forecasting method based on fuzzy evaluation |
| CN109902329A (en) * | 2018-09-21 | 2019-06-18 | 长江大学 | A kind of reservoir modeling auxiliary history-matching method, system, storage medium and equipment |
| CN110348137A (en) * | 2019-07-15 | 2019-10-18 | 西南石油大学 | A kind of water-drive pool seepage field evaluation method based on Vector Autoression Models |
-
2019
- 2019-12-30 CN CN201911394142.XA patent/CN113128734A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104238545A (en) * | 2014-07-10 | 2014-12-24 | 中国石油大学(北京) | Fault diagnosis and pre-warning system in oil refining production process and establishment method thereof |
| US20160208582A1 (en) * | 2015-01-19 | 2016-07-21 | International Business Machines Corporation | Resource identification using historic well data |
| CN109902329A (en) * | 2018-09-21 | 2019-06-18 | 长江大学 | A kind of reservoir modeling auxiliary history-matching method, system, storage medium and equipment |
| CN109740661A (en) * | 2018-12-28 | 2019-05-10 | 沈阳工业大学 | A kind of well fluid level adaptive forecasting method based on fuzzy evaluation |
| CN110348137A (en) * | 2019-07-15 | 2019-10-18 | 西南石油大学 | A kind of water-drive pool seepage field evaluation method based on Vector Autoression Models |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115759363A (en) * | 2022-11-01 | 2023-03-07 | 昆仑数智科技有限责任公司 | Model training method and device, and recovery ratio determining method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109587713B (en) | Network index prediction method and device based on ARIMA model and storage medium | |
| CN109242135B (en) | Model operation method, device and business server | |
| US9129228B1 (en) | Robust and fast model fitting by adaptive sampling | |
| CN109816221A (en) | Decision of Project Risk method, apparatus, computer equipment and storage medium | |
| CN110991495B (en) | Method, system, medium, and apparatus for predicting product quality in manufacturing process | |
| CN110969600A (en) | Product defect detection method and device, electronic equipment and storage medium | |
| US20230034061A1 (en) | Method for managing proper operation of base station and system applying the method | |
| CN110377519B (en) | Performance capacity test method, device and equipment of big data system and storage medium | |
| CN114918581A (en) | Welding parameter processing method and device, storage medium and processor | |
| CN111881058A (en) | Software engineering quality prediction method | |
| CN114238402A (en) | Alarm data processing method and device, storage medium and electronic equipment | |
| CN113128734A (en) | Method and device for predicting oil field yield | |
| CN110543869A (en) | Ball screw service life prediction method and device, computer equipment and storage medium | |
| CN109978172B (en) | Resource pool utilization rate prediction method and device based on extreme learning machine | |
| CN117711295A (en) | Display module control method, device, chip and medium based on artificial intelligence | |
| CN117648451A (en) | Data management method, system, device and medium for image processing | |
| CN113705074A (en) | Chemical accident risk prediction method and device | |
| CN111849544B (en) | Hydrocracking product quality automatic control method, device and storage | |
| CN115169832A (en) | Sensitivity analysis method and system based on curve form change | |
| CN114610590A (en) | Method, device and equipment for determining operation time length and storage medium | |
| CN114491936A (en) | Method and device for determining service life of high-pressure manifold and high-pressure manifold system | |
| CN114116482A (en) | Method and device for testing stability of CAD (computer-aided design) software, storage medium and processor | |
| CN114399209A (en) | Drilling operation risk prediction method, system and equipment based on edge cloud integration | |
| CN114676868A (en) | Logistics cargo quantity prediction method and device, computer equipment and storage medium | |
| CN115757002A (en) | Energy consumption determination method, device and equipment and computer readable 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 |