Method and device for determining coal-rock failure mode
Through CT scan and naive Bayes classifier combined with static load failure test, the failure mode of coal rock is accurately predicted, which solves the problem of judging coal rock damage patterns in the existing technology, and improves the stability of coal rock mass and engineering application. Controllability.
Patent Information
- Application Number
- CN202410411641.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-07
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-04-07
AI Technical Summary
The existing technology is difficult to accurately judge the damage form of coal rock, which makes it difficult to effectively control the crack generation, expansion direction and fault surface profile of coal rock mass in engineering applications, affecting the stability of tunnel surrounding rock and the formulation of excavation support schemes. .
The characteristic information of coal rock was obtained by CT scan, and the damage mode of coal rock was determined through a pre-constructed naive Bayes classifier, combined with the results of static load failure, and the classifier was constructed using prior probability and conditional probability to realize coal rock. lossless classification and damage pattern prediction.
Accurate failure mode prediction of coal rock is achieved, helping to control the crack generation and expansion direction of coal rock mass, maintain the stability of tunnel surrounding rock, and reasonably formulate excavation and support plans.
Smart Images

Figure CN118425201B_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of coal-rock technology, and in particular to a method and device for determining coal-rock failure modes. Background Art
[0002] Coal rock is a natural material, usually composed of coal matrix, primary cracks, primary pores and different mineral impurities. The formation process of coal rock determines the spatial distribution characteristics of its internal pores, cracks and mineral impurities, resulting in anisotropy in its mechanical properties. Therefore, the failure forms of coal rock with different structures under the influence of external forces will also be very different. In order to adapt to the problems faced in the actual engineering field, a more effective method is urgently needed to accurately judge the failure form of coal rock. Summary of the invention
[0003] The present disclosure aims to solve one of the technical problems in the related art at least to some extent.
[0004] To this end, the first embodiment of the present disclosure proposes a method for determining a coal-rock failure mode, comprising:
[0005] Perform CT scanning on multiple coal rocks to be tested to obtain multiple characteristic information of each coal rock to be tested;
[0006] Input multiple characteristic information of the coal rock to be tested into a pre-built naive Bayes classifier to determine the damage mode of the coal rock to be tested;
[0007] Among them, the naive Bayes classifier is constructed in the following way:
[0008] Perform CT scanning on multiple coal and rock samples to obtain multiple characteristic information of each coal and rock sample;
[0009] Conduct static load failure tests on multiple coal and rock samples to determine multiple failure modes of multiple coal and rock samples;
[0010] According to multiple characteristic information of multiple coal and rock samples, the value range of each characteristic information is divided into multiple intervals to obtain multiple value intervals corresponding to each characteristic information;
[0011] According to multiple failure modes of multiple coal and rock samples, the prior probability of each failure mode in the multiple failure modes and the conditional probability of each characteristic information corresponding to each failure mode in each value interval are determined;
[0012] A naive Bayes classifier is constructed based on the prior probability of each failure mode and the conditional probability of each feature information corresponding to each failure mode in each value interval.
[0013] In some embodiments of the present disclosure, the conditional probability of each characteristic information corresponding to each failure mode in each value interval is determined based on multiple failure modes of multiple coal rock samples, including: in coal rock samples belonging to the target failure mode, when the number of coal rock samples of the first characteristic information among the multiple characteristic information is equal to zero in at least one corresponding value interval, the conditional probability of the first characteristic information corresponding to the target failure mode in each value interval is determined using the Laplace smoothing formula; the target failure mode is one of the multiple failure modes.
[0014] In some embodiments of the present disclosure, the conditional probability of each characteristic information corresponding to each destruction mode in each value interval is determined based on multiple destruction modes of multiple coal rock samples, and also includes: in the coal rock samples belonging to the target destruction mode, when the number of coal rock samples of the first characteristic information among the multiple characteristic information in each corresponding value interval is not equal to zero, determining the number of the first coal rock samples of the first characteristic information in each value interval in the coal rock samples belonging to the target destruction mode, and the total number of coal rock samples belonging to the target destruction mode; based on the number of the first coal rock samples and the total number, determining the conditional probability of the first characteristic information corresponding to the target destruction mode in each value interval.
[0015] In some embodiments of the present disclosure, the expression of the naive Bayes classifier is as follows:
[0016]
[0017]
[0018] Among them, y j represents the jth failure mode, P(y j ) is the prior probability of the jth failure mode, P(x i |Y=y j ) represents the conditional probability of the i-th characteristic information xi corresponding to the j-th failure mode in the target value interval, the target value interval is the value interval to which the i-th characteristic information of the coal rock to be tested belongs, I is the number of characteristic information, J is the number of types of failure modes, and j is a positive integer less than or equal to J.
[0019] The second aspect of the present disclosure provides a device for determining a coal-rock failure mode, comprising:
[0020] The first determination module is used to perform CT scanning on a plurality of coal rocks to be tested, and obtain a plurality of characteristic information of each coal rock to be tested;
[0021] The second determination module is used to input multiple feature information of the coal rock to be tested into a pre-built naive Bayes classifier to determine the damage mode of the coal rock to be tested.
[0022] In some embodiments of the present disclosure, the device for determining the coal-rock failure mode further includes a building module; the building module includes:
[0023] A first determination unit is used to perform CT scanning on a plurality of coal and rock samples to obtain a plurality of characteristic information of each coal and rock sample;
[0024] A second determination unit is used to perform a static load failure test on a plurality of coal and rock samples to determine a plurality of failure modes of the plurality of coal and rock samples;
[0025] A third determining unit is used to divide the value range of each characteristic information into multiple intervals according to multiple characteristic information of multiple coal and rock samples, and obtain multiple value intervals corresponding to each characteristic information;
[0026] A fourth determination unit is used to determine the prior probability of each failure mode in the multiple failure modes and the conditional probability of each characteristic information corresponding to each failure mode in each value interval according to the multiple failure modes of the multiple coal and rock samples;
[0027] The construction unit constructs a naive Bayes classifier based on the prior probability of each failure mode and the conditional probability of each feature information corresponding to each failure mode in each value interval.
[0028] In some embodiments of the present disclosure, the fourth determination unit is specifically used to: in the coal-rock samples belonging to the target destruction mode, when the number of coal-rock samples of the first characteristic information among multiple characteristic information is equal to zero in at least one corresponding value interval, use the Laplace smoothing formula to determine the conditional probability of the first characteristic information corresponding to the target destruction mode in each value interval; the target destruction mode is one of the multiple destruction modes.
[0029] In some embodiments of the present disclosure, the fourth determination unit is also used to: in the coal-rock samples belonging to the target destruction mode, when the number of coal-rock samples in each corresponding value interval of the first characteristic information among multiple characteristic information is not equal to zero, determine the number of first coal-rock samples in each value interval of the first characteristic information in the coal-rock samples belonging to the target destruction mode, and the total number of coal-rock samples belonging to the target destruction mode; determine the conditional probability of the first characteristic information corresponding to the target destruction mode in each value interval based on the number of first coal-rock samples and the total number.
[0030] A third aspect of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;
[0031] The memory stores computer-executable instructions;
[0032] The processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.
[0033] The fourth aspect of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores computer execution instructions, and the computer execution instructions are used to implement the method described in the first aspect when executed by a processor.
[0034] The method for determining the coal rock failure mode provided by the present invention can realize non-destructive classification of coal rocks based on a pre-constructed naive Bayes classifier according to various characteristic information of coal rocks, and effectively predict the failure mode of coal rocks after being subjected to static load pressure. It is of great significance for accurately controlling the generation, expansion direction and formation of fracture surface profiles of coal rock cracks, maintaining the stability of tunnel surrounding rock, and reasonably formulating excavation and support plans.
[0035] Additional aspects and advantages of the present disclosure will be given in part in the following description and in part will be obvious from the following description or learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The above and / or additional aspects and advantages of the present disclosure will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:
[0037] Figure 1 A schematic diagram of a process for constructing a naive Bayes classifier provided in an embodiment of the present disclosure;
[0038] Figure 2 Schematic diagram of the shear failure mode, composite failure module and cleavage failure mode provided by the embodiments of the present disclosure;
[0039] Figure 3 A schematic flow chart of a method for determining a coal-rock failure mode provided by an embodiment of the present disclosure;
[0040] Figure 4 A schematic diagram of a device for determining coal-rock failure mode provided by an embodiment of the present disclosure;
[0041] Figure 5 A schematic diagram of another device for determining coal-rock failure mode provided in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0042] Embodiments of the present disclosure are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present disclosure, and should not be construed as limiting the present disclosure.
[0043] Specifically, the method and device for determining the coal-rock failure mode of the embodiment of the present disclosure are described below with reference to the accompanying drawings. In order to better understand the method for determining the coal-rock failure mode of the embodiment of the present disclosure, the construction of the naive Bayes classifier is first described. Figure 1 The following is a flow chart of a method for constructing a naive Bayes classifier provided in an embodiment of the present disclosure. Figure 1 As shown, the method for constructing the naive Bayes classifier may include the following steps:
[0044] Step 101: perform CT scanning on multiple coal and rock samples to obtain multiple feature information of each coal and rock sample.
[0045] By performing CT scanning on the coal rock to be tested, relevant parameters of the internal structure of the coal rock to be tested, such as pore volume, the number of pixels around the pore area, etc., are obtained, and multiple characteristic information of the coal rock to be tested is further determined based on the relevant parameters. In some embodiments of the present disclosure, the multiple characteristic information includes at least two of the following: porosity, pore fractal dimension, fracture ratio, fracture fractal dimension, mineral ratio and mineral fractal dimension. Optionally, in order to more comprehensively identify the internal structure of the coal rock, the multiple characteristic information includes porosity, pore fractal dimension, fracture ratio, fracture fractal dimension, mineral ratio and mineral fractal dimension. The determination of porosity, pore fractal dimension, fracture ratio, fracture fractal dimension, mineral ratio and mineral fractal dimension can refer to the following formula:
[0046] Porosity x1:
[0047] Pore fractal dimension x2: x2 = log(N1) / log(1 / r)
[0048] Crack rate x3:
[0049] Fracture fractal dimension x4: x4 = log(N2) / log(1 / r)
[0050] Mineral rate x5:
[0051] Mineral fractal dimension x6: x6 = log(N3) / log(1 / r)
[0052] Among them, V is the volume of the coal rock to be tested, V1 is the volume of the pores in the coal rock to be tested, V2 is the volume of the cracks in the coal rock to be tested, V3 is the volume of the minerals in the coal rock to be tested, N1 is the number of pixels around the pore area, N2 is the number of pixels around the crack area, N3 is the number of pixels around the mineral area, and r is a constant used to indicate the relative size of the area.
[0053] In some embodiments of the present disclosure, the pore fractal dimension x2, the fracture fractal dimension x4 and the mineral fractal dimension x6 can be extracted respectively through the Fractal Dimension module of the Avizo software, and the porosity x1, the fracture ratio x3 and the mineral ratio x5 can be extracted respectively through the Volume Fraction module and the Analysis module of the Avizo software.
[0054] Since the proportion and fractal dimension of a certain internal structure (such as cracks) of the coal rock mass will synergistically affect the static failure morphology of the coal rock, it will not have a great impact just because of the high value of a single characteristic. And through research on the literature, it is known that the proportion of pores in coal rock samples is very low, but it also has an important influence on the static failure morphology of coal rock. In order to improve the accuracy of judging the failure mode of coal rock, a comprehensive analysis can be performed based on multiple feature information. In some embodiments of the present disclosure, the feature information may include porosity, pore fractal dimension, crack ratio, crack fractal dimension, mineral ratio and mineral fractal dimension.
[0055] Step 102: Perform static load failure tests on multiple coal and rock samples to determine multiple failure modes of the multiple coal and rock samples.
[0056] To ensure the test effect, in some embodiments of the present disclosure, a static load failure test can be performed on the coal rock samples at the same loading speed (0.01 mm / min) to determine the failure mode corresponding to each coal rock sample. As an example, after the test, the failure characteristics of the coal rock samples can be observed, and the coal rock samples can be divided into three categories according to their failure characteristics, namely, shear failure mode, composite failure module and splitting failure mode. Figure 2 Schematic diagram of the shear failure mode, composite failure module and splitting failure mode provided by the embodiment of the present disclosure. Figure 2 As shown, the easy shear coal samples (a) and (b): under the action of load P, the damage caused by the main cracks penetrating the coal sample is shear failure; the composite failure coal sample (c): under the action of load P, the damage caused by the main cracks penetrating the coal sample is shear failure and splitting failure; the easy splitting coal sample (d): under the action of load p, the damage caused by the main cracks penetrating the coal sample is splitting failure
[0057] Step 103: divide the value range of each characteristic information into multiple intervals according to multiple characteristic information of multiple coal and rock samples, and obtain multiple value intervals corresponding to each characteristic information.
[0058] In some embodiments of the present disclosure, the maximum and minimum values of the same characteristic information in multiple coal and rock samples can be determined, and the maximum and / or minimum values of the same characteristic information divide the value range of the characteristic information into multiple intervals. As an example, for the six characteristic information of porosity, pore fractal dimension, fracture ratio, fracture fractal dimension, mineral ratio and mineral fractal dimension, the maximum porosity σ1, the maximum fracture ratio σ2, the maximum mineral ratio σ3, the minimum pore fractal dimension μ1, the minimum fracture fractal dimension μ2, the minimum mineral fractal dimension μ3, the maximum pore fractal dimension υ1, the maximum fracture fractal dimension υ2 and the maximum mineral fractal dimension υ3 can be determined. According to the maximum and / or minimum values of the aforementioned characteristic information, the value range of each characteristic information is divided into three value intervals:
[0059] Porosity:
[0060] Pore fractal dimension:
[0061] Crack rate:
[0062] Fracture fractal dimension:
[0063] Mineral Rate:
[0064] Mineral fractal dimension:
[0065] It should be noted that in the method for determining the coal rock failure mode disclosed in the present invention, the value range of each characteristic information can also be divided by other methods, and in the present embodiment, the value range of each characteristic information is divided into three value intervals for exemplary purposes only, and can also be divided into other numbers of value intervals, which is not limited in the present disclosure.
[0066] Step 104, according to the multiple failure modes of the multiple coal-rock samples, determine the prior probability of each failure mode in the multiple failure modes, and the conditional probability of each characteristic information corresponding to each failure mode in each value interval.
[0067] Among them, the prior probability of each failure mode in multiple failure modes can be referred to the following formula:
[0068]
[0069] Where P(Y=y j ) represents the jth failure mode y j The prior probability, n j is the jth failure mode y j is the number of coal rock samples, and n is the total number of coal rock samples.
[0070] In some embodiments of the present disclosure, in coal-rock samples belonging to the target damage mode, when the number of coal-rock samples of the first feature information among multiple feature information is equal to zero in at least one corresponding value interval, the conditional probability of the first feature information corresponding to the target damage mode in each value interval is determined using the Laplace smoothing formula, and the target damage mode is one of the multiple damage modes. As an example, in the case of coal-rock samples belonging to the jth damage mode y j In the coal rock samples, when the characteristic information x of multiple coal rock samples i The number of coal and rock samples n in one or more corresponding value intervals ijk = 0, the following formula is obtained by using Laplace smoothing to determine the characteristic information x corresponding to each failure mode: i The conditional probability P in each value interval jk (x i ):
[0071]
[0072] Where i = 1, 2…I, I is the number of feature information, j = 1, 2…J, J is the number of types of failure modes, k = 1, 2…K, K is the number of value intervals corresponding to each feature information, P jk (x i ) indicates that the failure mode is y j In the coal rock samples, the characteristic information x i The probability of belonging to the corresponding kth interval, n j is the jth failure mode y j The number of coal samples, n ijk Indicates that in the jth failure mode y j In the coal rock samples, the characteristic information x i The number of coal rocks in the corresponding kth interval.
[0073] In some embodiments of the present disclosure, in the coal-rock samples belonging to the target damage mode, when the number of coal-rock samples in each corresponding value interval of the first feature information among the multiple feature information is not equal to zero, the number of the first coal-rock samples in each value interval of the first feature information in the coal-rock samples belonging to the target damage mode and the total number of coal-rock samples belonging to the target damage mode are determined; based on the number of the first coal-rock samples and the total number, the conditional probability of the first feature information corresponding to the target damage mode in each value interval is determined. As an example, in the case of the coal-rock samples belonging to the jth damage mode y j In the coal rock samples, when the characteristic information x of multiple coal rock samples i When the number of coal-rock samples in each corresponding value interval is not zero, it is determined to belong to the failure mode y j Characteristic information x in coal rock samplesi The number of first coal-rock samples in each value interval and the total number of coal-rock samples belonging to the target failure mode are used to determine the conditional probability P of the first characteristic information corresponding to the target failure mode in each value interval according to the number of first coal-rock samples and the total number. jk (x i ):
[0074]
[0075] Among them, n j is the jth failure mode y j The number of coal samples, n i j k Indicates that in the jth failure mode y j In the coal rock samples, the characteristic information x i The number of coal rocks in the corresponding kth interval.
[0076] Taking the example of dividing the value range of each characteristic information into three value intervals in step 103, through the above steps, each failure mode y j Each corresponding feature information x i The conditional probability P in each value interval k jk (x i ):
[0077]
[0078]
[0079]
[0080] Step 105: construct a naive Bayes classifier based on the prior probability of each failure mode and the conditional probability of each feature information corresponding to each failure mode in each value interval.
[0081] In some embodiments of the present disclosure, the expression of the naive Bayes classifier is as follows:
[0082]
[0083]
[0084] Among them, y j represents the jth failure mode, P(y j ) is the prior probability of the jth failure mode, P(x i |Y=y j ) represents the jth failure mode y j The corresponding i-th feature information x iThe conditional probability in the target value interval, the target value interval is the value interval to which the i-th characteristic information of the coal rock to be tested belongs, I is the number of characteristic information, J is the number of types of failure modes, and j is a positive integer less than or equal to J. It should be noted that P(x i |Y=y j ) is the conditional probability P of the characteristic information xi corresponding to the damage mode yj in each value interval according to the target value interval jk (x i ) is determined in .
[0085] When using the constructed naive Bayes classifier to classify the failure modes of the coal rock to be tested, the naive Bayes classifier can determine the probability that the coal rock to be tested belongs to each failure mode based on multiple feature information of the coal rock to be tested, and determine the failure mode with the highest probability as the failure mode of the coal rock to be tested.
[0086] By implementing the disclosed embodiment, a naive Bayes classifier is pre-constructed through the prior probability of each failure mode and the conditional probability of each characteristic information corresponding to each failure mode in each value interval, and the relationship between the characteristic information of coal and rock and various failure modes is found. The naive Bayes classifier can realize non-destructive classification of coal and rock in actual working scenarios, and effectively predict the failure mode of coal and rock after being subjected to static load pressure.
[0087] Figure 3 The following is a flow chart of a method for determining a coal-rock failure mode provided by an embodiment of the present disclosure. Figure 3 As shown, the method for determining the coal-rock failure mode may include the following steps:
[0088] Step 301: Perform CT scanning on multiple coal rocks to be tested to obtain multiple characteristic information of each coal rock to be tested.
[0089] Step 302: Input multiple feature information of the coal rock to be tested into a pre-built naive Bayes classifier to determine the damage mode of the coal rock to be tested.
[0090] The naive Bayes classifier can be obtained by the construction method of the naive Bayes classifier described in any of the above embodiments, which will not be described in detail here. It should be noted that the naive Bayes classifier can be pre-constructed or constructed based on the latest data between each detection of the coal and rock to be tested. In addition, Figure 3 The method for determining the coal-rock failure mode of the embodiment shown is Figure 1 The execution subjects of the method for constructing the naive Bayes classifier in the embodiment shown can be the same or different, such as using the same computer to execute Figure 1 and Figure 3 The embodiment shown, or using different servers to process Figure 1 and Figure 3 The method of the illustrated embodiment.
[0091] According to multiple characteristic information of the coal rock to be tested, the damage mode of the coal rock to be tested is determined by a pre-built naive Bayes classifier, wherein the expression of the naive Bayes classifier is as follows:
[0092]
[0093]
[0094] Among them, y j represents the jth failure mode, P(y j ) is the prior probability of the jth failure mode, P(x i |Y=y j ) represents the conditional probability of the i-th characteristic information xi corresponding to the j-th failure mode yj in the target value interval, and the target value interval is the i-th characteristic information x of the coal rock to be tested. i The value interval belongs to, I is the number of characteristic information, J is the number of types of failure modes, and j is a positive integer less than or equal to J.
[0095] It should be noted that P(x i |Y=y j ) is based on the target value interval of the characteristic information of the coal and rock to be tested from the failure mode y j The corresponding feature information x i The conditional probability P in each value interval jk (x i ) is determined in .
[0096] As an example, assume that the characteristic information of the coal rock to be tested includes x1, x2, x3, x4, x5, x6, and the failure modes include y1, y2, y3. The probability P(y1| x ), first determine the target value intervals to which the characteristic information x1, x2, x3, x4, x5, x6 belong. According to the target value intervals to which the characteristic information x1, x2, x3, x4, x5, x6 to be tested belongs, the characteristic information x1 corresponding to the failure mode y1 is i The conditional probability P in each value interval 1k (x i ) to determine the conditional probability P(x i |Y=y1). Then, the probability that the coal rock to be tested belongs to the failure mode y1 is determined by the naive Bayes classifier. The probability that the coal rock to be tested belongs to the failure mode y1 is the same as the probability of the failure mode y3.
[0097] Therefore, the naive Bayes classifier can determine the probability that the tested coal rock belongs to each failure mode according to the characteristic information of the tested coal rock, and determine the failure mode corresponding to the maximum probability value as the failure mode to which the tested coal rock belongs.
[0098] By implementing the embodiments of the present disclosure, non-destructive classification of coal rocks can be achieved based on a pre-constructed naive Bayes classifier according to various characteristic information of coal rocks, and the failure mode of coal rocks after being subjected to static load pressure can be effectively predicted, which is of great significance for accurately controlling the generation, expansion direction and formation of fracture profiles of coal rock cracks, maintaining the stability of tunnel surrounding rocks, and rationally formulating excavation and support plans.
[0099] Figure 4 Schematic diagram of a device for determining coal-rock failure mode provided by an embodiment of the present disclosure. Figure 4 As shown, the device for determining the coal-rock failure mode includes: a first determination module 401 and a second determination module 402 .
[0100] The first determination module 401 is used to perform CT scanning on a plurality of coal rocks to be tested, and obtain a plurality of characteristic information of each coal rock to be tested.
[0101] The second determination module 402 is used to input multiple feature information of the coal rock to be tested into a pre-built naive Bayes classifier to determine the damage mode of the coal rock to be tested.
[0102] Optionally, in some embodiments of the present disclosure, Figure 5 As shown, the device for determining coal-rock failure mode further includes a construction module 503. The construction module 503 includes: a first determination unit 511, a second determination unit 512, a third determination unit 513, a fourth determination unit 514 and a construction unit 515.
[0103] The first determining unit 511 is used to perform CT scanning on multiple coal and rock samples to obtain multiple feature information of each coal and rock sample.
[0104] The second determination unit 512 is used to perform a static load failure test on the multiple coal and rock samples to determine multiple failure modes of the multiple coal and rock samples.
[0105] The third determining unit 513 is used to divide the value range of each characteristic information into multiple intervals according to multiple characteristic information of multiple coal and rock samples, and obtain multiple value intervals corresponding to each characteristic information.
[0106] The fourth determination unit 514 is used to determine the prior probability of each failure mode in the multiple failure modes and the conditional probability of each feature information corresponding to each failure mode in each value interval according to the multiple failure modes of the multiple coal-rock samples.
[0107] The construction unit 515 constructs a naive Bayes classifier based on the prior probability of each failure mode and the conditional probability of each feature information corresponding to each failure mode in each value interval.
[0108] In some embodiments of the present disclosure, the expression of the naive Bayes classifier is as follows:
[0109]
[0110]
[0111] Among them, y j represents the jth failure mode, P(y j ) is the prior probability of the jth failure mode, P(x i |Y=y j ) represents the conditional probability of the i-th characteristic information xi corresponding to the j-th failure mode in the target value interval, the target value interval is the value interval to which the i-th characteristic information of the coal rock to be tested belongs, I is the number of characteristic information, J is the number of types of failure modes, and j is a positive integer less than or equal to J.
[0112] In some embodiments of the present disclosure, the fourth determination unit 514 is specifically used to: in the coal-rock samples belonging to the target destruction mode, when the number of coal-rock samples of the first characteristic information among multiple characteristic information is equal to zero in at least one corresponding value interval, use the Laplace smoothing formula to determine the conditional probability of the first characteristic information corresponding to the target destruction mode in each value interval; the target destruction mode is one of the multiple destruction modes.
[0113] In some embodiments of the present disclosure, the fourth determination unit 514 is also used to: in the coal-rock samples belonging to the target destruction mode, when the number of coal-rock samples in each corresponding value interval of the first characteristic information among multiple characteristic information is not equal to zero, determine the number of first coal-rock samples in each value interval of the first characteristic information in the coal-rock samples belonging to the target destruction mode, and the total number of coal-rock samples belonging to the target destruction mode; determine the conditional probability of the first characteristic information corresponding to the target destruction mode in each value interval based on the number of first coal-rock samples and the total number.
[0114] in, Figure 5 501-502 and Figure 4 401-402 have the same function and structure.
[0115] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0116] In order to implement the above embodiments, the present disclosure also proposes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.
[0117] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.
[0118] In order to implement the above embodiments, the present disclosure also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.
[0119] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.
[0120] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present disclosure, "plurality" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0121] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present disclosure includes additional implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present disclosure belong.
[0122] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.
[0123] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0124] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.
Claims
1. A method for determining coal-rock failure mode, It is characterized in that The following steps are involved: Performing CT scanning on a plurality of coal rocks to be tested to obtain a plurality of characteristic information of each of the coal rocks to be tested; Inputting multiple characteristic information of the coal rock to be tested into a pre-built naive Bayes classifier to determine the damage mode of the coal rock to be tested; The naive Bayes classifier is constructed in the following way: Performing CT scanning on a plurality of coal and rock samples to obtain a plurality of characteristic information of each of the coal and rock samples; Performing static load failure tests on the plurality of coal and rock samples to determine a plurality of failure modes of the plurality of coal and rock samples; According to the plurality of characteristic information of the plurality of coal and rock samples, the value range of each characteristic information is divided into a plurality of intervals, and a plurality of value intervals corresponding to each characteristic information are obtained; According to the multiple failure modes of the multiple coal and rock samples, determine the prior probability of each of the multiple failure modes and the conditional probability of each of the characteristic information corresponding to each of the failure modes in each of the value intervals; Constructing the naive Bayes classifier based on the prior probability of each failure mode and the conditional probability of each feature information corresponding to each failure mode in each value interval; The expression of the naive Bayes classifier is as follows: in, Indicates j A failure mode, For the j The prior probability of the failure mode, Representative j The failure mode corresponds to i Feature information x i The conditional probability in the target value interval is the first i The value interval to which the feature information belongs, I is the number of feature information, J is the number of types of failure modes, j is less than or equal to J A positive integer.
2. The method according to claim 1, It is characterized in that Determining the conditional probability of each of the characteristic information corresponding to each of the failure modes in each of the value intervals according to the multiple failure modes of the multiple coal and rock samples includes: In the coal-rock samples belonging to the target destruction mode, when the number of coal-rock samples of the first characteristic information among the multiple characteristic information is equal to zero in at least one corresponding value interval, the Laplace smoothing formula is used to determine the conditional probability of the first characteristic information corresponding to the target destruction mode in each of the value intervals; the target destruction mode is one of the multiple destruction modes.
3. The method according to claim 2, It is characterized in that Determining the conditional probability of each of the characteristic information corresponding to each of the failure modes in each of the value intervals according to the multiple failure modes of the multiple coal and rock samples, further comprising: In the coal-rock samples belonging to the target damage mode, when the number of coal-rock samples in each corresponding value interval of the first characteristic information among the multiple characteristic information is not equal to zero, determine the number of the first coal-rock samples in each value interval of the first characteristic information among the coal-rock samples belonging to the target damage mode, and the total number of coal-rock samples belonging to the target damage mode; According to the first coal-rock sample quantity and the total quantity, the conditional probability of the first characteristic information corresponding to the target failure mode in each of the value intervals is determined.
4. A device for determining coal-rock failure mode, It is characterized in that include: A first determination module is used to perform CT scanning on a plurality of coal rocks to be tested, and obtain a plurality of characteristic information of each of the coal rocks to be tested; The second determination module is used to input multiple feature information of the coal rock to be tested into a pre-built naive Bayes classifier to determine the damage mode of the coal rock to be tested; The device also includes a building block, the building block including: A first determination unit is used to perform CT scanning on a plurality of coal and rock samples to obtain a plurality of characteristic information of each of the coal and rock samples; A second determination unit is used to perform a static load failure test on the plurality of coal and rock samples to determine a plurality of failure modes of the plurality of coal and rock samples; A third determining unit is used to divide the value range of each characteristic information into multiple intervals according to the multiple characteristic information of the multiple coal and rock samples, and obtain multiple value intervals corresponding to each characteristic information; A fourth determination unit is used to determine, according to the multiple failure modes of the multiple coal and rock samples, the prior probability of each of the multiple failure modes and the conditional probability of each of the characteristic information corresponding to each of the failure modes in each of the value intervals; A construction unit, which constructs the naive Bayes classifier based on the prior probability of each of the damage modes and the conditional probability of each of the feature information corresponding to each of the damage modes in each value interval; The expression of the naive Bayes classifier is as follows: in, Indicates j A failure mode, For the j The prior probability of the failure mode, Representative j The failure mode corresponds to i Feature information x i The conditional probability in the target value interval is the first i The value interval to which the feature information belongs, I is the number of feature information, J is the number of types of failure modes, j is less than or equal to J A positive integer.
5. The device according to claim 4, It is characterized in that The fourth determining unit is specifically configured to: In the coal-rock samples belonging to the target destruction mode, when the number of coal-rock samples of the first characteristic information among the multiple characteristic information is equal to zero in at least one corresponding value interval, the Laplace smoothing formula is used to determine the conditional probability of the first characteristic information corresponding to the target destruction mode in each of the value intervals; the target destruction mode is one of the multiple destruction modes.
6. The device according to claim 5, It is characterized in that The fourth determining unit is further configured to: In the coal-rock samples belonging to the target damage mode, when the number of coal-rock samples in each corresponding value interval of the first characteristic information among the multiple characteristic information is not equal to zero, determine the number of the first coal-rock samples in each value interval of the first characteristic information among the coal-rock samples belonging to the target damage mode, and the total number of coal-rock samples belonging to the target damage mode; According to the first coal-rock sample quantity and the total quantity, the conditional probability of the first characteristic information corresponding to the target failure mode in each of the value intervals is determined.
7. An electronic device, It is characterized in that include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 3.
8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 3 when executed by a processor.
