PDC tooth performance adjusting method and system, computer readable storage medium and PDC tooth

Abstract

The invention relates to the field of oil and gas field exploration and development, and discloses a PDC tooth performance adjusting method which comprises the following steps that training data are obtained, and the training data comprise stratum data, a PDC tooth failure form and an arrangement and combination mode of blocks on a diamond layer; a mapping relation model of input parameters and output parameters is constructed based on the training data, the input parameters comprise the stratum data, and the output parameters comprise permutation and combination modes of blocks on the diamond layer; training and optimizing the mapping relation model; and obtaining the permutation and combination mode of the blocks on the diamond layer with the optimal comprehensive performance of the PDC teeth based on the mapping relation model. According to the PDC tooth performance adjustment method and system and the computer readable storage medium, a more accurate, more convenient and more efficient scheme is provided for PDC tooth performance adjustment. In addition, the invention also relates to a PDC tooth.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas field exploration and development, and in particular, to a PDC tooth performance adjustment method, system and computer-readable storage medium. Further, the present invention also relates to a PDC tooth. Background Art

[0002] PDC (polycrystalline diamond composite) teeth are often welded and fixed to the base of the drill bit as the main cutting element of the PDC drill bit due to its excellent wear resistance and impact resistance. They can perform well in soft to medium-hard formations, but with the continuous increase in drilling depth and the increase in formation complexity, their practicality may be limited, especially when encountering extremely hard or extremely soft formations, the service life of the PDC drill bit will be greatly affected. In heterogeneous formations, such as sandstone mixed with mudstone layers, carbonate rock layers, or rock fracture development areas, PDC teeth are prone to impact failure when drilling due to the huge difference and sudden change in formation hardness. This failure not only causes damage to the drill bit and requires shutdown and replacement, thus affecting the drilling progress, but also increases the cost of equipment use and operating time, reducing drilling efficiency and economy.

[0003] In order to increase the service life of PDC drill bits and improve the wear resistance and impact resistance of PDC teeth, the prior art often starts with the preparation method of PDC teeth, and adjusts the wear resistance and impact resistance of PDC teeth by changing the particle size and ratio of diamond powder. This adjustment method requires a large number of experiments to determine the influence of different particle size ratios on the wear resistance and impact resistance of PDC teeth, and the research and development cycle is long.

[0004] Therefore, a new method for adjusting the wear resistance and impact resistance of PDC teeth is urgently needed to improve the research and development efficiency of PDC teeth and reduce production costs. Summary of the invention

[0005] The purpose of the present invention is to provide a PDC tooth performance adjustment method, which can use the formation data of the mine range to obtain the PDC tooth with the best comprehensive performance for the mine, and provide a more accurate and convenient solution for the performance adjustment of the PDC tooth.

[0006] In order to achieve the above-mentioned purpose, the first aspect of the present invention provides a method for adjusting the performance of a PDC tooth, the method comprising the following steps: obtaining training data, the training data including formation data, failure forms of the PDC tooth and the arrangement and combination of each block on the diamond layer; constructing a mapping relationship model between input parameters and output parameters based on the training data, the input parameters including the formation data, and the output parameters including the arrangement and combination of each block on the diamond layer; training and optimizing the mapping relationship model based on the failure forms of the PDC tooth; and obtaining the arrangement and combination of each block on the diamond layer with the best comprehensive performance of the PDC tooth based on the mapping relationship model.

[0007] Optionally, the formation data includes rock type, hardness and heterogeneity.

[0008] Optionally, the PDC tooth failure modes include wear failure and impact failure.

[0009] Optionally, the wear failure judgment index includes wear amount, wear area and wear rate, and the impact failure judgment index includes crack length, fracture area and impact force threshold.

[0010] Optionally, the PDC tooth performance adjustment method further includes preprocessing the training data.

[0011] Optionally, the preprocessing includes: encoding the formation data; quantifying and normalizing the failure form of the PDC teeth; and matrixing the arrangement and combination of each block on the diamond layer.

[0012] Optionally, the training and optimizing the mapping relationship model includes: constructing a loss function reflecting the comprehensive performance of the PDC tooth based on the PDC tooth wear amount, wear area, wear rate, crack length, fracture area and impact force threshold.

[0013] A second aspect of the present invention provides a PDC tooth performance adjustment system, which includes a data acquisition module for acquiring training data, wherein the training data includes formation data, PDC tooth failure forms, and arrangement and combination modes of each block on the diamond layer; a model construction module for constructing a mapping relationship model between input parameters and output parameters, wherein the input parameters include the formation data, and the output parameters include the arrangement and combination modes of each block on the diamond layer; a model training module for training and optimizing the mapping relationship model; and a model application module for obtaining the arrangement and combination modes of each block on the diamond layer with the best comprehensive performance of the PDC tooth.

[0014] Optionally, the PDC tooth performance adjustment system further includes a data processing module for preprocessing the collected training data.

[0015] Optionally, a third aspect of the present invention provides a computer-readable storage medium storing instructions, wherein the instructions are executed by a computer to cause the computer to perform multiple functions, including the following functions: obtaining training data, the training data including formation data, PDC tooth failure forms, and arrangement and combination of blocks on the diamond layer; constructing a mapping relationship model between input parameters and output parameters based on the training data, the input parameters including the formation data, and the output parameters including the arrangement and combination of blocks on the diamond layer; training and optimizing the mapping relationship model based on the PDC tooth failure form; and obtaining the arrangement and combination of blocks on the diamond layer with the best comprehensive performance of the PDC tooth based on the mapping relationship model.

[0016] Optionally, a fourth aspect of the present invention provides a PDC tooth, comprising a diamond layer, the diamond layer comprising at least one of a first block, a second block and a third block, the first block, the second block and the third block having different wear ratios, and the first block, the second block and the third block are combined into the diamond layer based on the deep learning-based method described in any one of claims 1 to 14.

[0017] Optionally, the diamond layer is formed into a cylindrical structure, and a transition surface is formed between the outer circumferential surface and the top surface of the diamond layer.

[0018] Optionally, the PDC tooth further comprises a substrate, the diamond layer is arranged above the substrate, and the diamond layer comprises at least one layer.

[0019] Optionally, the diamond layer includes a first layer and a second layer, the first layer is arranged close to the substrate, and the second layer is arranged far from the substrate.

[0020] Through the above technical scheme, the PDC tooth performance adjustment method provided by the present invention can obtain a specific PDC with the best comprehensive performance according to different formation characteristics by establishing a mapping relationship model between formation data and the arrangement and combination of each block in the diamond layer; at the same time, it can effectively reduce the labor cost investment of the performance adjustment method starting from the PDC tooth preparation method, as well as the research and development cycle of the PDC tooth; the PDC tooth performance adjustment method realizes an efficient, accurate and convenient PDC tooth performance adjustment scheme.

[0021] Other advantages of the present invention and the technical effects of the preferred embodiments will be further described in the following specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0023] Figure 1 is a flow chart of the steps of the PDC tooth performance adjustment method of the present invention;

[0024] Figure 2 It is a schematic diagram of the structure of the PDC tooth of the present invention;

[0025] Figure 3 It is a structural schematic diagram of a first specific embodiment of a PDC tooth of the present invention;

[0026] Figure 4 is a structural schematic diagram of a second specific embodiment of a PDC tooth of the present invention;

[0027] Figure 5 It is a schematic structural diagram of a third specific implementation mode of the PDC tooth of the present invention.

[0028] Description of Reference Numerals

[0029] 1-diamond layer, 11-outer circumferential surface, 12-top surface, 13-transition surface, 14-first layer, 15-second layer, 101-first block, 102-second block, 103-third block; 2-substrate. DETAILED DESCRIPTION

[0030] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0031] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "connection" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, it can be abutment, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0032] In the description of the present invention, some directional words are involved in order to clearly illustrate the technical solution of the present invention. It should be understood that the directional terms are based on the orientation or positional relationship shown in the drawings and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be understood as a limitation on the present invention.

[0033] In addition, the terms "first", "second", and "third" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first", "second", and "third" may explicitly or implicitly include one or more of the said features.

[0034] As a basic implementation of the present invention, refer to Figure 2The present invention provides a PDC tooth, which includes a substrate 2 and a diamond layer 1 arranged on the substrate 2. The substrate 2 may include but is not limited to sintered carbides, such as tungsten carbide, titanium carbide, chromium carbide or a combination thereof sintered with iron, nickel, cobalt or their alloys. The diamond particles in the diamond layer 1 can be diffused and bonded with the substrate 2 through a high temperature and high pressure environment to form a strong composite, namely the PDC tooth. The diamond layer 1 is a composite composed of at least one of a first block 101, a second block 102 and a third block 103. The first block 101, the second block 102 and the third block 103 are made of different formulas so that the three have different wear ratios and failure energies. Exemplarily, the component of the first block 101 can be a diamond formula with a good sintering density in the prior art. The first block 101 made based on the diamond formula can have extremely high hardness and wear resistance, and is suitable for cutting high-hardness formations, but the impact resistance of the first block 101 is poor. The components of the second block 102 are sintered carbide powder or secondary sintered carbide powder added to the components of the first block 101, so that the second block 102 made based on this component has a lower hardness than the first block 101, but has a higher impact resistance. The components of the third block 103 are transition metals such as cobalt, tungsten, nickel, and iron added to the components of the second block 102, so that the third block 103 made based on this component has a lower hardness than the second block 102, but has higher impact resistance and thermal stability. Paraffin wax can be added to each block component to aggregate the powder particles in each block component so that it has a certain molding ability. Subsequently, each block component added with paraffin wax can be placed in a mold for pre-pressing to obtain the first block 101, the second block 102, and the third block 103 to be assembled. The first block 101, the second block 102 and the third block 103 can be assembled into a diamond layer 1 according to certain rules to meet the drilling requirements of different strata. After the diamond layer 1 is assembled, the excess part is cut off and trimmed into a cylindrical shape, placed in a vacuum furnace for heating, paraffin and other impurities are removed, and then placed in a six-sided top press for high temperature and high pressure sintering to obtain a diamond layer 1, wherein the high temperature and high pressure sintering conditions are a temperature of 1400-1600°C, a pressure of 5.5-8GPa, and a sintering time of 20 minutes. In the above embodiment, the shapes of the first block 101, the second block 102 and the third block 103 can be cubes, cuboids, tetrahedrons, and other shapes that can achieve close packing. In the above embodiments, the amount of paraffin wax present in each block component mixture is 1-5wt%, the amount of sintered cemented carbide or secondary sintered cemented carbide present in the corresponding block component mixture is 10-80wt%, and the amount of transition metal elements such as cobalt, tungsten, nickel, and iron present in the corresponding block component mixture is 5-20wt%.

[0035] The first block 101, the second block 102 and the third block 103 described in the above embodiment can be assembled into a diamond layer 1 according to certain rules. The assembly rules can be determined by collecting drilling data of other wells in the formation and data of each PDC tooth on the drill bit, and by relying on experience to determine the arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1 of the PDC tooth. For example, if the PDC tooth of the previous well fails due to wear, the occupation amount of the first block 101 on the diamond layer 1 can be appropriately increased, and the occupation amount of the first block 101 on the diamond layer 1 can be 70-100%, so as to improve the effective cutting distance and wear resistance of the PDC tooth; if the PDC tooth of the previous well fails due to impact, the occupation amount of the first block 101 on the diamond layer 1 can be appropriately reduced, and the occupation amount of the second block 102 and the third block 103 on the diamond layer 1 can be increased, and the occupation amount of the first block 101 on the diamond layer 1 can be 0-50%, so as to improve the impact resistance of the PDC tooth; The arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1 can be adjusted according to the characteristics of the formation. For example, when the formation is highly abrasive, the occupation amount of the first block 101 on the diamond layer 1 can be increased appropriately, and the occupation amount of the first block 101 on the diamond layer 1 can be 70-100%. When the formation is a gravel layer or an inhomogeneous formation, the occupation amount of the first block 101 on the diamond layer 1 can be reduced appropriately, and the occupation amounts of the second block 102 and the third block 103 on the diamond layer 1 can be increased. The occupation amount of the first block 101 on the diamond layer 1 can be 0-50%. The above-mentioned arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1 determined by experience may be blind, so that the use effect of the PDC tooth in actual drilling is far from the expected goal. In order to obtain a PDC tooth with better comprehensive performance, the present invention also provides a PDC tooth performance adjustment method to automatically obtain the arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1 according to the formation characteristics. The specific PDC tooth performance adjustment method will be explained below and will not be elaborated here.

[0036] In some embodiments, the diamond layer 1 is composed of at least one of the first block 101, the second block 102 and the third block 103 to form a cylindrical structure, and a transition surface 13 is formed between the outer circumferential surface 11 and the top surface 12 of the cylindrical diamond layer 1. The transition surface 13 can be machined after the diamond layer 1 is formed and sintered, or the transition surface 13 can be pre-trimmed in the step of trimming the diamond layer 1 assembled by the first block 101, the second block 102 and the third block 103 into a cylindrical shape. The setting of the transition surface 13 can optimize the cutting performance of the PDC tooth, reduce the resistance in the cutting process, and improve the drilling efficiency. In addition, it can also reduce the cracking phenomenon of the PDC tooth during the drilling process, enhance the impact toughness of the PDC tooth, and help to extend the service life of the PDC tooth. The transition surface 13 in the above embodiment can be a smooth curved surface to reduce the friction resistance and vibration during the drilling process; the transition surface 13 can also be an inclined surface with a certain angle, which can show better rock breaking performance in certain specific formations. The angle between the transition surface 13 and the top surface 12 and the outer circumferential surface 11 and the setting height of the transition surface 13 on the diamond layer 1 can be determined according to specific formation characteristics and drill bit design requirements to meet the requirements for different performances of PDC teeth.

[0037] In some embodiments, at least one of the first block 101, the second block 102 and the third block 103 can form a diamond layer 1 having one or more layers. The first block 101, the second block 102 and the third block 103 can have the same shape and size parameters before being assembled and trimmed into the shape of the diamond layer 1, and the size parameters can be adjusted according to actual use requirements. Here, as a preferred embodiment, the first block 101, the second block 102 and the third block 103 can be a cubic block with a side length of 1mm, and each block is stacked with each other to form a diamond layer 1 with two layers, and the thickness of the diamond layer 1 is 2mm. In this embodiment, the diamond layer 1 includes a first layer 14 and a second layer 15, the first layer 14 is arranged close to the substrate 2, and the second layer 15 is arranged away from the substrate 2. The first layer 14 and the second layer 15 can be composed of the same block or different blocks. Exemplarily, the first layer 14 may be entirely composed of the third block 103, and the second layer 15 may be determined by experience through the drilling data of other wells in the mine and the failure form of the corresponding drill bit PDC teeth, and the arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1. The second layer 15 may also determine the arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1 according to the PDC tooth performance adjustment method provided by the present invention. The components of the third block 103 include a diamond formula with a good sintering density in the prior art, a sintered cemented carbide powder or a secondary sintered cemented carbide powder, and a transition metal powder of at least one of cobalt, tungsten, nickel, iron, etc. The third block 103 is added with a transition metal powder of at least one of cobalt, tungsten, nickel, etc., so as to improve the interface bonding strength between the diamond layer 1 and the substrate 2 and improve the overall performance of the PDC teeth. Therefore, the first layer 14 is preferably entirely composed of the third block 103. In addition, the first layer 14 may also be composed of the third block 103 in the middle region.

[0038] The PDC tooth of the present invention comprises a matrix 2 and a diamond layer 1, wherein the diamond layer 1 is composed of at least one of a plurality of first blocks 101, a second block 102 and a third block 103, and each block can determine the arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1 by experience through the drilling data of other wells within the mine and the failure form of the drill bit PDC teeth collected, and can also be determined by the PDC tooth performance adjustment method provided by the present invention, thereby obtaining a PDC tooth tailored to the formation characteristics, and the PDC tooth has excellent comprehensive performance in the formation, reduces the failure of the PDC tooth, can improve the service life of the PDC tooth, and is beneficial to the stability, safety and economy of the drilling operation.

[0039] Relatively preferred specific embodiments of the PDC teeth in the present invention will be provided below.

[0040] As a first relatively preferred specific embodiment, refer to Figure 3 The PDC tooth includes a matrix 2 and a diamond layer 1, wherein the diamond layer 1 includes a first layer 14 and a second layer 15, and the first layer 14 and the second layer 15 are both composed of a first block 101. The components of the first block 101 may include a diamond formula with a good sintering density in the prior art.

[0041] As a second relatively preferred specific embodiment, refer to Figure 4 The PDC tooth includes a substrate 2 and a diamond layer 1. The diamond layer 1 includes a first layer 14 and a second layer 15. The first layer 14 is composed of a third block 103. The third block 103 is combined into the central area of ​​the second layer 15 and extends to the four corners of the second layer 15 in a cross shape, dividing the second layer 15 into four areas. The first block 101 is arranged at the four edge positions of the four areas. The second block 102 is arranged around the first block 101, and the third block 103 is arranged around the second block 102. When one edge of the PDC tooth fails, it is not easy to penetrate the entire diamond layer 1, reducing the overall failure probability. At the same time, the PDC tooth can be rotated and reused, extending the service life of the PDC tooth.

[0042] As a third relatively preferred specific embodiment, see Figure 5 The PDC tooth includes a base 2 and a diamond layer 1, the diamond layer 1 includes a first layer 14 and a second layer 15, the first layer 14 is composed of a third block 103, a first block 101 is arranged at one edge position of the four edge positions of the second layer 15, a second block 102 is arranged at two edge positions, and a third block 103 is arranged at one edge position and the central area of ​​the second layer 15.

[0043] The wear resistance and impact resistance of the above three relatively preferred PDC teeth were tested, and the test results shown in Table 1 were obtained.

[0044]

[0045]

[0046] As can be seen from the above table, the PDC teeth of the first specific embodiment have higher wear resistance, but poor impact resistance, the PDC teeth of the second specific embodiment have higher wear resistance and higher impact resistance relative to the first specific embodiment, and the PDC teeth of the third specific embodiment have different wear resistance and impact resistance at different parts, and the required parts can be leaked out as working parts according to the characteristics of the target formation, so that one PDC tooth has multiple characteristic performances. Based on the PDC teeth of the above embodiments, users can select PDC teeth with different performances according to the formation characteristics and actual application scenarios. As another embodiment of the present invention, the present invention can also achieve more refined performance adjustment by adjusting the proportions of the formulas of the components in the first block 101, the second block 102 and the third block 103.

[0047] refer to Figure 1 The present invention provides a method for adjusting the performance of a PDC tooth, the method comprising the following steps: obtaining training data and preprocessing the training data; constructing a mapping relationship model between input parameters and output parameters based on the training data; training and optimizing the mapping relationship model; and obtaining an arrangement and combination mode of each block on the diamond layer 1 with the best comprehensive performance of the PDC tooth based on the mapping relationship model.

[0048] The above training data include formation data, PDC tooth failure forms, and the arrangement and combination of each block on the diamond layer 1, and may also include drilling parameters such as drilling pressure, rotation speed, mud flow, etc. Specifically, the formation data include rock type, hardness, rock blockiness, rock layer thickness, rock layer inclination, rock tensile strength, etc. PDC tooth failure forms include wear failure and impact failure, wherein the judgment indicators of wear failure include PDC tooth wear amount, wear height, wear volume, wear area, wear rate, etc., and the judgment indicators of impact failure include crack length, fragmentation area, impact force threshold, etc. The training data can be obtained by collecting drilling data and related test data from various mines.

[0049] The above steps of preprocessing the training data include cleaning the collected training data to remove outliers and missing values; standardizing or normalizing the training data to ensure the consistency of input parameters; and applying data dimensionality reduction methods to extract the main characteristic parameters of formation data and PDC tooth failure judgment index data. Data dimensionality reduction methods include but are not limited to principal component analysis, entropy weight method, etc.

[0050] Specifically, the process of preprocessing the stratigraphic data includes encoding the stratigraphic data, which includes rock type, hardness (such as RQD value, Mohs hardness, etc.), rock layer thickness, rock layer density, heterogeneity (such as core block, bedding characteristics, etc.). Different types of rocks can be coded according to the rock classification standard. For example, "1" can represent sedimentary rock, "2" can represent igneous rock, and "3" can represent metamorphic rock; according to the heterogeneity such as core block, bedding characteristics, etc., a hierarchical coding method can be used to represent it. For example, the core block can be divided into long columnar, short columnar, blocky, etc., and different codes are assigned to each. The rock hardness value can be converted into a coding form. For continuous variables such as RQD values, a segmented coding method is used to divide the hardness value into different intervals, and a code is assigned to each interval. For discrete variables such as Mohs hardness, its value can be directly used as the code. The stratigraphic data after the above coding is completed can be stored in the database for subsequent model construction and training. In addition, the formation data can also be the rock mass quality classification index of the entire borehole length and the basic information of the borehole. The acquisition of the data may include the following steps: obtaining the basic information of the borehole (such as the borehole number, location, depth, etc.) and the core image information; setting the minimum measurement range, dividing the entire borehole length range into multiple minimum measurement ranges; calculating the rock mass quality classification index within each minimum measurement range, and establishing a rock mass quality classification index database for the borehole; scoring and summing all rock mass quality classification indicators within each minimum measurement range based on the RMR rock mass quality classification standard, and obtaining all rock mass quality evaluation results within each minimum measurement range. When the above-mentioned formation data is preprocessed, the rock mass quality evaluation result can be converted into a digital code. For example, "1 to 5" represents the rock mass quality evaluation result "Ⅰ to Ⅴ". In the above example, the rock mass quality classification index includes the intact rock strength index, the rock quality RQD index, the rock mass joint spacing index, the rock mass joint state index, and the groundwater state index.

[0051] The failure forms of PDC teeth mainly include wear failure and impact failure. The main judgment indicators of wear failure are wear amount, wear area and wear rate. The wear amount can be obtained by measuring the mass or volume of the PDC teeth before and after use using a precision balance or three-dimensional scanning technology, such as the mass reduction and volume change of the diamond layer 1; the wear area can be quantified by recording the wear marks on the surface of the PDC teeth using a laser scanner or microscope, and extracting the contour of the wear area from it by calculating the area of ​​the wear area on the diamond layer 1 of the PDC teeth; the wear rate can be calculated by calculating the change in wear amount per unit time or by comparing the wear amount at different time points. The main judgment indicators of impact failure are crack length, fragmentation area and impact force threshold. Among them, the crack length can be measured by high-precision measuring tools on the cracks on the PDC teeth, and the fragmentation area can be determined by visual inspection or high-precision measuring tools. The area caused by fragmentation on the PDC teeth can be accurately measured using image processing software or area measuring instruments. The impact force threshold usually refers to the impact force that causes cracks, fragmentation or significant performance degradation of the PDC teeth. This data size can be directly obtained from the factory data of the PDC teeth. Since the quantitative index units of wear failure and impact failure are different, the two types of data can be normalized.

[0052] The normalized processing formula for wear volume is:

[0053]

[0054] in, represents the normalized wear amount, w represents the original wear amount, and w min Describes the minimum value in the original wear volume data set, w max Represents the maximum value in the original wear volume data set.

[0055] The normalized processing formula for the wear area is:

[0056]

[0057] in, represents the normalized wear amount, S represents the original wear amount, and S min Describes the minimum value in the original wear volume data set, S max Represents the maximum value in the original wear volume data set.

[0058] The processing formula for normalizing the wear rate is:

[0059]

[0060] Where v represents the wear rate, W represents the total wear amount, and T represents the usage time. represents the normalized wear rate, v bIndicates the wear rate of the PDC tooth under standard working conditions.

[0061] The normalization of crack length, fracture area and impact force threshold is similar to the normalization processing method of wear amount and wear area mentioned above, which will not be elaborated here.

[0062] In addition, the original parameter variables such as PDC tooth wear, wear area, wear rate, crack length, fracture area and impact force threshold can be standardized to obtain the standardized matrix data X * , the main calculation steps of the standardization process are:

[0063]

[0064] Where μ is the mean value corresponding to each original parameter variable, and σ is the standard deviation corresponding to each original parameter variable. Through the above calculation, each original parameter variable can be standardized so that the mean value of each original parameter variable is 0 and the standard deviation is 1.

[0065] The steps of arranging and combining the blocks on the matrix diamond layer 1 mainly include:

[0066] (1) Define each block type and assign a unique identifier to each block type.

[0067] Exemplarily, the diamond layer 1 is composed of at least one of a plurality of first blocks 101 , a second block 102 and a third block 103 , and “0” represents the first block 101 , “1” represents the second block 102 , and “3” represents the third block 103 .

[0068] (2) Create a block distribution matrix

[0069] A matrix is ​​created based on the number of mesh divisions of the diamond layer 1, so that each identifier in the matrix represents the type of block at the corresponding position. Exemplarily, the diamond layer 1 is composed of m×m blocks, and an m×m matrix is ​​created:

[0070]

[0071] In this matrix, r ij Indicates the identifier corresponding to the block type in the i-th row and j-th column of diamond layer 1.

[0072] For a multi-layer diamond layer 1, illustratively, the diamond layer 1 has two layers, and the data of the two layers can be stacked and merged into an m×2m matrix. In addition, two independent m×m matrices can be maintained for processing.

[0073] The mapping relationship model constructed based on the preprocessed training data is a hybrid model of convolutional neural network combined with fully connected layer, which includes input layer, hidden layer and output layer. The preprocessed stratigraphic data mainly includes classification coding data (rock type, core block type, etc.) and normalized stratigraphic data (rock hardness, rock thickness, rock density, etc.). An embedding layer can be set in the input layer to convert the classification coding data into a dense vector of fixed size, and the classification coding embedding vector is directly connected to the middle layer of the convolutional neural network or before the input of the fully connected layer. The stratigraphic data is multidimensional data, and each normalized stratigraphic data can be used as an input channel of the convolutional neural network. The hidden layer mainly includes the convolutional neural network part and the fully connected layer part. The convolutional neural network part includes the convolutional layer to extract the spatial features of the stratigraphic data; the activation layer uses activation functions such as ReLU and Sigmoid after each convolutional layer to introduce nonlinearity; the pooling layer is set between the convolutional layers to reduce the size and calculation amount of the feature map. The fully connected layer includes feature flattening, which is set after the last convolutional layer or pooling layer of the convolutional neural network and is used to flatten the feature map into a one-dimensional vector for input to the fully connected layer; the fully connected layer is used to further extract and combine features, and concatenate the embedding vector of the classification code with the flattened feature vector; the activation layer is set after the fully connected layer and uses activation functions such as ReLU and Sigmoid. The output parameters include the arrangement and combination of the first block 101, the second block 102 and the third block 103 on the diamond layer 1, which are output as matrix data. The number of neurons in the output layer matches the number of elements in the output matrix, and the loss function L listed below can be used to optimize and adjust the model parameters.

[0074] In the step of training and optimizing the mapping relationship model between input parameters and output parameters, a loss function reflecting the comprehensive performance of the PDC tooth is constructed based on the wear amount, wear area, wear rate, crack length, fracture area and impact force threshold of the PDC tooth. The loss function can be expressed as:

[0075]

[0076] Among them, τ w , τ S , τ v , τ L , τ A , τ P They are the weights of PDC tooth wear, wear area, wear rate, crack length, fracture area and impact force threshold, and their values ​​can be adjusted according to the specific application scenario and importance of PDC teeth. represents the normalized crack length, represents the standardized fragmentation area, P represents the actual impact force, and Ps Indicates the impact force threshold.

[0077] The preprocessed training data set is divided into training set, validation set and test set. The training set data is used to train the neural network model. The weights and biases are adjusted through the back propagation algorithm. The validation set is used to evaluate the model performance and hyperparameters are tuned as needed. The test set is used to evaluate the final performance of the mapping relationship model to ensure that the model has good generalization ability.

[0078] The mapping relationship model after training can be deployed to the decision support system of mine exploration to realize real-time or regular data input and output, so as to guide the design and production of PDC teeth, monitor the actual use effect of the PDC teeth in the input mine formation, collect feedback data for further optimization of the mapping relationship model, and apply the mapping relationship model to other mines or similar application scenarios to realize the comprehensive performance optimization of PDC teeth performance based on the characteristics of mine formations.

[0079] The third aspect of the present invention provides a PDC tooth performance adjustment system, which includes a data acquisition module for collecting training data, namely, formation data, PDC tooth failure forms, and the arrangement and combination of each block on the diamond layer 1; a model construction module, which uses the selected algorithm and framework to construct a mapping relationship model between input parameters and output parameters, including defining the input layer, hidden layer and output layer of the model, and setting the parameters of the layer; a model training module, which is used to train and optimize the mapping relationship model, and specifically, the performance of the model can be evaluated using a test set, and the model is tuned according to the evaluation results. The tuning process includes adjusting the model structure, changing the learning rate, using regularization, etc. to prevent overfitting of the model; a model application module, which is used to deploy the trained mapping relationship model to an actual application scenario, and predict the new input parameters to obtain the arrangement and combination of each block on the diamond layer 1 when the comprehensive performance of the PDC tooth is optimal.

[0080] Based on the above-mentioned PDC tooth performance adjustment system, the system may also include a data processing module, which can read and clean the training data collected by the data acquisition module, remove outliers, missing values, etc., to ensure the accuracy and completeness of the training data, and can also standardize or normalize the training data, as well as extract important features of the training data, to improve the accuracy and efficiency of constructing the mapping relationship model.

[0081] A fourth aspect of the present invention provides a computer-readable storage medium storing instructions, which are used by a computer to execute multiple functions, including the following functions: obtaining training data; constructing a mapping relationship model between input parameters and output parameters based on the training data; training and optimizing the mapping relationship model; and obtaining the arrangement and combination of each block on the diamond layer 1 with the best comprehensive performance of the PDC tooth based on the mapping relationship model.

[0082] The PDC tooth performance adjustment method, system and computer-readable storage medium provided by the present invention can automatically obtain the PDC tooth with the best comprehensive performance based on the formation characteristics, so that the PDC tooth maintains efficient and stable drilling capabilities under complex and changeable formation conditions, can extend the service life of the PDC tooth, and improve the drilling operation efficiency. Compared with the prior art that achieves the performance adjustment of the PDC tooth by adjusting the preparation method of the PDC tooth, the present invention provides a more efficient, more flexible and more accurate PDC tooth performance adjustment scheme. The PDC tooth provided by the present invention is made of a plurality of stacked blocks. When a crack or delamination or edge loss or detachment occurs on one blade surface of the PDC tooth, it is not easy to penetrate the entire diamond layer 1, thereby reducing the overall failure probability and increasing the service life.

[0083] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0084] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, a variety of simple modifications can be made to the technical solution of the present invention, and these simple modifications all belong to the protection scope of the present invention.

[0085] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations. In addition, the various different embodiments of the present invention can also be combined arbitrarily, as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for adjusting the performance of a PDC tooth, characterized in that: The following steps are involved: Acquiring training data, the training data including formation data, PDC tooth failure forms, and arrangement and combination of blocks on the diamond layer (1); Constructing a mapping relationship model between input parameters and output parameters based on the training data, wherein the input parameters include the formation data, and the output parameters include the arrangement and combination of each block on the diamond layer (1); Training and optimizing the mapping relationship model based on the PDC tooth failure form; Based on the mapping relationship model, an arrangement and combination mode of each block on the diamond layer (1) with the best comprehensive performance of the PDC tooth is obtained.

2. The PDC tooth performance adjustment method according to claim 1, characterized in that: The formation data includes rock type, hardness and heterogeneity.

3. The PDC tooth performance adjustment method according to claim 1, characterized in that: The PDC tooth failure modes include wear failure and impact failure.

4. The PDC tooth performance adjustment method according to claim 3, characterized in that: The wear failure judgment index includes the wear amount, the wear area and the wear rate, and the impact failure judgment index includes the crack length, the fracture area and the impact force threshold.

5. The PDC tooth performance adjustment method according to claim 1, characterized in that: The method also includes preprocessing the training data.

6. The PDC tooth performance adjustment method according to claim 5, characterized in that: The pre-processing comprises: encoding the formation data; Quantifying and normalizing the PDC tooth failure mode; The arrangement and combination of the blocks on the diamond layer (1) is matrixed.

7. The PDC tooth performance adjustment method according to claim 6, characterized in that: The training and optimization of the mapping relationship model based on the PDC tooth failure form includes: A loss function reflecting the comprehensive performance of the PDC tooth is constructed based on the PDC tooth wear amount, wear area, wear rate, crack length, fracture area and impact force threshold.

8. A PDC tooth performance adjustment system, characterized in that: include: A data acquisition module, used for acquiring training data, wherein the training data includes formation data, failure forms of PDC teeth, and arrangement and combination modes of blocks on the diamond layer (1); A model building module, used to build a mapping relationship model between input parameters and output parameters, wherein the input parameters include the formation data, and the output parameters include the arrangement and combination of each block on the diamond layer (1); A model training module, used for training and optimizing the mapping relationship model; The model application module is used to obtain the arrangement and combination mode of each block on the diamond layer (1) with the best comprehensive performance of the PDC tooth.

9. The PDC tooth performance adjustment system according to claim 8, characterized in that: It also includes a data processing module for preprocessing the collected training data.

10. A computer-readable storage medium storing instructions, wherein the instructions are executed by a computer to enable the computer to perform multiple functions, characterized in that: Features include: Acquiring training data, the training data including formation data, PDC tooth failure forms, and arrangement and combination of blocks on the diamond layer (1); Constructing a mapping relationship model between input parameters and output parameters based on the training data, wherein the input parameters include the formation data, and the output parameters include the arrangement and combination of each block on the diamond layer (1); Training and optimizing the mapping relationship model based on the PDC tooth failure form; Based on the mapping relationship model, an arrangement and combination mode of each block on the diamond layer (1) with the best comprehensive performance of the PDC tooth is obtained.

11. A PDC tooth, characterized in that: The invention comprises a diamond layer (1), wherein the diamond layer (1) comprises at least one of a first block (101), a second block (102) and a third block (103), wherein the first block (101), the second block (102) and the third block (103) have different wear ratios, and the first block (101), the second block (102) and the third block (103) are combined into the diamond layer (1) based on the PDC tooth performance adjustment method according to any one of claims 1 to 7.

12. The PDC tooth according to claim 11, characterized in that: The diamond layer (1) is formed into a cylindrical structure, and a transition surface (13) is formed between the outer circumferential surface (11) and the top surface (12) of the diamond layer (1).

13. The PDC tooth according to claim 11, characterized in that: It also comprises a substrate (2), the diamond layer (1) is arranged on the substrate (2), and the diamond layer (1) comprises at least one layer.

14. The PDC tooth according to claim 13, characterized in that: The diamond layer (1) comprises a first layer (14) and a second layer (15), wherein the first layer (14) is arranged close to the substrate (2), and the second layer (15) is arranged far from the substrate (2).

Images