Lithology identification method, device and system based on vibration signal and storage medium

Abstract

The application discloses a lithology identification method, device and system based on a vibration signal and a storage medium. The method comprises the following steps: acquiring a vibration signal sample of a drill bit when the drill bit is used to drill a rock sample in a work area, and extracting a signal characteristic parameter from the vibration signal sample; establishing a probability distribution relationship model between the lithology of the rock sample and the signal characteristic parameter of the vibration signal of the drill bit according to a corresponding relationship between the lithology of the rock sample and the signal characteristic parameter of the vibration signal sample; acquiring a vibration signal generated when the drill bit breaks the rock during drilling in the work area, and extracting a signal characteristic parameter from the vibration signal; and according to the signal characteristic parameter of the vibration signal, the lithology of the stratum in the work area drilled by the drill bit is inferred by using the probability distribution relationship model between the lithology of the rock in the work area and the signal characteristic parameter of the vibration signal of the drill bit.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of exploration, and particularly relates to a method, device and system for lithology identification using a while-drilling vibration signal and a storage medium. BACKGROUND

[0002] In a region with complex geological conditions, drilling operation is risky and costly, and the drilled stratum needs to be accurately mastered in time. Through accurate identification of the stratum, drilling engineering services such as adjustment of the drilling trajectory, selection of the casing position and size, and drilling fluid density can be better provided, and drilling risks can be effectively reduced and efficiency can be improved. At present, lithology identification is mainly performed through coring and well logging, but coring and well logging data have a certain lag. SUMMARY

[0003] In view of the above technical problems, the present application provides a new lithology identification technology based on a while-drilling vibration signal, which can provide a real-time and low-cost lithology identification method.

[0004] Firstly, the present application provides a lithology identification method based on a vibration signal, characterized in that the method comprises the following steps:

[0005] obtaining a vibration signal sample of a drill bit when drilling a rock sample in a work area, and extracting a signal feature parameter from the vibration signal sample;

[0006] establishing a probability distribution relationship model between the lithology of the rock in the work area and the signal feature parameter of the vibration signal of the drill bit according to a corresponding relationship between the lithology of the rock sample and the signal feature parameter of the vibration signal sample;

[0007] obtaining a vibration signal generated when the drill bit breaks the rock during drilling in the work area, and extracting a signal feature parameter from the vibration signal;

[0008] speculating the lithology of the stratum drilled by the drill bit in the work area according to the signal feature parameter of the vibration signal and using the probability distribution relationship model between the lithology of the rock in the work area and the signal feature parameter of the vibration signal of the drill bit.

[0009] According to one embodiment of the present application, in the above method, the signal feature parameter comprises a log energy of the signal and a log energy of the signal after filtering.

[0010] According to one embodiment of the present application, in the above method, the signal is frame-processed.

[0011] The frame signal data is converted from the time domain to the frequency domain, and the frequency spectrum of the frame signal data is determined.

[0012] The log energy of the frame signal data and the log energy of the frame signal data after filtering are calculated using the frequency spectrum of the frame signal data.

[0013] According to one embodiment of the present application, in the method, a relationship model between rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit is established according to a corresponding relationship between the lithology of the rock sample and the signal characteristic parameters of the vibration signal sample, and the relationship model includes:

[0014] According to the lithology of the rock sample and the signal characteristic parameters of the corresponding vibration signal sample, a probability distribution of the signal characteristic parameters of the vibration signals corresponding to different lithologies is determined, and a probability distribution relationship model describing the relationship between the rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit is established based on the probability distribution.

[0015] According to one embodiment of the present application, in the method, a probability distribution of the signal characteristic parameters of the vibration signals corresponding to different lithologies is determined according to the lithology of the rock sample and the signal characteristic parameters of the corresponding vibration signal sample, and a probability distribution relationship model describing the relationship between the rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit is established based on the probability distribution, and the probability distribution relationship model includes:

[0016] Based on the lithology of the rock sample and the signal characteristic parameters of the corresponding vibration signal sample, a Gaussian probability distribution of the signal characteristic parameters of the vibration signals corresponding to different lithologies is determined, and a Gaussian mixture probability model describing the relationship between the rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit is established based on the Gaussian probability distribution.

[0017] According to one embodiment of the present application, in the method, the lithology of the formation drilled by the drill bit is inferred by using the probability distribution relationship model between the rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit according to the signal characteristic parameters of the vibration signals.

[0018] According to one embodiment of the present application, in the method, the lithology of the formation drilled by the drill bit is inferred by using the Gaussian mixture probability model between the rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit according to the signal characteristic parameters of the vibration signals, and the lithology of the formation drilled by the drill bit is inferred by using a Bayesian estimation inversion method based on a Gaussian likelihood function.

[0019] According to one embodiment of the present application, in the method, the lithology of the formation drilled by the drill bit is inferred by using the Gaussian mixture probability model between the rock lithology of the work area and the signal characteristic parameters of the vibration signals of the drill bit according to the signal characteristic parameters of the vibration signals, and the lithology of the formation drilled by the drill bit is inferred by using a Bayesian estimation inversion method based on a Gaussian likelihood function.

[0020] According to the following formula, the probability value of the formation drilled by the drill bit being different lithology is calculated:

[0021]

[0022]

[0023] Wherein, I is prior lithology information; p(m|d, I) is lithology posterior probability density; p(m|I) is lithology prior probability density; p(d|I) is a normalization factor; L(m|d, I) is a Gaussian type likelihood function, which represents the probability of data d when the parameter is m; d represents signal characteristic parameters; m is lithology parameters; C T is a covariance matrix of data measurement error; g(m) is a relationship function between lithology parameters and signal characteristic parameters;

[0024] The lithology with the maximum probability is the lithology of the stratum drilled by the drill bit.

[0025] In addition, the present application also provides a lithology identification device based on vibration signals, characterized by comprising:

[0026] A sample acquisition module is configured to acquire vibration signal samples when a rock sample in a drilling area is obtained, and extract signal characteristic parameters from the vibration signal samples;

[0027] A relationship determination module is configured to determine a probability distribution relationship model between rock lithology in the drilling area and signal characteristic parameters of the vibration signals of the drill bit by analyzing the corresponding relationship between the lithology of the rock sample and the signal characteristic parameters of the vibration signal samples;

[0028] A signal acquisition module is configured to acquire vibration signals generated when the drill bit breaks rocks during drilling in the drilling area, and extract signal characteristic parameters from the vibration signals;

[0029] A lithology identification module is configured to infer the lithology of the stratum in the drilling area drilled by the drill bit according to the signal characteristic parameters of the vibration signals, and utilize the probability distribution relationship model between the rock lithology in the drilling area and the signal characteristic parameters of the vibration signals of the drill bit.

[0030] In addition, the present application also provides a lithology identification system based on vibration signals, characterized by comprising:

[0031] A signal acquisition device is configured to acquire vibration signal samples when a rock sample in a drilling area is obtained, and acquire vibration signals generated when the drill bit breaks rocks during drilling in the drilling area;

[0032] A memory and a processor are configured to execute a computer program stored in the memory, so as to realize the above-mentioned lithology identification method based on the vibration signal samples when a rock sample in a drilling area is obtained by the signal acquisition device, and the vibration signals generated when the drill bit breaks rocks during drilling in the drilling area.

[0033] In addition, the present application also provides a computer storage medium, characterized by storing a computer program executable by a processor, wherein the computer program realizes the above-mentioned lithology identification method when executed by the processor.

[0034] Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:

[0035] The lithology identification method based on the vibration signal provided by the application can identify the lithology of the stratum drilled in real time and efficiently, has high lithology identification precision, is beneficial to quickly identifying the stratum change in the drilling process, accurately identifies the horizon interface, improves the accuracy of the stratum horizon calibration, and has very high practical value.

[0036] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0037] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of the specification, illustrate embodiments of the present application, and are used to explain the present application together with the written description. The drawings are not intended to limit the present application, and in the drawings:

[0038] Figure 1 The step flow chart of the lithology identification method based on the vibration signal while drilling of the first embodiment of the present application is shown in the figure.

[0039] Figure 2 The step flow chart of the lithology identification method based on the vibration signal while drilling of the third embodiment of the present application is shown in the figure.

[0040] Figure 3 The schematic diagram of the extracted vibration signal characteristic parameter of the third embodiment of the present application is shown in the figure.

[0041] Fig. 4(a) and (b) are respectively the comparison schematic diagram of the lithology identified by the method of the present application and the real lithology of the third embodiment of the present application. DETAILED DESCRIPTION

[0042] The embodiments of the present application will be described in detail below with reference to the accompanying drawings and embodiments, so that how the present application applies technical means to solve technical problems and achieves technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, each embodiment in the present application and each feature in each embodiment can be combined with each other, and the technical solutions formed thereby are all within the protection scope of the present application.

[0043] During the drilling process, rock-breaking by the drill bit causes axial, lateral, and torsional vibrations in the drill string. These vibrations carry information about the stratum being drilled by the downhole drill bit. By collecting and analyzing the vibration signals generated by the drill bit during drilling, and analyzing the sensitivity parameters of these lithology-related vibration signals, the lithology of the drilled stratum can be identified. Therefore, to address the aforementioned technical problems existing in the prior art, the present invention proposes a new lithology identification technology based on vibration signals while drilling. This technology is a real-time, low-cost lithology identification method that facilitates rapid identification of stratum changes during drilling, pinpoints stratigraphic interfaces, and improves the accuracy of stratigraphic level calibration, thus possessing extremely high practical value.

[0044] The working principle of the technical solution of the present invention is explained below with reference to specific embodiments.

[0045] Example 1

[0046] like Figure 1 As shown, in order to timely and accurately grasp the lithology of the drilled formation during the drilling process, this embodiment provides a lithology identification method based on drilling vibration signals, which mainly includes the following steps:

[0047] S110, obtaining vibration signal samples of the drill bit when drilling rock samples in the drilling area, and extracting signal characteristic parameters from the vibration signal samples; the signal characteristic parameters include logarithmic energy of the signal and logarithmic energy after signal filtering.

[0048] S120 , establishing a probability distribution relationship model between the rock properties of the work area and the signal characteristic parameters of the vibration signal of the drill bit based on the corresponding relationship between the rock properties of the rock samples and the signal characteristic parameters of the vibration signal samples.

[0049] S130, obtaining a vibration signal generated when the drill bit breaks rock during drilling in the work area, and extracting signal characteristic parameters from the vibration signal;

[0050] S140 , based on the signal characteristic parameters of the vibration signal, the lithology of the stratum in the work area encountered by the drill bit is inferred using a probability distribution relationship model between the rock lithology of the work area and the signal characteristic parameters of the vibration signal of the drill bit.

[0051] Example 2

[0052] The above embodiment one describes the main idea of the technical scheme of the present application. Namely, in order to timely and accurately master the lithology of the drilled formation during the drilling process, the method for identifying the lithology of the formation drilled by the drill bit by using the vibration signal while drilling is used. In actual engineering application, the Gaussian mixed probability model is usually used to establish the probability distribution relationship model between the lithology of the formation in the work area and the signal characteristic parameters of the vibration signal of the drill bit, and then the lithology of the formation drilled by the drill bit is inversely calculated according to the probability distribution by using the Bayesian estimation based on the Gaussian type likelihood function. The main step process is as follows:

[0053] Obtaining the vibration signal sample of the drill bit when drilling the rock sample in the work area, and extracting the signal characteristic parameters from the vibration signal sample.

[0054] S210, obtaining the vibration signal sample of the drill bit when drilling the rock sample in the work area, and extracting the signal characteristic parameters from the vibration signal sample; the signal characteristic parameters of the vibration signal sample include the log energy of the signal and the log energy of the signal after filtering.

[0055] In this embodiment, this step mainly includes the following steps.

[0056] S211, performing frame processing on the vibration signal sample.

[0057] S212, converting each frame of signal data from the time domain to the frequency domain to determine the frequency spectrum of each frame of signal data.

[0058] S213, calculating the log energy of each frame of signal data and the log energy of each frame of signal data after filtering by using the frequency spectrum of each frame of signal data.

[0059] S220, establishing a probability distribution relationship model describing the relationship between the lithology of the rock in the work area and the signal characteristic parameters of the vibration signal of the drill bit according to the corresponding relationship between the lithology of the rock sample and the signal characteristic parameters of the vibration signal sample.

[0060] In this embodiment, this step mainly includes the following steps.

[0061] Based on the lithology of the rock sample and the signal characteristic parameters of the corresponding vibration signal sample, the Gaussian probability distribution of the signal characteristic parameters of the vibration signal corresponding to different lithologies is determined, and the Gaussian mixed probability model describing the relationship between the lithology of the rock in the work area and the signal characteristic parameters of the vibration signal of the drill bit is established based on the Gaussian probability distribution.

[0062] S230, obtaining the vibration signal generated when the drill bit breaks the rock during the drilling process in the work area, and extracting the signal characteristic parameters from the vibration signal; the signal characteristic parameters of the vibration signal also include the log energy of the signal and the log energy of the signal after filtering.

[0063] Similarly, this step mainly includes the following steps:

[0064] S231, frame processing is performed on the vibration signal;

[0065] S232, converting each frame of signal data from time domain to frequency domain to determine the frequency spectrum of each frame of signal data;

[0066] S233, calculating the log energy of each frame of signal data and the filtered log energy of each frame of signal data using the frequency spectrum of each frame of signal data.

[0067] S240, according to the signal characteristic parameters of the vibration signal, using the probabilistic distribution relationship model between the rock lithology of the work area and the signal characteristic parameters of the vibration signal of the drill bit to infer the lithology of the stratum drilled by the drill bit.

[0068] In this embodiment, this step mainly includes the following steps:

[0069] According to the signal characteristic parameters of the vibration signal, using the Gaussian mixture probability model between the rock lithology of the work area and the signal characteristic parameters of the vibration signal of the drill bit, according to the following formula, the probability of the lithology of the stratum drilled by the drill bit is inferred by the inversion method based on the Bayesian estimation of the Gaussian likelihood function:

[0070]

[0071]

[0072] where I is the prior lithology information; p(m|d, I) is the lithology posterior probability density; p(m|I) is the lithology prior probability density; p(d|I) is the normalization factor; L(m|d, I) is the Gaussian likelihood function, representing the probability of data d when the parameter is m; d represents the signal characteristic parameter; m is the lithology parameter; C T is the covariance matrix of data measurement error; g(m) is the relationship function between the lithology parameter and the signal characteristic parameter;

[0073] where the lithology with the maximum probability is the lithology of the stratum drilled by the drill bit.

[0074] Example Three

[0075] The technical solutions of the present application will be further described below in combination with the application of a work area (Appendices 1-4). In actual engineering applications, in order to accurately master the lithology of the stratum drilled in the drilling process in time, the lithology of the stratum drilled by the drill bit is identified using the vibration signal while drilling, and the vibration signal collected at the wellhead in the drilling process is processed according to the following technical process, which specifically includes (Appendix 5): Figure 2 、 3 and 4). In actual engineering applications, in order to accurately master the lithology of the stratum drilled in the drilling process in time, the lithology of the stratum drilled by the drill bit is identified using the vibration signal while drilling, and the vibration signal collected at the wellhead in the drilling process is processed according to the following technical process, which specifically includes (Appendix 5): Figure 2 ​

[0076] 1. Collecting vibration signals;

[0077] 2. Extracting characteristic parameters of vibration signals;

[0078] 3. Analyzing characteristic parameters of vibration signals;

[0079] 4. Lithology identification based on characteristic parameters of vibration signals.

[0080] In the embodiment, the step (1) includes:

[0081] Collecting vibration signals while drilling. Preferably, a wide-band three-component velocity detector is arranged around the wellhead where drilling is being carried out to collect vibration signals generated by the drill bit during drilling.

[0082] In the embodiment, the step (2) includes:

[0083] Extracting corresponding characteristic parameters from the collected vibration signals while drilling. The specific steps are as follows

[0084] 1. First, frame processing is performed on the vibration signals while drilling. N time sampling points form an observation unit x(n), 0≤n<N, called a frame. The adjacent two frames overlap W sample points, and W is usually 1 / 2N.

[0085] 2. Fast Fourier transform is performed on each frame of data to calculate the frequency spectrum

[0086] 3. The logarithmic energy e of each frame of data is calculated, and the calculation formula is

[0087] 4. The logarithmic energy amplitude spectrum is passed through a set of filters to calculate the logarithmic energy after passing through the filter set. Preferably, the filter set uses a triangular filter, and a set of center frequencies f m , m = 1, 2,..., M, and the frequency response of the triangular filter is wherein,

[0088] The calculation formula of the filtered logarithmic energy is

[0089] 5. The characteristic parameters of the vibration signals include the logarithmic energy e of each frame of data and the filtered logarithmic energy s(m).

[0090] In the embodiment, the step (3) includes:

[0091] In this step, representative rock samples in the drilling area are selected, the characteristic parameters of the vibration signals of the rock samples are extracted, and the lithology is recorded. Then, the probability distribution of the characteristic parameters of the vibration signals while drilling of different lithologies is established, which is used for subsequent lithology identification of the vibration signals while drilling.

[0092] As in Example Two, the Gaussian mixture probability model is used to represent the probability distribution of the characteristic parameters of the vibration signals while drilling of different lithologies:

[0093]

[0094] The probability distribution is represented as a weighted sum of K Gaussian distributions; where d is the characteristic parameter; m is the lithology; K is the number of Gaussian distributions, π k is the weighting coefficient, N(x|μ i ,Σ i ) is a Gaussian distribution, μ is the mean of the characteristic parameter, and Σ is the covariance matrix of the characteristic parameter. Finally, the model parameters of the Gaussian mixture model, i.e., the weighting coefficients π, the mean μ, and the variance Σ, are estimated by the commonly used expectation-maximization algorithm (EM algorithm).

[0095] In this embodiment, the content of step (4) includes:

[0096] In this step, the inversion method based on Bayesian estimation is used to infer the formation lithology. The lithology identification formula based on Bayesian estimation is as follows:

[0097]

[0098]

[0099] where I is the prior lithology information; p(m|d,I) is the lithology posterior probability density; p(m|I) is the lithology prior probability density; p(d|I) is the normalization factor; L(m|d,I) is the Gaussian likelihood function, representing the probability of data d when the parameter is m; d represents the signal characteristic parameter; m is the lithology parameter; C T is the covariance matrix of the data measurement error; g(m) is the relationship function between the lithology parameter and the signal characteristic parameter;

[0100] After calculating the probabilities of different lithologies using the above formula, the lithology with the maximum probability is the lithology of the formation drilled by the drill bit.

[0101] Of course, in the above lithology identification process, the Gaussian likelihood function can be further combined with the cutting logging data to adjust and optimize the inversion result in a timely manner, so as to improve the reliability of the inversion result.

[0102] It should be noted that the method of the embodiment of the present application can be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scenario, and be completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only execute one or more steps in the method of the embodiment of the present application, and the multiple devices can interact with each other to complete the method.

[0103] Embodiment four

[0104] To solve the above technical problems in the prior art, the embodiment provides a lithology identification device based on a vibration signal, which comprises:

[0105] A sample acquisition module is configured to acquire a vibration signal sample when a rock sample in a drilling area is drilled by a drill bit, and extract a signal feature parameter from the vibration signal sample.

[0106] A relationship determination module is configured to determine a probability distribution relationship model between the lithology of the rock in the drilling area and the signal feature parameter of the vibration signal of the drill bit by analyzing the corresponding relationship between the lithology of the rock sample and the signal feature parameter of the vibration signal sample.

[0107] A signal acquisition module is configured to acquire a vibration signal generated when the drill bit breaks the rock during drilling in the drilling area, and extract a signal feature parameter from the vibration signal.

[0108] A lithology identification module is configured to infer the lithology of the stratum in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probability distribution relationship model between the lithology of the rock in the drilling area and the signal feature parameter of the vibration signal of the drill bit.

[0109] The device of the above embodiment is used to implement the corresponding method in the above embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described here.

[0110] Embodiment five

[0111] In addition, to solve the above technical problems in the prior art, the embodiment of the present application further provides a lithology identification system based on a vibration signal, which comprises:

[0112] A signal acquisition device is configured to acquire a vibration signal sample when a rock sample in a drilling area is drilled by a drill bit, and a vibration signal generated when the drill bit breaks the rock during drilling.

[0113] A memory and a processor, wherein the processor is configured to execute a computer program stored in the memory, so as to realize the above lithology identification method based on the vibration signal sample acquired by the signal acquisition device when the rock sample in the drilling area is drilled by the drill bit, and the vibration signal generated when the drill bit breaks the rock during drilling.

[0114] Embodiment six

[0115] In addition, to solve the above technical problems existing in the prior art, the embodiment of the present application also provides a computer storage medium, characterized in that a computer program executable by a processor is stored therein, and the computer program realizes the lithology identification method when executed by the processor.

[0116] It can be understood that the same or similar parts in the above embodiments can be mutually referred to, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0117] Any process or method descriptions in flow charts or described elsewhere herein can be understood as representing one or more steps in a set of steps performed by functions that are part of the implementation, and that the functions can be implemented by hardware, software, firmware or any combination of them, and preferred embodiments of the present application contemplate that the functions can be implemented in the order discussed or in a different order, that the functions can be performed by different entities or locations, and that functions can be combined or separated into different functions.

[0118] It should be understood that each part of the present application can be realized by hardware, software, firmware or their combination. In the above embodiments, a plurality of steps or methods can be realized by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if realized by hardware, and as in another embodiment, it can be realized by any one or their combination of the following technologies known in the art: discrete logic circuit with logic gate circuit for implementing logic function on data signal, application specific integrated circuit with suitable combination logic gate circuit, programmable gate array (PGA), field programmable gate array (FPGA) and the like.

[0119] Those skilled in the art of the present technology can understand that all or part of the steps carried out by the above-mentioned embodiment method can be completed by a program instructing the relevant hardware, and the program can be stored in a computer readable storage medium, and the program includes one or a combination of the steps of the method embodiment when executed.

[0120] In addition, each functional unit in each embodiment of the present application can be integrated in one processing module, or each unit can exist physically separately, or two or more units can be integrated in one module. The above integrated module can be realized in the form of hardware or in the form of software functional module. The integrated module, if realized in the form of software functional module and sold or used as an independent product, can also be stored in a computer readable storage medium.

[0121] The storage medium mentioned above can be a read-only memory, a magnetic disk, an optical disk, or the like.

[0122] In the description of the present specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in an appropriate manner.

[0123] Although the embodiments disclosed by the present application are as described above, the content described is only the embodiments adopted for the purpose of facilitating the understanding of the present application, and is not intended to limit the present application. Any person skilled in the art of the present application can make any modification and change in the form of implementation and details without departing from the spirit and scope of the present application, but the protection scope of the present application shall be subject to the scope defined by the appended claims.

Claims

1. A lithology identification method based on a vibration signal, characterized in that, The method comprises the following steps: obtaining a vibration signal sample of a drill bit when the drill bit drills a rock sample in a work area, and extracting a signal characteristic parameter from the vibration signal sample; establishing a probability distribution relationship model between rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit according to a corresponding relationship between the rock lithology of the rock sample and the signal characteristic parameter of the vibration signal sample; obtaining a vibration signal generated when the drill bit drills a rock in the drilling process of the work area, and extracting a signal characteristic parameter from the vibration signal; wherein the signal characteristic parameter comprises a logarithmic energy of the signal and a signal filtered logarithmic energy, and the signal filtered logarithmic energy is obtained by using a triangular filter as a filter group; speculating the lithology of the formation drilled by the drill bit in the work area according to the signal characteristic parameter of the vibration signal and the probability distribution relationship model between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit; the step of speculating the lithology of the formation drilled by the drill bit in the work area according to the signal characteristic parameter of the vibration signal and the probability distribution relationship model between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit comprises: inverting the lithology of the formation drilled by the drill bit according to the signal characteristic parameter of the vibration signal and a Gaussian mixed probability model between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit by a Bayesian estimation inversion method based on a Gaussian type likelihood function; calculating a probability value of the lithology of the formation drilled by the drill bit according to the following formula: wherein, is the prior lithology information; is the posterior probability density of lithology; is the prior probability density of lithology; is the normalization factor; is the Gaussian-type likelihood function, representing the probability that the data is when the parameter is represents the signal feature parameter; is the lithology parameter; is the covariance matrix of data measurement error; is the relationship function between the lithology parameter and the signal feature parameter;​ taking the lithology with the maximum probability as the lithology of the formation drilled by the drill bit.

2. The method of claim 1, wherein, The step of extracting the signal characteristic parameter comprises the following steps: frame processing the signal; converting each frame of signal data from a time domain to a frequency domain to determine a frequency spectrum of each frame of signal data; calculating a logarithmic energy of each frame of signal data and a signal filtered logarithmic energy of each frame of signal data by using the frequency spectrum of each frame of signal data.

3. The method of claim 1, wherein, The step of establishing a relationship model between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit according to a corresponding relationship between the rock lithology of the rock sample and the signal characteristic parameter of the vibration signal sample comprises: determining a probability distribution of the signal characteristic parameter of the vibration signal corresponding to different lithologies according to the lithology of the rock sample and the signal characteristic parameter of the corresponding vibration signal sample, and establishing a probability distribution relationship model between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit based on the probability distribution.

4. The method of claim 3, wherein, The step of determining a probability distribution of the signal characteristic parameter of the vibration signal corresponding to different lithologies according to the lithology of the rock sample and the signal characteristic parameter of the corresponding vibration signal sample, and establishing a probability distribution relationship model describing a relationship between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit based on the probability distribution comprises: determining a Gaussian probability distribution of the signal characteristic parameter of the vibration signal corresponding to different lithologies based on the lithology of the rock sample and the signal characteristic parameter of the corresponding vibration signal sample, and establishing a Gaussian mixed probability model describing a relationship between the rock lithology of the work area and the signal characteristic parameter of the vibration signal of the drill bit.

5. A lithology identification device based on a vibration signal, characterized by, The method comprises the following steps: The sample acquisition module is configured to acquire a vibration signal sample when a rock sample in a drilling area is drilled by a drill bit and extract a signal feature parameter from the vibration signal sample. The relationship determination module is configured to determine a probabilistic distribution relationship model between rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit by analyzing a corresponding relationship between the rock lithology of the rock sample and the signal feature parameter of the vibration signal sample. The signal acquisition module is configured to acquire a vibration signal generated when a rock is broken by the drill bit during drilling in the drilling area and extract a signal feature parameter from the vibration signal, wherein the signal feature parameter includes a log energy of the signal and a log energy of the signal after filtering, and the log energy of the signal after filtering is obtained by using a triangular filter as a filter group. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. wherein, is the prior lithology information; is the posterior probability density of lithology; is the prior probability density of lithology; is a normalization factor; is a Gaussian-type likelihood function, representing the probability that the data is when the parameters are represents a signal feature parameter; is a lithology parameter; is a covariance matrix of data measurement error; is a relationship function between the lithology parameter and the signal feature parameter;​ The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit.

6. A lithology identification system based on a vibration signal, characterized by, The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit.

7. A computer storage medium, characterized in that The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of a formation in the drilling area drilled by the drill bit according to the signal feature parameter of the vibration signal and the probabilistic distribution relationship model between the rock lithology in the drilling area and the signal feature parameter of the vibration signal of the drill bit. The lithology identification module is configured to infer the lithology of

Images