A method and system for predicting energy consumption in the oil and gas industry

Abstract

The application discloses a kind of oil and gas field industry energy consumption prediction method and system, the method includes: collecting crude oil production, natural gas production and energy consumption, generates historical production energy consumption dataset;Using k-means clustering algorithm is classified to crude oil production and natural gas production two attribute data, obtain classification result and mark each category;The data set corresponding to each marked category is normalized respectively, records the normalization rule of each category, with the crude oil production and natural gas production as input, energy consumption as output, respectively establish and train the neural network energy consumption prediction model corresponding to each category;Get crude oil planned production and natural gas planned production, determine the category of planned production based on the classification result, and according to the normalization rule corresponding to the category, normalization is handled, and the normalized data is input into the energy consumption prediction model corresponding to the category, to obtain energy consumption prediction result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of oil and gas field production, in particular to a method and system for predicting energy consumption in the oil and gas field industry. BACKGROUND

[0002] Energy is the basis of economic development. With the rapid development of social economy worldwide, the consumption of energy has also increased dramatically, and energy problems have become increasingly prominent globally. At the same time, oil and gas field enterprises also face problems such as increased production energy consumption and relatively low production in the daily production process.

[0003] In response to the requirements of energy saving and emission reduction in the petrochemical industry, technical energy saving and management energy saving have become the focus of oil and gas field enterprises. Energy consumption prediction can help enterprises realize energy saving and consumption reduction, help oil and gas field enterprises reasonably arrange production, reduce energy dissipation in the production process, and improve the energy management efficiency of oil and gas field enterprises by analyzing historical energy consumption data and relying on artificial intelligence algorithms to ultimately predict future energy consumption of enterprises.

[0004] In the prior art, the energy consumption prediction problem is only regarded as a regression problem, that is, the influence factors of energy consumption are determined, which are used as a feature vector and input into a selected regression model, and then the energy consumption corresponding to the feature vector is used as an output to train the model until the loss function of the model converges. In this process, the internal spatial distribution characteristics of the data set are not considered. In the entire data set, their spatial distribution will form clusters with different distributions, and each cluster is a small subset with strong internal correlation. In the prediction process, the accuracy of the prediction result is low and the reference value is poor because the characteristics of each cluster are not fully considered.

[0005] In summary, there is an urgent need for a technical solution that can overcome the above problems, fully consider the characteristics of the data set, and improve the accuracy of the prediction result. SUMMARY

[0006] To overcome the above problems, the present application provides a method and system for predicting energy consumption in the oil and gas field industry, which can solve the problem of predicting energy consumption in the production process of oil and gas field enterprises, help oil and gas field enterprises reasonably arrange production, reduce energy dissipation in the production process, and improve the energy management efficiency of oil and gas field enterprises.

[0007] In a first aspect of the embodiments of the present application, a method for predicting energy consumption in the oil and gas field industry is provided, which comprises:

[0008] Collecting crude oil production, natural gas production and energy consumption to generate a historical production energy consumption data set;

[0009] The crude oil production and the natural gas production are selected as attribute data, the k-means clustering algorithm is used to classify the historical production energy consumption dataset according to the attribute data, a classification result is obtained, and each category is labeled;

[0010] The data set corresponding to each labeled category is normalized respectively, the natural gas production and the crude oil production are mapped to 0 to 1, the normalization rule of each category is recorded, the crude oil production and the natural gas production are taken as input, the energy consumption is taken as output, a neural network energy consumption prediction model corresponding to each category is established and trained respectively, and an energy consumption prediction model corresponding to each category is obtained;

[0011] The planned crude oil production and the planned natural gas production are obtained, the category to which the planned crude oil production and the planned natural gas production belong is determined based on the classification result, normalization processing is performed according to the normalization rule corresponding to the category, the normalized data is input into the energy consumption prediction model corresponding to the category, and an energy consumption prediction result is obtained.

[0012] In a second aspect of the embodiment of the present application, an oil and gas field industry energy consumption prediction system is provided, and the system comprises:

[0013] A data acquisition module is configured to acquire the crude oil production, the natural gas production and the energy consumption, and generate a historical production energy consumption dataset;

[0014] A classification module is configured to select the crude oil production and the natural gas production as attribute data, use the k-means clustering algorithm to classify the historical production energy consumption dataset according to the attribute data, obtain a classification result, and label each category;

[0015] A data processing module is configured to perform normalization processing on the data set corresponding to each labeled category, map the natural gas production and the crude oil production to 0 to 1, record the normalization rule of each category, take the crude oil production and the natural gas production as input, take the energy consumption as output, establish and train a neural network energy consumption prediction model corresponding to each category respectively, and obtain an energy consumption prediction model corresponding to each category;

[0016] A prediction module is configured to obtain the planned crude oil production and the planned natural gas production, determine the category to which the planned crude oil production and the planned natural gas production belong based on the classification result, perform normalization processing according to the normalization rule corresponding to the category, input the normalized data into the energy consumption prediction model corresponding to the category, and obtain an energy consumption prediction result.

[0017] In a third aspect of the embodiments of the present application, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method for predicting energy consumption in the oil and gas field industry when executing the computer program.

[0018] In a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, wherein the computer readable storage medium stores a computer program, and the computer program is executable on a processor to implement the method for predicting energy consumption in the oil and gas field industry.

[0019] The method and system for predicting energy consumption in the oil and gas field industry provided by the present application can effectively solve the problem of predicting energy consumption in the production process of oil and gas field enterprises, reduce energy dissipation in the production process of oil and gas field enterprises, and improve the energy management efficiency and intelligent management level of oil and gas field enterprises. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0021] Figure 1 is a flowchart of the method for predicting energy consumption in the oil and gas field industry according to an embodiment of the present application.

[0022] Figure 2 is a flowchart of collecting historical production energy consumption data set according to a specific embodiment of the present application.

[0023] Figure 3 is a flowchart of data classification according to a specific embodiment of the present application.

[0024] Figure 4 is a flowchart of data processing of an embodiment of the present application.

[0025] Figure 5 is a flowchart of oil and gas field energy consumption prediction of an embodiment of the present application.

[0026] Figure 6 is a schematic diagram of a prediction system architecture of oil and gas field industry energy consumption of an embodiment of the present application.

[0027] Figure 7 is a schematic diagram of a computer device structure of an embodiment of the present application. DETAILED DESCRIPTION

[0028] The principles and spirits of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present application, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0029] Those skilled in the art know that the embodiments of the present application can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present disclosure can be embodied in the form of a complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0030] According to the embodiments of the present application, a prediction method and system of oil and gas field industry energy consumption are provided.

[0031] The principles and spirits of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are given only to enable those skilled in the art to better understand and implement the present application, and do not limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0032] Figure 1 is a flowchart of a prediction method of oil and gas field industry energy consumption of an embodiment of the present application. As shown in Figure 1 , the method comprises:

[0033] Step S101, collecting crude oil production, natural gas production and energy consumption to generate a historical production energy consumption dataset;

[0034] Step S102, selecting the crude oil production and natural gas production as attribute data, using a k-means clustering algorithm to classify the historical production energy consumption dataset according to the attribute data, obtaining a classification result and marking each category;

[0035] Step S103, normalize the data set corresponding to each category of the mark respectively, map the natural gas production and crude oil production to between 0 and 1, record the normalization rule of each category, take the crude oil production and natural gas production as input and the energy consumption as output, and establish and train a neural network energy consumption prediction model corresponding to each category to obtain an energy consumption prediction model corresponding to each category.

[0036] Step S104, obtain the planned crude oil production and natural gas production, determine the category to which the planned crude oil production and natural gas production belong on the basis of the classification result, perform normalization processing according to the normalization rule corresponding to the category, input the normalized data into the energy consumption prediction model corresponding to the category, and obtain an energy consumption prediction result.

[0037] In an embodiment, step S101 further includes:

[0038] checking whether there is missing data in the historical production energy consumption data set;

[0039] if there is, filling the missing data by using the arithmetic mean of adjacent data;

[0040] after filling, manually confirming the rationality, if not, correcting, and obtaining a data complete and reasonable historical production energy consumption data set.

[0041] In step S101, at least 60 historical data are collected, each corresponding to the crude oil production, natural gas production and energy consumption of one month. That is, at least 5 years of historical production data and energy consumption data are collected.

[0042] In step S102, when the k-means clustering algorithm is used to classify the historical production energy consumption data set according to attribute data, the number of classification categories is 2-4; wherein, the number of historical data and the number of classification categories can be adjusted according to actual conditions to ensure that the number of data items contained in each category is not less than 20.

[0043] In step S103, the specific process further includes:

[0044] taking the monthly crude oil production and natural gas production in the historical production energy consumption data set as input and the monthly energy consumption as output, respectively establishing and training a three-layer neural network energy consumption prediction model containing 2 input layer nodes and 1 output layer node, and obtaining an energy consumption prediction model corresponding to each category after training.

[0045] Among them, the number of intermediate layer neurons in the three-layer neural network energy consumption prediction model can be between 2 and 4, which can be determined according to the size of the data set in each category.

[0046] In step S104, the specific process further includes:

[0047] The planned crude oil production and the planned natural gas production are acquired, and a KNN algorithm is used to determine the category to which the planned crude oil production and the planned natural gas production belong based on the classification result.

[0048] In order to more clearly explain the prediction method of the energy consumption of the oil and gas field industry, each step will be described below in combination with a specific embodiment, however, it should be noted that the embodiment is only used to better illustrate the present application and does not constitute an improper limitation on the present application.

[0049] Step S101:

[0050] Reference Figure 2 is a flowchart of a process of collecting a historical production energy consumption data set of a specific embodiment of the present application. As shown in Figure 2 , the specific process is as follows:

[0051] Step S11, according to the time sequence, collect the historical monthly natural gas production, crude oil production and comprehensive energy consumption data of the oil and gas field enterprise within a period of time in the form of a triple data D(X1, X2, Y), wherein X1 represents the monthly natural production of the enterprise, X2 represents the monthly crude oil production of the enterprise, and Y represents the monthly comprehensive energy consumption of the enterprise.

[0052] When collecting historical data, it is necessary to ensure that the amount of collected triple data is not less than 60, that is, at least 5 years of monthly historical production data and energy consumption data of the enterprise.

[0053] Step S12, arrange all the triple data in time sequence and check whether there is a missing value; if there is a missing value, execute step S13; if there is no missing value, execute step S14.

[0054] Step S13, use the arithmetic mean of adjacent data to replace the missing value, and consult business experts to ensure the validity and accuracy of the newly calculated missing value.

[0055] Since the filled missing value is the arithmetic mean of adjacent data, there may be unreasonable cases, so manual confirmation can be performed to ensure the validity and accuracy of the missing value.

[0056] Step S14, take this data set as a historical production energy consumption data set and mark it as D i (X1, X2, Y).

[0057] Step S102:

[0058] Reference Figure 3 is a flowchart of a data classification process of a specific embodiment of the present application. As shown in Figure 3The specific process is shown in the figure:

[0059] In step S21, the K-means clustering algorithm is used to classify the data set D i (X1, X2, Y) according to the attribute (X1, X2). In the classification process, the number of categories M is ensured to be between 2 and 4, and the number of data items contained in each category is ensured to be not less than 20.

[0060] In step S22, the classification result is obtained, and each category is marked as C i(i＝1,2,3…) .

[0061] Step S103:

[0062] Referring to Figure 4 , the flowchart of the data processing of a specific embodiment of the present application is shown. As Figure 4 shown, the specific process is as follows:

[0063] In step S31, for the data set D i (X1, X2, Y) in each category C i , the (X1, X2) attribute is normalized, and the value of the two attributes is mapped to between 0 and 1, and the normalization rule is recorded.

[0064] In step S32, the normalized data in category C i is marked as d i (x1, x2, Y); in each category, a three-layer neural network energy consumption prediction model is constructed, the input node contains two neurons, the middle layer contains 3 neurons (the number of neurons can be determined according to the size of the data set), and the output layer contains one neuron. In the training process, the (x1, x2) attribute is used as the input of the network, and Y is used as the output of the network. After training, the root mean square error RMSE is used as the evaluation index of the network, and the neural network corresponding to each category C i(i＝1，2，…,M) is marked as N i(i＝1，2，…,M) .

[0065] Step S104:

[0066] Referring to Figure 5 , the flowchart of the oil and gas field energy consumption prediction of a specific embodiment of the present application is shown. As Figure 5 shown, the specific process is as follows:

[0067] In step S41, the crude oil production and natural gas production of an enterprise in the future several months are collected, and the binary tuple T i (Z1, Z2) is marked, and the attribute (Z1, Z2) represents the natural gas production and the crude oil production.

[0068] Step S42, the two-tuple data set T i Adopting KNN algorithm, judging the specific category C it belongs to i (As described in step S102).

[0069] Step S43, according to the normalization rule corresponding to its category, normalizing the data set, and marking the normalized data set as t i (z1, z2);

[0070] Step S44, inputting the (z1, z2) attribute of the data set to the category C i corresponding neural network N i , marking the output of the network as R', and obtaining the final energy consumption prediction result.

[0071] It should be noted that although the operations of the method of the present application are described in a specific order in the above embodiments and drawings, this does not require or imply that the operations must be performed in this specific order, or that all of the shown operations must be performed to achieve the desired result. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be divided into multiple steps.

[0072] After introducing the method of the exemplary embodiment of the present application, next, with reference to Figure 6 a prediction system for energy consumption in the oil and gas field industry according to the exemplary embodiment of the present application is introduced.

[0073] The implementation of the prediction system for energy consumption in the oil and gas field industry can refer to the implementation of the above method, and the repeated parts will not be described again. The term "module" or "unit" used below can be a combination of software and / or hardware that achieves a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware, or a combination of software and hardware implementation is also possible and contemplated.

[0074] Based on the same inventive concept, the present application also proposes a prediction system for energy consumption in the oil and gas field industry, as shown in Figure 6 , the system comprises:

[0075] The data acquisition module 610 is used to acquire crude oil production, natural gas production and energy consumption, and generate a historical production energy consumption data set;

[0076] The classification module 620 is used to select the crude oil production and natural gas production as attribute data, and classify the historical production energy consumption data set according to the attribute data by adopting a k-means clustering algorithm, to obtain a classification result and mark each category;

[0077] The data processing module 630 is configured to perform normalization processing on the data set corresponding to each category of the label respectively, map the natural gas production and the crude oil production to a range of 0 to 1, record the normalization rule of each category, take the crude oil production and the natural gas production as input and the energy consumption as output, establish and train a neural network energy consumption prediction model corresponding to each category respectively, and obtain an energy consumption prediction model corresponding to each category.

[0078] The prediction module 640 is configured to obtain a planned crude oil production and a planned natural gas production, determine the category to which the planned crude oil production and the planned natural gas production belong based on the classification result, perform normalization processing according to the normalization rule corresponding to the category, input the normalized data into the energy consumption prediction model corresponding to the category, and obtain an energy consumption prediction result.

[0079] In an embodiment, the data collection module 610 is further configured to:

[0080] check whether there is missing data in the historical production energy consumption data set;

[0081] if there is, fill the missing data by using the arithmetic mean of adjacent data;

[0082] after filling, manually confirm the rationality, if the rationality is not confirmed, correct the historical production energy consumption data set to obtain a complete and reasonable historical production energy consumption data set.

[0083] In an embodiment, the data collection module 610 collects at least 60 historical data, and each historical data corresponds to the crude oil production, the natural gas production and the energy consumption of one month.

[0084] In an embodiment, when the classification module 620 classifies the historical production energy consumption data set according to attribute data by using the k-means clustering algorithm, the number of classification categories is 2-4.

[0085] In an embodiment, the data processing module 630 is specifically configured to:

[0086] take the monthly crude oil production and the monthly natural gas production in the historical production energy consumption data set as input and the monthly energy consumption as output, establish and train a three-layer neural network energy consumption prediction model including two input layer nodes and one output layer node respectively, and obtain the energy consumption prediction model corresponding to each category after the training is completed.

[0087] In an embodiment, the prediction module 640 is specifically configured to:

[0088] obtain a planned crude oil production and a planned natural gas production, determine the category to which the planned crude oil production and the planned natural gas production belong based on the classification result by using the KNN algorithm.

[0089] It should be noted that, although several modules of the prediction system of energy consumption in the oil and gas field industry are mentioned in the foregoing detailed description, such a division is merely exemplary and not mandatory. Indeed, according to embodiments of the application, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided into several modules.

[0090] Based on the foregoing inventive concept, as Figure 7 The application also proposes a computer device 700 comprising a memory 710, a processor 720 and a computer program 730 stored on the memory 710 and executable on the processor 720, the processor 720 implementing the foregoing method for predicting energy consumption in the oil and gas field industry when executing the computer program 730.

[0091] Based on the foregoing inventive concept, the application proposes a computer readable storage medium storing a computer program, the computer program being executable by a processor to implement the foregoing method for predicting energy consumption in the oil and gas field industry.

[0092] The method and system for predicting energy consumption in the oil and gas field industry according to the application, by collecting crude oil production, natural gas production and energy consumption, generates a historical production energy consumption dataset; selects the crude oil production and natural gas production as attribute data, classifies the historical production energy consumption dataset according to the attribute data using a k-means clustering algorithm, obtains a classification result and labels each category; normalizes the dataset corresponding to each labeled category respectively, maps the natural gas production and crude oil production two attributes to between 0 and 1, records the normalization rule of each category, takes the crude oil production and natural gas production as input and the energy consumption as output, respectively establishes and trains a neural network energy consumption prediction model corresponding to each category, and obtains an energy consumption prediction model corresponding to each category; obtains a planned crude oil production and a planned natural gas production, determines the category to which the planned crude oil production and the planned natural gas production belong based on the classification result, and performs normalization processing according to the normalization rule corresponding to the category, inputs the normalized data into the energy consumption prediction model corresponding to the category, and obtains an energy consumption prediction result. The method effectively solves the problem of predicting energy consumption in the production process of oil and gas field enterprises, reduces energy dissipation in the production process of oil and gas field enterprises, and improves the energy management efficiency and intelligent management level of oil and gas field enterprises.

[0093] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0094] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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 illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 means for performing each of the functions specified in the flowchart illustrations and / or block diagrams.

[0095] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 means for performing each of the functions specified in the flowchart illustrations and / or block diagrams.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 means for performing each of the functions specified in the flowchart illustrations and / or block diagrams.

[0097] Finally, it should be noted that the above-described embodiments are merely specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit the present application, and the protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacements to some technical features therein, within the technical scope disclosed by the present application. Such modifications, changes or replacements do not cause the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method of predicting energy consumption in the oil and gas industry, characterized by, The method comprises: Collecting crude oil production, natural gas production and energy consumption to generate a historical production energy consumption dataset; Selecting the crude oil production and natural gas production as attribute data, and classifying the historical production energy consumption dataset according to the attribute data by using a k-means clustering algorithm to obtain a classification result and mark each category; Performing normalization processing on the data set corresponding to each marked category, mapping the natural gas production and crude oil production two attributes to between 0 and 1, recording the normalization rule of each category, taking the crude oil production and natural gas production as input and the energy consumption as output, respectively establishing and training a neural network energy consumption prediction model corresponding to each category to obtain an energy consumption prediction model corresponding to each category; Obtaining planned crude oil production and planned natural gas production, determining the category to which the planned crude oil production and planned natural gas production belong on the basis of the classification result, and performing normalization processing according to the normalization rule corresponding to the category, inputting the normalized data into the energy consumption prediction model corresponding to the category to obtain an energy consumption prediction result; In the step of collecting crude oil production, natural gas production and energy consumption to generate a historical production energy consumption dataset, the following steps are included: According to the triple data format D ( X 1, X 2, Y ) According to the time sequence, collect the monthly natural gas production, crude oil production and comprehensive energy consumption data of the oil and gas field enterprise history in a period of time, wherein, X 1 represents the monthly natural production of the enterprise, X 2 represents the monthly crude oil production of the enterprise, Y represents the monthly comprehensive energy consumption of the enterprise; When collecting historical data, the amount of collected triple data is not less than 60; Arranging all the triple data in chronological order and checking whether there are missing values; If there are missing values, replacing the missing values with the arithmetic mean of adjacent data and consulting business experts to ensure the effectiveness and accuracy of the newly calculated missing values; If there is no missing value, this dataset is taken as the historical production energy consumption dataset, marked as D i ( X 1, X 2, Y )。 2. The method of claim 1, wherein, When classifying the historical production energy consumption dataset according to attribute data by using a k-means clustering algorithm, the number of classification categories is 2-4.

3. The method of claim 1, wherein, Taking the crude oil production and natural gas production as input and the energy consumption as output, respectively establishing and training a neural network energy consumption prediction model corresponding to each category to obtain an energy consumption prediction model corresponding to each category, comprising: Taking the monthly crude oil production and natural gas production in the historical production energy consumption dataset as input and the monthly energy consumption as output, respectively establishing and training a three-layer neural network energy consumption prediction model containing 2 input layer nodes and 1 output layer node, and obtaining an energy consumption prediction model corresponding to each category after training.

4. The method of claim 1, wherein, Obtaining planned crude oil production and planned natural gas production, determining the category to which the planned crude oil production and planned natural gas production belong on the basis of the classification result, comprising: Obtaining planned crude oil production and planned natural gas production, and determining the category to which the planned crude oil production and planned natural gas production belong on the basis of the classification result by using a KNN algorithm.

5. A system for predicting energy consumption in the oil and gas industry, characterized by, The system comprises: A data collection module for collecting crude oil production, natural gas production and energy consumption to generate a historical production energy consumption dataset; A classification module for selecting the crude oil production and natural gas production as attribute data, classifying the historical production energy consumption dataset according to the attribute data by using a k-means clustering algorithm, obtaining a classification result and marking each category; The data processing module is configured to perform normalization processing on the data set corresponding to each category of the label respectively, map the natural gas production and the crude oil production to a range of 0 to 1, record the normalization rule of each category, take the crude oil production and the natural gas production as input and the energy consumption as output, establish and train a neural network energy consumption prediction model corresponding to each category respectively, and obtain an energy consumption prediction model corresponding to each category. The prediction module is configured to obtain a planned crude oil production and a planned natural gas production, determine the category to which the planned crude oil production and the planned natural gas production belong based on the classification result, perform normalization processing according to the normalization rule corresponding to the category, input the normalized data into the energy consumption prediction model corresponding to the category, and obtain an energy consumption prediction result. The data collection module is configured to: According to the triple data format D ( X 1, X 2, Y ) According to the time sequence, collect the monthly natural gas production, crude oil production and comprehensive energy consumption data of the oil and gas field enterprise history in a period of time, wherein, X 1 represents the monthly natural production of the enterprise, X 2 represents the monthly crude oil production of the enterprise, Y represents the monthly comprehensive energy consumption of the enterprise; collect no less than 60 triple data when collecting historical data; arrange all the triple data in time sequence and check whether there is a missing value; if there is a missing value, replace the missing value with an arithmetic mean of adjacent data, and consult a business expert to ensure the effectiveness and accuracy of the newly calculated missing value; If there is no missing value, this dataset is taken as the historical production energy consumption dataset, marked as D i ( X 1, X 2, Y ) 6. The system for predicting energy consumption in the oil and gas industry of claim 5, wherein, when the classification module classifies the historical production energy consumption data set according to attribute data by using the k-means clustering algorithm, the number of classification categories is 2-4.

7. The system for predicting energy consumption in the oil and gas industry of claim 5, wherein, The data processing module is configured to: take the monthly crude oil production and the monthly natural gas production in the historical production energy consumption data set as input and the monthly energy consumption as output, establish and train a three-layer neural network energy consumption prediction model containing 2 input layer nodes and 1 output layer node respectively, and obtain an energy consumption prediction model corresponding to each category after the training is completed.

8. The system for predicting energy consumption in the oil and gas industry of claim 5, wherein, The prediction module is configured to: obtain a planned crude oil production and a planned natural gas production, and determine the category to which the planned crude oil production and the planned natural gas production belong based on the classification result by using the KNN algorithm.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the method of any one of claims 1 to 4 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program implements the method of any one of claims 1 to 4 when executed by the processor.

Images