Exploration model generation method, device and system based on intrinsic characteristics and prospecting method, device and system based on intrinsic characteristics

Abstract

The invention provides a prospecting model generation and prospecting method, device and system based on intrinsic characteristics, and belongs to the technical field of mineral resource exploration, and the method comprises the steps: obtaining vibration signals which are collected by an optical resonance type acousto-optic sensor and are fed back after vibration excitation is applied to mineral resources with different characteristics, and the characteristics comprise types, grades, structures and reserves; performing iterative training on an initial model by taking a machine learning algorithm as the initial model, taking the vibration signal as input and taking different features as output; and outputting the completely trained initial model as a final prospecting model. The technical problem that underground deep mineral resource information is difficult to accurately obtain in the prior art is effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of mineral exploration, and in particular to a prospecting model generation based on intrinsic characteristics and a prospecting method, device and system. Background Art

[0002] Traditional prospecting techniques include geological surveys, geophysical surveys, and geochemical surveys. Geological surveys primarily rely on observing and analyzing geological features such as surface rocks, strata, and structures to infer the presence of potential mineral deposits underground. However, this method has limited ability to detect deep deposits and relies on the experience and expertise of geologists.

[0003] Geophysical prospecting uses changes in geophysical fields to search for underground mineral deposits, such as gravity prospecting, magnetic prospecting, and electrical prospecting. These methods infer underground geological structure and mineral distribution by measuring anomalies in the geophysical field, but they are often limited by geological conditions, are ineffective in detecting mineral deposits in complex geological environments, and cannot accurately distinguish between different types of mineral deposits. Geochemical prospecting analyzes the chemical composition of media such as soil, rock, and water to search for geochemical anomalies associated with mineral deposits. However, this method has a limited sampling range and is easily affected by the surface environment and human activities, resulting in reduced data accuracy and reliability.

[0004] With the development of science and technology, some new prospecting technologies have gradually emerged, such as remote sensing technology and drone exploration. These technologies can quickly obtain geological information over a large area, but it is still difficult to accurately obtain information about mineral deposits deep underground. Summary of the Invention

[0005] In view of this, it is necessary to provide a prospecting model generation and prospecting method, device and system based on intrinsic characteristics to solve the technical problem that the existing technology is difficult to accurately obtain deep underground mineral information.

[0006] In order to solve the above technical problems, in a first aspect, the present invention provides a method for generating a prospecting model based on intrinsic characteristics, comprising: Acquiring vibration signals fed back by optical resonance acoustic and optical sensors after applying vibration excitation to mineral deposits with different characteristics, wherein the characteristics include: type, grade, structure, and reserves; Using the classification algorithm as an initial model, and using the vibration signal as input and the different features as output to iteratively train the initial model; The fully trained initial model is output as the final prospecting model for outputting the characteristics of the mineral deposit to be identified based on the vibration signal of the mineral deposit to be identified.

[0007] In some embodiments of the present invention, the step of obtaining vibration signals fed back by optical resonance acousto-optic sensors after applying vibration excitation to mineral deposits with different characteristics includes: sending a control signal to an active transmitting source pre-placed on the surface of the mineral deposit to apply vibration excitation to the mineral deposit; The device receives a vibration signal sent from an optical resonance type acoustic and optical sensor pre-placed on the surface of the mineral deposit.

[0008] In some embodiments of the present invention, before iteratively training the initial model using the vibration signal as input and the different features as output, the method further includes: performing filtering and denoising processing on the vibration signal; Feature extraction is performed on the vibration signal that has been completely filtered and denoised to obtain intrinsic vibration information, wherein the intrinsic vibration information includes: resonance frequency, vibration amplitude, and vibration phase.

[0009] In some embodiments of the present invention, the iterative training of the initial model using the vibration signal as input and the different features as output includes: After the initial model traverses the vibration signal and different features, adjusting the parameters of the initial model based on a cross-validation method; Train the initial state after adjusting the parameters and calculate the loss function value of this round of training; If the loss function value is not greater than a preset threshold and / or the number of iterations reaches a preset maximum number, the iteration stops; otherwise, the parameters of the initial model continue to be adjusted based on the cross-validation method.

[0010] In a second aspect, the present invention further provides a prospecting method based on intrinsic characteristics, comprising: Acquiring a vibration signal fed back by an optical resonance acousto-optic sensor after applying vibration excitation to a target area; Inputting the vibration signal into a prospecting model generated by the prospecting model generation method described in any one of the above methods; Based on the output of the prospecting model, it is determined whether there is a mineral deposit in the target area and the type, grade, structure and reserves of the mineral deposit.

[0011] In some embodiments of the present invention, before inputting the vibration signal into the prospecting model, the method further includes: performing filtering and denoising processing on the vibration signal; Feature extraction is performed on the vibration signal that has been completely filtered and denoised to obtain intrinsic vibration information, wherein the intrinsic vibration information includes: resonance frequency, vibration amplitude, and vibration phase.

[0012] In a third aspect, the present invention further provides a device for generating a prospecting model based on intrinsic characteristics, comprising: A data acquisition module is used to acquire vibration signals fed back by optical resonance acoustic and optical sensors after applying vibration excitation to mineral deposits with different characteristics, wherein the characteristics include: type, grade, structure and reserves; a model training module, configured to use the classification algorithm as an initial model, the vibration signal as input, and the different features as output to iteratively train the initial model; The model output module is used to output the fully trained initial model as the final prospecting model for outputting the characteristics of the mineral deposit to be identified based on the vibration signal of the mineral deposit to be identified.

[0013] In a fourth aspect, the present invention further provides a prospecting model generation system based on intrinsic characteristics, comprising: A prospecting model generating device as described in any one of the above device items; Active emission sources and optical resonance acousto-optic sensors; Wherein, the active emission source and the optical resonance type acoustic and optical sensor are both placed on the surface of the mineral deposit, and the active emission source and the optical resonance type acoustic and optical sensor are both communicatively connected to the prospecting model generating device.

[0014] The beneficial effects of the present invention are: the present invention provides a method for generating a prospecting model based on intrinsic characteristics. First, the present invention obtains vibration signals through optical resonance acousto-optic sensors with weak sound signal detection capabilities, noise suppression capabilities in complex environments, and characteristic signal identification capabilities, and can effectively collect high-quality deep mineral vibration signals, reducing the impact of environmental factors on detection results from the signal source; secondly, the present invention inputs the obtained vibration signals and their corresponding mineral characteristics into a machine learning algorithm for training, and extracts the mapping relationship between the deep mineral vibration signals and characteristics through the machine learning algorithm, and then establishes a prospecting model that can identify minerals with different characteristics deep underground according to vibration signals, effectively solving the technical problem that the existing technology is difficult to accurately obtain deep underground mineral information. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic flow chart of an embodiment of a method for generating a prospecting model based on intrinsic characteristics provided by the present invention; Figure 2 for Figure 1 A flow chart of an embodiment of step S101; Figure 3 for Figure 1 A flow chart of an embodiment of step S104; Figure 4 A schematic flow chart of an embodiment of a prospecting method based on intrinsic characteristics provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of a device for generating a prospecting model based on intrinsic characteristics provided by the present invention; Figure 6 A schematic structural diagram of an embodiment of a system for generating a prospecting model based on intrinsic characteristics provided by the present invention; Figure 7 This is a structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0018] In the description of the embodiments of the present invention, unless otherwise specified, "plurality" means two or more. "And / or" describes the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone.

[0019] The terms "first," "second," and so on, used in the embodiments of the present invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, technical features designated as "first" or "second" may explicitly or implicitly include at least one such feature.

[0020] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0021] The present invention provides a prospecting model generation based on intrinsic characteristics and a prospecting method, device and system, which are respectively described below.

[0022] Figure 1 A schematic flow chart of an embodiment of the method for generating a prospecting model provided by the present invention is shown as follows: Figure 1 As shown in FIG, the method for generating a prospecting model includes: S101. Obtain vibration signals fed back by optical resonance acousto-optic sensors after applying vibration excitation to mineral deposits with different characteristics.

[0023] Among them, the characteristics include: type, grade, structure and reserves.

[0024] It should be noted that the present invention uses an optical resonance acousto-optic sensor because the sensor has the following advantages: (1) It has the ability to detect weak acoustic signals and can accurately detect weak vibration signals of mineral deposits in complex environments; (2) It has noise suppression capability, which can effectively reduce the interference of external noise and improve the quality of the signal; (3) It has the ability to identify characteristic signals and can accurately identify the intrinsic vibration signals of mineral deposits.

[0025] like Figure 2 Specifically, in some embodiments of the present invention, step S101 includes: S201 : Send a control signal to an active transmitting source pre-placed on the surface of a mineral deposit to apply vibration excitation to the mineral deposit.

[0026] It should be understood that in step S201 , the characteristic information of the mineral deposit to which the stimulus is applied is already known.

[0027] S202: Receive a vibration signal sent from an optical resonance type acousto-optic sensor pre-placed on the surface of the mine.

[0028] Ideally, when placing sensors, choose an area with flat terrain, no obvious obstacles, and stable geological structures. Use specialized positioning equipment to determine the sensor installation location, ensuring that the spacing between sensors is uniform and meets design requirements. During installation, secure the sensors to a custom-made base to ensure good contact with the ground to improve signal acquisition sensitivity.

[0029] In a specific embodiment, two mining scenarios are mainly set up to obtain representative training data, including: (1) Large outdoor laboratories: For example, minerals of the desired type (hematite, magnetite, copper ore, etc.), grade, volume, and specific shape are arranged at a certain distance to avoid mutual interference, buried at a specific depth (1m, 3m, 5m, etc.), and classified, numbered, and recorded in detail. A high-precision vibration test platform is used to apply vibration excitation of different frequencies and amplitudes to each sample. The vibration response of the sample is measured using equipment such as optical resonance acoustic and optical sensors, and parameters such as the sample's intrinsic resonance frequency, vibration amplitude, and vibration attenuation phase are recorded. Each sample is tested multiple times, and the average value is taken to improve the accuracy of the data. The test data is stored in a database to provide data support for subsequent analysis.

[0030] (2) Known mineral deposits: Use a vibration signal transmitter to set appropriate vibration signal parameters based on the geological conditions and exploration requirements of the known mineral deposits. For example, for deep mineral deposits, the amplitude and duration of the vibration signal can be appropriately increased to ensure that the signal can effectively propagate to the mineral deposit location. The transmitter transmits the vibration signal through a transmitting probe on the ground or underground. The optical resonance type acoustic and optical sensor collects the vibration signal in real time and converts the collected analog signal into a digital signal. The digital signal is transmitted to the data acquisition terminal via a data line. The data acquisition terminal performs preliminary amplification, filtering and other processing on the signal, and stores the processed data on the hard disk for subsequent analysis.

[0031] Since the initial signal obtained by the sensor contains noise, it will affect the training effect of the model. In addition, the training data actually used in the process of training the model are the characteristic parameters in the signal. Therefore, it is necessary to perform feature extraction processing on the vibration signal to better train the model. To this end, the present invention also includes the following steps: S102: Filter and denoise the vibration signal.

[0032] Preferably, first, a low-pass filter is used to remove high-frequency noise in the signal, and a high-pass filter is used to remove low-frequency interference. Then, an adaptive filtering algorithm is used to further reduce the impact of the noise.

[0033] S103 , performing feature extraction on the vibration signal that has undergone filtering and denoising to obtain intrinsic vibration information.

[0034] Preferably, the signal spectrum is analyzed using algorithms such as the Fast Fourier Transform (FFT) to extract its frequency components. By analyzing these frequency components, characteristic parameters such as the mineral's intrinsic resonance frequency are determined. Simultaneously, other characteristic parameters, such as the amplitude ratio of the characteristic frequencies, are calculated to provide more feature information for establishing the mapping relationship.

[0035] The intrinsic vibration information includes: resonance frequency, vibration amplitude and vibration phase.

[0036] After filtering out the noise influence and extracting the feature parameters that can be directly used for training, the present invention further includes: S104: Using the classification algorithm as the initial model, and using the vibration signal as input and different features as output, the initial model is iteratively trained.

[0037] It should be understood that the main function of step S104 is to extract the mapping relationship between the features and the vibration signals, and to train a model based on the mapping relationship to predict the corresponding mineral features according to the vibration signals.

[0038] Preferably, a machine learning software platform is used, along with an appropriate classification algorithm, such as a support vector machine (SVM). The SVM algorithm is trained using characteristic parameters of known mineral deposits as input data and corresponding information such as category, grade, structure, and reserves as output data. During training, the model is optimized using methods such as cross-validation, adjusting model parameters to improve accuracy and generalization. After multiple rounds of training and optimization, an accurate mapping model is obtained.

[0039] like Figure 3 In some embodiments of the present invention, step S104 includes: S301. After the initial model traverses the vibration signal and different features, the parameters of the initial model are adjusted based on a cross-validation method.

[0040] S302: Perform training on the initial state after adjusting the parameters, and calculate the loss function value of this round of training.

[0041] S303: If the loss function value is not greater than a preset threshold and / or the number of iterations reaches a preset maximum number, the iteration stops; otherwise, the parameters of the initial model continue to be adjusted based on the cross-validation method.

[0042] S105 , outputting the fully trained initial model as the final prospecting model for outputting the characteristics of the mineral deposit to be identified based on the vibration signal of the mineral deposit to be identified.

[0043] Compared with the existing technology, the present invention provides a method for generating a prospecting model based on intrinsic characteristics. First, the present invention obtains vibration signals through optical resonance acousto-optic sensors with the ability to detect weak sound signals, suppress noise in complex environments, and identify characteristic signals. It can effectively collect high-quality vibration signals of deep mineral deposits and reduce the impact of environmental factors on detection results from the signal source; secondly, the present invention inputs the obtained vibration signals and their corresponding mineral deposit characteristics into a machine learning algorithm for training, and extracts the mapping relationship between the vibration signals and characteristics of deep mineral deposits through the machine learning algorithm, and then establishes a prospecting model that can identify mineral deposits with different characteristics deep underground according to vibration signals, effectively solving the technical problem that the existing technology is difficult to accurately obtain deep underground mineral deposit information.

[0044] like Figure 4 In a second aspect, the present invention further provides a prospecting method based on intrinsic characteristics, comprising: S401: Acquire a vibration signal fed back by an optical resonance acousto-optic sensor after applying vibration excitation to a target area.

[0045] It should be understood that in step S401, the mineral deposit information in the target area is unknown. In this unknown area, optical resonance-type acoustic and optical sensors should be deployed and active-source vibration signals should be emitted in the same manner as in known areas. After collecting the vibration response signals, the same signal processing and feature extraction as in known areas should be performed.

[0046] S402: Filter and denoise the vibration signal.

[0047] S403 : performing feature extraction on the vibration signal that has undergone filtering and denoising to obtain intrinsic vibration information.

[0048] The intrinsic vibration information includes: resonance frequency, vibration amplitude and vibration phase.

[0049] S404: Input the vibration signal into the prospecting model.

[0050] S405: Determine whether there are mineral deposits in the target area and the type, grade, structure and reserves of the mineral deposits based on the output of the prospecting model.

[0051] like Figure 5 In a third aspect, the present invention further provides a prospecting model generating device 50, comprising: The data acquisition module 510 is used to acquire vibration signals fed back by optical resonance acoustic and optical sensors after applying vibration excitation to mineral deposits with different characteristics, wherein the characteristics include type, grade, structure and reserves; The model training module 520 is used to iteratively train the initial model using the classification algorithm as the initial model, the vibration signal as the input, and different features as the output; The model output module 530 is used to output the trained initial model as the final prospecting model for outputting the characteristics of the mineral deposit to be identified based on the vibration signal of the mineral deposit to be identified.

[0052] like Figure 6 In a fourth aspect, the present invention further provides a prospecting model generation system 60, comprising: The prospecting model generating device 50 as described in any one of the above device items; Active emission source 610 and optical resonance type acousto-optic sensor 620; The active emission source 610 and the optical resonance type acoustic and optical sensors 620 are both placed on the surface of the mine, and the active emission source 610 and the plurality of optical resonance type acoustic and optical sensors 620 are both communicatively connected to the prospecting model generating device 50 .

[0053] Those skilled in the art will appreciate that all or part of the process flow of the above-described method embodiment can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0054] The above is a detailed introduction to the generation of prospecting models based on intrinsic characteristics and the prospecting method, device and system provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for generating a prospecting model based on intrinsic characteristics, characterized in that: include: Acquiring vibration signals fed back by optical resonance acoustic and optical sensors after applying vibration excitation to mineral deposits with different characteristics, wherein the characteristics include: type, grade, structure, and reserves; Using the classification algorithm as an initial model, and using the vibration signal as input and the different features as output to iteratively train the initial model; The fully trained initial model is output as the final prospecting model for outputting the characteristics of the mineral deposit to be identified based on the vibration signal of the mineral deposit to be identified.

2. The method for generating a prospecting model according to claim 1, wherein: The method of obtaining vibration signals fed back by optical resonance acousto-optic sensors after applying vibration excitation to mineral deposits with different characteristics includes: sending a control signal to an active transmitting source pre-placed on the surface of the mineral deposit to apply vibration excitation to the mineral deposit; The device receives a vibration signal sent from an optical resonance type acoustic and optical sensor pre-placed on the surface of the mineral deposit.

3. The method for generating a prospecting model according to claim 1, wherein: Before iteratively training the initial model using the vibration signal as input and the different features as output, the method further includes: performing filtering and denoising processing on the vibration signal; Feature extraction is performed on the vibration signal that has been completely filtered and denoised to obtain intrinsic vibration information, wherein the intrinsic vibration information includes: resonance frequency, vibration amplitude, and vibration phase.

4. The method for generating a prospecting model according to claim 1, wherein: The iterative training of the initial model using the vibration signal as input and the different features as output includes: After the initial model traverses the vibration signal and different features, adjusting the parameters of the initial model based on a cross-validation method; Train the initial state after adjusting the parameters and calculate the loss function value of this round of training; If the loss function value is not greater than a preset threshold and / or the number of iterations reaches a preset maximum number, the iteration stops; otherwise, the parameters of the initial model continue to be adjusted based on the cross-validation method.

5. A prospecting method based on intrinsic characteristics, characterized in that: include: Acquiring a vibration signal fed back by an optical resonance acousto-optic sensor after applying vibration excitation to a target area; Inputting the vibration signal into a prospecting model generated by the method for generating a prospecting model based on intrinsic characteristics according to any one of claims 1 to 4; Based on the output of the prospecting model, it is determined whether there is a mineral deposit in the target area and the type, grade, structure and reserves of the mineral deposit.

6. The prospecting method based on intrinsic characteristics according to claim 4, characterized in that: Before inputting the vibration signal into the prospecting model, the method further includes: performing filtering and denoising processing on the vibration signal; Feature extraction is performed on the vibration signal that has been completely filtered and denoised to obtain intrinsic vibration information, wherein the intrinsic vibration information includes: resonance frequency, vibration amplitude, and vibration phase.

7. A device for generating a prospecting model based on intrinsic characteristics, characterized in that: include: A data acquisition module is used to acquire vibration signals fed back by optical resonance acoustic and optical sensors after applying vibration excitation to mineral deposits with different characteristics, wherein the characteristics include: type, grade, structure and reserves; a model training module, configured to use the classification algorithm as an initial model, the vibration signal as input, and the different features as output to iteratively train the initial model; The model output module is used to output the trained initial model as the final prospecting model for outputting the characteristics of the mineral deposit to be identified based on the vibration signal of the mineral deposit to be identified.

8. A prospecting model generation system based on intrinsic characteristics, characterized in that: include: The device for generating a prospecting model based on intrinsic characteristics as claimed in claim 7; Active emission sources and optical resonance acousto-optic sensors; Wherein, the active emission source and the optical resonance type acoustic and optical sensor are both placed on the surface of the mineral deposit, and the active emission source and the optical resonance type acoustic and optical sensor are both communicatively connected to the prospecting model generating device.

Images