Multi-domain small-scale fracture identification method based on probabilistic neural network and related equipment

Abstract

The invention discloses a multi-domain small-scale fracture identification method based on a probabilistic neural network, and the method comprises the steps: carrying out the edge detection of the three-instant attributes of a seismic record, fully mining the fracture information of the attributes, such as amplitude, frequency, phase, and the like, and carrying out the multi-domain small-scale fracture optimization and detection through employing the probabilistic neural network technology. And finally, accurate identification of the small-scale fracture is completed. According to the innovation, the working speed and quality of small-scale fracture recognition are improved, the accuracy and credibility of small fracture prediction are enhanced, an important basis is provided for combination of geological and seismic data, and a good foundation is laid for subsequent seismic comprehensive interpretation, oil and gas reservoir dynamic and static characteristic analysis, oil and gas reservoir development scheme adjustment and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of comprehensive seismic interpretation, and specifically relates to a multi-domain small-scale fault identification method based on a probabilistic neural network and related equipment. Background Art

[0002] Faults are not only the seepage system of low-permeability reservoirs, but also important places for the enrichment and storage of oil and gas. The precise identification of small-scale fault systems is one of the important research contents in the exploration and development of complex oil and gas reservoirs. Small-scale fault systems are relatively small in scale and difficult to identify and predict, which is a global research problem. Carrying out the identification of small and micro-fault systems and accurately predicting the spatial distribution of faults are important for improving the success rate of exploration and the efficiency of oil and gas reservoir development.

[0003] There are many commonly used fault prediction methods in the industry, including 3D seismic attribute prediction technology based on post-stack attributes, multi-wave and multi-component prediction technology based on shear wave splitting phenomenon, and P-wave azimuthal anisotropy prediction technology based on P-wave kinematics and dynamics. However, these methods have problems such as large computational complexity, low resolution and accuracy in small-scale fault prediction, fuzzy fault strike and dip, and great noise influence, which cannot provide strong support for oil and gas exploration and development. In recent years, fault identification technology based on deep learning has developed rapidly. Through convolutional neural networks, probabilistic neural networks, residual neural networks and other methods, it can extract information such as medium- and large-scale fault planes and fault strikes, and realize automatic identification and interpretation of faults. Summary of the invention

[0004] The present invention provides a multi-domain small-scale fracture identification method and related equipment based on a probabilistic neural network, which solves the problems of existing methods such as large computational complexity, low resolution and accuracy in predicting small-scale fractures, fuzzy fracture orientation and inclination, and great influence of noise, and is unable to provide strong support for oil and gas exploration and development.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The multi-domain small-scale fracture identification method based on probabilistic neural network has the following characteristics:

[0007] Transform the earthquake record data to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake;

[0008] The instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake are subjected to edge detection to obtain multi-domain fault information;

[0009] The multi-domain fracture information is input into the trained multi-domain small-scale fracture identification model to obtain the fracture data volume.

[0010] Preferably, the process of acquiring the multi-domain small-scale fracture identification model is as follows:

[0011] Randomly generate fault models with different lengths, dips, fault throws, and seismic noise levels that conform to the actual conditions of the work area;

[0012] Obtain earthquake records based on the fault model;

[0013] Transform the seismic records to obtain instantaneous amplitude, instantaneous phase and instantaneous frequency attributes, and obtain various information of the seismic records in the time domain and frequency domain;

[0014] The lateral variation information is obtained from the instantaneous amplitude, instantaneous phase and instantaneous frequency attributes to characterize the fracture;

[0015] The instantaneous amplitude, instantaneous phase and instantaneous frequency attributes of edge detection are used as training data, and the forward fracture model is used as the label, of which 70% is set as the training set and 30% is set as the validation set. The neural network model is used for training. When the accuracy of the validation set reaches 90%, the training is completed.

[0016] Preferably, the neural network model adopts a probabilistic neural network.

[0017] Preferably, Hilbert transform is used to obtain instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake.

[0018] Preferably, the specific process of using Hilbert transform to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake is: firstly transforming the earthquake record into an analytical signal, and then defining the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake through the analytical signal;

[0019] The transformation formula is:

[0020] s(t)=s r (t)+js i (t),

[0021] where s i (t),s r (t) is the result after Hilbert transformation;

[0022] The definition formula of the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquakes defined by analytical signals is:

[0023]

[0024]

[0025]

[0026] Among them, A i (t),ψ i (t), f i(t) represents the instantaneous amplitude, instantaneous phase, and instantaneous frequency respectively.

[0027] Preferably, the Canny edge detection algorithm is used to obtain the lateral change information from the instantaneous amplitude, instantaneous phase and instantaneous frequency attributes.

[0028] Preferably, the specific method for obtaining the seismic record according to the fault model is to perform a convolution operation on the generated fault model and the seismic wavelet of the work area to obtain a synthetic seismic record.

[0029] The multi-domain small-scale fracture identification system based on probabilistic neural network includes:

[0030] Transformation module: transforms the earthquake record data to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake;

[0031] Detection module: The instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake are subjected to edge detection to obtain multi-domain fracture information;

[0032] Identification module: Input the multi-domain fracture information into the trained multi-domain small-scale fracture identification model to obtain the fracture data volume.

[0033] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the multi-domain small-scale fracture identification method based on a probabilistic neural network are implemented.

[0034] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the multi-domain small-scale fracture identification method based on a probabilistic neural network.

[0035] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a multi-domain small-scale fault identification method based on probabilistic neural network, which fully mines the fault information of attributes such as amplitude, frequency, and phase by performing edge detection on the "three instant" attributes of seismic records, and then uses probabilistic neural network technology to optimize and detect multi-domain small-scale faults, and finally completes the accurate identification of small-scale faults. This innovation improves the speed and quality of small-scale fault identification, enhances the accuracy and credibility of micro-fault prediction, provides an important basis for the combination of geological and seismic data, and lays a good foundation for subsequent comprehensive earthquake interpretation, dynamic and static characteristics analysis of oil and gas reservoirs, and adjustment of oil and gas reservoir development plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of the multi-domain small-scale fracture identification method based on probabilistic neural network of the present invention;

[0037] Figure 2 It is a block diagram of the multi-domain small-scale fracture identification system based on probabilistic neural network of the present invention;

[0038] Figure 3 This is a flow chart of the multi-domain small-scale fracture identification technology based on probabilistic neural network in an embodiment of the present invention.

[0039] Figure 4 It is a comparison chart between synthetic seismic records and “three moments” attributes.

[0040] Figure 5 It is a fracture information graph of edge detection with “three moments” attributes.

[0041] Figure 6 This is the result map of multi-domain small-scale fault identification (the light color is the seismic discontinuity detection body, which represents the fault development area), where a is the coherence body and seismic superposition map, and b is the small-scale fault detection body and seismic superposition map of this method. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0043] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0045] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0046] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0047] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0048] like Figure 1 As shown, the present invention provides a multi-domain small-scale fracture identification method based on probabilistic neural network, comprising:

[0049] S101 transforms the earthquake record data to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake;

[0050] S102 performs edge detection on the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake to obtain multi-domain fault information;

[0051] S103 inputs the multi-domain fracture information into the trained multi-domain small-scale fracture recognition model to obtain a fracture data volume.

[0052] The process of obtaining the multi-domain small-scale fracture identification model is as follows:

[0053] Randomly generate fault models with different lengths, dips, fault throws, and seismic noise levels that conform to the actual conditions of the work area;

[0054] Obtain earthquake records based on the fault model;

[0055] Transform the seismic records to obtain instantaneous amplitude, instantaneous phase and instantaneous frequency attributes, and obtain various information of the seismic records in the time domain and frequency domain;

[0056] The lateral variation information is obtained from the instantaneous amplitude, instantaneous phase and instantaneous frequency attributes to characterize the fracture;

[0057] The instantaneous amplitude, instantaneous phase and instantaneous frequency attributes of edge detection are used as training data, and the forward fracture model is used as the label, of which 70% is set as the training set and 30% is set as the validation set. The neural network model is used for training. When the accuracy of the validation set reaches 90%, the training is completed.

[0058] The neural network model adopts a probabilistic neural network.

[0059] Hilbert transform is used to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake.

[0060] The specific process of using Hilbert transform to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake is as follows: firstly, the earthquake record is transformed into an analytical signal, and then the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake are defined by the analytical signal;

[0061] The transformation formula is:

[0062] s(t)=s r (t)+js i (t),

[0063] where s i (t),s r (t) is the result after Hilbert transformation;

[0064] The definition formula of the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquakes defined by analytical signals is:

[0065]

[0066]

[0067]

[0068] Among them, A i (t),ψ i (t), f i (t) represents the instantaneous amplitude, instantaneous phase, and instantaneous frequency respectively.

[0069] The Canny edge detection algorithm is used to obtain the lateral change information from the instantaneous amplitude, instantaneous phase and instantaneous frequency attributes.

[0070] The specific method for obtaining seismic records based on the fault model is to perform a convolution operation on the generated fault model and the seismic wavelet of the work area to obtain a synthetic seismic record.

[0071] Another embodiment of the present invention provides a multi-domain small-scale fracture identification method based on a probabilistic neural network, such as Figure 3 As shown:

[0072] Step 1: Randomly generate fault models with different lengths, dips, fault throws, and seismic noise levels that conform to the actual conditions of the work area;

[0073] Step 2: Convolve the generated fault model with the seismic wavelet of the work area to obtain a synthetic seismic record;

[0074] Step 3: Perform Hilbert transform on the seismic records to obtain the "three instantaneous" attributes (i.e., instantaneous amplitude, instantaneous phase, and instantaneous frequency) to obtain a variety of information about the seismic records in the time domain and frequency domain.

[0075] Suppose the input signal is s(t), and the result after Hilbert transform is s i (t),s r (t), the corresponding analytical signal is:

[0076] s(t)=s r (t)+js i (t), (1)

[0077] The "three instant" properties can be defined by analyzing the signal as follows:

[0078]

[0079] Among them, A i (t),ψ i (t), f i (t) represents the instantaneous amplitude, instantaneous phase, and instantaneous frequency respectively.

[0080] Step 4: Use the Canny edge detection algorithm on the "three-moment" attributes to obtain the lateral change information to characterize the fracture;

[0081]

[0082] Among them, G(x,y) and Θ(x,y) represent the magnitude and direction of the gradient.

[0083] Step 5: Use the "three-moment" attributes of edge detection as training data and the forward fracture model as labels, 70% of which are set as training sets and 30% as validation sets. Use probabilistic neural networks for training. When the accuracy of the validation set reaches 90%, the training is completed.

[0084] Probabilistic neural network (PNN) is a branch of radial basis network, which is often used for pattern classification. It integrates density function estimation and Bayesian decision theory into traditional radial basis network, with simple training process and fast convergence.

[0085] Probabilistic neural network (PNN) is a neural network model based on statistical principles. Its essence is a parallel algorithm developed based on the Bayesian minimum risk criterion and is a completely forward calculation process. It has a short training time, is not easy to produce local optimality, and has a high classification accuracy. No matter how complex the classification problem is, as long as there is enough training data, it can be guaranteed to obtain the optimal solution under the Bayesian criterion. Therefore, this paper uses probabilistic neural network to perform intelligent optimization of three-dimensional spatial morphology and reduce the multiple solutions of micro-fracture identification.

[0086]

[0087] Among them, p is the probability matrix of fracture, and R is the matrix related to fracture direction.

[0088] Step 6: Process the actual earthquake record data in steps 3 and 4, and use it as input to identify the tiny faults in the work area using the trained probabilistic neural network, and finely characterize their distribution characteristics such as location, length, dip, fault distance, etc., to achieve the purpose of small-scale fault identification.

[0089] 1. Figure 3 This is a flowchart of multi-domain small-scale fault identification technology based on probabilistic neural network. This method mainly uses multi-domain attribute edge detection and probabilistic neural network to identify small-scale faults. First, the fault model established by forward modeling is used to synthesize seismic records and calculate their "three instant" attributes to obtain various information of seismic records in time domain and frequency domain. Then, the Canny edge detection algorithm is used for the "three instant" attributes to obtain the fault information. Finally, the probabilistic neural network is used to identify the small faults in the work area and finely characterize the distribution characteristics of small-scale faults.

[0090] 2. Figure 4 This is a comparison chart between synthetic seismic records and the "three instant" attributes. The instantaneous amplitude and instantaneous phase are less affected by noise and can better reflect the characteristics of the fault in the seismic record. The instantaneous frequency is greatly affected by noise and has a poor effect in characterizing the fault.

[0091] 3. Figure 5 It is the result of fault identification with different attributes. The "three instants" attributes can generally better reflect the characteristics of faults in earthquake records, and contain multi-domain (time domain and frequency domain) information, which expands the amount of fault information in earthquake records and can better mine the details of small-scale faults. Compared with the fault information of the "three instants" attributes, the multi-domain small-scale fault identification result map has higher fault accuracy, the details of the fault become clear and continuous, the noise is effectively suppressed, and the spatial distribution is more real and natural, laying a good foundation for the prediction of small-scale cracks.

[0092] 4. Figure 6 This is a comparison chart of the seismic identification results of small-scale faults in the actual work area. Compared with the traditional post-stack coherence body fault identification technology, the new technology has higher accuracy in identifying small-scale faults, clearer and more continuous details, and the new technology is significantly better than the traditional coherence body technology in identifying small and micro-scale faults.

[0093] like Figure 2 As shown, the present invention also provides a multi-domain small-scale fracture identification system based on probabilistic neural network, which is characterized by comprising:

[0094] Transformation module: transforms the earthquake record data to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake;

[0095] Detection module: The instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake are subjected to edge detection to obtain multi-domain fracture information;

[0096] Identification module: Input the multi-domain fracture information into the trained multi-domain small-scale fracture identification model to obtain the fracture data volume.

[0097] A terminal device is provided in one embodiment of the present invention. The terminal device of this embodiment includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0098] The computer program may be divided into one or more modules / units, and the one or more modules / units are stored in the memory and executed by the processor to accomplish the present invention.

[0099] The terminal device may be a computing device such as a desktop computer, a notebook, a palmtop computer, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0100] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0101] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0102] If the module / unit integrated in the terminal device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0103] Although the embodiments of the present invention are described above in conjunction with the accompanying drawings, the present invention is not limited to the above-mentioned specific embodiments and application fields, and the above-mentioned specific embodiments are only illustrative and instructive, rather than restrictive. Under the guidance of the specification, a person skilled in the art can also make many forms without departing from the scope of protection of the claims of the present invention, all of which belong to the scope of protection of the present invention.

Claims

1. A multi-domain small-scale fracture identification method based on probabilistic neural network, which has the following characteristics: Transform the earthquake record data to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake; The instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake are subjected to edge detection to obtain multi-domain fault information; The multi-domain fracture information is input into the trained multi-domain small-scale fracture identification model to obtain the fracture data volume.

2. The multi-domain small-scale fracture identification method based on probabilistic neural network according to claim 1 is characterized in that: The process of obtaining the multi-domain small-scale fracture identification model is as follows: Randomly generate fault models of different lengths, dips, fault throws, and seismic noise levels that are in line with the actual conditions of the work area; Obtain earthquake records based on the fault model; Transform the seismic records to obtain instantaneous amplitude, instantaneous phase and instantaneous frequency attributes, and obtain various information of the seismic records in the time domain and frequency domain; The lateral variation information is obtained from the instantaneous amplitude, instantaneous phase and instantaneous frequency attributes to characterize the fracture; The instantaneous amplitude, instantaneous phase and instantaneous frequency attributes of edge detection are used as training data, and the forward fracture model is used as the label, of which 70% is set as the training set and 30% is set as the validation set. The neural network model is used for training. When the accuracy of the validation set reaches 90%, the training is completed.

3. The multi-domain small-scale fracture identification method based on probabilistic neural network according to claim 2 is characterized in that: The neural network model adopts a probabilistic neural network.

4. The multi-domain small-scale fracture identification method based on probabilistic neural network according to claim 2 is characterized in that: Hilbert transform is used to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake.

5. The multi-domain small-scale fracture identification method based on probabilistic neural network according to claim 4 is characterized in that: The specific process of using Hilbert transform to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake is as follows: firstly, the earthquake record is transformed into an analytical signal, and then the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquake are defined by the analytical signal; The transformation formula is: s(t)=s r (t)+js i (t), where s i (t),s r (t) is the result after Hilbert transformation; The definition formula of the instantaneous amplitude, instantaneous phase and instantaneous frequency data of earthquakes defined by analytical signals is: Among them, A i (t),ψ i (t), f i (t) represents the instantaneous amplitude, instantaneous phase, and instantaneous frequency respectively.

6. The multi-domain small-scale fracture identification method based on probabilistic neural network according to claim 2 is characterized in that: The Canny edge detection algorithm is used to obtain the lateral change information from the instantaneous amplitude, instantaneous phase and instantaneous frequency attributes.

7. The multi-domain small-scale fracture identification method based on probabilistic neural network according to claim 2 is characterized in that: The specific method for obtaining seismic records based on the fault model is to perform a convolution operation on the generated fault model and the seismic wavelet of the work area to obtain a synthetic seismic record.

8. A multi-domain small-scale fracture identification system based on probabilistic neural network, characterized by: include: Transformation module: transforms the earthquake record data to obtain the instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake; Detection module: The instantaneous amplitude, instantaneous phase and instantaneous frequency data of the earthquake are subjected to edge detection to obtain multi-domain fracture information; Identification module: Input the multi-domain fracture information into the trained multi-domain small-scale fracture identification model to obtain the fracture data volume.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the multi-domain small-scale fracture identification method based on probabilistic neural network as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the multi-domain small-scale fracture identification method based on a probabilistic neural network as claimed in any one of claims 1 to 7 are implemented.

Images