Quantitative analysis method and system for in-situ leaching uranium mining flow field

Abstract

The invention provides a quantitative analysis method and system for an in-situ leaching uranium mining flow field. According to the method, the historical flow and pressure time sequence data of the liquid injection pipeline are collected, the flow pressure matrix reflecting the working state of the liquid injection pump is constructed, and the resonance frequency band energy characteristics are extracted to generate the pump health assessment map. Fluid scattering signals are synchronously collected and converted into a three-dimensional flow velocity vector diagram, fluid acoustic impedance parameters are calculated in combination with the flow velocity modulus and the direction change rate, and a flow field turbulence thermodynamic diagram is generated. And further dynamically matching the pump health assessment map with the turbulence thermodynamic diagram, calculating a flow field stability index, and generating a liquid injection pump adjusting instruction and a fault early warning report according to a preset risk threshold value and a deviation degree. And through multi-source data fusion and dynamic correlation analysis, real-time monitoring and active regulation and control on the stability of the in-situ leaching uranium mining flow field and the health state of the liquid injection pump are realized. According to the technical scheme, the efficiency and precision of quantitative analysis of the flow field can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of quantitative analysis of flow field, in particular to a quantitative analysis method and system for flow field of in-situ leaching of uranium. BACKGROUND

[0002] During the operation of the in-situ leaching of uranium injection system, mechanical failure of the injection pump may cause abnormal injection flow, pressure fluctuation and imbalance of flow field between the injection and extraction wells, resulting in uneven distribution of leaching agent, decreased dissolution efficiency of uranium ore body and even well site safety accidents. The technical requirement focuses on identifying the imbalance trend of the flow field at the initial stage of mechanical failure, and providing data support for dynamic regulation and control of extraction and injection strategies. The system needs to have the ability to sensitively capture weak mechanical abnormal signals, and at the same time, to analyze the nonlinear relationship between flow field disturbance and mechanical failure.

[0003] The existing scheme for this requirement is an online correction diagnosis system based on physical model and real-time data. This scheme constructs a coupled physical model of the mechanical operation of the injection pump and the underground water flow field, combines real-time monitoring data such as injection pressure, injection and extraction well water level, and formation permeability, and dynamically corrects the model parameters to reflect the current working condition. The system uses the comparison results of the flow field response characteristics output by the model and the actual monitoring data to identify the influence degree of mechanical failure on the flow field. Its core advantage is that it does not need to rely on artificial experience judgment, and can realize quantitative correlation analysis of mechanical abnormalities and flow field imbalance, improving the diagnosis efficiency and accuracy.

[0004] Although this existing scheme can partially meet the real-time diagnosis requirement, it still has significant limitations. The physical model has strong dependence on the formation parameters, and in complex geological conditions, the deviation between the model prediction and the actual flow field may occur, resulting in distorted diagnosis results. The system has a lag in response to sudden mechanical failure, and it is difficult to complete early warning and regulation before the critical point of flow field imbalance, and there is still a risk of pressure imbalance between the injection and extraction wells causing well wall collapse. In addition, the online correction process of the model has high requirements for computing resources, and when deployed in the field, it may be limited by the hardware performance of the edge computing device, affecting the timeliness of diagnosis. SUMMARY

[0005] The present application provides a quantitative analysis method and system for flow field of in-situ leaching of uranium to solve the problems of low efficiency and poor precision in quantitative analysis of flow field in the prior art.

[0006] In a first aspect, the present application provides a quantitative analysis method for flow field of in-situ leaching of uranium, comprising:

[0007] obtaining historical flow data and pressure time series data of the in-situ leaching of uranium injection pipeline, combining the historical flow data and the pressure time series data according to the time dimension to construct a flow pressure matrix reflecting the working state of the injection pump;

[0008] extracting a resonance frequency band energy feature of the liquid injection pump from the flow pressure matrix, and constructing a pump health evaluation atlas according to an intensity distribution of the resonance frequency band energy feature;

[0009] synchronously collecting a fluid scattering signal of the in-situ leaching uranium liquid injection pipeline, and converting the fluid scattering signal into a three-dimensional flow velocity vector diagram reflecting a three-dimensional space flow velocity distribution;

[0010] calculating a fluid acoustic impedance parameter according to a flow velocity vector modulus and a direction change rate of each spatial position in the three-dimensional flow velocity vector diagram, and generating a flow field turbulence thermodynamic map characterizing local turbulence intensity of the flow field based on the fluid acoustic impedance parameter;

[0011] dynamically matching the pump health evaluation atlas and the flow field turbulence thermodynamic map, calculating a stability index of the in-situ leaching uranium flow field, and generating an adjustment instruction set and a fault early warning report of the liquid injection pump according to a deviation degree of the stability index from a preset risk threshold.

[0012] Optionally, the dynamically matching the pump health evaluation atlas and the flow field turbulence thermodynamic map to calculate the stability index of the in-situ leaching uranium flow field comprises:

[0013] aligning a vibration energy time sequence in the pump health evaluation atlas and an intensity time sequence of the flow field turbulence thermodynamic map on a time axis to generate a time alignment data set;

[0014] extracting pump vibration feature values and turbulence intensity data at corresponding time points from the time alignment data set in the in-situ leaching uranium liquid injection pipeline region, and establishing a dynamic transfer relationship between the pump vibration feature values and the turbulence intensity data;

[0015] calculating a conversion proportion value of pump vibration energy and flow field turbulence intensity through the dynamic transfer relationship, and combining the conversion proportion value in time sequence to generate a stability index reflecting a stability degree of the in-situ leaching uranium flow field.

[0016] Optionally, the extracting pump vibration feature values and turbulence intensity data at corresponding time points from the time alignment data set in the in-situ leaching uranium liquid injection pipeline region, and establishing a dynamic transfer relationship between the pump vibration feature values and the turbulence intensity data comprises:

[0017] extracting pump vibration feature values and turbulence intensity data at corresponding time points in the in-situ leaching uranium liquid injection pipeline region from the time alignment data set, and arranging and combining the pump vibration feature values, the turbulence intensity data, and a density parameter of the uranium ore leaching agent in time sequence to generate a time sequence data set;

[0018] Based on the time series data set, an initial correlation between the pump vibration characteristic value and the turbulence intensity data is established, and an initial correlation that matches the direction is screened based on a preset lixiviant fluid motion rule, and the screened initial correlation is superimposed as a dynamic transmission relationship.

[0019] Optionally, a resonance frequency band energy feature of the liquid injection pump is extracted from the flow pressure matrix, and a pump health evaluation atlas is constructed according to the intensity distribution of the resonance frequency band energy feature, including:

[0020] The flow pressure matrix is divided into frequency intervals, and the energy cumulative value of the frequency interval is calculated, and based on the vibration transmission characteristics of the liquid injection pump, the frequency interval with the energy cumulative value exceeding a preset background noise threshold is screened as a target resonance frequency band;

[0021] The peak energy intensity data and the frequency band width data of the target resonance frequency band are extracted as the resonance frequency band energy feature, and the energy attenuation gradient of adjacent target resonance frequency bands is calculated;

[0022] According to the matching relationship between the frequency band width data and the energy attenuation gradient, a pump health evaluation atlas is generated.

[0023] Optionally, according to the flow velocity vector module and the direction change rate of each spatial position in the three-dimensional flow velocity vector diagram, a fluid acoustic impedance parameter is calculated, and a flow field turbulence thermodynamic diagram representing the local turbulence intensity of the flow field is generated based on the fluid acoustic impedance parameter, including:

[0024] The flow velocity vector module and the direction change rate of adjacent time points of each spatial position in the three-dimensional flow velocity vector diagram are obtained, and the density parameter of the uranium ore lixiviant, the flow velocity vector module and the direction change rate are superimposed to generate a fluid acoustic impedance parameter;

[0025] The difference between the fluid acoustic impedance parameter and the preset reference acoustic resistance value is converted into turbulence intensity data, and the turbulence intensity data of adjacent spatial positions is spatially transmitted to generate a turbulence intensity distribution of the liquid injection pipeline cross section;

[0026] Based on the gradient change rate of the turbulence intensity distribution, a flow field turbulence thermodynamic diagram representing the local turbulence intensity of the flow field is constructed.

[0027] Optionally, the fluid scattering signal is converted into a three-dimensional flow velocity vector diagram reflecting the three-dimensional flow velocity distribution, including:

[0028] The frequency offset of each signal acquisition point in the fluid scattering signal is analyzed to obtain signal change data, and based on the propagation characteristics of the signal acquisition acoustic wave in the uranium ore lixiviant, the signal change data is converted into a directional flow velocity component;

[0029] According to the spatial coordinate position of the injection pipeline section, a spatial relationship parameter of adjacent signal collection points is identified, and direction flow velocity components at the same spatial position are combined into a spatial flow velocity vector according to the spatial relationship parameter;

[0030] The injection pipeline section is divided into spatial grids, and the spatial flow velocity vector is associated and mapped with the spatial grids to generate a three-dimensional flow velocity vector diagram.

[0031] Optionally, according to a deviation degree of a preset risk threshold and the stability index, a set of adjustment instructions of the injection pump and a fault warning report are generated, including:

[0032] A deviation amount value of the stability index and the preset risk threshold is calculated, and a flow field control level including a primary adjustment level, an intermediate adjustment level and an emergency control level is determined according to the deviation amount value;

[0033] Historical operation data and current working parameters of the injection pump are acquired, and an adjustment parameter group corresponding to the flow field control level is matched in the historical operation data, an offset amount of the adjustment parameter group and the current working parameters is calculated, and a set of adjustment instructions of the injection pump is generated;

[0034] When the deviation amount value reaches the emergency control level and the time length exceeds a preset time threshold, a fault warning report is triggered.

[0035] In a second aspect, the application provides a quantitative analysis system of a flow field of in-situ leaching of uranium, including:

[0036] An acquisition module acquires historical flow data and pressure time series data of an injection pipeline of in-situ leaching of uranium, and combines the historical flow data and the pressure time series data according to a time dimension to construct a flow-pressure matrix reflecting a working state of an injection pump;

[0037] An extraction module extracts a resonance frequency band energy feature of the injection pump from the flow-pressure matrix, and constructs a pump health evaluation atlas according to an intensity distribution of the resonance frequency band energy feature;

[0038] A conversion module synchronously acquires fluid scattering signals of the injection pipeline of in-situ leaching of uranium, and converts the fluid scattering signals into a three-dimensional flow velocity vector diagram reflecting a three-dimensional spatial flow velocity distribution;

[0039] A generation module calculates a fluid acoustic impedance parameter according to a flow velocity vector module and a direction change rate of each spatial position in the three-dimensional flow velocity vector diagram, and generates a flow field turbulence thermodynamic diagram characterizing a local turbulence intensity of a flow field based on the fluid acoustic impedance parameter;

[0040] The matching module dynamically matches the pump health evaluation graph and the flow field turbulent thermal graph, calculates the stability index of the in-situ leaching uranium flow field, and generates the adjustment instruction set and the failure warning report of the liquid injection pump according to the deviation degree of the preset risk threshold and the stability index.

[0041] In a third aspect, the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component, and realize the in-situ leaching uranium flow field quantitative analysis method of the first aspect.

[0042] In a fourth aspect, the present application provides a computer storage medium, which stores a computer program, and when the computer program is executed by a computer, the in-situ leaching uranium flow field quantitative analysis method of the first aspect is realized.

[0043] In the embodiments of the present application, the historical flow data and the pressure time series data of the in-situ leaching uranium liquid injection pipeline are acquired, the historical flow data and the pressure time series data are combined according to the time dimension to construct a flow pressure matrix reflecting the working state of the liquid injection pump; the resonance frequency band energy features of the liquid injection pump are extracted from the flow pressure matrix, and a pump health evaluation graph is constructed according to the intensity distribution of the resonance frequency band energy features; the fluid scattering signal of the in-situ leaching uranium liquid injection pipeline is synchronously acquired, and the fluid scattering signal is converted into a three-dimensional flow velocity vector graph reflecting the three-dimensional space flow velocity distribution; the fluid acoustic impedance parameters are calculated according to the flow velocity vector modulus and the direction change rate of each space position in the three-dimensional flow velocity vector graph, and a flow field turbulent thermal graph characterizing the local turbulent intensity of the flow field is generated based on the fluid acoustic impedance parameters; the pump health evaluation graph and the flow field turbulent thermal graph are dynamically matched, the stability index of the in-situ leaching uranium flow field is calculated, and the adjustment instruction set and the failure warning report of the liquid injection pump are generated according to the deviation degree of the preset risk threshold and the stability index.

[0044] The technical scheme of the present application has the following beneficial effects:

[0045] The application can intuitively reflect the working state change of the liquid injection pump by combining historical flow data and pressure time series data in the time dimension, providing multi-dimensional dynamic data support for subsequent health assessment. By analyzing the energy distribution of the resonance frequency band, the abnormal vibration characteristics of the liquid injection pump can be accurately identified, potential failure risks can be warned in advance, and the reliability of the equipment operation can be improved. By converting the fluid scattering signal into a three-dimensional flow velocity vector diagram, the flow velocity distribution and flow direction of the fluid in the liquid injection pipeline can be visualized in real time, providing high-precision spatial data for flow field analysis. Through acoustic impedance parameter calculation, the local turbulence intensity of the flow field is quantitatively characterized, and the instability region of the flow field is revealed, providing key parameter basis for optimizing the liquid injection process. By correlating the health status of the pump with the turbulence characteristics of the flow field, a stability index is dynamically calculated to realize comprehensive evaluation of the operation state of the in-situ leaching uranium flow field, supporting real-time regulation and failure warning.

[0046] Further, by synchronizing the time series of pump vibration energy and the time series of flow field turbulence intensity, a unified time reference data set is formed; then based on the data set, pump vibration characteristic parameters and corresponding turbulence intensity information are extracted, and a dynamic correlation model between the two is constructed; finally, by quantifying the conversion coefficient between pump vibration energy and turbulence intensity, and integrating according to the time series, a dynamic index representing the stability of the flow field is generated. Through precise time axis alignment and dynamic transfer relationship modeling, deep correlation analysis of pump vibration characteristics and flow field turbulence intensity is realized, thereby significantly improving the calculation accuracy of the in-situ leaching uranium flow field stability index. This process not only can reflect the coupling relationship between the flow field and the equipment operation state in real time, but also provides a scientific basis for failure warning and process parameter optimization of the liquid injection pump, ultimately reducing production risks and improving resource exploitation efficiency.

[0047] These aspects or other aspects of the application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0049] Figure 1 A flow chart of a quantitative analysis method of an in-situ leaching uranium flow field provided by the application is shown;

[0050] Figure 2 A structural schematic diagram of a quantitative analysis system of an in-situ leaching uranium flow field provided by the application is shown;

[0051] Figure 3 A structural schematic diagram of a computing device provided by the application is shown. DETAILED DESCRIPTION

[0052] In order to enable persons skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application.

[0053] In some of the processes described in the specification and claims of the application and in the accompanying drawings, a plurality of processes are described in a specific order. However, it should be clear to a person skilled in the art that these processes can be performed in an order different from that in which they appear in this text or in parallel, and the serial numbers of the processes, such as 101, 102, etc., are only used to distinguish different processes, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer processes, and the processes can be performed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this text are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do "first" and "second" represent different types.

[0054] The flow field diagnosis technology of the existing in-situ leaching uranium injection system mainly relies on the online correction method based on the physical model. Such method realizes the correlation analysis of mechanical failure and flow field imbalance by constructing the coupling model of injection pump mechanical operation and underground water flow field, and dynamically correcting the model parameters combined with real-time monitoring data. However, this technical route has significant limitations. On the one hand, the physical model has strong dependence on parameters such as stratum permeability and rock mass structure, and in complex geological conditions, the model prediction may be distorted due to parameter uncertainty, thereby weakening the reliability of the diagnosis results. On the other hand, the system has a lag in response to sudden mechanical abnormalities, and it is difficult to complete the early warning before the critical point of flow field imbalance, resulting in difficulty in avoiding the risk of pressure imbalance between injection and extraction wells. In addition, the online correction process of the model has high demand for computing resources, and the deployment of edge devices is limited, further restricting the timeliness and field adaptability of diagnosis.

[0055] In view of the above problems, the application provides a kind of quantitative analysis method of in-situ leaching uranium flow field based on multi-source data fusion and dynamic matching.The method integrates the historical flow and pressure time series data of injection pipeline, constructs the flow pressure matrix reflecting the working state of injection pump, and extracts the resonance band energy feature to generate pump health evaluation atlas, so as to realize sensitive capture of mechanical abnormal signal.Simultaneous acquisition of fluid scattering signal and conversion into three-dimensional flow vector diagram, combined with fluid acoustic impedance parameter calculation to generate flow field turbulence thermodynamic diagram, so as to accurately depict the local disturbance characteristics of flow field.Through dynamic matching of pump health atlas and flow field turbulence thermodynamic diagram, dynamic index representing the stability of flow field is generated, and adjustment instruction and early warning report are generated based on risk threshold.The scheme discards the strong dependence of traditional physical model, realizes real-time correlation analysis of flow field and equipment state through data-driven mode, significantly improves the response speed and diagnosis accuracy of sudden failure.At the same time, its multi-dimensional data fusion and efficient calculation architecture reduces the dependence on hardware resources, and provides reliable technical support for safe and efficient operation of in-situ leaching uranium under complex geological conditions.

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0057] Figure 1 A flow chart of a quantitative analysis method of in-situ leaching uranium flow field is provided for the embodiments of the present application, as shown in Figure 1 The method comprises:

[0058] 101, obtain the historical flow data and pressure time series data of the injection pipeline of in-situ leaching uranium, combine the historical flow data and the pressure time series data according to time dimension to construct a flow pressure matrix reflecting the working state of injection pump;

[0059] In this step, the flow pressure matrix is composed of the historical flow data and pressure time series data of the injection pipeline, and is formed into a two-dimensional matrix after alignment according to time dimension.

[0060] The historical flow data refers to the time series data of instantaneous flow or cumulative flow recorded during the past operation of the injection pipeline of in-situ leaching uranium, which is used to analyze the long-term operation law of injection pump.

[0061] The time dimension refers to the measurement scale of time as a description and expression variable, which is used to quantify the sequence, duration and change law of event occurrence.

[0062] The pressure time series data refers to a data sequence of pressure values collected by the liquid injection pipeline in the running process and arranged in time sequence, reflecting the system load change.

[0063] In the embodiments of the present application, first, the system collects historical flow data and pressure time series data of the in-situ leaching uranium liquid injection pipeline in real time through high-precision sensors, and the sampling frequency needs to cover the complete cycle of pump operation. Subsequently, the collected historical flow data and pressure time series data are aligned in time dimension, the time series of the two groups of data are matched by using time stamp, and abnormal time points caused by sensor failure or communication delay are eliminated to ensure data consistency. Finally, the aligned data are arranged in time sequence to form a flow pressure matrix containing time stamp, flow value and pressure value.

[0064] In a certain in-situ leaching uranium project, high-precision flow meters and pressure transmitters are deployed in the liquid injection pipeline to collect flow and pressure data in real time. Through dynamic time warping algorithm, the flow and pressure data of the past week are integrated into a flow pressure matrix updated every second. If there is a case of inconsistent sensor collection frequency, linear interpolation is used to supplement the missing values to ensure the integrity of the matrix.

[0065] 102、extracting the resonance frequency band energy features of the liquid injection pump from the flow pressure matrix, and constructing a pump health evaluation map according to the intensity distribution of the resonance frequency band energy features;

[0066] In this step, the resonance frequency band energy features refer to the energy distribution in a specific frequency range generated by mechanical vibration of the liquid injection pump in the running process.

[0067] The pump health evaluation map refers to quantifying the abnormal states such as wear, looseness or bearing failure of the pump by analyzing the intensity changes of these energy features.

[0068] The intensity distribution refers to the distribution law of vibration energy and turbulence intensity in time or space dimension, which is quantified by statistical or frequency domain analysis.

[0069] In the embodiments of the present application, first, the pressure time series data in the flow pressure matrix is subjected to fast Fourier transform to convert it from time domain signal to frequency domain signal, so as to identify the resonance frequency band energy features generated in the running process of the liquid injection pump. Subsequently, the frequency domain signal is divided into multiple resonance frequency bands, the energy value of each resonance frequency band is calculated by energy integration algorithm, and the intensity distribution law is analyzed. Finally, the energy values of each frequency band are combined with the time sequence to construct a pump health evaluation map, in which the horizontal axis is time, the vertical axis is frequency band energy value, and the color gradient represents the energy intensity change.

[0070] In the above-mentioned in-situ leaching uranium project, the flow pressure matrix is analyzed in the frequency domain, and it is found that the vibration energy of the liquid injection pump is significantly enhanced in a specific frequency band. Further calculation of the energy intensity distribution in this frequency band shows that the energy level increases from "medium" to "high" in a certain time period, which corresponds to the change of the color in the pump health evaluation atlas from green to red, indicating the risk of bearing wear.

[0071] 103、synchronous acquisition of the fluid scattering signal of the in-situ leaching uranium liquid injection pipeline, and conversion of the fluid scattering signal into a three-dimensional flow velocity vector diagram reflecting the three-dimensional spatial flow velocity distribution;

[0072] In this step, the fluid scattering signal refers to the fluid motion reflection signal collected by ultrasonic waves or Doppler radar, and its intensity is related to the fluid velocity.

[0073] The three-dimensional spatial flow velocity distribution refers to the distribution state of the flow velocity size and direction of the fluid at each spatial position in the liquid injection pipeline, which is usually obtained by ultrasonic wave or Doppler radar technology.

[0074] The three-dimensional flow velocity vector diagram refers to the generation of the flow velocity size and direction of each spatial point in the liquid injection pipeline by analyzing the scattering signal, which intuitively reflects the complexity of fluid flow.

[0075] In the embodiments of the present application, first, the system deploys multiple groups of ultrasonic sensor arrays at key positions of the in-situ leaching uranium liquid injection pipeline, realizes real-time monitoring of the fluid motion state in the pipeline by emitting high-frequency sound waves and receiving fluid scattering signals reflected by the fluid. Subsequently, the fluid scattering signals collected are analyzed in time and frequency domains, the size and direction of the fluid velocity are calculated using the Doppler shift effect, and the flow velocity vector data of each measurement point are generated in combination with the spatial distribution information of the sensors. Finally, the flow velocity vector data of all spatial points are mapped into a three-dimensional coordinate system, the flow velocity information of the areas not directly measured is supplemented by an interpolation algorithm, and a three-dimensional flow velocity vector diagram covering the entire pipeline space is formed.

[0076] In the above-mentioned in-situ leaching uranium project, multiple groups of ultrasonic sensors are installed in the liquid injection pipeline to synchronously collect scattering signals. In a certain collection, the sensor detects a flow velocity vector with a specific value and direction, the flow velocity vector of the unmeasured point in the middle of the pipeline is calculated by an interpolation algorithm, and finally a three-dimensional flow velocity vector diagram is generated, showing that the overall flow field presents a spiral flow.

[0077] 104、According to the flow velocity vector modulus and direction change rate of each spatial position in the three-dimensional flow velocity vector diagram, the fluid acoustic impedance parameter is calculated, and the flow field turbulence thermodynamic diagram characterizing the local turbulence intensity of the flow field is generated based on the fluid acoustic impedance parameter;

[0078] In this step, the flow velocity vector modulus refers to the size of the fluid velocity, indicating the movement rate of the fluid at a certain point.

[0079] Directional change rate refers to the rate of change of the direction of fluid velocity per unit time, and is used to describe the instability or vortex characteristics of fluid motion in the flow field.

[0080] The fluid acoustic impedance parameter reflects the resistance characteristics of the fluid to the propagation of sound waves.

[0081] The local turbulence intensity of the flow field characterizes the degree of turbulence of the fluid in a specific area. It is usually calculated by the Reynolds stress or the root mean square value of velocity fluctuation, reflecting the intensity of fluid mixing or energy dissipation.

[0082] The turbulence thermogram quantifies the turbulence intensity in the flow field through the spatiotemporal distribution of acoustic impedance parameters. High turbulence areas appear as high temperature colors in the thermogram, such as red.

[0083] In the embodiment of the present application, first, the velocity vector modulus and directional change rate at each spatial position are extracted from the three-dimensional velocity vector diagram. Combined with the known fluid density and sound velocity, the acoustic impedance parameters of the fluid at the corresponding position are calculated through acoustic impedance. Subsequently, the fluid acoustic impedance parameters are associated with the spatiotemporal gradient of the velocity vector modulus using a turbulence intensity model to quantify the turbulence intensity in the local area. Finally, the calculated turbulence intensity value is mapped into a flow field turbulence thermodynamic map according to the spatial coordinates. The distribution pattern of turbulence in the flow field is intuitively characterized by a color gradient, such as blue for low turbulence and red for high turbulence.

[0084] In the three-dimensional velocity vector diagram, a region exhibited a sudden increase in the velocity vector modulus and a significant increase in the rate of change of direction. Calculation of the acoustic impedance parameters for this region revealed significantly higher turbulence intensity than surrounding areas. This region was marked red in the turbulence thermodynamic map, indicating a potential risk of localized blockage.

[0085] 105. Dynamically match the pump health assessment map with the flow field turbulence thermodynamic map to calculate the stability index of the in-situ leaching uranium flow field, and generate an adjustment instruction set and a fault warning report for the injection pump based on the degree of deviation between a preset risk threshold and the stability index.

[0086] In this step, dynamic matching refers to aligning the pump health assessment map with the flow field turbulence thermodynamic map in time series and establishing a correlation model between the two.

[0087] The stability index is used to evaluate the coordinated stability of the flow field and equipment by quantifying the conversion ratio of vibration energy to turbulence intensity.

[0088] The preset risk threshold refers to the upper or lower limit of the stability index set by the system based on safety standards or engineering experience, which is used to determine whether the adjustment or early warning mechanism needs to be triggered.

[0089] The degree of deviation refers to the degree of deviation between the stability index of the actual operating parameters and the preset risk threshold, which is used to quantify the severity of the system's deviation from the normal state.

[0090] The adjustment instruction set refers to a set of operation commands generated according to the system stability analysis result, used for optimizing the device running state.

[0091] The fault early warning report refers to diagnostic information generated when the system detects an abnormal state, containing fault type, occurrence time, severity and recommended treatment measures, used to guide maintenance decisions.

[0092] In the embodiments of the present application, first, the pump health assessment atlas generated in step 102 is aligned with the flow field turbulent thermal map generated in step 104 according to the time stamp, and the data correlation of the two is established. Subsequently, the dynamic time warping algorithm is used to match the characteristics of the two groups of data, and the cooperative change relationship between pump vibration energy and turbulent intensity is extracted. Based on this relationship, the stability index is calculated. Finally, the stability index is compared with the preset risk threshold value, and if it deviates from the threshold value, the adjustment instruction set is triggered and the fault early warning report is generated, realizing the real-time optimization and risk control of the injection pump running state.

[0093] At a certain moment, the pump health assessment atlas shows that the resonance energy suddenly rises, while the turbulent intensity in the corresponding area of the turbulent thermal map decreases, and the stability index after dynamic matching is lower than the threshold value. The system generates an adjustment instruction set, recommends adjusting the injection flow rate, and generates a fault early warning report, prompting to check the pump bearing wear condition.

[0094] In summary, steps 101 to 105 realize real-time monitoring and linkage control of in-situ leaching uranium flow field and injection pump state through cooperative analysis of flow pressure matrix, resonance frequency band energy characteristics, three-dimensional flow velocity vector diagram, fluid acoustic impedance parameters and dynamic matching model. Compared with traditional physical models, it does not need to rely on geological parameter assumptions, and the response speed to sudden failures is improved. In the practical application of uranium mines, this method successfully reduces the failure rate of injection pumps, improves leaching efficiency, and significantly reduces the well wall collapse accidents caused by flow field imbalance, providing high-robustness technical support for in-situ leaching of uranium under complex geological conditions.

[0095] In order to solve the problem of correlation analysis of pump vibration energy and flow field turbulent intensity in the injection pipeline of in-situ leaching uranium, the scheme integrates the dynamic data of pump health assessment atlas and flow field turbulent thermal map through time axis alignment technology. The vibration characteristics and turbulent intensity of the key time points in the injection pipeline area are extracted, and the dynamic transmission relationship between the two is established. Based on this relationship, the conversion proportion of vibration energy to turbulent intensity is quantified, a time sequence index reflecting the stability of the flow field is generated, and the quantitative evaluation of the dynamic balance state of the flow field is realized, providing real-time data support for subsequent regulation. In some embodiments, the pump health assessment atlas and the flow field turbulent thermal map are dynamically matched in step 105, and the stability index of the in-situ leaching uranium flow field is calculated, including:

[0096] 201. Align the vibration energy time series in the pump health assessment atlas with the intensity time series of the flow field turbulence thermodynamic map to generate a time-aligned data set;

[0097] In step 201, the vibration energy time series in the pump health assessment map records the changes in vibration energy over time during the operation of the injection pump. The intensity time series in the flow field turbulence thermogram reflects the temporal changes in the local turbulence intensity of the flow field. Time axis alignment involves synchronizing two sets of time series data in the timestamp dimension through an algorithm to eliminate data misalignment caused by sampling frequency differences or time deviations. The time-aligned dataset is a structured data set that contains the vibration energy and turbulence intensity values ​​at the same time point after alignment.

[0098] In an embodiment of the present application, first, a vibration energy time series is extracted from the pump health assessment atlas, which records the change of vibration energy over time during the operation of the injection pump. At the same time, a turbulence intensity time series is extracted from the flow field turbulence thermogram to reflect the dynamic changes of the local turbulence intensity in the flow field. Subsequently, a distance matrix is ​​constructed to calculate the local similarity of vibration energy and turbulence intensity in the time dimension, and the dynamic programming method is used to search for the optimal alignment path to ensure that the time series reaches the minimum cumulative distance after nonlinear stretching or compression. After the alignment is completed, if there are missing timestamp values, linear interpolation is used to supplement the data points. Finally, the aligned vibration energy and turbulence intensity are combined in chronological order to generate a structured time-aligned data set containing corresponding data at the same time point, which provides input for subsequent dynamic transfer relationship modeling.

[0099] 202. In an in-situ leaching uranium injection pipeline area, extract pump vibration characteristic values ​​and turbulence intensity data at corresponding time points from the time-aligned dataset, and establish a dynamic transmission relationship between the pump vibration characteristic values ​​and the turbulence intensity data;

[0100] In step 202, the pump vibration eigenvalue refers to a quantitative indicator extracted from the time-aligned dataset that characterizes the pump vibration state. The turbulence intensity data refers to the local turbulence intensity value at the corresponding time point in the flow field turbulence thermogram. The dynamic transfer relationship describes the nonlinear mapping between the pump vibration eigenvalue and the turbulence intensity data, typically established through cross-correlation analysis or machine learning models.

[0101] In an embodiment of the present application, first, based on the time-aligned data set generated in step 201, the pump vibration eigenvalues ​​and turbulence intensity data at corresponding time points are extracted in the in-situ leaching uranium injection pipeline area. The cross-correlation function is used to analyze the time lag relationship between the pump vibration eigenvalues ​​and the turbulence intensity data to determine the delayed effect of the vibration energy change on the turbulence response. Subsequently, a random forest regression model is used to establish a dynamic transfer relationship, with the input variables being the vibration eigenvalues ​​and their historical change trends, and the output variable being the predicted turbulence intensity value. During the model training process, the hyperparameters are optimized through cross-validation to ensure the accuracy of the dynamic transfer relationship. Finally, the trained model is used to predict the response of turbulence intensity to pump vibration in real time, forming a dynamic transfer relationship between the pump vibration eigenvalues ​​and the turbulence intensity data, laying the foundation for the calculation of the conversion ratio value.

[0102] 203. Calculate the conversion ratio of pump vibration energy to flow field turbulence intensity using the dynamic transfer relationship, and combine the conversion ratios in chronological order to generate a stability index reflecting the stability of the in-situ uranium leaching flow field.

[0103] In step 203, pump vibration energy refers to the energy carried by the vibration generated by the pump body during the operation of the injection pump due to the unbalanced movement of mechanical components or the instability of fluid flow. The flow field turbulence intensity refers to a physical quantity that describes the intensity of turbulence in fluid motion and is generally defined as the ratio of the root mean square value of the velocity pulsation to the average flow velocity. The conversion ratio value refers to the quantitative ratio between the pump vibration energy and the flow field turbulence intensity. The stability index is calculated by integrating the time series of the conversion ratio value and combining it with a preset threshold value to characterize the stability level of the flow field.

[0104] In an embodiment of the present application, first, based on the dynamic transfer relationship established in step 202, the pump vibration energy time series is used as input through a random forest regression model to calculate the predicted value of the flow field turbulence intensity at the corresponding time point. According to the difference between the predicted turbulence intensity value and the actually measured turbulence intensity value, the conversion ratio value of the pump vibration energy and the flow field turbulence intensity is calculated. Subsequently, the time series of the conversion ratio value is smoothed using an exponentially weighted moving average algorithm to eliminate short-term fluctuation interference and highlight long-term trends. Finally, the smoothed conversion ratio value is compared with the preset risk threshold to generate a stability index reflecting the degree of stability of the flow field. The higher the stability index, the more unstable the flow field is, and the more likely it is that an adjustment instruction or warning needs to be triggered.

[0105] Here's a specific example:

[0106] In an in-situ leaching uranium project, high-precision vibration sensors and ultrasonic flow meters are deployed in the liquid injection pipeline. In step 201, the vibration energy time series and the turbulence intensity time series are aligned to generate a time-aligned dataset that is updated every second. In step 202, the running data for a certain period of time is selected, the vibration characteristic value and the turbulence intensity data are extracted, and the cross-correlation function is used to find the lag of turbulence intensity behind vibration energy. Then, the dynamic transfer relationship is trained through the random forest model to predict the response of turbulence intensity to vibration. In step 203, the conversion ratio value is calculated, and after smoothing, the stability index is generated. When the stability index exceeds the threshold for a continuous time, the system triggers the liquid injection flow adjustment instruction, and reduces the vibration energy to suppress the growth of turbulence intensity.

[0107] In summary, steps 201 to 203 achieve real-time correlation analysis of pump vibration energy and flow field turbulence intensity in the liquid injection pipeline of in-situ leaching uranium by time axis alignment, dynamic transfer relationship modeling, and stability index calculation. The time-aligned dataset ensures data consistency, the dynamic transfer relationship reveals the nonlinear mapping rule of vibration and turbulence, and the stability index provides a quantitative basis for risk warning and adjustment decision-making. The overall process improves the accuracy and response speed of flow field stability monitoring, reduces equipment failure rate, and prolongs the service life of the liquid injection pump.

[0108] To solve the problem of multi-source data correlation modeling and dynamic transfer relationship construction in the liquid injection pipeline of in-situ leaching uranium, the scheme selects the initial correlation relationship with physical consistency through fluid motion rules, eliminates non-matching interference, and finally generates a dynamic transfer relationship model. Through multi-parameter collaborative analysis, the correlation reliability is enhanced, the analysis accuracy of vibration and turbulence interaction characteristics is improved, and the foundation for flow field stability calculation is laid. In some embodiments, in step 202, the pump vibration characteristic value and the turbulence intensity data at the corresponding time point in the liquid injection pipeline area of in-situ leaching uranium are extracted from the time-aligned dataset, and the dynamic transfer relationship between the pump vibration characteristic value and the turbulence intensity data is established, including:

[0109] 301. Extracting the pump vibration characteristic value and the turbulence intensity data at the corresponding time point in the liquid injection pipeline area of in-situ leaching uranium from the time-aligned dataset, and arranging and combining the pump vibration characteristic value, turbulence intensity data, and density parameter of the uranium ore leaching agent in time sequence to generate a time series dataset;

[0110] In step 301, the pump vibration characteristic value refers to a quantitative indicator that characterizes the vibration state of the liquid injection pump. The turbulence intensity data refers to the reflection of the local turbulence intensity of the flow field. The density parameter of the uranium ore leaching agent refers to the physical property of the leaching agent, which directly affects the fluid motion law. The time series dataset refers to a multi-dimensional time series data set arranged in time sequence after three groups of data, which is used to support subsequent correlation relationship modeling.

[0111] In the embodiments of the present application, first, the pump vibration characteristic value and the turbulence intensity data corresponding to the time point in the in-situ leaching uranium liquid injection pipeline area are extracted from the time alignment data set, and the density parameter of the uranium ore leaching agent is synchronously called. Since the sampling frequency of the density parameter may be lower than that of the vibration and turbulence data, a linear interpolation algorithm is used to supplement the density value of the missing time point to ensure that the time resolution of the three groups of data is consistent. Subsequently, the dynamic time warping algorithm is used to perform secondary alignment on the time stamps of the three groups of data to eliminate the slight time offset caused by the sensor response delay or data transmission jitter, so that all parameters correspond strictly under the same time reference. Finally, the calibrated pump vibration characteristic value, turbulence intensity data and density parameter of the uranium ore leaching agent are arranged row by row in time sequence to generate a time series data set indexed by time stamp, and each row of record contains three groups of parameters at the same time point, providing structured input for subsequent correlation relationship modeling.

[0112] 302. Based on the time series data set, an initial correlation relationship between the pump vibration characteristic value and the turbulence intensity data is established, and the initial correlation relationship that matches the direction is filtered based on a preset leaching agent fluid motion rule, and the filtered initial correlation relationship is superimposed as a dynamic transfer relationship.

[0113] In step 302, the initial correlation relationship refers to the mapping rule between the pump vibration characteristic value and the turbulence intensity data initially established by statistical methods or machine learning models. The preset leaching agent fluid motion rule refers to the fluid behavior constraint condition set based on fluid mechanics theory. The initial correlation relationship that matches the direction refers to the causal relationship that conforms to the fluid motion rule, such as the increase of vibration energy leading to the rise of turbulence intensity.

[0114] In the embodiments of the present application, first, based on the time series data set generated in step 301, the cross-correlation function analysis is used to calculate the time lag correlation between the pump vibration characteristic value and the turbulence intensity data, and the initial correlation relationship is initially established. The lag correlation coefficient of the two groups of data is calculated through a sliding window to identify the time delay and intensity mapping rule between the vibration energy change and the turbulence intensity response. Subsequently, in combination with the preset leaching agent fluid motion rule, the initial correlation relationship that matches the direction of the physical rule is filtered. For example, if the turbulence intensity rises synchronously when the vibration characteristic value increases and conforms to the fluid acceleration effect driven by density, the correlation is retained; if the correlation direction conflicts with the fluid motion rule, it is excluded. Finally, the initial correlation relationship that matches the direction after filtering is superimposed through a random forest regression model to construct a dynamic transfer relationship.

[0115] The following is a specific example:

[0116] In a certain in-situ uranium leaching project, vibration sensors, ultrasonic flowmeters, and density transmitters were deployed in the injection pipeline. Pump vibration eigenvalues, turbulence intensity data, and leachate density parameters were extracted from the time-aligned dataset. Missing time point data were supplemented through linear interpolation, and a time series dataset was generated after dynamic time warping and alignment. A cross-correlation function was used to identify a time-lagged correlation between vibration energy and turbulence intensity. This was verified by combining leachate density data to confirm that this corresponded to the fluid acceleration effect, and initial correlations with matching directions were selected. Subsequently, the selected correlations were superimposed using a random forest model to construct a dynamic transfer relationship model. When the leachate density suddenly increased, the model predicted that the turbulence intensity would increase due to density-driven changes in flow velocity. The dynamic transfer relationship automatically adjusted the correlation weights to ensure that the predicted results matched the actual flow field behavior.

[0117] In summary, steps 301 to 302, through the construction of a time series dataset and the modeling of dynamic transfer relationships, enable correlation analysis of multi-source data in the in-situ uranium injection pipeline and dynamic mapping under physical constraints. The time series dataset integrates vibration, turbulence, and density parameters, providing a unified data foundation for correlation modeling. The dynamic transfer relationship, by screening initial correlations that match their directions and then overlaying them, ensures that the prediction results conform to the laws of fluid motion. This overall process improves the accuracy of flow field stability assessments, optimizes the injection pump operating parameter adjustment strategy, and reduces the risk of equipment failures caused by fluid fluctuations.

[0118] In order to solve the problem of multi-source data feature extraction and dynamic mapping in the health status assessment of in-situ leaching uranium injection pumps, the solution extracts key energy characteristic parameters, such as peak intensity and bandwidth, by screening the resonance frequency bands that exceed the background noise threshold. Combining the spatial matching relationship between the energy attenuation gradient and the frequency band characteristics, a health assessment map that intuitively reflects the operating status of the pump is generated. Through the comprehensive analysis of frequency domain characteristics and attenuation laws, non-destructive monitoring and abnormality identification of the mechanical state of the pump are achieved. In some embodiments, in step 102, the resonance frequency band energy characteristics of the injection pump are extracted from the flow pressure matrix, and the pump health assessment map is constructed according to the intensity distribution of the resonance frequency band energy characteristics, including:

[0119] 401. Divide the flow pressure matrix into frequency intervals, calculate the energy accumulation values ​​of the frequency intervals, and select, based on the vibration transmission characteristics of the injection pump, the frequency intervals in which the energy accumulation values ​​exceed a preset background noise threshold as target resonance frequency bands;

[0120] In step 401, the frequency interval refers to the discrete frequency bands delineated by spectral analysis. The cumulative energy value represents the sum of the signal energy within each frequency band. The preset background noise threshold refers to the minimum energy threshold set based on ambient noise statistics. The target resonant frequency band refers to the frequency band where the cumulative energy value exceeds the threshold, reflecting the resonant characteristics of the pump vibration transmission.

[0121] In the embodiments of the present application, firstly, the flow pressure matrix collected during the operation of the liquid injection pump is subjected to fast Fourier transform to convert the time domain signal into frequency domain data. Subsequently, the frequency domain data is divided into multiple frequency intervals according to a fixed step, and each interval corresponds to a specific frequency band range. Then, the power spectrum density integration method is used to calculate the energy cumulative value of the signal in each frequency interval, and the total energy of the frequency band is obtained by accumulating the power density values of each frequency point in the frequency band. Based on the vibration transmission characteristics of the liquid injection pump and the preset background noise threshold value statistically obtained from historical operation data, the frequency intervals with energy cumulative values exceeding the threshold value are screened out and marked as target resonance frequency bands.

[0122] 402、extracting the peak energy intensity data and the frequency band width data of the target resonance frequency band as resonance frequency band energy characteristics, and calculating the energy attenuation gradient of adjacent target resonance frequency bands;

[0123] In step 402, the peak energy intensity data refers to the maximum energy value of the signal in the target resonance frequency band. The frequency band width data refers to the frequency span representing the frequency band. The resonance frequency band energy characteristics refer to a set of quantitative energy parameters extracted for the resonance frequency band in system vibration analysis, which are used to represent the energy distribution law and dynamic characteristics of the system in the resonance state. The energy attenuation gradient refers to the normalized slope of the energy difference between adjacent target resonance frequency bands, which reflects the distribution law of the pump vibration energy.

[0124] In the embodiments of the present application, firstly, the peak energy intensity data and the frequency band width data of each frequency band are extracted from the target resonance frequency bands output from step 401. Subsequently, all target resonance frequency bands are arranged in the order of frequency band appearance, the difference value of the peak energy intensity data between adjacent frequency bands is calculated, and the energy attenuation trend is quantified using the linear regression algorithm in combination with the ratio of the frequency band width data to generate the energy attenuation gradient. For example, if the energy of a certain frequency band is significantly higher than that of the adjacent frequency bands and the frequency band width is narrow, the energy attenuation gradient is large, indicating that the vibration energy is concentrated and released; on the contrary, if the energy distribution is flat and the frequency band width is wide, the gradient is small. This step reveals the dynamic distribution law of the pump vibration energy through the correlation analysis of energy and frequency band width.

[0125] 403、generating a pump health evaluation map according to the matching relationship between the frequency band width data and the energy attenuation gradient.

[0126] In step 403, the matching relationship refers to the correlation analysis between the two. The pump health evaluation map refers to a visual health state mapping diagram generated based on the matching relationship, which is used to determine whether the pump has resonance fatigue or structural damage.

[0127] In the embodiments of the present application, first, the frequency band width data obtained in step 402 is input into the Pearson correlation coefficient analysis model with the energy attenuation gradient to calculate the linear correlation of the two. Based on the correlation coefficient, a health state mapping function is constructed, taking the frequency band width data as the horizontal axis and the energy attenuation gradient as the vertical axis, and a pump health evaluation atlas is generated after dimension reduction processing by principal component analysis. The depth of color in the atlas reflects the health state. If the frequency band width is narrow and the energy attenuation gradient is steep in a certain area, the color is reddish, indicating that the pump may have local resonance fatigue; if the frequency band width is wide and the gradient is gentle, the color is greenish, indicating that the running state is stable. The health state of the pump is intuitively presented to assist fault warning and maintenance decision-making.

[0128] The following is a specific example:

[0129] In a certain in-situ leaching uranium project, the flow pressure matrix collected during the operation of the liquid injection pump contains sampling data. The data is converted to the frequency domain by fast Fourier transform and divided into multiple frequency bands. After calculating the energy accumulation value of each frequency band, the frequency bands with energy exceeding the background noise threshold are selected as the target resonance frequency bands. The peak energy intensity and frequency band width of the target resonance frequency band are extracted, and the energy attenuation gradient between adjacent frequency bands is calculated after arranging them in order. The frequency band width and the energy attenuation gradient are analyzed for correlation to generate a health evaluation atlas. If the color of a certain area in the atlas is significantly reddish, it indicates that the pump may have high-frequency resonance abnormalities, and the liquid injection speed needs to be adjusted or the bearing needs to be repaired.

[0130] In summary, steps 401 to 403 realize dynamic evaluation of the health state of the liquid injection pump through frequency spectrum analysis and energy feature extraction of the flow pressure matrix. Step 401 selects the target resonance frequency band to filter environmental noise interference; step 402 quantifies the energy attenuation law to identify vibration abnormal patterns; and step 403 provides intuitive decision support through atlas visualization. The overall process improves the accuracy of pump equipment fault warning in in-situ leaching uranium projects, reduces the risk of sudden shutdown due to resonance fatigue, and prolongs the service life of the equipment.

[0131] To solve the problem of dynamic modeling of flow field turbulence characteristics in the liquid injection pipeline of in-situ leaching uranium, the scheme calculates the fluid acoustic impedance parameters through the modulus and direction change rate of three-dimensional flow velocity vectors, and establishes a mapping relationship between turbulence intensity and acoustic impedance by combining the density of the leaching agent. The spatial transfer algorithm is used to generate the turbulence intensity distribution of the cross section of the liquid injection pipeline, and further construct a heat map through the gradient change rate. The flow velocity dynamic characteristics are converted into quantifiable turbulence intensity representation, providing visual basis for identifying local unstable areas of the flow field. In some embodiments, in step 104, the fluid acoustic impedance parameters are calculated according to the flow velocity vector modulus and direction change rate of each spatial position in the three-dimensional flow velocity vector diagram, and a flow field turbulence heat map representing the local turbulence intensity of the flow field is generated based on the fluid acoustic impedance parameters, including:

[0132] 501. Obtain the velocity vector modulus and the directional change rate at each spatial position in the three-dimensional velocity vector diagram and adjacent time points, and superimpose the density parameter of the uranium ore leaching agent, the velocity vector modulus, and the directional change rate to generate a fluid acoustic impedance parameter.

[0133] In step 501, the velocity vector modulus refers to the magnitude of the velocity vector. The directional change rate refers to the rate of change in the deflection angle of the velocity direction at adjacent time points. The density parameter of the uranium ore leachate refers to the mass per unit volume of the leachate used to dissolve and carry uranium during in-situ leaching and recovery. The fluid acoustic impedance parameter is a composite parameter formed by superimposing the density parameter of the uranium ore leachate, the velocity vector modulus, and the directional change rate. It is used to characterize the fluid's ability to transmit vibration energy.

[0134] In this embodiment, the velocity vector modulus and velocity direction deflection angles at each spatial location are first extracted from a three-dimensional velocity vector diagram to calculate the directional change rate. Subsequently, the density parameter of the uranium ore leachate, collected in real time by sensors, is weighted and fused with the velocity vector modulus and directional change rate to generate the fluid acoustic impedance parameter. This provides the basis for subsequent turbulence intensity calculations.

[0135] 502. Convert the difference between the fluid acoustic impedance parameter and a preset reference acoustic impedance value into turbulence intensity data, and spatially transfer the turbulence intensity data of adjacent spatial positions to generate a turbulence intensity distribution of the injection pipe cross section;

[0136] In step 502, the difference between the fluid acoustic impedance parameter and the preset baseline acoustic impedance value refers to the deviation between the actual fluid impedance and the standard value. Turbulence intensity data refers to the fluid pulsation intensity index calculated using this deviation. Spatial transfer refers to the interpolation and expansion of turbulence intensity data at adjacent spatial points. Turbulence intensity distribution refers to the spatial distribution of turbulence intensity at each point within the cross-section of the injection pipeline.

[0137] In this embodiment, the fluid acoustic impedance parameter output from step 501 is first compared with a preset baseline acoustic impedance value measured in the laboratory, and the difference at each point is calculated. Subsequently, based on the correlation between turbulence intensity and acoustic impedance in fluid mechanics, the difference is converted into turbulence intensity data. Next, a Kriging interpolation algorithm is used to spatially expand the turbulence intensity data at adjacent spatial locations, filling in the values ​​in areas not directly measured, and generating a turbulence intensity distribution covering the entire cross-section of the injection pipe.

[0138] 503. Based on the gradient change rate of the turbulence intensity distribution, construct a flow field turbulence thermodynamic map that characterizes the local turbulence intensity of the flow field.

[0139] In step 503, the gradient change rate refers to the change rate of the turbulence intensity between adjacent points in space. The local turbulence intensity of the flow field refers to a physical quantity that describes the degree of fluctuation of the velocity of the fluid in a certain spatial region. The flow field turbulence heat map refers to the conversion of the gradient change rate into a visual heat map through color mapping, which is used to intuitively show the degree of fluctuation of the local turbulence intensity of the flow field.

[0140] In the embodiments of the present application, first, the turbulence intensity distribution generated in step 502 is subjected to spatial gradient calculation, and the finite difference method is used to calculate the turbulence intensity difference value of adjacent spatial positions and normalize it into a gradient change rate. Subsequently, the gradient change rate is generated into a flow field turbulence heat map according to a preset color mapping rule. In the flow field turbulence heat map, the area with high gradient change rate is marked with high saturation color, indicating that the turbulence intensity fluctuates violently and there is a high-risk area; the area with low gradient change rate is marked with low saturation color, indicating that the flow field is stable. This step assists in identifying the turbulence abnormal area in the flow field through gradient analysis and visualization.

[0141] The following is a specific example:

[0142] In a certain in-situ leaching uranium project, the uranium ore leaching agent in the liquid injection pipeline flows at a high flow rate, and the pipeline cross section is circular. The three-dimensional flow velocity vector diagram is collected by the flow field measurement equipment, the flow velocity modulus of a certain point is large, the direction change rate is moderate, and the density sensor measures that the density is within the normal range. After weighted fusion, the fluid acoustic impedance parameter of the point is relatively high. The preset reference acoustic resistance value is the standard value, the difference value is calculated and converted into turbulence intensity data, and the turbulence intensity distribution of the entire cross section is obtained through Kriging interpolation, such as the turbulence intensity at the pipe elbow is significantly higher than that at the straight section. The turbulence intensity gradient change rate at the elbow is calculated to be high, and the heat map is marked with red color, prompting that the area needs to be strengthened for flow field regulation.

[0143] In summary, steps 501 to 503 realize the accurate characterization of the flow field turbulence characteristics of the liquid injection pipeline of the in-situ leaching uranium project through dynamic modeling of the fluid acoustic impedance parameter, spatial interpolation of the turbulence intensity distribution, and visual analysis of the flow field turbulence heat map. Step 501 quantifies the response characteristics of the fluid to the vibration energy, step 502 inversely calculates the turbulence intensity through the acoustic impedance deviation and extends the spatial distribution, and step 503 intuitively locates the high-risk area through gradient analysis and heat map. The overall process improves the accuracy of flow field turbulence monitoring, provides a scientific basis for optimizing the liquid injection process parameters, reducing pipeline wear and energy consumption, and significantly improves the uranium ore recovery rate and equipment operation safety.

[0144] To solve the problem of precise reconstruction of the three-dimensional flow field of the in-situ leaching of uranium injection pipeline, the scheme is based on the frequency shift analysis of fluid scattering signals, combined with the characteristics of sound wave propagation to derive the directional flow velocity component, and reconstruct the three-dimensional flow velocity vector through the spatial coordinate relationship. The vector data is mapped to the grid space of the injection pipeline to generate a high-resolution three-dimensional flow velocity vector map. Through signal inversion and spatial reconstruction technology, the dynamic capture and spatial distribution quantization of complex flow field structure are realized. In some embodiments, the step 103 of converting the fluid scattering signals into a three-dimensional flow velocity vector map reflecting the three-dimensional spatial flow velocity distribution comprises:

[0145] 601. Analyzing the frequency shift of each signal collection point in the fluid scattering signal to obtain signal change data, and converting the signal change data into a directional flow velocity component based on the propagation characteristics of the signal collection sound wave in the uranium ore leaching agent;

[0146] In step 601, the frequency shift refers to the Doppler shift value of the signal collection point caused by fluid motion. The signal change data refers to the dynamic change record of the frequency shift over time. The propagation characteristics refer to the basic properties and regularity of the operation and development of the propagation activities in human society, which is the core feature that distinguishes the propagation behavior from other social behaviors. The directional flow velocity component refers to the decomposition value of the direction and size of the fluid velocity obtained by inverting the signal change data through the sound wave propagation characteristics.

[0147] In the embodiments of the present application, first, the fluid scattering signals of the fluid in the injection pipeline are collected by the sound wave sensor or radar device, and the frequency shift of each signal collection point is extracted. Then, based on the propagation characteristics of the sound wave in the uranium ore leaching agent, the frequency shift is converted into signal change data. Finally, using the Doppler effect model, the signal change data is inverted into a directional flow velocity component. The direction and speed of fluid motion are preliminarily quantized.

[0148] 602. According to the spatial coordinate position of the injection pipeline cross section, the spatial relationship parameters of adjacent signal collection points are identified, and the directional flow velocity components at the same spatial position are combined into a spatial flow velocity vector according to the spatial relationship parameters;

[0149] In step 602, the spatial coordinate position refers to the three-dimensional coordinates of each signal collection point in the injection pipeline cross section. The spatial relationship parameter refers to the geometric relationship between adjacent collection points. The spatial flow velocity vector is the comprehensive velocity vector synthesized by combining multiple directional flow velocity components at the same spatial position.

[0150] In the embodiments of the present application, firstly, the specific spatial coordinate position of each signal acquisition point in space is determined according to the three-dimensional model data of the injection pipeline section. Then, the spatial relationship parameters between adjacent acquisition points, such as the straight-line distance or the included angle between two points, are calculated to describe the spatial distribution characteristics. Next, the directional flow velocity components obtained from multiple detection angles at the same spatial position are integrated through a data fusion algorithm to eliminate errors caused by detection angle differences or noise, and a comprehensive velocity vector of the position is generated.

[0151] 603. The injection pipeline section is divided into spatial grids, and the spatial flow velocity vector is associated and mapped with the spatial grids to generate a three-dimensional flow velocity vector diagram.

[0152] In step 603, the spatial grid refers to a regular or adaptive grid unit after discretization of the injection pipeline section. The associated mapping refers to the process of matching the spatial flow velocity vector with the corresponding grid unit. The three-dimensional flow velocity vector diagram refers to the visualized distribution diagram of the flow velocity vector on the grid unit, which intuitively displays the dynamic characteristics of the flow field.

[0153] In the embodiments of the present application, firstly, according to the geometric shape of the injection pipeline section, a grid division method such as uniform grid division or adaptive grid division is used to generate a spatial grid. Then, the spatial flow velocity vector output by step 602 is mapped to the corresponding spatial grid through a spatial interpolation algorithm. For example, if the coordinates of a grid center point are known, the spatial flow velocity vector of the point is assigned to the grid, and this operation is repeated to cover all spatial grids. Finally, a three-dimensional flow velocity vector diagram is generated using vector field visualization technology to intuitively present the velocity and direction distribution of the flow field, realizing the global characterization of the flow field characteristics.

[0154] The following is a specific example:

[0155] In a certain in-situ leaching uranium project, the diameter of the injection pipeline is large, and the uranium ore leaching agent flows in a complex flow state. The fluid scattering signals of multiple points in the pipeline are collected by a sound wave detection device. The frequency offset of a point is analyzed, and the directional flow velocity component of the point is inversely calculated combined with the sound wave propagation characteristics. According to the three-dimensional coordinates of the point and the spatial relationship of adjacent points, the spatial flow velocity vector is generated by integrating multiple directional flow velocity components. The pipeline section is divided into regular grids, the vector data is mapped to the grids through an interpolation method, and a three-dimensional flow velocity vector diagram is generated to intuitively display the high-speed vortex area at the pipeline elbow, which assists in optimizing the injection process parameters.

[0156] In summary, steps 601 to 603 achieve accurate modeling of the in-situ leaching uranium injection pipeline flow field through fluid scattering signal analysis, spatial flow velocity vector synthesis, and three-dimensional flow velocity vector map generation. Step 601 quantifies fluid motion characteristics, step 602 eliminates spatial measurement bias and synthesizes vectors, and step 603 globally characterizes flow field dynamics through gridding and visualization. The overall process improves the accuracy and intuitiveness of flow field monitoring, providing a scientific basis for efficient delivery of leaching agents, prediction of pipeline wear, and process optimization, significantly improving leaching efficiency and equipment safety.

[0157] To solve the problems of injection pipeline wear, leaching agent delivery efficiency decline and potential equipment failure caused by unstable flow field in the process of uranium leaching, the scheme divides the flow field control level by calculating the deviation of the stability index from the preset threshold value, and generates an instruction set based on historical operation data matching adjustment parameter groups. When the deviation reaches the emergency level and continues to exceed the limit, a warning is triggered, forming a closed-loop control mechanism. Combined with real-time evaluation and historical data-driven, the whole process management from risk identification to active intervention is realized, ensuring the safe and stable operation of the in-situ leaching uranium system. In some embodiments, step 105 generates adjustment instruction set and fault warning report of the injection pump according to the deviation of the preset risk threshold value from the stability index, including:

[0158] 701、Calculate the deviation value of the stability index from the preset risk threshold value, and determine the flow field control level including the primary adjustment level, the intermediate adjustment level and the emergency control level according to the deviation value;

[0159] In step 701, the preset risk threshold value refers to the stability critical value set according to historical flow field accident data and safety standards. The deviation value refers to the difference between the stability index and the preset risk threshold value, which is used to evaluate the degree of deviation of the current flow field from the safety range. The primary adjustment level refers to slight deviation, which can be restored to stability by adjusting the injection pump parameters slightly. The intermediate adjustment level refers to moderate deviation, which requires comprehensive adjustment of the pump flow, pressure and pipeline layout. The emergency control level refers to serious deviation, which requires immediate triggering of the pump protection and starting of manual intervention. The flow field control level refers to a hierarchical system for guiding control strategy, which is divided according to the degree of deviation of the flow field stability from the preset safety threshold.

[0160] In the embodiments of the present application, first, based on the principle of Doppler effect, the rate of change of velocity is inverted into the velocity component of the fluid in different directions to generate a stability index. Then, the stability index is compared with the preset risk threshold to calculate the deviation amount value. Finally, the flow field control level is divided according to the deviation amount, if the deviation amount is small, it is determined as the primary regulation level; if the deviation amount is moderate, it is determined as the intermediate regulation level; if the deviation amount significantly exceeds the threshold, it is determined as the emergency control level. Through signal analysis, physical model derivation and condition judgment, the whole process completes the dynamic mapping from the original signal to the control level.

[0161] 702, obtain the historical operation data and the current working parameter of the liquid filling pump, match the adjustment parameter group corresponding to the flow field control level in the historical operation data, calculate the deviation amount of the adjustment parameter group and the current working parameter, and generate the adjustment instruction set of the liquid filling pump;

[0162] In step 702, the historical operation data refers to the historical parameter record of the liquid filling pump under different working conditions, including flow, head, power, efficiency, etc. The current working parameter refers to the parameter under the real-time running state of the liquid filling pump. The adjustment parameter group refers to the historical parameter combination corresponding to a specific flow field control level. The deviation amount refers to the difference between the adjustment parameter group and the current working parameter, which is used to generate the adjustment instruction. The adjustment instruction set refers to the control command of the liquid filling pump generated according to the deviation amount, such as adjusting the valve opening, motor speed or the number of parallel pumps.

[0163] In the embodiments of the present application, first, the historical operation data of the liquid filling pump is called from the database. According to the flow field control level determined in step 701, the historical adjustment parameter group matching the level is selected. Then, the adjustment parameter group is compared with the current working parameter to calculate the deviation amount. Next, the adjustment instruction set designed by the deviation amount is generated, if the deviation amount is small, small adjustment instruction is generated through control algorithm. If the deviation amount is large, multi-parameter collaborative adjustment instruction is generated by using data fusion technology. Finally, the adjustment instruction set is output to the liquid filling pump control system to realize parameter dynamic correction and complete the closed-loop response from historical experience to real-time regulation.

[0164] 703, when the deviation amount value reaches the emergency control level and the time duration exceeds the preset time threshold, a fault warning report is triggered.

[0165] In step 703, the emergency control level refers to the level classification triggered when the flow field deviation amount reaches the emergency value range and the duration exceeds the preset threshold, indicating that the system is in a high-risk state. The preset time threshold refers to the emergency response time set according to the equipment tolerance limit. The fault warning report refers to the alarm information containing time, location, deviation amount, control level and suggested measures, which is used to inform the operator to intervene.

[0166] In the embodiments of the present application, first, the deviation value calculated in the real-time monitoring step 701 and the duration are monitored, and the time series analysis technology is used to determine whether the emergency control condition is met. If the deviation reaches the emergency control level and the duration exceeds the preset time threshold, the fault warning logic is triggered. Subsequently, a fault warning report is generated through a sound and light alarm device or a communication protocol, and the content includes time, location, deviation value and recommended measures, realizing rapid response and intervention to high-risk state.

[0167] The following is a specific example:

[0168] In a certain in-situ leaching uranium project, the real-time monitoring of the injection pump shows that the flow field stability index is lower than the preset safety threshold, and the deviation is in a low range, which is determined as a primary adjustment level. The system retrieves historical operation data and matches to the adjustment parameter group corresponding to this level. There is a slight difference between the current working parameters and the target parameters, and the adjustment instruction is generated after calculating the deviation. The control algorithm adjusts the speed of the pump to the target flow range, and adjusts the valve opening to increase the pressure to the matching value. If the stability index further decreases subsequently, the deviation enters the medium range, which is determined as a medium adjustment level, and the system matches a more stringent adjustment parameter group to generate more frequent adjustment instructions to quickly respond to changes. If the deviation continues to expand significantly beyond the safety range and the duration exceeds the preset threshold, a fault warning report is triggered to notify the operator to check the pipeline anomaly or adjust the injection rate to prevent equipment damage and production interruption.

[0169] In summary, steps 701 to 703 realize intelligent control of the uranium injection process by dynamically quantifying the flow field stability, matching historical data to generate accurate adjustment instructions, and implementing a multi-level warning mechanism. The system controls the flow field deviation within the preset safety range by adjusting the injection pump parameters in real time, significantly reducing the risk of pipe wear. At the same time, based on historical operation data, the optimal adjustment parameter group is matched to reduce trial and error costs and improve leaching agent delivery efficiency. The emergency warning mechanism can identify potential faults in advance to avoid equipment damage and production interruption. In addition, the closed-loop control logic formed by combining the pump performance curve and the flow field stability model realizes data-driven decision optimization, significantly improving the reliability and economy of the leaching system, and providing technical support for safe and efficient operation of the uranium leaching process.

[0170] Figure 2 A structure diagram of a flow field quantification analysis system for in-situ leaching of uranium is provided for the embodiments of the present application, as shown in Figure 2 The system comprises:

[0171] The acquisition module 21 acquires historical flow data and pressure time series data of the in-situ leaching uranium injection pipeline, combines the historical flow data with the pressure time series data according to the time dimension, to construct a flow pressure matrix reflecting the working state of the injection pump;

[0172] The extraction module 22 extracts the resonant frequency band energy features of the liquid injection pump from the flow pressure matrix, and constructs a pump health assessment atlas according to the intensity distribution of the resonant frequency band energy features;

[0173] The conversion module 23 synchronously acquires the fluid scattering signals of the in-situ leaching uranium liquid injection pipeline, and converts the fluid scattering signals into a three-dimensional flow velocity vector diagram reflecting the three-dimensional space flow velocity distribution;

[0174] The generation module 24 calculates the fluid acoustic impedance parameters according to the flow velocity vector modulus and direction change rate of each spatial position in the three-dimensional flow velocity vector diagram, and generates a flow field turbulence thermodynamic diagram characterizing the local turbulence intensity of the flow field based on the fluid acoustic impedance parameters;

[0175] The matching module 25 dynamically matches the pump health assessment atlas with the flow field turbulence thermodynamic diagram, calculates the stability index of the in-situ leaching uranium flow field, and generates the adjustment instruction set and the fault warning report of the liquid injection pump according to the deviation degree of the stability index from the preset risk threshold.

[0176] Figure 2 The quantitative analysis system of the in-situ leaching uranium flow field can perform Figure 1 The quantitative analysis method of the in-situ leaching uranium flow field of the embodiment described above does not need to be repeated. The specific way of executing the operation of each module and unit of the quantitative analysis system of the in-situ leaching uranium flow field in the above embodiment has been described in detail in the embodiment related to the method, which will not be described in detail here.

[0177] In one possible design, Figure 2 The quantitative analysis system of the in-situ leaching uranium flow field of the embodiment described above can be implemented as a computing device, such as Figure 3 As shown, the computing device can include a storage component 31 and a processing component 32.

[0178] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0179] The processing component 32 is configured to execute the above Figure 1 The quantitative analysis method of the in-situ leaching uranium flow field of the embodiment.

[0180] The processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components, configured to perform the methods described above.

[0181] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage devices or their combinations, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0182] Of course, the computing device can also include other components, such as an input / output interface, a display component, a communication component, etc.

[0183] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0184] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0185] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform, and the computing device can be a cloud server, and the processing component, the storage component, etc. can be a basic server resource rented or purchased from the cloud computing platform.

[0186] The embodiment of the application further provides a computer storage medium, which stores a computer program, and the computer program can implement the above Figure 1 A quantitative analysis method of a flow field of in-situ leaching uranium.

[0187] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0188] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0189] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0190] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A quantitative analysis method for the flow field of in-situ leaching uranium, characterized in that: include: Acquiring historical flow data and pressure time series data of an in-situ leaching uranium injection pipeline, and combining the historical flow data with the pressure time series data according to a time dimension to construct a flow and pressure matrix reflecting the working status of the injection pump; Extracting the resonance frequency band energy characteristics of the infusion pump from the flow-pressure matrix, and constructing a pump health assessment map based on the intensity distribution of the resonance frequency band energy characteristics; synchronously collecting fluid scattering signals of the in-situ leaching uranium injection pipeline, and converting the fluid scattering signals into a three-dimensional velocity vector diagram reflecting the three-dimensional spatial velocity distribution; Calculating the fluid acoustic impedance parameters according to the velocity vector modulus and directional change rate at each spatial position in the three-dimensional velocity vector diagram, and generating a flow field turbulence thermodynamic map representing the local turbulence intensity of the flow field based on the fluid acoustic impedance parameters; The pump health assessment map is dynamically matched with the flow field turbulence thermodynamic map to calculate the stability index of the in-situ uranium leaching flow field. Based on the degree of deviation between a preset risk threshold and the stability index, an adjustment instruction set and a fault warning report for the injection pump are generated.

2. The method according to claim 1, characterized in that Dynamically matching the pump health assessment map with the flow field turbulence thermodynamic map to calculate the stability index of the in-situ leaching uranium flow field includes: Aligning the vibration energy time series in the pump health assessment atlas with the intensity time series of the flow field turbulence thermodynamic map to generate a time-aligned data set; In the in-situ leaching uranium injection pipeline area, extracting pump vibration characteristic values ​​and turbulence intensity data at corresponding time points from the time-aligned dataset, and establishing a dynamic transmission relationship between the pump vibration characteristic values ​​and the turbulence intensity data; The conversion ratio of pump vibration energy to flow field turbulence intensity is calculated through the dynamic transfer relationship, and the conversion ratio values ​​are combined in chronological order to generate a stability index reflecting the stability of the in-situ leaching uranium flow field.

3. The method according to claim 2, characterized in that In the in-situ leaching uranium injection pipeline area, extracting pump vibration characteristic values ​​and turbulence intensity data at corresponding time points from the time-aligned dataset, and establishing a dynamic transmission relationship between the pump vibration characteristic values ​​and the turbulence intensity data, including: Extracting pump vibration characteristic values ​​and turbulence intensity data at corresponding time points in the in-situ leaching uranium injection pipeline area from the time-aligned dataset, and arranging and combining the pump vibration characteristic values, turbulence intensity data, and density parameters of the uranium ore leaching agent in chronological order to generate a time series dataset; Based on the time series data set, an initial correlation relationship between the pump vibration characteristic value and the turbulence intensity data is established, and based on the preset solvent fluid movement law, the initial correlation relationship with matching direction is screened, and the screened initial correlation relationship is superimposed as a dynamic transfer relationship.

4. The method according to claim 1, wherein Extracting the resonance frequency band energy characteristics of the infusion pump from the flow-pressure matrix, and constructing a pump health assessment map based on the intensity distribution of the resonance frequency band energy characteristics, including: Dividing the flow pressure matrix into frequency intervals, calculating the energy accumulation values ​​of the frequency intervals, and selecting the frequency intervals where the energy accumulation values ​​exceed a preset background noise threshold as target resonance frequency bands based on the vibration transmission characteristics of the infusion pump; extracting peak energy intensity data and bandwidth data of the target resonance frequency band as resonance frequency band energy characteristics, and calculating energy attenuation gradients of adjacent target resonance frequency bands; A pump health assessment map is generated based on a matching relationship between the frequency bandwidth data and the energy attenuation gradient.

5. The method according to claim 1, characterized in that Calculating the fluid acoustic impedance parameters according to the velocity vector modulus and directional change rate at each spatial position in the three-dimensional velocity vector diagram, and generating a flow field turbulence thermodynamic map representing the local turbulence intensity of the flow field based on the fluid acoustic impedance parameters, including: Obtaining the velocity vector modulus and the directional change rate at each spatial position in the three-dimensional velocity vector diagram and adjacent time points, and superimposing the density parameter of the uranium ore leaching agent, the velocity vector modulus and the directional change rate to generate a fluid acoustic impedance parameter; Converting the difference between the fluid acoustic impedance parameter and a preset reference acoustic impedance value into turbulence intensity data, and spatially transferring the turbulence intensity data of adjacent spatial positions to generate a turbulence intensity distribution of the injection pipe cross section; Based on the gradient change rate of the turbulence intensity distribution, a flow field turbulence thermodynamic map representing the local turbulence intensity of the flow field is constructed.

6. The method according to claim 1, characterized in that Converting the fluid scattering signal into a three-dimensional velocity vector diagram reflecting the three-dimensional spatial velocity distribution includes: Analyzing the frequency offset of each signal collection point in the fluid scattering signal to obtain signal change data, and converting the signal change data into a directional flow velocity component based on the propagation characteristics of the signal collection sound wave in the uranium ore leaching agent; Identifying spatial relationship parameters of adjacent signal acquisition points based on the spatial coordinate position of the injection pipe cross section, and combining directional flow velocity components at the same spatial position into a spatial flow velocity vector based on the spatial relationship parameters; The cross section of the injection pipe is divided into spatial grids, and the spatial flow velocity vector is associated and mapped with the spatial grids to generate a three-dimensional flow velocity vector map.

7. The method according to claim 1, characterized in that According to the degree of deviation between the preset risk threshold and the stability index, an adjustment instruction set and a fault warning report for the injection pump are generated, including: Calculating a deviation value between the stability index and a preset risk threshold, and determining a flow field control level including a primary regulation level, a secondary regulation level, and an emergency control level according to the deviation value; Acquiring historical operating data and current operating parameters of the injection pump, matching the adjustment parameter group corresponding to the flow field control level in the historical operating data, calculating the offset between the adjustment parameter group and the current operating parameters, and generating an adjustment instruction set for the injection pump; When the deviation value reaches the emergency control level and the duration exceeds the preset time threshold, a fault warning report is triggered.

8. A quantitative analysis system for in-situ leaching uranium flow field, characterized in that: include: An acquisition module acquires historical flow data and pressure time series data of an in-situ leaching uranium injection pipeline, combines the historical flow data with the pressure time series data according to a time dimension, and constructs a flow and pressure matrix reflecting the working status of the injection pump; an extraction module, which extracts the resonance frequency band energy characteristics of the infusion pump from the flow-pressure matrix and constructs a pump health assessment map based on the intensity distribution of the resonance frequency band energy characteristics; a conversion module for synchronously collecting fluid scattering signals of the in-situ leaching uranium injection pipeline and converting the fluid scattering signals into a three-dimensional velocity vector diagram reflecting the three-dimensional spatial velocity distribution; a generation module for calculating fluid acoustic impedance parameters according to the velocity vector modulus and directional change rate at each spatial position in the three-dimensional velocity vector diagram, and generating a flow field turbulence thermodynamic map representing the local turbulence intensity of the flow field based on the fluid acoustic impedance parameters; A matching module dynamically matches the pump health assessment map with the flow field turbulence thermodynamic map, calculates the stability index of the in-situ leaching uranium flow field, and generates an adjustment instruction set and a fault warning report for the injection pump based on the degree of deviation between a preset risk threshold and the stability index.

9. A computing device, characterized in that The method comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a quantitative analysis method for an in-situ leaching uranium flow field as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that A computer program is stored, and when the computer program is executed by a computer, the quantitative analysis method of the in-situ leaching uranium flow field according to any one of claims 1 to 7 is implemented.

Images