A method for classifying shale gas well types

Abstract

The present invention discloses a shale gas well type classification method, comprising the steps of S1, obtaining original data of evaluation parameters of multiple stable production wells and test production wells; S2, standardizing the original data of the evaluation parameters; S3, calculating the distance coefficient according to the standardized data of the stable production wells; S4, classifying all the stable production wells according to the principle that the smaller the distance coefficient between two wells, the stronger the correlation; S5, after determining the number of stable production well classifications, calculating the comprehensive evaluation parameter S according to the standardized data; S6, taking the average value of each standardized parameter of each type of stable production well to construct a standard fuzzy set A; constructing a fuzzy set B to be identified for all test production wells; calculating the closeness between each fuzzy set to be identified and each standard fuzzy set, the greater the closeness, the more similar the standard fuzzy set is to the fuzzy set to be identified, and the test production well to be identified is classified into the stable production well category with the largest closeness.

Description

Technical Field

[0001] The invention relates to the technical field of shale gas exploitation, and in particular to a method for classifying shale gas well types. Background Art

[0002] Shale gas is a hot area in global oil and gas exploration. With the continuous advancement of production, the number of shale gas wells is increasing, and the production capacity of different shale gas wells varies significantly. For example, in the Luzhou block of the Sichuan Basin, the post-pressure test production of Well L203, Well Y101H1-2, and Well Y101H3-4 is 137.9×104m 3 / d、46.8×104m 3 / d, 0.8×104m 3 / d. Therefore, it is necessary to reasonably classify shale gas wells and study the production laws of different types of gas wells to guide the production of similar wells.

[0003] Previous researchers usually used geological static parameters (such as effective thickness, formation pressure, etc.) or production dynamic parameters (such as open flow, gas production per unit casing pressure drop, etc.) to classify shale gas wells into three categories: I, II, and III. This classification method has the following problems: ① It uses geological static evaluation or production dynamic evaluation in isolation without combining the two, ignoring the general trend of "geology-engineering integration"; ② Almost all current classification schemes classify shale gas wells into three categories, without adjusting or subdividing the gas well types according to actual production conditions, which is not conducive to the refinement of single well capacity evaluation; ③ The traditional classification method is a hard division, that is, it is only applicable when each data point clearly belongs to a specific category, and it is no longer applicable when the category of the data point is unclear or has overlapping features. For example, the evaluation criteria for shale gas wells in a certain block are: when the effective thickness of shale is greater than 45m, the gas saturation is greater than 50%, and the formation pressure coefficient is greater than 1.2, it is a Class I gas well; when the effective thickness of shale is between 30m and 45m, the gas saturation is between 40% and 50%, and the formation pressure coefficient is between 0.8 and 1.2, it is a Class II gas well; and a certain gas well has an effective shale thickness of 60m, a gas saturation of 30%, and a formation pressure coefficient of 0.9, which has the characteristics of both Class I and Class II gas wells, and cannot be directly classified.

[0004] Therefore, the existing shale gas well type evaluation methods are still unable to accurately and meticulously evaluate shale gas wells, resulting in deviations in gas well classification. Summary of the invention

[0005] In view of the problem that the existing shale gas well type evaluation method is still unable to accurately and meticulously evaluate shale gas wells, resulting in deviations in gas well classification, the present invention provides a shale gas well type classification method.

[0006] The method for classifying shale gas well types provided by the present invention comprises the following steps:

[0007] S1. Obtaining the original data of evaluation parameters of multiple stable production wells and test production wells;

[0008] The evaluation parameters include six parameters: effective thickness, gas saturation, formation pressure, open flow, gas production per unit casing pressure drop, and peak daily gas production. The original data of the three parameters of effective thickness, gas saturation, and formation pressure are obtained based on geological data; the original data of the three parameters of open flow, gas production per unit casing pressure drop, and peak daily gas production are obtained based on production data.

[0009] Preferably, original data of evaluation parameters of at least 10 stable production wells are obtained.

[0010] S2. In order to eliminate the influence of dimension, the original data of evaluation parameters are standardized. The formula is as follows:

[0011]

[0012] Where: Zx ij is the value of the i-th row and j-th column after standardization, x ij is the parameter value of the i-th row and j-th column before standardization; max[x ij ] is the maximum value in the original data; min[x ij ] is the minimum value in the original data.

[0013] S3. Calculate the distance coefficient d between every two stable production wells based on the standardized data of the stable production wells. ij , d ij The calculation formula is as follows:

[0014]

[0015] Where: x ik is the parameter of the i-th row and k-th column in the standardized data, x jk is the parameter of the jth column and the kth row in the standardized data, and m is the number of single wells.

[0016] S4. Classify all stable production wells according to the principle that the smaller the distance coefficient between two wells, the stronger the correlation; the method is as follows:

[0017] S41, sorting all distance coefficients except 0 in ascending order, merging the two gas wells corresponding to the smallest distance coefficient ranked first into one category to form a new individual, and the new individual continues to participate in subsequent merging and classification together with other gas wells;

[0018] S42, merging the two gas wells corresponding to the second-ranked distance coefficient into one category to form a new individual; and the new individual continues to participate in subsequent merging and classification together with other gas wells;

[0019] S43. According to the above method, the distance coefficient ranked third is used for merging and classification, and this cycle is repeated until all gas wells are classified into the number q types required for production, and the classification is stopped to obtain q different types of gas wells; where 1≤q≤m, q and m are positive integers, and m is the number of single wells.

[0020] In the above steps S41-S43, each time the merge classification is performed, the corresponding distance coefficient d ij , merge the gas wells corresponding to the i-th row and the gas wells corresponding to the j-th column into the same category, and remove the row and column corresponding to the larger number in i and j; then repeat the subsequent merging and classification operations on the remaining data.

[0021] Preferably, in step S43, the condition for stopping classification is: until the distance coefficient reaches d ij When the maximum value is ≤0.100, the classification is stopped and q different types of gas wells are obtained.

[0022] S5. After determining the number of stable production wells, calculate the comprehensive evaluation parameter S based on the standardized data. The comprehensive evaluation parameter S is equal to the sum of the six standardized evaluation parameter values:

[0023] S = standardized effective thickness + standardized gas saturation + standardized formation pressure + standardized open flow rate - standardized gas production per unit casing pressure drop + standardized peak daily gas production.

[0024] Then, the average value of the comprehensive evaluation parameter S of all gas wells of the same type is taken; according to the order of the average values ​​from large to small, each type is named as Class I gas well, Class II gas well, Class III gas well, ... Class Q gas well.

[0025] S6. Take the average value of the standardized parameters of each type of gas wells in stable production wells to construct a standard fuzzy set A, and obtain standard fuzzy sets A1, A2, A3, ...A q .

[0026] A = (average effective thickness, average gas saturation, average density and formation pressure, average open flow rate, average gas production per unit casing pressure drop, peak daily gas production).

[0027] According to the same method, the average values ​​of the standardized parameters of all test wells are taken to construct the fuzzy set B to be identified for all test wells, and the fuzzy sets to be identified B1, B2, B3, ... B are obtained respectively. n , n is the number of test wells.

[0028] B = (average effective thickness, average gas saturation, average density and formation pressure, average open flow rate, average gas production per unit casing pressure drop, peak daily gas production).

[0029] S7. Calculate the closeness between each fuzzy set to be identified and each standard fuzzy set. The larger the closeness, the more similar the standard fuzzy set is to the fuzzy set to be identified. Then the test well to be identified is classified into the stable production well category with the largest closeness.

[0030] The formula for calculating closeness is as follows:

[0031]

[0032] Where: σ(A,B) represents the closeness between A and B; A and B represent the standard fuzzy set and the fuzzy set to be identified respectively; n represents the total number of elements in the fuzzy set; x c represents the cth element in the fuzzy set; ∧ represents the infimum of two elements; ∨ represents the supremum of two elements.

[0033] Compared with the prior art, the present invention is beneficial in that:

[0034] (1) This method uses the mathematical method of fuzzy clustering combined with fuzzy identification. First, it considers both the static parameters of geology and the dynamic parameters of production, classifies the stable production wells, and arbitrarily selects the number of categories according to production needs. Then, it classifies the types of test wells. This can better evaluate the development potential of test wells and ensure that more technology and funds are invested in high-potential test wells, thereby improving the overall rate of return. This is of great significance to the efficient development of shale gas fields.

[0035] (2) Traditional methods only consider geological factors or production factors in isolation, while the present invention combines the two. The general trend of "geology-engineering integration" helps to comprehensively evaluate the potential of gas wells and minimize risks.

[0036] (3) The traditional method divides gas wells into three categories. The present invention can arbitrarily select the number of categories according to production needs and local conditions, which is conducive to the refinement of single well productivity evaluation.

[0037] (4) The traditional classification method is hard classification, that is, it is only applicable when each data point obviously belongs to a specific category. The present invention is also applicable when the categories of the data points of the gas wells are unclear or have overlapping features.

[0038] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. DETAILED DESCRIPTION

[0039] The preferred embodiments of the present invention are described below. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0040] The shale gas well type classification method of the present invention is applied to a specific case, and the steps are as follows:

[0041] 1. For a shale gas block, a batch of static evaluation parameters of stable production wells and test wells are obtained based on geological data, including effective thickness, gas saturation, and formation pressure. Dynamic evaluation parameters are obtained based on production data, including open-flow rate, gas production per unit casing pressure drop, and peak daily gas production. The larger the effective thickness, the more organic matter and pore space can be provided, and the higher the gas production. Gas saturation refers to the proportion of gas in rock pores. The higher the gas saturation in the shale reservoir, the stronger the storage capacity of gas in the shale pores and the higher the gas production. As the formation pressure increases, the gas volume is compressed, the more free gas is stored in the same space, and the higher the gas production. The open-flow rate indicates the ideal flow rate that the gas can achieve without any flow resistance. The higher the open-flow rate, the more effectively the gas can flow to the wellbore in the underground reservoir, and the higher the gas production. The unit casing pressure drop refers to the pressure drop required to maintain a certain gas production. When the unit casing pressure drop increases, it means that a greater pressure needs to be applied to maintain the flow of gas, that is, a higher pressure drop will make the gas flow more difficult, thereby reducing the gas production. Therefore, when other conditions are the same, the higher the gas production per unit casing pressure drop, the lower the gas production. A high peak daily gas production indicates that the gas well has a strong production capacity in the early stage of exploitation and can contribute more gas production in a shorter time. Therefore, the total gas production of a gas well with a higher peak daily gas production is often higher. Therefore, in the present invention, the effective thickness, gas saturation, formation pressure, unimpeded flow, gas production per unit casing pressure drop, and peak daily gas production are selected as evaluation parameters to well reflect the production capacity of a single well. In this embodiment, 15 stable production wells and 10 test production wells are selected. The original data of the evaluation parameters of all stable production wells are shown in Table 1, and the original data of the evaluation parameters of all test production wells are shown in Table 2.

[0042] Table 1 Original data of evaluation parameters of stable production wells

[0043]

[0044]

[0045] Table 2 Original data of evaluation parameters of test wells

[0046]

[0047] Second, standardize the data of the original evaluation parameters to eliminate the influence of the dimension. The formula used for standardization is:

[0048]

[0049] Where: Zx ij After standardization, it is the value of the i-th row and j-th column, xij is the parameter observation value of the i-th row and j-th column before standardization; max[x ij ] is the maximum value in the original data; min[x ij ] is the minimum value in the original data.

[0050] The standardized evaluation parameters of stable production wells and test production wells are shown in Tables 3 and 4, respectively.

[0051] Table 3 Standardized evaluation parameters for stable production wells

[0052]

[0053]

[0054] Table 4 Standardized evaluation parameters of test wells

[0055]

[0056] 3. Calculate the distance coefficient d between every two stable production wells based on the standardized data of stable production wells in Table 3 ij , the distance coefficient is calculated as follows:

[0057]

[0058] Where: x ik is the parameter of the i-th row and k-th column in the standardized data, x jk is the parameter of the jth column and kth row in the standardized data, m is the number of single wells, and k represents the kth row of the matrix.

[0059] The calculated distance coefficient d between every two stable production wells ij See Table 5.

[0060] Table 5 Distance coefficient between every two stable production wells

[0061]

[0062] 4. For any two gas wells, the smaller the distance coefficient between them, the stronger the correlation. Based on this principle, all stable production wells are merged and classified. The specific steps of merging and classification are as follows:

[0063] (1) Before the merger, it was divided into 15 categories, with each well being a separate category;

[0064] (2) First merge, find the minimum value d of the distance coefficient other than 0 13，9 =0.017, now it is divided into 14 categories, A13 and A9 are combined into 1 category, and each of the remaining wells is a separate category, and 13 rows and 13 columns are crossed out.

[0065] (3) Second merge, find the minimum value d among the remaining data except 0 5，3 =0.027, now it is divided into 13 categories, A13 and A9 are combined into 1 category, A5 and A3 are combined into 1 category, and each of the remaining wells is a separate category, with 5 columns and 5 rows crossed out.

[0066] (4) The third merge: find the minimum value d among the remaining data except 0 15，7 =0.031, now it is divided into 12 categories, A13 and A9 are combined into 1 category, A5 and A3 are combined into 1 category, A15 and A7 are combined into 1 category, and each of the remaining wells is a separate category, and 15 rows and 15 columns are crossed out.

[0067] (5) The fourth merge: find the minimum value d among the remaining data except 0 8，9 =0.033, now it is divided into 11 categories, A13, A9 and A8 are combined into 1 category, A5 and A3 are combined into 1 category, A15 and A7 are combined into 1 category, and each of the remaining wells is a separate category, and 9 rows and 9 columns are crossed out.

[0068] (6) The fifth merge: find the minimum value d among the remaining data except 0 14，4 =0.037, now it is divided into 10 categories, A13, A9, A8 are combined into 1 category, A5 and A3 are combined into 1 category, A15 and A7 are combined into 1 category, A14 and A4 are combined into 1 category, and each of the remaining wells is a separate category, and 14 rows and 14 columns are crossed out.

[0069] (7) The sixth merge: find the minimum value d among the remaining data except 0 3，7 =0.044, now it is divided into 9 categories, A13, A9, A8 are combined into 1 category, A5, A3, A15, A7 are combined into 1 category, A14 and A4 are combined into 1 category, and each of the remaining wells is a separate category, and 7 rows and 7 columns are crossed out.

[0070] (8) The seventh merge: find the minimum value d among the remaining data except 0 11，3 =0.060, now it is divided into 8 categories, A13, A9, A8 are combined into 1 category, A5, A3, A15, A7, A11 are combined into 1 category, A14 and A4 are combined into 1 category, and each of the remaining wells is a separate category, and 11 rows and 11 columns are crossed out.

[0071] (9) The eighth merge: find the minimum value d among the remaining data except 0 8，1 =0.065, now it is divided into 7 categories, A13, A9, A8, A1 are combined into 1 category, A5, A3, A15, A7, A11 are combined into 1 category, A14 and A4 are combined into 1 category, and each of the remaining wells is a separate category, and 8 rows and 8 columns are crossed out.

[0072] (10) The ninth merge: find the minimum value d among the remaining data except 012，4 =0.068, now it is divided into 6 categories, A13, A9, A8, A1 are combined into 1 category, A5, A3, A15, A7, A11 are combined into 1 category, A14, A4, A12 are combined into 1 category, and each of the remaining wells is a separate category, and 12 rows and 12 columns are crossed out.

[0073] (11) For the 10th merge, find the minimum value d among the remaining data except 0 2，6 =0.087, now it is divided into 5 categories, A13, A9, A8, A1 are combined into 1 category, A5, A3, A15, A7, A11 are combined into 1 category, A14, A4, A12 are combined into 1 category, A2 and A6 are combined into 1 category, A10 is a separate category, and 6 rows and 6 columns are crossed out.

[0074] (12) The 11th merge, find the minimum value d among the remaining data except 0 10，2 =0.100, now it is divided into 4 categories, A13, A9, A8, A1 are combined into 1 category, A5, A3, A15, A7, A11 are combined into 1 category, A14, A4, A12 are combined into 1 category, A2, A6, A10 are combined into 1 category, and 10 rows and 10 columns are crossed out.

[0075] (13) The 12th merge, find the minimum value d in the remaining data except 0 4，3 =0.135, now it is divided into 3 categories, A13, A9, A8, A1 are combined into 1 category, A5, A3, A15, A7, A11, A4, A14, A12 are combined into 1 category, A2, A6, A10 are combined into 1 category, and 4 rows and 4 columns are crossed out.

[0076] (14) The 13th merge, find the minimum value d among the remaining data except 0 3，1 =0.159, now it is divided into 2 categories, A13, A9, A8, A1, A5, A3, A15, A7, A11, A4, A14, A12 are combined into 1 category, A2, A6, A10 are combined into 1 category, and 3 rows and 3 columns are crossed out.

[0077] (15) The 14th merge, find the minimum value d among the remaining data except 0 2，1 =0.245, at this time all wells are classified as category 1.

[0078] In this example, there are 15 gas wells in total, which can be classified into 15 categories at most and at least 1 category, as shown in Table 6. The same numbers in the table indicate the same category under the classification scheme.

[0079] Table 6 Division scheme

[0080]

[0081] In this example, the selection can be divided into 1 to 15 categories. In actual applications, the number of classification types can be determined according to production needs. ij To determine the classification category. ij When ≤0.100, it indicates that the correlation between the two samples is very strong and they can be classified into the same category. ij The number of categories corresponding to the maximum value among ≤0.100 is taken as the final number of categories selected.

[0082] In this embodiment, the distance coefficient d during the eleventh merging 10，2 =0.100 satisfies the above conditions. At this time, A13, A9, A8, and A1 are combined into the first category, A5, A3, A15, A7, and A11 are combined into the second category, A14, A4, and A12 are combined into the third category, and A2, A6, and A10 are combined into the fourth category, for a total of 4 categories.

[0083] 5. After determining the number of stable production well types, establish the comprehensive evaluation parameter S of shale gas wells based on the standardized data, and take the average value of the comprehensive evaluation parameter S of all gas wells of the same type, and sort them from large to small according to the average value. The calculation formula of the comprehensive evaluation parameter is as follows:

[0084] S = standardized effective thickness + standardized gas saturation + standardized formation pressure + standardized open flow rate - standardized gas production per unit casing pressure drop + standardized peak daily gas production.

[0085] According to the calculation formula of comprehensive evaluation parameters, the average value of comprehensive evaluation parameters of the first type of gas wells is S1 = 0.718, the average value of comprehensive evaluation parameters of the second type of gas wells is S2 = 0.468, the average value of comprehensive evaluation parameters of the third type of gas wells is S3 = 0.367, and the average value of comprehensive evaluation parameters of the fourth type of gas wells is S4 = 1.086. Because S4>S1>S2>S3, A2, A6, and A10 wells are the best and are classified as Class I gas wells, A13, A9, A8, and A1 wells are relatively good and are classified as Class II gas wells, A5, A3, A15, A7, and A11 wells are relatively poor and are classified as Class III gas wells, and A14, A4, and A12 wells are the worst and are classified as Class IV gas wells.

[0086] 6. Based on the original data of each well that has been classified, the standardized parameters of each type of well are averaged to construct the standard fuzzy set A. The standardized evaluation parameters of all test wells are used in the same way to construct the fuzzy set B to be identified.

[0087] In this embodiment, the standard fuzzy set established by the stable production well is as follows:

[0088] Standard fuzzy set A1 of type I gas well:

[0089] A1=(0.056, 0.070, 0.120, 0.936, 0.112, 0.016);

[0090] Standard fuzzy set A2 for type II gas wells:

[0091] A2=(0.034, 0.048, 0.094, 0.791, 0.261, 0.012);

[0092] Standard fuzzy set A3 for Class III gas wells:

[0093] A3=(0.015, 0.025, 0.069, 0.719, 0.367, 0.007);

[0094] Standard fuzzy set A4 for type IV gas wells:

[0095] A4=(0.042, 0.037, 0.079, 0.675, 0.467, 0.002).

[0096] The fuzzy sets to be identified established by the test well are as follows:

[0097] Well B1: B1 = (0.038, 0.050, 0.063, 0.688, 0.459, 0.005);

[0098] Well B2: B2 = (0.030, 0.018, 0.071, 1.000, 0.168, 0.017);

[0099] Well B3: B3=(0.059, 0.057, 0.103, 0.844, 0.345, 0.023);

[0100] Well B4: B4 = (0.036, 0.008, 0.082, 0.782, 0.283, 0.016);

[0101] Well B5: B5 = (0.007, 0.025, 0.090, 0.802, 0.304, 0.009);

[0102] Well B6: B6 = (0.016, 0.059, 0.106, 0.854, 0.418, 0.000);

[0103] Well B7: B7 = (0.027, 0.037, 0.071, 0.938, 0.428, 0.007);

[0104] Well B8: B8 = (0.022, 0.028, 0.078, 0.886, 0.231, 0.012);

[0105] Well B9: B9=(0.045, 0.052, 0.089, 0.813, 0.356, 0.010);

[0106] Well B10: B 10 =(0.040, 0.036, 0.065, 0.979, 0.418, 0.005).

[0107] 7. Calculate the closeness between each fuzzy set to be identified and each standard fuzzy set. The formula for calculating the closeness is as follows:

[0108]

[0109] Where: σ(A,B) represents the closeness between A and B; A and B represent the standard fuzzy set and the fuzzy set to be identified respectively; n represents the total number of elements in the fuzzy set; x c represents the cth element in the fuzzy set; ∧ represents the infimum of two elements; ∨ represents the supremum of two elements.

[0110] The calculated closeness is shown in Table 7. According to the principle of selecting the closest, the larger the closeness, the more similar the standard fuzzy set is to the fuzzy set to be identified. In this case, the test well to be identified is classified into the stable production well category with the largest closeness.

[0111] Table 7 The closeness σ between the fuzzy set to be identified and the standard fuzzy set

[0112] <![CDATA[B1]]> <![CDATA[B2]]> <![CDATA[B3]]> <![CDATA[B4]]> <![CDATA[B5]]> <![CDATA[B6]]> <![CDATA[B7]]> <![CDATA[B8]]> <![CDATA[B9]]> <![CDATA[B 10 ]]> <![CDATA[A1]]> 0.577 0.826 0.765 0.915 0.697 0.710 0.731 0.796 0.550 0.720 <![CDATA[A2]]> 0.761 0.749 0.867 0.746 0.916 0.817 0.769 0.870 0.735 0.750 <![CDATA[A3]]> 0.868 0.660 0.812 0.608 0.863 0.818 0.797 0.765 0.888 0.773 <![CDATA[A4]]> 0.963 0.587 0.759 0.571 0.753 0.800 0.789 0.680 0.935 0.768 Gas well type Ⅳ Ⅰ Ⅱ Ⅰ Ⅱ Ⅲ Ⅲ Ⅱ Ⅳ Ⅲ

[0113] It can be seen from Table 7 that among the test wells B1 to B10, B2 and B4 belong to Class I gas wells, B3, B5, and B8 belong to Class II gas wells, B6, B7, and B10 belong to Class III gas wells, and B1 and B9 belong to Class IV gas wells.

[0114] The above description is only a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as a preferred embodiment as above, it is not intended to limit the present invention. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A method for classifying shale gas well types, characterized in that: The following steps are involved: S1. Obtaining the original data of evaluation parameters of multiple stable production wells and test production wells; The evaluation parameters include six parameters: effective thickness, gas saturation, formation pressure, open flow, gas production per unit casing pressure drop and peak daily gas production; S2, standardizing the raw data of the evaluation parameters; S3. Calculate the distance coefficient d between every two stable production wells based on the standardized data of the stable production wells. ij , the calculation formula is as follows: Where: x ik is the parameter of the i-th row and k-th column in the standardized data, x jk is the parameter of the jth column and the kth row in the standardized data, and m is the number of single wells; S4. Classify all stable production wells according to the principle that the smaller the distance coefficient between two wells, the stronger the correlation; the method is as follows: S41, sorting all distance coefficients except 0 in ascending order, merging the two gas wells corresponding to the smallest distance coefficient ranked first into one category to form a new individual, and the new individual continues to participate in subsequent merging and classification together with other gas wells; S42, merging the two gas wells corresponding to the distance coefficient ranked second into one category to form a new individual; The new individual will continue to participate in the subsequent merger classification together with other gas wells; S43, according to the above method, the distance coefficient ranked third is used for merging and classification, and this cycle is repeated until all gas wells are classified into the number q of types required for production, and the classification is stopped to obtain q different types of gas wells; where 1≤q≤m, q and m are positive integers, and m is the number of single wells; S5. After determining the number of stable production wells, calculate the comprehensive evaluation parameter S according to the standardized data. The comprehensive evaluation parameter S is equal to the sum of the six standardized evaluation parameter values. Then take the average value of the comprehensive evaluation parameter S of all gas wells of the same type. According to the order of the average value from large to small, name each type in turn as Class I gas well, Class II gas well, Class III gas well, ... Class Q gas well; S6. Take the average value of the standardized parameters of each type of gas wells in stable production wells to construct a standard fuzzy set A, and obtain standard fuzzy sets A1, A2, A3, ...A q ; A = (average effective thickness, average gas saturation, average density and formation pressure, average open flow rate, average gas production per unit casing pressure drop, peak daily gas production) According to the same method, the fuzzy set B to be identified is constructed for all the test wells, and the fuzzy sets to be identified are B1, B2, B3, ... B n , n is the number of test wells; S7, calculating the closeness between each fuzzy set to be identified and each standard fuzzy set, the greater the closeness, the more similar the standard fuzzy set is to the fuzzy set to be identified, and the test production well to be identified is classified into the stable production well category with the largest closeness; The formula for calculating closeness is as follows: Where: σ(A,B) represents the closeness between A and B; A and B represent the standard fuzzy set and the fuzzy set to be identified respectively; n represents the total number of elements in the fuzzy set; x c represents the cth element in the fuzzy set; ∧ represents the infimum of two elements; ∨ represents the supremum of two elements.

2. The method for classifying shale gas well types according to claim 1, characterized in that: In step S4, each time the merge classification is performed, the corresponding distance coefficient d ij , merge the gas wells corresponding to the i-th row and the gas wells corresponding to the j-th column into the same category, and remove the row and column corresponding to the larger number in i and j; then repeat the subsequent merging and classification operations on the remaining data.

3. The method for classifying shale gas well types according to claim 1, characterized in that: In step S1, original data of three parameters, namely effective thickness, gas saturation and formation pressure, are obtained based on geological data; original data of three parameters, namely open flow rate, gas production per unit casing pressure drop and peak daily gas production, are obtained based on production data.

4. The method for classifying shale gas well types according to claim 3, characterized in that: In step S1, original data of evaluation parameters of at least 10 stable production wells are obtained.

5. The method for classifying shale gas well types according to claim 1, characterized in that: In step S2, the formula for standardization is as follows: Where: Zx ij is the value of the i-th row and j-th column after standardization, x ij is the parameter value of the i-th row and j-th column before standardization; max[x ij ] is the maximum value in the original data; min[x ij ] is the minimum value in the original data.

6. The method for classifying shale gas well types according to claim 1, characterized in that: Step S43: The condition for stopping classification is: until the distance coefficient reaches d ij When the maximum value is ≤0.100, the classification is stopped and q different types of gas wells are obtained.

Images