Polar region drilling and completion environment pollution division method and system based on optimized radial basis network

Abstract

The invention relates to the field of environmental risk assessment, and discloses a polar region drilling and completion environmental pollution division method and system based on an optimized radial basis network. The method specifically comprises the steps of obtaining pollution data corresponding to each preset pollution index, determining input of a radial basis function network according to the pollution data, adaptively adjusting the position of a center sample point of the radial basis function network according to data density, and obtaining a target optimization radial basis function network, so that the problems of over-fitting and under-fitting can be avoided as much as possible, and the accuracy of the target optimization radial basis function network is improved. And the generalization capability of the radial basis function network is improved. The pollution degree of each sample is calculated through the target optimization radial basis function network, the corresponding pollution level is obtained, the nonlinear relation in the data can be fitted more accurately, and the accuracy of pollution risk assessment is improved.

Description

Technical Field

[0001] The present application relates to the field of environmental risk assessment, and in particular to a method and system for polar drilling and completion environmental pollution classification based on an optimized radial basis function network. Background Art

[0002] Drilling and completion operations in polar regions often carry high pollution risks due to their unique environmental and climatic conditions. Furthermore, due to the lack of environmental pollution data in polar regions, existing pollution risk assessment methods rely primarily on traditional statistical models (such as linear regression) and shallow neural networks (such as BP neural networks).

[0003] Due to the complex characteristics of polar drilling and completion environmental data, these methods are limited by model structure and parameter optimization methods when processing complex polar drilling and completion environmental data. This makes it difficult to effectively extract the deep correlations between pollution indicators, resulting in low accuracy in pollution level classification. For example, linear regression methods assume a linear relationship between pollution indicators and pollution levels, which cannot adapt to the complex nonlinear pollution characteristics of reality. Shallow neural networks are prone to falling into local optimality, affecting assessment accuracy.

[0004] In addition, the environmental data of polar drilling and completion operations is multi-source data with an uneven data distribution, that is, there are data-dense areas and sparse areas. Traditional methods lack targeted optimization strategies when dealing with this distribution, and are prone to overfitting in data-dense areas and underfitting in data-sparse areas, resulting in insufficient generalization ability of the model and poor stability of the evaluation results.

[0005] Therefore, existing methods still have problems of insufficient accuracy and poor adaptability when processing complex environmental data of polar drilling and completion operations. Summary of the Invention

[0006] The present application provides a polar drilling and completion environmental pollution classification method based on an optimized radial basis function network to solve the problems of insufficient accuracy and poor adaptability in the existing technology when processing complex environmental data of polar drilling and completion operations.

[0007] Correspondingly, the present application also provides a polar drilling and completion environmental pollution classification system based on an optimized radial basis function network, an electronic device, and a computer-readable storage medium to ensure the implementation and application of the above method.

[0008] In order to solve the above technical problems, the present application discloses a method for polar drilling and completion environmental pollution classification based on an optimized radial basis function network, the method comprising:

[0009] Obtain pollution data corresponding to each preset pollution index;

[0010] The input of the radial basis function network is determined according to the pollution data, and the position of the central sample point of the radial basis function network is adaptively adjusted according to the data density to obtain the target optimized radial basis function network;

[0011] The pollution degree of each sample is calculated through the target optimization radial basis function network to obtain the corresponding pollution level.

[0012] Preferably, the input of the radial basis function network is determined according to the pollution data, and the position of the central sample point of the radial basis function network is adaptively adjusted according to the data density to obtain the target optimized radial basis function network, including:

[0013] According to the pollution data, the characteristic parameters of each pollution index of each sample point are extracted as the input of the radial basis function network;

[0014] Set the optimization algorithm to adjust the importance weight of the sample points by adjusting the distribution density, error contribution and sparsity of the sample points;

[0015] The central sample point position of the radial basis function network is determined according to the importance weight of the sample point.

[0016] Preferably, an optimization algorithm is set to adjust the importance weights of sample points by adjusting the distribution density, error contribution, and sparsity of the sample points, including:

[0017] Assign adjustable hyperparameters to the distribution density, error contribution, and sparsity of sample points;

[0018] Dynamically adjust the values of hyperparameters through optimization algorithms;

[0019] The importance weight of the sample point is calculated based on the distribution density, error contribution, sparsity and the value of the corresponding hyperparameter of the sample point.

[0020] Preferably, the importance weight of the sample points is calculated based on the distribution density, error contribution, sparsity and corresponding hyperparameter values of the sample points, including:

[0021] The importance weight of the sample points is calculated according to the central sample point selection rule; the central sample point selection rule is:

[0022] W(x i )=α·D(x i )+β·E(x i )+γ·U(x i )

[0023] Among them, D(x i ) represents the sample point x i The distribution density in the feature space, E(x i ) represents the sample point xi In terms of contribution to the output error, U(x i ) represents the sparsity of sample points, and α, β, and γ are the corresponding hyperparameters.

[0024] Preferably, before determining the input of the radial basis function network according to the contamination data and adaptively adjusting the position of the central sample point of the radial basis function network according to the data density, and obtaining the target optimized radial basis function network, the method further comprises:

[0025] Preprocess the contaminated data; preprocessing methods include cleaning and normalization.

[0026] Preferably, obtaining pollution data corresponding to each preset pollution index includes:

[0027] The actual pollution conditions in polar drilling operations were simulated in an environment with a temperature of -5°C to -15°C, and pollution data of various pollution indicators were obtained.

[0028] Preferably, the pollution indicators include oil content, heavy metal content, PAHs characteristics and leaching toxicity.

[0029] The present application also discloses a polar drilling and completion environmental pollution classification system based on an optimized radial basis function network, the system comprising:

[0030] A data acquisition module is used to obtain pollution data corresponding to each preset pollution index;

[0031] The model training module is used to determine the input of the radial basis function network according to the pollution data, and adaptively adjust the position of the central sample point of the radial basis function network according to the data density to obtain the target optimized radial basis function network;

[0032] The risk assessment module is used to calculate the pollution degree of each sample through the target optimization radial basis function network to obtain the corresponding pollution level.

[0033] The present application also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, one or more methods described in the present application are implemented.

[0034] The present application also discloses a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, one or more methods described in the present application are implemented.

[0035] This application has at least the following beneficial effects:

[0036] 1. In this application, the central sample point position of the radial basis function network is adaptively adjusted according to the data density to obtain the target optimized radial basis function network, which can avoid overfitting and underfitting problems as much as possible and improve the generalization ability of the radial basis function network.

[0037] 2. This application uses a target-optimized radial basis function network to perform pollution risk classification, which can effectively process complex pollution data in polar drilling operations, avoid the rough assessment of pollution risks in traditional methods, and provide a more accurate and real-time pollution risk analysis.

[0038] 3. This application adapts to the polar environment and simulates the actual pollution conditions in polar drilling operations under low-temperature conditions, obtaining more representative and realistic pollution data, thereby improving the reliability and practical application value of the assessment results.

[0039] 4. Based on the target optimization of radial basis function network, this application can quickly evaluate the pollution degree of different pollution indicators without a large number of experiments, which significantly saves experimental time and cost and improves the evaluation efficiency.

[0040] Additional aspects and advantages of the present application will be given in the following description, which will become apparent from the following description, or will be understood through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0042] Figure 1 A flowchart of a method for polar drilling and completion environmental pollution classification based on an optimized radial basis function network provided in an embodiment of the present application;

[0043] Figure 2 A sample diagram of drill cuttings from a polar oil and gas well provided in an embodiment of the present application;

[0044] Figure 3 A surface graph of pollution indicators provided in an embodiment of the present application;

[0045] Figure 4 A heat map of pollution indicators provided in the embodiment of this application;

[0046] Figure 5 Radar chart of pollution indicators provided in the embodiment of this application;

[0047] Figure 6 A schematic diagram of the structure of a polar drilling and completion environmental pollution classification system based on an optimized radial basis function network provided in an embodiment of the present application;

[0048] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following describes embodiments of the present application in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application.

[0050] It will be understood by those skilled in the art that, unless expressly stated otherwise, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of this application refers to the presence of features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" used herein includes all or any units and all combinations of one or more associated listed items.

[0051] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art in the art to which the present invention pertains. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with their meanings in the context of the prior art and, unless specifically defined as herein, will not be interpreted in an idealized or overly formal sense.

[0052] The solution provided in the embodiments of the present application can be executed by any electronic device, such as a terminal device or a server, wherein the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited to this. The terminal and the server can be directly or indirectly connected via wired or wireless communication, and this application does not limit this. With respect to the technical problems existing in the prior art, the polar drilling and completion environmental pollution classification method and system based on the optimized radial basis function network provided in this application is intended to solve at least one of the technical problems of the prior art.

[0053] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0054] The present application embodiment provides a possible implementation method, such as Figure 1 As shown, a flowchart of a method for polar drilling and completion environmental pollution classification based on an optimized radial basis function network is provided. The solution can be executed by any electronic device, and optionally, can be executed on a server or terminal device.

[0055] like Figure 1 As shown in , the method may include the following steps:

[0056] Step 101: Obtain pollution data corresponding to each preset pollution index.

[0057] In the embodiment of the present application, characteristic polar conditions are set for polar drilling operations to obtain more representative and realistic pollution data.

[0058] Step 102 : determining the input of the radial basis function network according to the contamination data, and adaptively adjusting the position of the central sample point of the radial basis function network according to the data density to obtain a target optimized radial basis function network.

[0059] In the embodiment of the present application, a radial basis function (RBF) is used as an activation function to construct a three-layer neural network (input layer, hidden layer, output layer), and the center point position of the RBF network is adjusted through an optimization algorithm to enhance the learning ability of the model.

[0060] During the optimization training of a radial basis function network, if the central sample points are too concentrated in high-density areas of the training data, overfitting is likely to occur. Even if the radial basis function network performs well in these areas, its generalization ability on unseen data will be poor, resulting in increased prediction error. If the central sample points are sparsely distributed or poorly selected, underfitting is likely to occur, which means that the radial basis function network may not accurately capture the nonlinear characteristics of the data, affecting its overall prediction ability.

[0061] Optimizing the central sample points can solve the above-mentioned overfitting or underfitting phenomenon. This can be achieved in the following ways:

[0062] 1) Improve data coverage: By optimizing the central sample points so that they are evenly distributed throughout the data space, rather than just concentrated in certain high-density areas, it helps improve the model's ability to learn low-density areas and reduce the risk of underfitting.

[0063] 2) Enhance local adaptability: Appropriately reduce the number of central sample points in data-dense areas to prevent the model from overfitting local patterns, and reasonably increase the number of central sample points in data-sparse areas to enhance the ability to capture edge areas.

[0064] In the embodiment of the present application, the data density adaptive distribution center point is adopted. A density clustering algorithm (such as DBSCAN) is used to analyze the distribution of contaminated data, and fewer central sample points are selected in data-dense areas to avoid overfitting caused by redundant points. In data-sparse areas, the sample center points are appropriately increased so that the model can more accurately predict the data trends in these areas. This method ensures the reasonable distribution of central sample points in the entire data space, thereby improving the generalization ability.

[0065] Step 103 : Calculate the pollution degree of each sample through the target optimized radial basis function network to obtain the corresponding pollution level.

[0066] The results of pollution risk assessment can provide a basis for environmental protection measures for drilling operations and help decision makers identify and respond to potential environmental risks.

[0067] In this embodiment, pollution data corresponding to each preset pollution indicator is obtained, the input of the radial basis function network is determined based on the pollution data, and the position of the central sample point of the radial basis function network is adaptively adjusted according to the data density to obtain a target-optimized radial basis function network. This can minimize overfitting and underfitting problems and improve the generalization ability of the radial basis function network. By calculating the pollution level of each sample through the target-optimized radial basis function network and obtaining the corresponding pollution level, it can more accurately fit the nonlinear relationships in the data and improve the accuracy of pollution risk assessment.

[0068] In an optional embodiment, obtaining pollution data corresponding to each preset pollution index includes:

[0069] The actual pollution conditions in polar drilling operations were simulated in an environment with a temperature of -15°C to -5°C, and pollution data of various pollution indicators were obtained.

[0070] The drilling cuttings samples selected in the examples of this application were taken from polar oil and gas drilling sites. Figure 2 At normal temperature and pressure, the mixture appears as a dark brown, relatively viscous solid-liquid two-phase mixture with a pungent petroleum odor. To adapt to the unique environment of polar drilling operations, pollution data simulation experiments were conducted at low temperatures ranging from -15°C to -5°C to obtain pollution data corresponding to various pollution indicators.

[0071] In an optional embodiment, the pollution indicators include oil content, heavy metal content, polycyclic aromatic hydrocarbon characteristics and leaching toxicity.

[0072] The examples of this application were tested to determine the pollution data of oil content, heavy metal content, polycyclic aromatic hydrocarbon characteristics and leaching toxicity. The oil content of drill cuttings can be determined by azeotropic distillation and Soxhlet extraction-infrared oil tester. The water content and oil content of the sample are 18.35%. The heavy metal content is shown in Table 1 below, mainly copper, lead, mercury, etc. The ∑PAHS content reaches 572 mg / kg, of which medium-ring (4-ring) and low-ring (2-3-ring) PAHs dominate. Under low temperature conditions, the leaching toxicity of drill cuttings is high.

[0073] Table 1 Heavy metal content of drill cuttings samples

[0074]

[0075] In an optional embodiment, before determining the input of the radial basis function network based on the contamination data and adaptively adjusting the position of the central sample point of the radial basis function network based on the data density to obtain the target optimized radial basis function network, the method further includes:

[0076] Preprocess the contaminated data; preprocessing methods include cleaning and normalization.

[0077] In the present embodiment, the pollution data corresponding to each pollution indicator was cleaned to remove outliers, missing values, and noise to ensure data quality. The data was then normalized to eliminate dimensional differences between different indicators and improve data comparability for subsequent analysis.

[0078] In an optional embodiment, the input of the radial basis function network is determined according to the pollution data, and the position of the central sample point of the radial basis function network is adaptively adjusted according to the data density to obtain the target optimized radial basis function network, including:

[0079] According to the pollution data, the characteristic parameters of each pollution index of each sample point are extracted as the input of the radial basis function network;

[0080] Set the optimization algorithm to adjust the importance weight of the sample points by adjusting the distribution density, error contribution and sparsity of the sample points;

[0081] The central sample point position of the radial basis function network is determined according to the importance weight of the sample point.

[0082] In an optional embodiment, based on the pollution data, characteristic parameters of each pollution index of each sample point are extracted as inputs of a radial basis function network, which is specifically implemented as follows:

[0083] 1. Extraction of oil content characteristic parameters

[0084] Oil content is a key indicator for measuring the degree of oil contamination in drill cuttings. The Soxhlet extraction-infrared oil measurement method (HJ 637-2018) was used to determine the total oil content (expressed as a percentage by mass) in drill cuttings. To more comprehensively assess its environmental impact, the following characteristic parameters were also extracted:

[0085] Oil saturation (S0): The calculation formula is S0 = oil content / water content, which is used to measure the ratio of oil content to water content in drill cuttings.

[0086] 2. Extraction of characteristic parameters of heavy metal content

[0087] Heavy metal pollution assessments must consider their total concentration, mobility, and biotoxicity. The heavy metal content in drill cuttings was measured using inductively coupled plasma mass spectrometry (ICP-MS, HJ700-2014), and the following characteristic parameters were further extracted:

[0088] Toxicity Equivalent Factor (TEQ): Based on the standards set by USEPA and WHO, heavy metals (such as Pb, Hg, Cd, As) are assigned toxicity weights and the comprehensive toxicity index (unit: mg / L) is calculated:

[0089] TEQ=∑C i ×TEF i

[0090] Among them, C i is the heavy metal concentration, TEF i Toxicity factor.

[0091] 3. Extraction of characteristic parameters of polycyclic aromatic hydrocarbons (PAHs)

[0092] PAHs are highly persistent and biotoxic. Their characteristics are extracted based on the EPA 16 priority PAHs standards (EPA

[0093] 8270D-2007), detected by gas chromatography-mass spectrometry (GC-MS), and further analyzed:

[0094] Ring number distribution: PAHs are divided into low-ring (23 rings), medium-ring (4 rings), and high-ring (56 rings) according to their molecular structure. The low-ring / high-ring ratio is calculated to measure their volatility (low-ring PAHs are volatile) and persistence (high-ring PAHs are persistent).

[0095] 4. Extraction of leaching toxicity characteristic parameters

[0096] Leaching toxicity reflects the release characteristics of pollutants under environmental changes such as rainfall and groundwater flow. According to the solid waste leaching toxicity test method (HJ / T300-2007), the leaching concentration of drill cuttings pollutants was measured and the following characteristic parameters were extracted:

[0097] pH dependence: The concentration of pollutants in the leachate was measured under different pH values (3, 5, 7, 9), and the pH-leaching curve was drawn to analyze the effect of acid-base conditions on the release of pollutants.

[0098] Electrical conductivity (EC): The total amount of soluble contaminants in drill cuttings is assessed by electrical conductivity measurement (μS / cm). The higher the EC value, the more mobile the contaminants.

[0099] In an optional embodiment, an optimization algorithm is set to adjust the importance weights of sample points by adjusting the distribution density, error contribution, and sparsity of the sample points, including:

[0100] Assign adjustable hyperparameters to the distribution density, error contribution, and sparsity of sample points;

[0101] Dynamically adjust the values of hyperparameters through optimization algorithms;

[0102] The importance weight of the sample point is calculated based on the distribution density, error contribution, sparsity and the value of the corresponding hyperparameter of the sample point.

[0103] In the embodiment of the present application, the radial basis function of the radial basis function network is shown as follows:

[0104] Φ ij =φ(||x i -c j ||)

[0105] Among them, ||x i -c j || represents the sample point x i To the center sample point c j Each sample point includes the characteristic parameters of each pollution indicator.

[0106] At the central sample point c j In terms of selection, in the embodiment of the present application, the distribution density, error contribution and sparsity of the sample points are taken into consideration to adjust the selection strategy of the central sample points, so as to improve the generalization ability of the radial basis function network by affecting the subsequent training process. Among them, by introducing hyperparameters to weigh the influence of distribution density, error contribution and sparsity, the optimization network can dynamically adjust the respective hyperparameters to adjust the influence of distribution density, error contribution and sparsity, thereby realizing the dynamic adjustment of the importance weights of the sample points. During the training process, the stability of the optimized radial basis function network is verified by cross-validation or leave-one-out method to avoid overfitting.

[0107] In an optional embodiment, the importance weight of the sample points is calculated based on the distribution density, error contribution, sparsity and corresponding hyperparameter values of the sample points, including:

[0108] The importance weight of the sample points is calculated according to the central sample point selection rule; the central sample point selection rule is:

[0109] W(x i )=α·D(x i )+β·E(x i )+γ·U(x i )

[0110] Among them, D(x i ) represents the sample point x i The distribution density in the feature space indicates the distribution of feature parameters in the feature space; E(x i ) represents the sample point x i The contribution to the output error indirectly reflects the influence of the characteristic parameters on the model performance; U(x i ) represents the sparsity of the sample point, measures its redundancy with other samples, and affects the weight calculation; α, β, and γ are the corresponding hyperparameters.

[0111] By adjusting the central sample point position of the radial basis function network through the above method, the overfitting and underfitting problems that may exist in the traditional radial basis function network can be avoided. The target optimized radial basis function network obtained after optimization can more accurately fit the nonlinear relationship in the data and improve the accuracy of pollution risk assessment.

[0112] In an optional embodiment, the pollution degree of each sample is calculated by using a target optimized radial basis function network to obtain the corresponding pollution level, including:

[0113] The pollution degree of each sample is calculated through the target optimization radial basis function network to obtain the score of each pollution index; the score reflects the potential impact on the environment.

[0114] Scores for each pollution indicator are divided according to pre-defined pollution classification criteria to obtain the corresponding pollution level. This pollution level ultimately forms a set of pollution risk factors. The results of the pollution risk assessment can provide a basis for environmental protection measures during drilling operations, helping decision-makers identify and address potential environmental risks.

[0115] The pollution level classification standards (low pollution, medium pollution, high pollution) preset in the embodiment of the present application are shown in Table 2:

[0116] Table 2 Pollution level classification standards

[0117]

[0118] In the embodiment of the present application, the pollution degree of each sample point (such as sample 1, sample 2, sample 2 and sample 4) is calculated, and the obtained results are shown in Figure 3The pollution index surface diagram shown, Figure 4 The pollution index heat map shown and Figure 5 The pollution index radar chart is shown. After the final classification, the pollution index scores and pollution levels are as follows:

[0119] Oil content: Score = 0.45, Level = Medium pollution

[0120] Heavy metal content: Score = 0.18, Level = Low pollution

[0121] PAHs characteristics: Score = 0.69, Level = High Pollution

[0122] Leaching toxicity: Score = 0.74, Level = High Contamination

[0123] according to Figure 3-5 Among the pollution indicators, PAHs characteristics and leaching toxicity are the main high-pollution factors, and their contribution to environmental risks is the most significant. Figure 3 The pollution index surface plot shows that PAHs characteristics and leaching toxicity scored high in many samples, showing a strong pollution trend, while oil content fluctuated within the medium pollution range, indicating that its pollution impact on the environment was inferior to PAHs characteristics and leaching toxicity. In contrast, the pollution scores of heavy metal content were generally low, belonging to low pollution indicators, indicating that its contribution to overall pollution was relatively small. Figure 4 The pollution index heat map shown further verifies this trend. The colors of PAHs characteristics and leaching toxicity are relatively dark, which intuitively reflects their high pollution characteristics, while the colors of heavy metal content are generally lighter, further indicating that the pollution level is relatively low. Figure 5 The pollution index radar chart shown clearly demonstrates the distribution characteristics of various pollution indicators, among which PAHs characteristics and leaching toxicity cover a wider range, highlighting the importance of their pollution risks.

[0124] Based on the same principle as the method provided in the embodiment of the present application, the embodiment of the present application also provides a polar drilling and completion environmental pollution classification system based on an optimized radial basis function network, such as Figure 6 As shown, the system includes:

[0125] The data acquisition module 601 is used to obtain pollution data corresponding to each preset pollution index;

[0126] The model training module 602 is used to determine the input of the radial basis function network according to the pollution data, and adaptively adjust the position of the central sample point of the radial basis function network according to the data density to obtain the target optimized radial basis function network;

[0127] The risk assessment module 603 is used to calculate the pollution degree of each sample through the target optimization radial basis function network to obtain the corresponding pollution level.

[0128] In this embodiment, pollution data corresponding to each preset pollution indicator is obtained, the input of the radial basis function network is determined based on the pollution data, and the position of the central sample point of the radial basis function network is adaptively adjusted according to the data density to obtain a target-optimized radial basis function network. This can minimize overfitting and underfitting problems and improve the generalization ability of the radial basis function network. By calculating the pollution level of each sample through the target-optimized radial basis function network and obtaining the corresponding pollution level, it can more accurately fit the nonlinear relationships in the data and improve the accuracy of pollution risk assessment.

[0129] The polar drilling and completion environmental pollution classification system based on the optimized radial basis function network provided in the embodiment of the present application can achieve Figures 1 to 5 To avoid repetition, the various processes implemented in the method embodiment will not be described again here.

[0130] The polar drilling and completion environment pollution classification system based on optimized radial basis function network in the embodiment of the present application can execute the polar drilling and completion environment pollution classification method based on optimized radial basis function network provided in the embodiment of the present application. The implementation principle is similar. The actions performed by each module and unit in the polar drilling and completion environment pollution classification system based on optimized radial basis function network in each embodiment of the present application correspond to the steps in the polar drilling and completion environment pollution classification method based on optimized radial basis function network in each embodiment of the present application. For the detailed functional description of each module of the polar drilling and completion environment pollution classification system based on optimized radial basis function network, please refer to the description of the corresponding polar drilling and completion environment pollution classification method based on optimized radial basis function network shown in the previous text, which will not be repeated here.

[0131] Based on the same principle as the method shown in the embodiment of the present application, the embodiment of the present application also provides an electronic device, which may include but is not limited to: a processor and a memory; a memory for storing a computer program; a processor for executing the polar drilling and completion environmental pollution classification method based on an optimized radial basis function network shown in any optional embodiment of the present application by calling a computer program. Compared with the prior art, the polar drilling and completion environmental pollution classification method based on an optimized radial basis function network provided in the present application obtains pollution data corresponding to each preset pollution index, determines the input of the radial basis function network based on the pollution data, and adaptively adjusts the position of the central sample point of the radial basis function network according to the data density to obtain a target optimized radial basis function network, which can avoid overfitting and underfitting problems as much as possible and improve the generalization ability of the radial basis function network. By calculating the pollution degree of each sample through the target optimized radial basis function network and obtaining the corresponding pollution level, it is possible to more accurately fit the nonlinear relationship in the data and improve the accuracy of pollution risk assessment.

[0132] In an optional embodiment, an electronic device is also provided, such as Figure 7 As shown, Figure 7 The electronic device 700 shown may be a server, including a processor 701 and a memory 703. The processor 701 and the memory 703 are connected, for example, via a bus 702. Optionally, the electronic device 700 may further include a transceiver 704. It should be noted that in actual applications, the number of transceivers 704 is not limited to one, and the structure of the electronic device 700 does not constitute a limitation on the embodiments of the present application.

[0133] The processor 701 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 701 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0134] The bus 702 may include a path for transmitting information between the above components. The bus 702 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 702 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0135] The memory 703 can be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0136] The memory 703 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 701. The processor 701 is used to execute the application code stored in the memory 703 to implement the content shown in the above method embodiment.

[0137] Among them, electronic devices include but are not limited to: mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 7 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0138] The server provided in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited to these. The terminal and the server can be directly or indirectly connected through wired or wireless communication, and this application does not limit this.

[0139] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0140] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0141] It should be noted that the computer-readable storage medium mentioned above in this application may also be a computer-readable signal medium or a combination of a computer-readable storage medium and a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0142] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0143] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0144] According to one aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to implement the polar drilling and completion environmental contamination classification method and system based on an optimized radial basis function network, as provided in the various optional implementations described above.

[0145] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0146] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0147] The modules described in the embodiments of this application may be implemented in software or hardware. In some cases, the name of a module does not limit the module itself. For example, a data acquisition module may also be described as a "data acquisition module for acquiring pollution data corresponding to various preset pollution indicators."

[0148] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A method for polar drilling and completion environmental pollution classification based on optimized radial basis function network, characterized in that: The method comprises: Obtain pollution data corresponding to each preset pollution index; Determining the input of the radial basis function network according to the pollution data, and adaptively adjusting the position of the central sample point of the radial basis function network according to the data density to obtain a target optimized radial basis function network; The pollution degree of each sample is calculated by the target optimized radial basis function network to obtain the corresponding pollution level.

2. The polar drilling and completion environmental pollution classification method based on optimized radial basis function network according to claim 1 is characterized in that: The step of determining the input of the radial basis function network according to the contamination data and adaptively adjusting the position of the central sample point of the radial basis function network according to the data density to obtain the target optimized radial basis function network includes: Extracting characteristic parameters of each pollution index of each sample point as input of the radial basis function network according to the pollution data; Set the optimization algorithm to adjust the importance weight of the sample points by adjusting the distribution density, error contribution and sparsity of the sample points; The central sample point position of the radial basis function network is determined according to the importance weight of the sample point.

3. The polar drilling and completion environmental pollution classification method based on optimized radial basis function network according to claim 2 is characterized in that: The setting optimization algorithm adjusts the importance weight of the sample points by adjusting the distribution density, error contribution and sparsity of the sample points, including: Assign adjustable hyperparameters to the distribution density, error contribution, and sparsity of sample points; Dynamically adjust the value of the hyperparameter by the optimization algorithm; The importance weight of the sample point is calculated based on the distribution density, error contribution, sparsity and the value of the corresponding hyperparameter of the sample point.

4. The polar drilling and completion environmental pollution classification method based on optimized radial basis function network according to claim 3 is characterized in that: The importance weight of the sample points is calculated based on the distribution density, error contribution, sparsity and corresponding hyperparameter values of the sample points, including: The importance weight of the sample points is calculated according to the central sample point selection rule; the central sample point selection rule is: W(x i )=α·D(x i )+β·E(x i )+γ·U(x i ) Among them, D(x i ) represents the sample point x i The distribution density in the feature space, E(x i ) represents the sample point x i In terms of contribution to the output error, U(x i ) represents the sparsity of sample points, and α, β, and γ are the corresponding hyperparameters.

5. The polar drilling and completion environmental pollution classification method based on optimized radial basis function network according to claim 1 is characterized in that: Before determining the input of the radial basis function network according to the contamination data and adaptively adjusting the position of the central sample point of the radial basis function network according to the data density to obtain the target optimized radial basis function network, the method further includes: The contaminated data is preprocessed; the preprocessing method includes cleaning and normalization.

6. The polar drilling and completion environmental pollution classification method based on optimized radial basis function network according to claim 1 is characterized in that: The obtaining of pollution data corresponding to each preset pollution index includes: The actual pollution conditions in polar drilling operations were simulated in an environment with a temperature of -15°C to -5°C, and pollution data of various pollution indicators were obtained.

7. The polar drilling and completion environmental pollution classification method based on optimized radial basis function network according to any one of claims 1 to 6, characterized in that: The pollution indicators include oil content, heavy metal content, polycyclic aromatic hydrocarbon characteristics and leaching toxicity.

8. A polar drilling and completion environmental pollution classification system based on optimized radial basis function network, characterized in that: The system comprises: A data acquisition module is used to obtain pollution data corresponding to each preset pollution index; A model training module is used to determine the input of the radial basis function network according to the pollution data, and adaptively adjust the position of the central sample point of the radial basis function network according to the data density to obtain a target optimized radial basis function network; The risk assessment module is used to calculate the pollution degree of each sample through the target optimized radial basis function network to obtain the corresponding pollution level.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the method according to any one of claims 1 to 7 is implemented when the processor executes the program.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images