Coal facies well logging classification method, system, device, storage medium and program product

Abstract

This application discloses a coal facies logging classification method, system, equipment, storage medium, and program product, belonging to the field of coalfield geological exploration technology. First, by selecting reference wells and collecting multi-source data, a reliable data foundation is provided for coal facies classification, avoiding the limitations of subjective assignment. Second, by evaluating the correlation between coal facies parameters and logging data, logging data categories that conform to geological laws are selected, effectively eliminating noisy data irrelevant to coal facies types and improving the effectiveness of the training dataset used for model training. By determining the significance between logging data and coal facies types, a reliable statistical correlation between the logging data used for model training and coal facies types is ensured, improving the quality of model training and the accuracy of prediction. Finally, by training a coal facies evaluation model and applying it to prediction wells, the objectivity and accuracy of coal facies classification are guaranteed. This solves the technical problems of strong subjectivity and low classification efficiency in existing technologies.

Description

Technical Field

[0001] This application belongs to the field of coalfield geological exploration technology, specifically involving coal-phase logging classification methods, systems, equipment, storage media, and program products. Background Technology

[0002] Coalbed methane (CBM) logging technology, as a crucial component of the CBM exploration technology system, plays an irreplaceable supporting role in the accurate identification of coal reservoirs and the quantitative characterization of their physical properties. Coal facies research, as the core geological foundation and scientific basis for CBM logging technology, reveals differences in coal bodies and their control mechanisms on CBM enrichment and development through in-depth analysis of coal-forming swamp environments (such as water depth and redox conditions). This provides crucial support for the interpretation of reservoir physical properties from logging parameters, accurate coal facies identification, and the assessment of development potential.

[0003] Currently, existing methods for studying coal facies primarily rely on laboratory analysis and testing to obtain relevant parameters for identifying coal facies and classifying coal facies types. However, this method's over-reliance on laboratory analysis and testing results in the underutilization of a large amount of abundant well logging data. Furthermore, given that coal facies is a qualitative variable, only reflecting classification and lacking numerical variation or magnitude distinctions, current coal facies classification methods not only limit the application value of well logging data in coal facies evaluation but also suffer from insufficient objectivity and limited accuracy. Summary of the Invention

[0004] The purpose of this application is to provide a coal phase logging classification method, system, equipment, storage medium, and program product that can solve the problems of insufficient objectivity and limited accuracy in existing coal phase logging classification methods.

[0005] To solve the above-mentioned technical problems, this application is implemented as follows: In a first aspect, embodiments of this application provide a coal-phase logging classification method, including: Select a reference well, collect various coal phase parameters and logging data for each coal seam in the reference well, and classify the coal phase type of each coal seam in the reference well according to the various coal phase parameters; Based on the various coal phase parameters and well logging data corresponding to each coal seam, the correlation between each type of coal phase parameter and each type of well logging data is evaluated to determine the category of well logging data that conforms to geological laws. For all categories of logging data that conform to geological patterns, determine the significance of all logging data with the coal facies type to determine the target logging data for each coal facies type; Label the target well logging data for each coal phase type with coal phase type labels, generate a training dataset, and use the training dataset to train the coal phase evaluation model to be trained, so as to obtain the trained coal phase evaluation model. The target category logging data of the predicted well is input into the trained coal phase evaluation model to obtain the classification probability of each coal phase type in each coal seam in the predicted well, and the coal phase classification result of each coal seam in the predicted well is determined to generate the coal phase logging classification result of the predicted well.

[0006] Furthermore, based on the various coal facies parameters and well logging data corresponding to each coal seam, the correlation between each type of coal facies parameter and each type of well logging data is evaluated to determine the category of well logging data that conforms to geological laws, including: Based on the various coal phase parameters and well logging data corresponding to each coal seam, the average value of each type of coal phase parameter and the average value of each type of well logging data are determined respectively. Based on the various coal phase parameters and well logging data corresponding to each coal seam, the average value of each coal phase parameter and the average value of each well logging data, the correlation between each coal phase parameter and each well logging data is determined respectively. By analyzing the correlation and correlation threshold between each type of coal phase parameter and each type of well logging data, the category of well logging data that conforms to geological laws is determined.

[0007] Furthermore, for all categories of logging data conforming to geological patterns, the significance between all logging data and the coal facies type is determined to identify target logging data for each coal facies type, including: For a coal phase type and a type of logging data, calculate the first probability that each logging parameter in the type of logging data is related to the coal phase type and the second probability that it is not related to the coal phase type. Based on the first probability and the second probability of each logging parameter in the logging data, calculate the first likelihood function value related to the coal facies type and the second likelihood function value unrelated to the coal facies type; Based on the first and second likelihood function values ​​of the well logging data and the coal facies type, determine the likelihood ratio between the well logging data and the coal facies type. Based on the likelihood ratio between the type of logging data and the type of coal facies, and a preset rejection region, the significance between the type of logging data and the type of coal facies is determined. If the significance between the logging data of this type and the coal facies type is higher than the significance threshold, the logging data of this type is determined as the target logging data of the coal facies type. Repeat the above steps to obtain the significance between each type of logging data and each type of coal facies, so as to determine the target logging data for each coal facies type.

[0008] Furthermore, the coal phase parameters include at least the vegetation preservation index and the gelation index; Collect various coal phase parameters for each coal seam in the reference well, including: Submicroscopic component analysis was performed on each coal seam in the reference well to obtain the vegetation preservation index and gelation index of each coal seam in the reference well. The coal facies type of each coal seam in the reference well is classified according to the various coal facies parameters, including: The coal facies type of each coal seam in the reference well is determined based on the pre-established coal facies type classification principle, as well as the vegetation preservation index and gelation index of each coal seam.

[0009] Furthermore, the various logging data include at least: well diameter, spontaneous potential, spontaneous gamma, density, photoelectric cross-sectional index, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons; The categories of well logging data conforming to geological laws include at least: natural gamma, density, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons; The determination of the categories of well logging data that conform to geological laws includes: Based on the correlation between each type of coal phase parameter and each type of well logging data, determine the absolute value of the correlation between each type of coal phase parameter and each type of well logging data; The category of well logging data that conforms to geological laws is determined based on the absolute value of the correlation and the correlation threshold.

[0010] Furthermore, the coal phase evaluation model to be trained includes at least multiple coal phase evaluation sub-models; the training dataset includes at least various target logging data corresponding to each coal phase type. The training dataset is used to train the coal phase evaluation model to be trained, including: Input the target logging data of each coal phase type into the coal phase evaluation model to be trained, and obtain the sub-model scores of each target logging data of each coal phase type through each coal phase evaluation sub-model; Based on the coal phase type labels corresponding to the target logging data of each coal phase type, the model parameters of each coal phase evaluation sub-model are updated, wherein each model parameter of each coal phase evaluation sub-model represents the degree of influence of a type of target logging data on a type of coal phase.

[0011] Secondly, embodiments of this application provide a coal phase logging classification system, including: The selection module is used to select a reference well, collect various coal phase parameters and logging data of each coal seam in the reference well, and classify the coal phase type of each coal seam in the reference well according to the various coal phase parameters. The evaluation module is used to evaluate the correlation between each type of coal phase parameter and each type of well logging data based on the various coal phase parameters and well logging data corresponding to each coal seam, so as to determine the category of well logging data that conforms to geological laws. The target logging data determination module is used to determine the saliency between all logging data and the coal facies type for all categories of logging data that conform to geological laws, so as to determine the target logging data for each coal facies type; The model training module is used to label the target well logging data of each coal phase type with coal phase type labels, generate a training dataset, and use the training dataset to train the coal phase evaluation model to be trained, so as to obtain the trained coal phase evaluation model. The generation module is used to input the logging data of the target category of the predicted well into the trained coal phase evaluation model, obtain the classification probability of each coal phase type of each coal seam in the predicted well, determine the coal phase classification result of each coal seam in the predicted well, and generate the coal phase logging classification result of the predicted well.

[0012] Thirdly, embodiments of this application provide an electronic device, including: processor; Memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the coal phase logging classification method as described in the first aspect.

[0013] Fourthly, embodiments of this application provide a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a terminal's processor, enables the terminal to perform the coal phase logging classification method as described in the first aspect.

[0014] Fifthly, embodiments of this application provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the coal phase logging classification method as described in the first aspect.

[0015] In this embodiment, firstly, by selecting reference wells and collecting multi-source data, a reliable data foundation for coal facies classification is provided, avoiding the limitations of subjective assignment. Secondly, by evaluating the correlation between coal facies parameters and well logging data, well logging data categories that conform to geological laws are selected, effectively eliminating noisy data unrelated to coal facies types and improving the effectiveness of the training dataset used for model training. By determining the significance between well logging data and coal facies types, a reliable statistical association between the well logging data used for model training and coal facies types is ensured, improving the quality of model training and the accuracy of prediction. Finally, by training the coal facies evaluation model and applying it to prediction wells, the objectivity and accuracy of coal facies classification are guaranteed. This solves the technical problems of strong subjectivity and low classification efficiency in existing technologies. Attached Figure Description

[0016] Figure 1 A flowchart illustrating the steps of a coal phase logging classification method provided in an embodiment of this application is shown. Figure 2 A heatmap showing the correlation between the vegetation preservation index (TPI) and various types of well logging data provided in one embodiment of this application is illustrated. Figure 3 A heatmap showing the correlation between the gelation index (GI) and various types of well logging data provided in one embodiment of this application is illustrated. Figure 4 A schematic diagram of the structure of a coal phase logging classification system provided in an embodiment of this application is shown; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0018] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0019] The coal phase logging classification method, system, equipment, storage medium, and program products provided in this application will be described in detail below with reference to the accompanying drawings and through specific embodiments and application scenarios.

[0020] With the continuous advancement of coalbed methane exploration and development in my country, and the deepening research on coalbed methane reservoirs, our understanding of the geological factors restricting coalbed methane production has become increasingly comprehensive. Coalbed methane logging technology, as a key means of coalbed methane exploration, has become an important technical support for coalbed methane exploration, playing a crucial role in qualitative identification of coal reservoirs, quantitative interpretation of coal petrography and quality, quantitative interpretation of coal seam gas content, and quantitative interpretation of coal reservoir porosity and permeability. In addition to conventional logging methods such as sonic transit time, compensated density, natural gamma, compensated neutron, dual lateral resistivity, and spontaneous potential logging, unconventional logging methods such as sonic arrays, imaging logging, and energy spectrum logging are also gradually being applied to coalbed methane research.

[0021] Coal facies study, as a crucial component of coal reservoir geology research, analyzes factors influencing the coal-forming swamp environment, such as water depth, redox environment, and nutrient supply. This allows for in-depth exploration of the differences in coal formed within this environment and, consequently, their impact on coalbed methane enrichment and development. Accurate coal facies identification contributes to a comprehensive and in-depth understanding of coalbed methane reservoir characteristics, providing a solid geological basis for efficient coalbed methane development. Therefore, conducting coal facies identification research has significant practical implications.

[0022] Previous studies on coal facies primarily relied on laboratory analysis and testing to obtain relevant parameters for identifying different coal facies types. This resulted in the underutilization of a wealth of well logging data. Furthermore, since coal facies is a qualitative variable, reflecting only classification and lacking numerical variation or magnitude, current coal facies classification methods not only limit the application value of well logging data in coal facies evaluation but also suffer from insufficient objectivity and limited accuracy.

[0023] Figure 1 A flowchart illustrating the steps of a coal phase logging classification method according to an embodiment of this application is shown. (Refer to...) Figure 1 This application provides a coal phase logging classification method, including: S10. Select a reference well, collect various coal phase parameters and logging data for each coal seam in the reference well, and classify the coal phase type of each coal seam in the reference well according to the various coal phase parameters.

[0024] Specifically, a reference well refers to a drilled well with detailed geological data and experimental analysis data (such as coal facies parameters). The data from reference wells are used to establish and validate geological models, providing a foundation for subsequent predictions and assessments. Coal facies parameters are indicators characterizing the depositional environment, material composition, and structural features of coal seams, and are important bases for classifying coal facies types. Well logging data refers to geophysical parameters continuously collected in the wellbore using logging instruments, reflecting the physical properties of the formation rocks, and are an important source of information for geological interpretation and reservoir evaluation. Coal facies types refer to the classification of coal seams with similar coal-forming environments and characteristics based on coal facies parameters. Different coal facies types correspond to different coalbed methane enrichment patterns and development potential.

[0025] For example, the reference well is a well selected artificially with complete core data and a detailed geochemical analysis report. Various logging data are extracted from the actual measured logging curves, including at least well diameter, spontaneous potential, density, natural gamma, photoelectric cross section index, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons. Coal facies parameters are obtained through submicroscopic component testing and analysis results, specifically including gelation index (GI) and vegetation preservation index (TPI). Coal facies types include at least wetland forest swamp facies, aquatic forest swamp facies, wetland herbaceous swamp facies, and deep-water herbaceous swamp facies.

[0026] In some embodiments, the coal phase parameters include at least the vegetation preservation index and the gelation index; Various coal phase parameters of each coal seam in the reference well were collected, including: submicroscopic component testing of each coal seam in the reference well to obtain the vegetation preservation index and gelation index of each coal seam in the reference well.

[0027] The coal facies type of each coal seam in the reference well is determined based on various coal facies parameters, including: determining the coal facies type of each coal seam in the reference well according to the pre-constructed coal facies type classification principles, as well as the vegetation preservation index and gelation index of each coal seam.

[0028] Specifically, the pre-constructed coal facies classification principles are based on a summary of extensive geological research and experimental data, defining the correspondence or threshold ranges between different coal facies types and coal facies parameters such as vegetation preservation index and gelation index. This application does not impose specific limitations. Submicroscopic component analysis is used to obtain the vegetation preservation index and gelation index of each coal seam in the reference well, ensuring the accuracy of various coal facies parameters in each coal seam of the reference well. This provides reliable data support for coal facies classification, ensuring the accuracy of coal facies type classification and providing reliable data support for the subsequent assessment of the correlation between well logging data and coal facies types, thereby guaranteeing the accuracy and reliability of subsequent coal facies well logging classification results.

[0029] For example, Table 1 shows the coal facies type classification principles for the reference well. When the coal facies parameters include gelation index (GI) and vegetation preservation index (TPI), the pre-constructed coal facies type classification criteria are shown in Table 1: By clarifying the range of gelation index (GI) and vegetation preservation index (TPI) corresponding to each coal facies type, the specific coal facies type can be determined. Specifically, the coal facies types should at least cover four categories: wetland forest swamp facies, aquatic forest swamp facies, wetland herbaceous swamp facies, and deep-water herbaceous swamp facies. In actual operation, after collecting the coal facies parameters of each coal seam in the reference well, the coal facies type of each coal seam can be determined according to the coal facies type classification principles in Table 1.

[0030] Table 1. Principles for classifying coal facies types in reference wells

[0031] This application embodiment selects reference wells with detailed geological data and experimental data, collects coal phase parameters and logging data for each coal seam, and clearly classifies the coal phase types of each coal seam based on the coal phase parameters. This realizes the association between known coal phase types and corresponding logging data, forming a standardized sample basis. It provides a reliable correspondence between coal phase types and logging data for subsequent coal phase identification. By associating specific coal phase types with various types of logging data, it avoids the accuracy problem of coal phase identification based on a single indicator, and ensures the accuracy of subsequent coal phase identification.

[0032] S20. Based on the various coal phase parameters and logging data corresponding to each coal seam, evaluate the correlation between each type of coal phase parameter and each type of logging data in order to determine the category of logging data that conforms to geological laws.

[0033] Specifically, correlation refers to the degree of interrelation between each type of coal phase parameter and each type of well logging data. It is used to measure the statistical relationship between coal phase parameters and well logging data to identify well logging data that influences coal phase classification. Well logging data that conforms to geological laws refers to well logging data whose trend or numerical range is consistent with known stratigraphic rocks, fluids, and geological processes. Correlation assessment methods can include Pearson correlation coefficient, Spearman rank correlation coefficient, or Kendall rank correlation coefficient; this application does not impose specific limitations on these methods. By assessing the correlation between each type of coal phase parameter and each type of well logging data, well logging data with potential correlation to coal phase type can be screened out, while irrelevant or weakly correlated well logging data can be excluded, ensuring the accuracy of subsequent coal phase evaluation models.

[0034] In some embodiments, S20, based on various coal facies parameters and well logging data corresponding to each coal seam, the correlation between each type of coal facies parameter and each type of well logging data is evaluated to determine the category of well logging data that conforms to geological laws, including: S21. Based on the various coal phase parameters and well logging data corresponding to each coal seam, determine the average value of each type of coal phase parameter and the average value of each type of well logging data.

[0035] S22. Based on the various coal phase parameters and logging data corresponding to each coal seam, the average value of each coal phase parameter and the average value of each logging data, determine the correlation between each coal phase parameter and each logging data.

[0036] S23. Determine the category of well logging data that conforms to geological laws by comparing the correlation and correlation threshold between each type of coal phase parameter and each type of well logging data.

[0037] Specifically, the average values ​​of each coal facies parameter and each type of logging data can be calculated using the arithmetic mean, weighted average, or other commonly used statistical measures of central tendency. Before assessing the correlation between each coal facies parameter and each type of logging data, the coal facies parameters and logging data are first normalized to obtain normalized versions. Then, based on the normalized versions, the correlation between each coal facies parameter and each type of logging data is calculated using the Pearson correlation coefficient. Finally, the calculated correlation between each coal facies parameter and each type of logging data is compared with a preset correlation threshold to determine the category of logging data that conforms to geological patterns.

[0038] In some embodiments, S23, determining the category of well logging data that conforms to geological patterns includes: Based on the correlation between each type of coal phase parameter and each type of well logging data, the absolute value of the correlation between each type of coal phase parameter and each type of well logging data is determined.

[0039] Based on the absolute value of the correlation and the correlation threshold, the category of well logging data that conforms to geological laws is determined.

[0040] For example, Table 2 shows various coal facies parameters and logging data of a reference well provided in an embodiment of this application. Figure 2 This application presents a heatmap illustrating the correlation between the vegetation preservation index (TPI) and various types of well logging data, according to an embodiment of this application. Figure 3 A heatmap illustrating the correlation between the gelation index (GI) and various logging data provided in one embodiment of this application is shown. Referring to Table 2, the various logging data include at least: wellbore diameter, spontaneous potential, spontaneous gamma, density, photoelectric cross-sectional index, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons. After normalizing various coal phase parameters and logging parameters, the correlation between each coal phase parameter and each type of logging data is calculated based on the Pearson correlation coefficient, generating... Figure 2 Correlation heatmap between vegetation preservation index (TPI) and various well logging data and Figure 3 A heatmap showing the correlation between the gelation index (GI) and various well logging data, in which... Figure 2 The heatmap visually illustrates the correlation between the vegetation preservation index (TPI) and various well logging data (caliber CAL, natural gamma ray GR, density DEN, sonic transit time AC, deep lateral resistivity RLLD, shallow lateral resistivity RLLS, compensated neutron CNL, spontaneous potential SP, and photoelectric cross section index PE). Figure 3 A heatmap visually illustrates the correlation between the gelation index (GI) and various logging data types (caliber CAL, natural gamma ray GR, density DEN, sonic transit time AC, deep lateral resistivity RLLD, shallow lateral resistivity RLLS, compensated neutron CNL, spontaneous potential SP, and photoelectric cross-section index PE). When the correlation threshold is greater than or equal to 0.5, the categories of geologically consistent logging data related to both the vegetation preservation index (TPI) and the gelation index (GI) are: compensated neutron CNL, natural gamma ray GR, density DEN, sonic transit time AC, deep lateral resistivity RLLD, and shallow lateral resistivity RLLS.

[0041] Table 2. Reference well coal facies parameters and logging data.

[0042] This application transforms the assessment of the correlation between coal phase parameters and well logging data from subjective experience-based judgment to objective quantitative analysis. By calculating average values, a stable reference benchmark is established for various coal phase parameters and well logging data, effectively mitigating the impact of data fluctuations and outliers, and ensuring the robustness of subsequent correlation analysis. The correlation between each type of coal phase parameter and each type of well logging data is calculated based on the average value, quantifying the statistical correlation strength between each type of coal phase parameter and each type of well logging data, avoiding over-reliance on experience-based judgment. By comparing the calculated correlation with a preset correlation threshold, well logging data categories with strong correlations to coal phase parameters can be objectively screened. Screening well logging data types that conform to geological laws based on correlation and correlation thresholds provides high-quality, high-reliability input data for subsequent coal phase type identification and model training, ensuring the accuracy of the overall coal phase well logging classification results.

[0043] S30. For all categories of logging data that conform to geological laws, determine the significance of all logging data with coal facies type to determine the target logging data for each coal facies type.

[0044] Specifically, significance refers to the reliability of the correlation between well logging data and coal facies type; target well logging data refers to well logging data that, after correlation assessment and significance testing, is determined to be indicative of coal facies classification.

[0045] In some embodiments, S30, for all categories of logging data conforming to geological patterns, the saliency between all logging data and coal facies types is determined to identify target logging data for each coal facies type, including: S31. For a coal phase type and a type of logging data, calculate the first probability that each logging parameter in the type of logging data is related to the coal phase type and the second probability that it is not related to the coal phase type.

[0046] S32. Based on the first probability and the second probability of each logging parameter in this type of logging data, calculate the first likelihood function value related to this type of coal phase type and the second likelihood function value unrelated to this type of coal phase type.

[0047] S33. Based on the first and second likelihood function values ​​of the logging data and the coal facies type, determine the likelihood ratio between the logging data and the coal facies type.

[0048] S34. Based on the likelihood ratio between this type of logging data and this type of coal facies type, and the preset rejection region, determine the significance between this type of logging data and this type of coal facies type.

[0049] S35. If the significance of this type of logging data with this type of coal facies type is higher than the significance threshold, then this type of logging data shall be identified as the target logging data for this type of coal facies type.

[0050] S36. Repeat the above steps to obtain the significance between each type of logging data and each type of coal facies, so as to determine the target logging data for each coal facies type.

[0051] Specifically, the first probability quantifies the likelihood of observing a certain logging parameter value under a given specific coal facies type; the second probability quantifies the likelihood of observing the same logging parameter value under a different coal facies type. The calculation methods for both are flexible: it can be assumed that the logging parameter follows a known statistical distribution (such as a normal distribution or gamma distribution) under a specific coal facies type, and the distribution parameters (mean, variance) can be estimated using reference well data, then the probability can be calculated using a probability density function; alternatively, non-parametric methods (such as empirical frequency statistics, histogram analysis, kernel density estimation) can be used to directly estimate the probability from reference well data. This application does not impose any restrictions on this approach.

[0052] The likelihood function value measures the likelihood of the observed set of well logging data under a specific hypothesis (the well logging parameters are "related" or "unrelated" to the coal facies type). In the specific calculation, assuming that the parameters in a certain well logging data category are independent of each other under a given coal facies type, the likelihood function value can be expressed as: the product of the "corresponding probabilities" of all well logging parameters in this category (the first probability under the "related" hypothesis and the second probability under the "unrelated" hypothesis). The likelihood ratio is the ratio of the likelihood function value under the "related" hypothesis to the likelihood function value under the "unrelated" hypothesis, and is used to quantify the relative support degree of "the well logging parameters are related to this coal facies type" relative to "unrelated" (supporting "related" when LR > 1 and supporting "unrelated" when LR < 1). The preset rejection region is the critical range of the likelihood ratio defined based on the significance threshold (such as α = 0.05) and the statistical distribution (such as the chi-square distribution), and is used to determine whether the "related" hypothesis holds. Comparing the calculated likelihood ratio with the rejection region, if the likelihood ratio falls within the rejection region, it indicates that the "first probability under the given coal facies type" is significantly higher than the "second probability under non-this coal facies type", that is, the observed data better supports the alternative hypothesis that "the well logging parameters are related to this coal facies type", and the association between the two has statistical significance; if the likelihood ratio does not fall within the rejection region, it means that the difference between the first probability and the second probability does not reach the significance threshold, and there is not enough evidence to determine that there is a significant association between the two. By matching the likelihood ratio with the rejection region, the "relative support degree of probability" is transformed into a "statistical significance conclusion", clarifying whether the indication significance of the well logging parameters for the coal facies type is reliable, and providing a quantitative basis for the feature screening and geological interpretation of the subsequent coal facies recognition model.

[0053] Exemplarily, first, determine the first likelihood function value according to the following formula:

[0054] Where is the hypothesis that this type of well logging data is related to this type of coal facies type, are the respective data in this type of well logging data, and P is the first probability that the i-th well logging data in this type of well logging parameters is related to this type of coal facies type.

[0055] Determine the second likelihood function value according to the following formula:

[0056] Where is the hypothesis that this type of well logging data is unrelated to this type of coal facies type, are the respective data in this type of well logging data, and P is the second probability that the i-th well logging data in this type of well logging parameters is unrelated to this type of coal facies type.

[0057] Then, determine the likelihood ratio of this type of well logging data to this type of coal facies type according to the following formula:

[0058] in, This represents the likelihood ratio between this type of well logging data and this type of coal facies.

[0059] The default rejection domain is:

[0060] Where c represents the significance threshold, which is 0.05.

[0061] S40. Label the target well logging data for each coal phase type with coal phase type labels, generate a training dataset, and use the training dataset to train the coal phase evaluation model to be trained, so as to obtain the trained coal phase evaluation model.

[0062] Specifically, the coal phase evaluation model to be trained can be a simple decision tree model or a support vector machine model. By associating each target well logging data sample with its corresponding coal phase type, a labeled training dataset is formed to guide the coal phase evaluation model in learning and optimizing its internal parameters. Each sample in the training dataset consists of input features (i.e., target well logging data) and a corresponding correct output label (i.e., coal phase type label). By inputting the training dataset, the model parameters of the coal phase evaluation model to be trained are iteratively adjusted until the model can well fit the relationship between well logging data and coal phase type.

[0063] For example, the trained coal phase evaluation model is represented by the following formula:

[0064] Where P(y=k|x) represents the k-th coal phase type. This is a type of well logging data. This represents the probability that this type of well logging data corresponds to the k-th coal facies type. Let be a constant parameter for the k-th coal phase type. Let be the weighting parameters for the i-th type of well logging data. Let represent the logging parameters of the i-th type of logging data.

[0065] The coal phase evaluation model is trained using the training dataset. For each coal phase type, the constant parameters of the coal phase type and the weight parameters of the corresponding well logging data are updated to obtain the trained coal phase evaluation model.

[0066] In some embodiments, the coal phase evaluation model to be trained includes at least a plurality of coal phase evaluation sub-models; the training dataset includes at least various target logging data corresponding to each coal phase type; S40. Train the coal phase evaluation model to be trained using the training dataset, including: S41. Input the target logging data of each coal phase type into the coal phase evaluation model to be trained. Through each coal phase evaluation sub-model, obtain the sub-model scores of each target logging data of each coal phase type.

[0067] S42. Based on the coal phase type labels corresponding to the target logging data of each coal phase type, update the model parameters of each coal phase evaluation sub-model. Each model parameter of each coal phase evaluation sub-model represents the degree of influence of a type of target logging data on a type of coal phase.

[0068] Specifically, each coal facies evaluation sub-model is responsible for identifying a specific coal facies type (e.g., the probability of one sub-model classifying it as a wetland-forest-swamp facies, and the probability of another classifying it as a deep-water herbaceous-swamp facies). By inputting target well logging data for each coal facies type from the training dataset into the coal facies evaluation model to be trained, each sub-model receives a score, allowing each sub-model to independently process and make preliminary predictions on the input well logging data. The score output by each sub-model represents its confidence level or probability estimate that the input data belongs to a specific coal facies type. By comparing the predicted scores of the sub-models with the actual coal facies type labels, the internal parameters of the sub-models are adjusted to reduce prediction errors and improve the accuracy of the coal facies evaluation models. During the model parameter update process, cross-validation can also be used to verify the accuracy of the coal facies evaluation models.

[0069] S50. Input the logging data of the target category of the predicted well into the trained coal phase evaluation model to obtain the classification probability of each coal phase type in each coal seam in the predicted well, determine the coal phase classification result of each coal seam in the predicted well, and generate the coal phase logging classification result of the predicted well.

[0070] Specifically, a prediction well refers to a well to be evaluated that requires coal phase logging classification. The target category logging data for the prediction well refers to logging data that includes at least all target category logging data from the training dataset. The classification probability refers to the numerical estimate given by the trained coal phase evaluation model of the likelihood that a coal seam in the prediction well belongs to any of the various coal phase types. The coal phase classification result refers to the final coal phase type of each coal seam in the prediction well, determined based on the classification probabilities. The coal phase logging classification result refers to the probability that the prediction well belongs to each coal phase type. By inputting the target category logging data of the prediction well into the trained coal phase evaluation model, the classification probabilities of each coal phase type in each coal seam in the prediction well are obtained, thus determining the coal phase classification result for each coal seam in the prediction well. Based on the coal phase classification result and corresponding classification probabilities of each coal seam in the logging, as well as the weight determined by the thickness of each coal seam, the coal phase logging classification result of the prediction well can be obtained.

[0071] For example, the trained coal phase evaluation model is represented by the following formula:

[0072]

[0073]

[0074] The trained coal phase evaluation model includes three coal phase evaluation sub-models. , , These represent the sub-model scores of a coal phase evaluation sub-model.

[0075] Based on the coal phase type labels corresponding to various target logging data for each coal phase type, the weight parameters of each coal phase evaluation sub-model for each logging data (compensated neutron CNL, natural gamma ray GR, density DEN, acoustic transit time AC, deep lateral resistivity RLLD, and shallow lateral resistivity RLLS) are updated, resulting in a trained coal phase evaluation model. When using the trained coal phase evaluation model to classify the coal phase of each coal seam in the prediction well, each sub-model outputs the probability value of the corresponding coal phase classification for each coal seam in the prediction well. For example, when using the trained coal phase evaluation model to classify the coal phase of a coal seam in the prediction well, if the coal phase logging classification results include water-covered forest, deep-water herbaceous land, wetland herbaceous land, and wetland forest, the three coal phase evaluation sub-models output the probability values ​​of the coal phase type of the coal seam in the prediction well as water-covered forest, deep-water herbaceous land, and wetland herbaceous land, respectively. Based on the principle that the total probability is 1, the probability that the coal phase type of the coal seam in the prediction well is wetland forest can be determined.

[0076] For example, Table 3 shows the coal facies logging classification results for the predicted wells. Referring to Table 3, the logging data for the target category of each predicted well includes compensated neutron, natural gamma, density, sonic transit time, deep lateral resistivity, and shallow lateral resistivity. By inputting the logging data for the target category of the predicted wells into the trained coal facies evaluation model, the coal facies logging classification results for each predicted well are obtained (for example, the coal facies logging classification results for predicted well J1-2 are: water-covered forest 7.57%, deep-water herbaceous 69.39%, wetland herbaceous 0.00%, and wetland forest 23.04%).

[0077] Table 3. Coal-facies logging classification results of predicted wells

[0078] In this embodiment, firstly, by selecting reference wells and collecting multi-source data, a reliable data foundation for coal facies classification is provided, avoiding the limitations of subjective assignment. Secondly, by evaluating the correlation between coal facies parameters and well logging data, well logging data categories that conform to geological laws are selected, effectively eliminating noisy data unrelated to coal facies types and improving the effectiveness of the training dataset used for model training. By determining the significance between well logging data and coal facies types, a reliable statistical association between the well logging data used for model training and coal facies types is ensured, improving the quality of model training and the accuracy of prediction. Finally, by training the coal facies evaluation model and applying it to prediction wells, the objectivity and accuracy of coal facies classification are guaranteed. This solves the technical problems of strong subjectivity and low classification efficiency in existing technologies.

[0079] Figure 4 A schematic diagram of the structure of a coal phase logging classification system according to an embodiment of this application is shown. (Refer to...) Figure 4 This application provides a coal phase logging classification system, including: Module 10 is used to select a reference well, collect various coal phase parameters and logging data of each coal seam in the reference well, and classify the coal phase type of each coal seam in the reference well according to the various coal phase parameters. Evaluation module 20 is used to evaluate the correlation between each type of coal phase parameter and each type of well logging data based on the various coal phase parameters and well logging data corresponding to each coal seam, so as to determine the category of well logging data that conforms to geological laws. The target logging data determination module 30 is used to determine the significance between all logging data and coal facies type for all categories of logging data that conform to geological laws, so as to determine the target logging data for each coal facies type; The model training module 40 is used to label the target well logging data for each coal phase type with coal phase type labels, generate a training dataset, and use the training dataset to train the coal phase evaluation model to be trained, so as to obtain the trained coal phase evaluation model. The generation module 50 is used to input the logging data of the target category of the predicted well into the trained coal phase evaluation model, obtain the classification probability of each coal phase type of each coal seam in the predicted well, determine the coal phase classification result of each coal seam in the predicted well, and generate the coal phase logging classification result of the predicted well.

[0080] In some embodiments, the evaluation module 20 includes: The first determining unit is used to determine the average value of each type of coal phase parameter and the average value of each type of well logging data based on the various coal phase parameters and well logging data corresponding to each coal seam. The second determining unit is used to determine the correlation between each type of coal phase parameter and each type of well logging data based on the various coal phase parameters and well logging data corresponding to each coal seam, the average value of each type of coal phase parameter and the average value of each type of well logging data. The third determining unit is used to determine the category of well logging data that conforms to geological laws by comparing the correlation and correlation threshold between each type of coal phase parameter and each type of well logging data.

[0081] In some embodiments, the target logging data determination module 30 includes: The first calculation unit is used to calculate, for a coal phase type and a well logging data type, the first probability that each well logging parameter in the well logging data is related to the coal phase type and the second probability that is not related to the coal phase type; The second calculation unit is used to calculate, based on the first probability and the second probability of each logging parameter in the logging data, the first likelihood function value related to the coal phase type and the second likelihood function value unrelated to the coal phase type; The fourth determining unit is used to determine the likelihood ratio between the type of well logging data and the type of coal facies based on the first likelihood function value and the second likelihood function value of the type of well logging data and the type of coal facies. The fifth determining unit is used to determine the significance between the type of logging data and the type of coal facies based on the likelihood ratio between the type of logging data and the type of coal facies and a preset rejection region; The sixth determining unit is used to determine the type of well logging data as the target well logging data for the type of coal facies when the significance between the type of well logging data and the type of coal facies is higher than the significance threshold; The seventh determination unit is used to repeat the above steps to obtain the significance between each type of logging data and each type of coal phase, so as to determine the target logging data for each coal phase.

[0082] In some embodiments, the coal phase parameters include at least the vegetation preservation index and the gelation index; Selecting module 10 includes: The testing unit is used to perform submicroscopic component testing on each coal seam in the reference well to obtain the vegetation preservation index and gelation index of each coal seam in the reference well. The eighth determining unit is used to determine the coal phase type of each coal seam in the reference well based on the pre-constructed coal phase type classification principles, as well as the vegetation preservation index and gelation index of each coal seam.

[0083] In some embodiments, the various logging data include at least: well diameter, spontaneous potential, spontaneous gamma, density, photoelectric cross-sectional index, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons; The categories of logging data that conform to geological laws include at least: natural gamma, density, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons; The third determining unit includes: The first determining subunit is used to determine the absolute value of the correlation between each type of coal phase parameter and each type of well logging data based on the correlation between each type of coal phase parameter and each type of well logging data; The second determining sub-unit is used to determine the category of well logging data that conforms to geological laws based on the absolute value of the correlation and the correlation threshold.

[0084] In some embodiments, the coal phase evaluation model to be trained includes at least a plurality of coal phase evaluation sub-models; the training dataset includes at least various target logging data corresponding to each coal phase type; Model training module 40 includes: The input unit is used to input various target logging data of each coal phase type into the coal phase evaluation model to be trained. Through each coal phase evaluation sub-model, the sub-model scores of various target logging data of each coal phase type are obtained respectively. The update unit is used to update the model parameters of each coal phase evaluation sub-model based on the coal phase type labels corresponding to the target logging data of each coal phase type. Each model parameter of each coal phase evaluation sub-model represents the degree of influence of a type of target logging data on a type of coal phase.

[0085] Figure 5 A schematic diagram of the structure of an electronic device according to an embodiment of this application is shown. (Refer to...) Figure 5 One embodiment of this application provides an electronic device, including: processor; Memory is used to store processor-executable instructions; The processor is configured to execute instructions to implement any of the coal phase logging classification methods.

[0086] In this embodiment, the computer device includes a processor, memory, and network interface connected via a system bus. The computer device's processor provides computational and control capabilities. Its memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The computer device's database stores data samples. Its network interface is used for communication with external terminals via a network connection. When the processor executes the computer program, it implements any coal-phase logging classification method.

[0087] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0088] This application also provides a computer-readable storage medium, which, when the instructions in the computer-readable storage medium are executed by the processor of a terminal, enables the terminal to execute any coal phase logging classification method.

[0089] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0090] Optionally, a readable storage medium can be coupled to the processor, enabling the processor to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processor. The processor and the readable storage medium can reside in application-specific integrated circuits (ASICs). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0091] This application also provides a computer program product, which includes a computer program that, when executed by a processor, implements any coal phase logging classification method.

[0092] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0093] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. 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, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0094] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0095] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0096] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0097] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0098] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0099] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0100] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A coal phase logging classification method, characterized in that, include: Select a reference well, collect various coal phase parameters and logging data for each coal seam in the reference well, and classify the coal phase type of each coal seam in the reference well according to the various coal phase parameters; Based on the various coal phase parameters and well logging data corresponding to each coal seam, the correlation between each type of coal phase parameter and each type of well logging data is evaluated to determine the category of well logging data that conforms to geological laws. For all categories of logging data that conform to geological patterns, determine the significance of all logging data with the coal facies type to determine the target logging data for each coal facies type; Label the target well logging data for each coal phase type with coal phase type labels, generate a training dataset, and use the training dataset to train the coal phase evaluation model to be trained, so as to obtain the trained coal phase evaluation model. The target category logging data of the predicted well is input into the trained coal phase evaluation model to obtain the classification probability of each coal phase type in each coal seam in the predicted well, and the coal phase classification result of each coal seam in the predicted well is determined to generate the coal phase logging classification result of the predicted well.

2. The method as described in claim 1, characterized in that, Based on the various coal facies parameters and well logging data corresponding to each coal seam, the correlation between each type of coal facies parameter and each type of well logging data is evaluated to determine the category of well logging data that conforms to geological laws, including: Based on the various coal phase parameters and well logging data corresponding to each coal seam, the average value of each type of coal phase parameter and the average value of each type of well logging data are determined respectively. Based on the various coal phase parameters and well logging data corresponding to each coal seam, the average value of each coal phase parameter and the average value of each well logging data, the correlation between each coal phase parameter and each well logging data is determined respectively. By analyzing the correlation and correlation threshold between each type of coal phase parameter and each type of well logging data, the category of well logging data that conforms to geological laws is determined.

3. The method as described in claim 1, characterized in that, For all categories of well logging data conforming to geological patterns, the significance between all well logging data and the coal facies type is determined to identify target well logging data for each coal facies type, including: For a coal phase type and a type of logging data, calculate the first probability that each logging parameter in the type of logging data is related to the coal phase type and the second probability that it is not related to the coal phase type. Based on the first probability and the second probability of each logging parameter in the logging data, calculate the first likelihood function value related to the coal facies type and the second likelihood function value unrelated to the coal facies type; Based on the first and second likelihood function values ​​of the well logging data and the coal facies type, determine the likelihood ratio between the well logging data and the coal facies type. Based on the likelihood ratio between the type of logging data and the type of coal facies, and a preset rejection region, the significance between the type of logging data and the type of coal facies is determined. If the significance between the logging data of this type and the coal facies type is higher than the significance threshold, the logging data of this type is determined as the target logging data of the coal facies type. Repeat the above steps to obtain the significance between each type of logging data and each type of coal facies, so as to determine the target logging data for each coal facies type.

4. The method as described in claim 1, characterized in that, The coal phase parameters include at least the vegetation preservation index and the gelation index; Collect various coal phase parameters for each coal seam in the reference well, including: Submicroscopic component analysis was performed on each coal seam in the reference well to obtain the vegetation preservation index and gelation index of each coal seam in the reference well. The coal facies type of each coal seam in the reference well is classified according to the various coal facies parameters, including: The coal facies type of each coal seam in the reference well is determined based on the pre-established coal facies type classification principle, as well as the vegetation preservation index and gelation index of each coal seam.

5. The method as described in claim 1, characterized in that, The various types of logging data include at least: well diameter, spontaneous potential, spontaneous gamma, density, photoelectric cross-sectional index, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons; The categories of well logging data conforming to geological laws include at least: natural gamma, density, deep lateral resistivity, shallow lateral resistivity, sonic transit time, and compensated neutrons; The determination of the categories of well logging data that conform to geological laws includes: Based on the correlation between each type of coal phase parameter and each type of well logging data, determine the absolute value of the correlation between each type of coal phase parameter and each type of well logging data; The category of well logging data that conforms to geological laws is determined based on the absolute value of the correlation and the correlation threshold.

6. The method as described in claim 1, characterized in that, The coal phase evaluation model to be trained includes at least multiple coal phase evaluation sub-models; The training dataset includes at least various target logging data corresponding to each type of coal phase; The training dataset is used to train the coal phase evaluation model to be trained, including: Input the target logging data of each coal phase type into the coal phase evaluation model to be trained, and obtain the sub-model scores of each target logging data of each coal phase type through each coal phase evaluation sub-model; Based on the coal phase type labels corresponding to the target logging data of each coal phase type, the model parameters of each coal phase evaluation sub-model are updated, wherein each model parameter of each coal phase evaluation sub-model represents the degree of influence of a type of target logging data on a type of coal phase.

7. A coal phase logging classification system, characterized in that, include: The selection module is used to select a reference well, collect various coal phase parameters and logging data of each coal seam in the reference well, and classify the coal phase type of each coal seam in the reference well according to the various coal phase parameters. The evaluation module is used to evaluate the correlation between each type of coal phase parameter and each type of well logging data based on the various coal phase parameters and well logging data corresponding to each coal seam, so as to determine the category of well logging data that conforms to geological laws. The target logging data determination module is used to determine the saliency between all logging data and the coal facies type for all categories of logging data that conform to geological laws, so as to determine the target logging data for each coal facies type; The model training module is used to label the target well logging data of each coal phase type with coal phase type labels, generate a training dataset, and use the training dataset to train the coal phase evaluation model to be trained, so as to obtain the trained coal phase evaluation model. The generation module is used to input the logging data of the target category of the predicted well into the trained coal phase evaluation model, obtain the classification probability of each coal phase type of each coal seam in the predicted well, determine the coal phase classification result of each coal seam in the predicted well, and generate the coal phase logging classification result of the predicted well.

8. An electronic device, characterized in that, include: processor; Memory for storing processor-executable instructions; The processor is configured to execute the instructions to implement the coal phase logging classification method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the terminal, the terminal is able to perform the coal phase logging classification method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the coal phase logging classification method as described in any one of claims 1-6.

Images