Intelligent identification method and system for ecological application level of oilfield chemical agent

Abstract

The invention relates to an oil field chemical agent ecological application grade intelligent identification method and system, and belongs to the technical field of oil field chemical safety and environmental protection. The identification method comprises the following steps: establishing an environmental protection analysis and prediction model based on an oilfield chemical agent ecological application grade database; and completing the environmental protection risk grade prediction of the oilfield chemical agent based on the environmental protection analysis and prediction model and the environmental protection evaluation data of the to-be-tested oilfield chemical agent sample. The environmental protection analysis and prediction model for evaluating the multi-dimensional environmental protection performance of the oilfield chemical agent is provided, efficient prediction of the application conditions of the oilfield chemical agent is achieved, safety and environmental protection accidents caused by improper use of the oilfield chemical agent are reduced, the hierarchical management efficiency of the oilfield chemical agent is improved, and the economic benefit is increased. The method is of great significance to oil field speed increasing and efficiency increasing and environmental protection.

Description

Technical Field

[0001] The invention belongs to the technical field of oilfield chemical safety and environmental protection, and in particular relates to an intelligent identification method and system for the ecological application level of oilfield chemicals. Background Art

[0002] Many exploration and development blocks in oil and gas field units are located in important national ecosystem service function areas and ecologically sensitive and fragile areas such as important biodiversity, soil conservation, wind and sand fixation, water conservation, and agricultural product provision. It is very important to strengthen environmental protection in exploration and development blocks. As an important product throughout the entire process of oil production, oilfield chemicals are used in oil exploration, drilling, gathering, transportation, storage and transportation. Oilfield chemicals are of various types and complex components, and there are potential environmental hazards to the environment. According to the evaluation of the toxicity of oilfield chemical products and the degree of pollution they can bring, and in response to the different ecological conditions and environmental protection requirements of each development area, the implementation of environmental risk classification management of oilfield chemicals is of great significance to the acceleration and efficiency improvement of oilfields and environmental protection. Summary of the invention

[0003] In response to the above problems, the present invention provides a method and system for intelligently identifying the ecological application level of oilfield chemicals, which analyzes simulation data on the environmental performance evaluation of oilfield chemicals with clear ecological application levels, identifies features in the data, and uses this as a basis for intelligently predicting the ecological application level of environmental performance evaluation data of different types of oilfield chemicals, thereby providing support for the hierarchical management of oilfield chemicals.

[0004] The first object of the present invention is to provide an intelligent identification method for the ecological application level of oilfield chemicals.

[0005] The identification method comprises:

[0006] Establish an environmental analysis and prediction model based on the ecological application level database of oilfield chemicals;

[0007] Based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested, the environmental risk level of oilfield chemicals is predicted.

[0008] In an embodiment of the present invention, the establishment of the oilfield chemical ecological application level database includes:

[0009] Collect environmental performance data of existing ecological application grade oilfield chemicals;

[0010] Process the environmental performance data of existing ecological application grade oilfield chemicals;

[0011] Based on the processed data, an oilfield chemical ecological application level database is established.

[0012] In an embodiment of the present invention, the data processing includes data cleaning, duplicate value processing, outlier value processing, missing value processing, normalization processing and feature extraction and selection.

[0013] In the embodiment of the present invention, the environmental performance data include indicators of plant biodegradability, microbial toxicity, plant toxicity, animal toxicity, heavy metal content, infection performance, flash point and organic toxic component content.

[0014] In an embodiment of the present invention, the environmental analysis and prediction model is established based on the oilfield chemical ecological application level database, including:

[0015] Based on the oilfield chemical ecological application level database and identification model, the characteristics of the oilfield chemical ecological application level data are extracted;

[0016] Based on the characteristics of the ecological application level data of oilfield chemicals, learning and training are carried out;

[0017] Based on the learning and training results, an environmental analysis and prediction model is established.

[0018] In an embodiment of the present invention, the recognition model is a decision tree model or an online learning decision model.

[0019] In an embodiment of the present invention, the online learning decision model is one of a multi-classification online learning algorithm and an online regression learning algorithm.

[0020] The second object of the present invention is to provide an intelligent identification system for the ecological application level of oilfield chemicals.

[0021] The identification system comprises:

[0022] The prediction model building module is used to build an environmental analysis prediction model based on the oilfield chemical ecological application level database;

[0023] The risk level identification module is used to complete the environmental risk level prediction of oilfield chemicals based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested.

[0024] A third object of the present invention is to provide an electronic device.

[0025] The electronic device comprises: a processor coupled to a memory;

[0026] The memory is used to store computer programs;

[0027] The processor is used to execute the computer program stored in the memory so that the electronic device executes the method as described above.

[0028] A fourth object of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium includes a program or an instruction, and when the program or the instruction is executed on a computer, the computer executes the method as described above.

[0029] Beneficial effects of the present invention:

[0030] The present invention provides an intelligent identification method and system for the ecological application grade of oilfield chemicals, proposes an environmental analysis and prediction model for evaluating the environmental performance of oilfield chemicals from multiple dimensions, realizes efficient prediction of the application conditions of oilfield chemicals, reduces safety and environmental accidents caused by improper use of oilfield chemicals, and improves the efficiency of graded management of oilfield chemicals, which is of great significance to speeding up and increasing the efficiency of oilfields and protecting the environment.

[0031] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A flow chart of an intelligent identification method for ecological application level of oilfield chemicals according to an embodiment of the present invention is shown;

[0034] Figure 2 A data processing flow chart according to an embodiment of the present invention is shown;

[0035] Figure 3 A diagram showing a decision tree structure of oilfield chemicals according to an embodiment of the present invention is shown;

[0036] Figure 4 A framework diagram of an intelligent identification system for ecological application level of oilfield chemicals according to an embodiment of the present invention is shown;

[0037] Figure 5 A framework diagram of an electronic device according to an embodiment of the present invention is shown;

[0038] In the figure: prediction model building module 1; risk identification module 2; electronic device 300; processor 301; memory 302. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] like Figure 1 As shown, a method for intelligently identifying the ecological application level of oilfield chemicals according to an embodiment of the present invention includes:

[0041] Step S1, establishing an environmental analysis and prediction model based on the oilfield chemical ecological application level database;

[0042] Step S2: Based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested, the environmental risk level of the oilfield chemical is predicted.

[0043] In step S1, the establishment of the oilfield chemical ecological application level database includes:

[0044] Step A1, collecting environmental performance data of existing ecological application grade oilfield chemicals;

[0045] Step A2, processing the environmental performance data of existing ecological application grade oilfield chemicals;

[0046] Step A3: Based on the processed data, establish an oilfield chemical ecological application level database.

[0047] In step A1, the collection of environmental performance data of existing ecological application grade oilfield chemicals may include:

[0048] Collect existing environmental performance data of oilfield chemicals;

[0049] Integrate the taxonomy information of ecological application of all known oilfield chemicals, including the ecological application grade information of known oilfield chemicals and the corresponding environmental performance evaluation;

[0050] Quantify the environmental performance evaluation of known oilfield chemicals;

[0051] Based on the quantitative results obtained, each known oilfield chemical is divided into several ecological application levels through expert consultation or quantitative scoring, and finally the environmental performance data and evaluation data of oilfield chemicals with existing ecological application levels are formed;

[0052] In step A2, the data processing includes data cleaning, duplicate value processing, outlier processing, missing value processing, normalization processing, feature extraction and selection. The specific process is as follows: Figure 2 shown.

[0053] In step A3, based on the obtained quantification results, the obtained quantification results are written and stored to obtain an oilfield chemical ecological application grade database, wherein the environmental performance data include plant biodegradation performance, microbial toxicity, plant toxicity, animal toxicity, heavy metal content, infection performance, flash point and organic toxic component content indicators. By way of example, the environmental performance data of a certain oilfield chemical and the classification of grades are given in an embodiment of the present invention, as shown in Table 1. By way of example, in an embodiment of the present invention, each known oilfield chemical is divided into four ecological application grades: Grade I (A) (extremely important for ecological protection), Grade II (B) (relatively important for ecological protection), Grade III (C) (moderately important for ecological protection), and Grade IV (D) (generally important for ecological protection). The data results in Table 1 are written and stored to obtain an oilfield chemical ecological application grade database.

[0054] Table 1

[0055]

[0056] Table 1 (continued)

[0057]

[0058]

[0059] In step S1, the environmental analysis and prediction model is established based on the oilfield chemical ecological application level database, including:

[0060] Based on the oilfield chemical ecological application level database and identification model, the characteristics of the oilfield chemical ecological application level data are extracted;

[0061] Based on the characteristics of the ecological application level data of oilfield chemicals, learning and training are carried out;

[0062] Based on the learning and training results, an environmental analysis and prediction model is established.

[0063] The recognition model is one of a decision tree model and an online learning decision model;

[0064] The decision tree model is suitable for small sample data. It uses a decision tree algorithm to learn the training sample data, generate a decision tree classification model, and then classify and predict the test data.

[0065] Online learning decision model: used to process big data scenarios, using online learning algorithms to learn training sample data and predict sample data labels. The loss value is calculated based on the difference between the predicted label and the true label, and the classifier decision function is updated to generate an online learning decision model, thereby classifying and predicting the test data.

[0066] Therefore, a specific identification model is selected according to the library size of the ecological application level database of specific oilfield chemicals;

[0067] In some embodiments of the present invention, illustratively, a decision tree model is used to process the oilfield chemical ecological application level database, and the specific results are as follows:

[0068] The classic C4.5 decision tree algorithm is used to learn the rule table, develop the oilfield chemical classification decision model, and generate a decision tree classifier (such as Figure 3 shown), Figure 3 In the above figure, entropy is entropy, samples is samples, value is value, and class is class. According to this decision tree classifier, decision makers can be guided to make reasonable choices for oilfield chemicals.

[0069] The data of various indicators such as microbial toxicity and arsenic content of a certain type of oilfield chemical are entered into the basic database of oilfield chemical agents, and the corresponding oilfield chemical agent decision tree model is called. The generated decision tree model is used to output its predicted category, that is, the ecological application level.

[0070] The online learning decision model is one of a multi-classification online learning algorithm and an online regression learning algorithm;

[0071] The multi-classification online learning algorithm is a noise-resistant online multi-classification kernel learning algorithm, which establishes an online kernel learning multi-classifier by introducing a ramp loss function, a ramp adaptive parameter setting strategy, and a kernel function, thereby realizing online prediction of data streams.

[0072] The online regression learning algorithm: a large-scale noise-resistant online regression algorithm, solves the large-scale regression analysis problem of noise-rich data by introducing a canal loss function with noise-resistant and sparse performance.

[0073] In some embodiments of the present invention, illustratively, a multi-classification online learning algorithm is used to process the oilfield chemical ecological application level database, and the specific results are as follows:

[0074] Select the model kernel function and initialize the multi-classifier decision function; determine the training sample set and the test sample set, and select the kernel function according to the specific data characteristics Initialize the decision function f for multi-classification problems (0) =0;

[0075] Collect data streams and use the current multi-classification decision function f (t-1) Predict data stream sample x t Category labels; Use multi-classification decision functions to predict category labels of data stream samples Collect data stream samples in a one-by-one manner and use the current multi-classification decision function f (t-1) Predict the tth sample in the data stream Category labels:

[0076] Get sample x t The true label y t , calculate the adaptive parameter s of the ramp loss function of the sample point according to the ramp adaptive parameter setting strategy; calculate the adaptive parameter s of the ramp loss function of the sample, the specific function formula is shown in formula (1):

[0077]

[0078] In formula (1), c is the number of sample categories, n is the number of samples;

[0079] Calculate the sample x t Adaptive ramp loss; get sample x t and its true label y t After that, the ramp loss is calculated according to the following formula (2): r(y i f(x i ));

[0080]

[0081] In formula (2),

[0082] According to the ramp adaptive parameters and adaptive ramp loss l obtained above t , if 0<l t ≤1-s, the classifier decision function is updated according to the following formula (3) to generate a multi-classification online learning decision model, and then classify and predict the test data.

[0083]

[0084] The data of various indicators such as microbial toxicity and arsenic content of a certain type of oilfield chemical are entered into the basic database of oilfield chemical agents, and the corresponding oilfield chemical agent decision tree model is called. The generated decision tree model is used to output its predicted category, that is, the ecological application level.

[0085] In some embodiments of the present invention, by way of example, an online regression learning algorithm is used to process the oilfield chemical ecological application level database, and the specific results are as follows:

[0086] The noise-tolerant parameter δ is introduced to improve the classic loss function ∈-insensitive and obtain a non-convex canal loss function. Based on the canal loss function, a noise-tolerant online regression algorithm is designed, wherein the non-convex canal loss function is shown in formula (4).

[0087]

[0088] In formula (4), z is the difference between the predicted value and the actual value, and ∈ is the loss parameter.

[0089] The canal loss function is used to construct the objective function of the regression problem, and the objective function is shown in formula (5).

[0090]

[0091] In formula (5),

[0092] In the basic framework of the stochastic gradient descent algorithm, the functional Gateaux derivative is used to iteratively solve the optimization problem. Iterate according to formula (6);

[0093]

[0094] The noise-tolerant online regression problem can be transformed into Right now

[0095] n is the sample size.

[0096] Solve the optimization problem under the basic framework of the stochastic gradient descent algorithm. The specific iterative steps are:

[0097]

[0098] The gradient operator is Where τ = sign(f t-1 (x t )-y t ), λ is the regularization parameter, and η is the algorithm step factor to achieve a smooth update of the decision function. Generate an online regression learning decision model to classify and predict the test data.

[0099] The data of various indicators such as microbial toxicity and arsenic content of a certain type of oilfield chemical are entered into the basic database of oilfield chemicals, and the corresponding online learning algorithm is called to generate a decision tree model to output its predicted category, that is, the ecological application level.

[0100] In step S2, the environmental risk level prediction of oilfield chemicals is completed based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested, specifically:

[0101] The environmental evaluation data of the 10 oilfield chemical samples to be tested in Table 2 were respectively substituted into the environmental analysis and prediction model of multi-dimensional environmental performance evaluation obtained by using the decision tree model, multi-classification online learning algorithm and online regression learning algorithm to obtain the prediction results of the environmental risk level of oilfield chemicals, that is, the prediction of the environmental risk level of oilfield chemicals was completed. The specific results are shown in Table 2.

[0102] Table 2

[0103]

[0104]

[0105] like Figure 4 As shown, in some embodiments of the present invention, an intelligent identification system for ecological application level of oilfield chemicals is provided, and the identification system comprises:

[0106] The prediction model building module 1 is used to build an environmental analysis prediction model based on the oilfield chemical ecological application level database;

[0107] The risk level identification module 2 is used to complete the environmental risk level prediction of oilfield chemicals based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested.

[0108] like Figure 5 As shown, some embodiments of the present invention provide an electronic device, the electronic device 300, comprising: a processor 301, the processor 301 is coupled to a memory 302;

[0109] The memory 302 is used to store computer programs;

[0110] The processor 301 is configured to execute the computer program stored in the memory 302 so that the electronic device executes the method described in the above embodiment.

[0111] In certain embodiments of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a program or an instruction. When the program or the instruction is executed on a computer, the computer is enabled to execute the method described in the above embodiments.

[0112] According to an embodiment of the present invention, the computer-readable storage medium may be a non-volatile computer-readable computer-readable storage medium, for example, may include but is not limited to: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, an electronic device or a device.

[0113] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent identification method for the ecological application level of oilfield chemicals, characterized in that: include: Establish an environmental analysis and prediction model based on the ecological application level database of oilfield chemicals; Based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested, the environmental risk level of oilfield chemicals is predicted.

2. The intelligent identification method of ecological application level of oilfield chemicals according to claim 1 is characterized in that: The establishment of the oilfield chemical ecological application grade database includes: Collect environmental performance data of existing ecological application grade oilfield chemicals; Process the environmental performance data of existing ecological application grade oilfield chemicals; Based on the processed data, an oilfield chemical ecological application level database is established.

3. The intelligent identification method of ecological application level of oilfield chemicals according to claim 2 is characterized in that: The data processing includes data cleaning, duplicate value processing, outlier processing, missing value processing, normalization processing and feature extraction and selection.

4. The intelligent identification method of ecological application level of oilfield chemicals according to claim 2 is characterized in that: The environmental performance data include indicators of plant biodegradability, microbial toxicity, plant toxicity, animal toxicity, heavy metal content, infection performance, flash point and organic toxic component content.

5. The intelligent identification method of ecological application level of oilfield chemicals according to claim 1 is characterized in that: The environmental protection analysis and prediction model is established based on the oilfield chemical ecological application level database, including: Based on the oilfield chemical ecological application level database and identification model, the characteristics of the oilfield chemical ecological application level data are extracted; Based on the characteristics of the ecological application level data of oilfield chemicals, learning and training are carried out; Based on the learning and training results, an environmental analysis and prediction model is established.

6. The intelligent identification method of ecological application level of oilfield chemicals according to claim 5 is characterized in that: The recognition model is one of a decision tree model and an online learning decision model.

7. The intelligent identification method of ecological application level of oilfield chemicals according to claim 6 is characterized in that: The online learning decision model is a type of multi-classification online learning algorithm and an online regression learning algorithm.

8. An intelligent identification system for ecological application level of oilfield chemicals, characterized in that: include: The prediction model building module is used to build an environmental analysis prediction model based on the oilfield chemical ecological application level database; The risk level identification module is used to complete the environmental risk level prediction of oilfield chemicals based on the environmental analysis prediction model and the environmental evaluation data of the oilfield chemical samples to be tested.

9. An electronic device, characterized in that: include: a processor coupled to the memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory so that the electronic device performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a program or an instruction. When the program or the instruction is executed on a computer, the computer is caused to perform the method according to any one of claims 1 to 7.

Images