A rapid identification and fishing control system for foreign objects inside a geothermal well

Abstract

The present invention discloses a rapid identification and recovery control system for foreign objects inside a geothermal well, which relates to the technical field of identification and recovery control of foreign objects inside a geothermal well, and includes an initial identification and positioning module, a real-time data acquisition module, a data analysis and flow prediction module, a flow state classification module, a stable flow identification module, and a dynamic flow optimization module; the initial identification and positioning module deploys a high-resolution camera inside the geothermal well to perform initial foreign object identification and positioning operations with a set starting exposure time. The present invention uses a high-resolution camera and a built-in measurement module to collect hot water flow data in real time, combines a machine learning model to dynamically adjust the exposure time, realizes high-precision identification under static flow, shortens the exposure time under dynamic fluctuations to reduce motion blur, effectively improves the identification accuracy and efficiency, reduces the risk of missed detection, optimizes the camera response speed and parameter settings, and enables it to flexibly respond to complex environmental changes.

Description

Technical Field

[0001] The present invention relates to the technical field of foreign object identification, salvage and control inside a geothermal well, and particularly to a rapid foreign object identification, salvage and control system inside a geothermal well. Background Art

[0002] The identification and salvage of foreign objects inside a geothermal well refer to the process of using professional techniques to identify and remove possible foreign objects in the well, such as sediment, gravel, metal parts or biological debris, etc. during the operation of the geothermal well, in order to ensure the smoothness of the wellbore and the safety of equipment. This process usually uses downhole video detection equipment or sensors to locate foreign objects, combined with mechanical salvage tools (such as salvage claws, magnetic adsorbers or steel cable nets) to accurately capture and remove foreign objects, preventing them from affecting the water flow circulation of the geothermal well, the operation of the pump body or causing equipment damage. This technology not only ensures the stable operation of the geothermal system, but also extends the equipment life and improves the utilization efficiency of geothermal resources.

[0003] During the process of identifying and salvaging foreign objects inside a geothermal well, a high-resolution camera is a commonly used and effective positioning device. Such cameras have high-definition imaging capabilities and are equipped with a strong light illumination system, which can provide a clear picture of the well interior in low-light or turbid environments. Operators can accurately observe the type, size and specific location of foreign objects in the well through real-time video transmission, ensuring that the salvage tools can effectively aim at the foreign objects. Some high-resolution cameras also support optical zoom and remote control, making them flexible to apply in different depths and complex environments. The high-temperature and pressure-resistant design makes it suitable for the high-temperature and high-pressure environment of the geothermal well, providing an important guarantee for accurately identifying foreign objects and safe salvage.

[0004] The existing technologies have the following deficiencies:

[0005] High-resolution cameras in the existing technologies usually use a fixed exposure time for image acquisition to obtain stable and clear images in complex downhole environments. Inside a geothermal well, due to extremely limited lighting conditions and the presence of interference such as high temperature, high pressure and turbid liquids, the fixed exposure time can effectively reduce image noise, avoid brightness fluctuations caused by frequent exposure adjustments, and improve the accuracy of foreign object identification.

[0006] However, the flow velocity and direction of hot water inside a geothermal well are often unstable, which is likely to form fluctuations within the camera's field of view, increasing the difficulty of observing foreign objects. If the fixed exposure time continues to be used in such a highly dynamic environment, the captured images by the camera are prone to motion blur, and the shape and edges of foreign objects are difficult to clearly present. In severe cases, foreign objects with small volumes or inconspicuous surface features may not be recognized at all, resulting in missing the best opportunity for salvage, directly affecting the success rate of the task, and even endangering the safe operation of the geothermal well.

[0007] The above information disclosed in the background section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0008] The object of the present invention is to provide a rapid identification and salvage control system for foreign objects inside a geothermal well. It uses a high-resolution camera for initial identification and combines with the measurement module built in the camera to collect real-time flow data of hot water, establish a comprehensive data set. Through in-depth analysis and prediction by a machine learning model, it dynamically adjusts the exposure time of the camera to maintain high-precision image acquisition under static and stable flow, and under dynamic and fluctuating flow, it shortens the exposure time to effectively reduce motion blur caused by water flow vortices. This not only improves the accuracy and efficiency of foreign object identification, reduces the risk of missed detection, but also optimizes the response speed and parameter settings of the camera, enabling the system to flexibly adapt to dynamic changes in complex environments, so as to solve the problems in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solution: A rapid identification and salvage control system for foreign objects inside a geothermal well, including an initial identification and positioning module, a real-time data acquisition module, a data analysis and flow prediction module, a flow state classification module, a stable flow identification module, and a dynamic flow optimization module;

[0010] The initial identification and positioning module deploys a high-resolution camera inside the geothermal well to perform initial foreign object identification and positioning operations with a set starting exposure time;

[0011] The real-time data acquisition module, while performing foreign object identification and positioning, uses the measurement module built in the high-resolution camera to obtain real-time flow data of hot water inside the geothermal well and establish a comprehensive data set;

[0012] The data analysis and flow prediction module deeply analyzes the collected data set, extracts key features reflecting the flow state of hot water inside the geothermal well, performs anomaly analysis and processing on the extracted key features within a set monitoring window, and inputs the feature data after anomaly analysis and processing into a pre-trained machine learning model to perform real-time prediction on the flow situation of hot water inside the geothermal well;

[0013] The flow state classification module divides the flow situation of hot water within the monitoring window into two categories: dynamic and fluctuating type and static and stable type based on the prediction results of the machine learning model;

[0014] The stable flow identification module continues to use the high-resolution camera to perform foreign object identification and positioning with the set starting exposure time for the hot water flow in the geothermal well classified as static and stable type;

[0015] The dynamic flow optimization module, for the hot water flow in geothermal wells classified as dynamically fluctuating, optimizes and adjusts the exposure time of the high-resolution camera according to the predicted dynamic hot water flow conditions. Specifically, it shortens the exposure time of the camera to reduce motion blur caused by the rapid flow and eddies of the hot water.

[0016] Preferably, the set starting exposure time is optimized according to the lighting conditions of the geothermal well and the expected static flow environment to ensure that the high-resolution camera can capture high-quality images.

[0017] Preferably, the measurement module built into the high-resolution camera is a sensing unit integrated inside the high-resolution camera, which is used to detect and analyze the physical parameters of the environment inside the geothermal well in real time.

[0018] Preferably, the key features reflecting the hot water flow state inside the geothermal well are extracted. Among them, the extracted key features include the formation frequency, intensity of the eddies inside the geothermal well, and the deviation amplitude of the water flow direction inside the geothermal well. After performing anomaly analysis on the formation frequency, intensity of the eddies inside the geothermal well, and the deviation amplitude of the water flow direction inside the geothermal well within the set monitoring window, an eddy formation index and a flow direction deviation index are generated respectively. The eddy formation index is used to measure the occurrence frequency and intensity of the eddies inside the geothermal well, reflecting the turbulence degree and instability of the water flow in the well, and the flow direction deviation index is used to measure the change amplitude of the water flow direction inside the geothermal well, reflecting the degree of deviation of the water flow from the original direction.

[0019] Preferably, the eddy formation index and the flow direction deviation index generated after performing anomaly analysis within the monitoring window are input into a pre-trained machine learning model to generate a water flow dynamic coefficient, and the water flow dynamic coefficient is used to predict the flow conditions of the hot water inside the geothermal well in real time.

[0020] Preferably, the specific steps for generating the eddy formation index after performing anomaly analysis on the formation frequency and intensity of the eddies inside the geothermal well within the set monitoring window are as follows:

[0021] Within the monitoring window, first collect the instantaneous velocity of the hot water flow and the change rate of the pressure gradient. The instantaneous velocity of the hot water flow and the change rate of the pressure gradient are closely related to the formation of eddies. The preliminary expressions for the eddy formation frequency and eddy intensity are: In the formula, v(t) represents the instantaneous flow velocity of the hot water at time t. represents the change rate of the pressure gradient at time t, T represents the time length of the monitoring window, f vortex represents the eddy formation frequency, representing the frequency of fluctuations of the water flow velocity within the monitoring window, S vortex represents the eddy intensity, representing the combined effect of velocity and pressure gradient;

[0022] After identifying the eddy current formation frequency and eddy current intensity, a weighting process is performed on the eddy current formation frequency and eddy current intensity to calculate their comprehensive influence within the monitoring window. A non-linear weight function is used for the weighting calculation, and the calculation expression is: In the formula, α and β are the weight coefficients of the eddy current formation frequency and eddy current intensity respectively. W(f, S) is a non-linear weight function used to comprehensively evaluate the combined influence of the eddy current formation frequency and eddy current intensity of the water flow in the geothermal well on the water flow state;

[0023] Through the non-linear weight function, the final eddy current formation index is further generated. The eddy current formation index combines the eddy current formation frequency, eddy current intensity and their non-linear influence, providing an accurate assessment of the water flow turbulence degree and instability. The specific expression is:

[0024]

[0025] , where γ represents the suppression coefficient used to control the influence of drastic acceleration changes, dt represents the cumulative acceleration change used to capture the drastic change of the flow velocity over time, I vortex is the eddy current formation index.

[0026] Preferably, within the set monitoring window, the specific steps for generating the flow direction offset index after performing abnormal analysis on the offset amplitude of the water flow direction in the geothermal well are as follows:

[0027] Within the set monitoring window, the instantaneous direction vector of the hot water flow direction is collected and compared with the originally set flow direction vector to calculate the offset angle of the flow direction. The calculation expression is:

[0028]

[0029] , where θ(t) represents the water flow offset angle at time t, v t represents the water flow direction vector at time t, v0 represents the original reference direction vector, · represents the vector dot product operator, and ||*|| represents the modulus of the vector used to calculate the magnitude of the direction vector;

[0030] Within the monitoring window, the offset angles at all time points are accumulated, and the contribution of the offset is adjusted in combination with the flow velocity weight coefficient. The calculation expression is: Among them,

[0031]

[0032] , where ΔΘ is the cumulative offset angle within the monitoring window, w(t) is the flow velocity weight coefficient at time t used to amplify the influence of the high-speed water flow offset, and δ is the flow velocity weight factor used to adjust the sensitivity of the weight;

[0033] Using the cumulative offset angle and the time span within the monitoring window, a flow direction offset index is generated. The flow direction offset index reflects the overall offset trend of the water flow within the monitoring window, and the calculation expression is:

[0034]

[0035] , where, I 偏移 represents the flow direction offset index, which is used to measure the amplitude of the water flow direction change. S 偏移 represents the effective area with offset within the monitoring window. A 井 represents the total cross-sectional area of the geothermal well.

[0036] Preferably, when predicting the flow condition of the hot water in the geothermal well through a machine learning model within the monitoring window, the water flow dynamic coefficient generated is compared and analyzed with a preset reference threshold of the water flow dynamic coefficient, and the hot water flow condition within the monitoring window is classified. The specific classification steps are as follows:

[0037] If the water flow dynamic coefficient is greater than or equal to the reference threshold of the water flow dynamic coefficient, the hot water flow condition within the monitoring window is classified as dynamic fluctuation type;

[0038] If the water flow dynamic coefficient is less than the reference threshold of the water flow dynamic coefficient, the hot water flow condition within the monitoring window is classified as static stable type.

[0039] Preferably, according to the predicted dynamic flow condition of the hot water, the exposure time of the high-resolution camera is optimized and adjusted. The specific steps are as follows:

[0040] Calculate the exposure time adjustment coefficient using the water flow dynamic coefficient and the reference threshold of the water flow dynamic coefficient, which is used to quantify the intensity of the fluctuation and determine the degree of shortening of the exposure time. The calculation expression is:

[0041]

[0042] , where, K a is the exposure time adjustment coefficient, 0 < K a < 1, Water Flow represents the currently predicted water flow dynamic coefficient, C r is the reference threshold of the water flow dynamic coefficient;

[0043] Based on the starting exposure time and the exposure time adjustment coefficient, calculate the adjusted actual exposure time. The calculation expression is: T d = K a · T s , where, T d represents the actually adjusted exposure time after dynamic adjustment, T sIndicates the starting exposure time, the initial setting value under stable state;

[0044] According to the rate of change of the water flow dynamic coefficient, the actual exposure time is optimized in real time to ensure that the system responds to rapid changes in the environment and calculates the final exposure time. The calculation expression is:

[0045]

[0046] , where T f represents the final exposure time after real-time feedback, λ is the feedback weight factor, which controls the sensitivity of time adjustment, is the rate of change of the water flow dynamic coefficient with respect to time.

[0047] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0048] The present invention utilizes a high-resolution camera for initial recognition, and combines it with a built-in measurement module in the camera to collect hot water flow data in real time, establish a comprehensive data set, and dynamically adjust the camera's exposure time after in-depth analysis and prediction by a machine learning model, so that it can maintain high-precision image acquisition under static stable flow, and effectively reduce motion blur caused by water vortex under dynamic fluctuating flow by shortening the exposure time. This not only improves the accuracy and efficiency of foreign object recognition and reduces the risk of missed detection, but also optimizes the camera's response speed and parameter settings, so that the system can flexibly adapt to dynamic changes in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0050] Figure 1 The present invention is a schematic diagram of a module of a control system for quickly identifying and salvaging foreign objects inside a geothermal well. DETAILED DESCRIPTION

[0051] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0052] The present invention provides Figure 1A rapid identification and retrieval control system for foreign objects inside a geothermal well, as shown, includes an initial identification and positioning module, a real-time data acquisition module, a data analysis and flow prediction module, a flow state classification module, a steady flow identification module, and a dynamic flow optimization module;

[0053] The initial identification and positioning module deploys a high-resolution camera inside the geothermal well to perform initial foreign object identification and positioning operations with a set starting exposure time;

[0054] This step aims to obtain initial image data of the well environment and provide clear and stable visual information.

[0055] The set starting exposure time should be optimized according to the lighting conditions of the geothermal well and the expected static flow environment to ensure that the camera can capture high-quality images, laying a solid foundation for subsequent data analysis and model prediction.

[0056] The real-time data acquisition module, while performing foreign object identification and positioning, uses the measurement module built into the high-resolution camera to obtain real-time flow data of the hot water inside the geothermal well and establish a comprehensive data set;

[0057] The collected data should include but not be limited to key parameters such as the flow rate, flow direction, temperature, pressure, and eddy current intensity of the hot water. These data can comprehensively reflect the dynamic changes of the hot water inside the well and provide necessary information support for feature extraction and flow state prediction.

[0058] The measurement module built into the high-resolution camera is a sensing unit integrated inside the high-resolution camera for real-time detection and analysis of key physical parameters of the geothermal well environment. These measurement modules usually include temperature sensors, pressure sensors, accelerometers, flow rate sensors, and optical ranging modules. Among them, the temperature sensor monitors the water temperature change inside the well, the pressure sensor detects the water pressure fluctuation, the accelerometer senses the vibration or tilt change when the camera moves, the flow rate sensor measures the speed and direction of the liquid, and the optical ranging module determines the distance between the camera and the target foreign object in real time through laser or ultrasonic technology. These data are integrated into a comprehensive data set to provide accurate environmental information support for the camera's image acquisition and foreign object identification, ensuring that the system can flexibly respond in a dynamic and complex downhole environment and achieve precise positioning and identification.

[0059] The data analysis and flow prediction module deeply analyzes the collected data set, extracts key features reflecting the flow state of the hot water inside the geothermal well, performs anomaly analysis and processing on the extracted key features within a set monitoring window, and inputs the feature data after anomaly analysis and processing into a pre-trained machine learning model to perform real-time prediction on the flow situation of the hot water inside the geothermal well;

[0060] The key features reflecting the flow state of hot water in the geothermal well are extracted, among which the extracted key features include the formation frequency and intensity of the vortex in the geothermal well and the deviation amplitude of the flow direction of the water in the geothermal well. Within the set monitoring window, the formation frequency and intensity of the vortex in the geothermal well and the deviation amplitude of the flow direction of the water in the geothermal well are subjected to abnormal analysis and processing, and then the vortex formation index and the flow direction deviation index are generated respectively. The vortex formation index is used to measure the occurrence frequency and intensity of the vortex in the geothermal well, reflecting the turbulence degree and instability of the water flow in the well. The flow direction deviation index is used to measure the change amplitude of the water flow direction in the geothermal well, reflecting the degree to which the water flow deviates from the original direction.

[0061] The vortex formation index and flow direction deviation index generated after abnormal analysis within the monitoring window are input into the pre-trained machine learning model to generate the water flow dynamic coefficient, and the flow of hot water in the geothermal well is predicted in real time through the water flow dynamic coefficient.

[0062] A pre-trained machine learning model is one that has been trained and optimized with a large amount of historical data before making real-time predictions. The training process involves collecting characteristic data related to the flow of hot water in geothermal wells, such as vortex formation frequency, intensity, flow direction deviation amplitude, etc., and using this data to perform supervised or unsupervised learning on the model. The model continuously adjusts its internal parameters during the training phase to minimize errors, enabling it to capture the complex patterns and dynamic changes in the flow state of hot water. These models usually use advanced algorithms such as deep neural networks (DNNs), support vector machines (SVMs), or long short-term memory networks (LSTMs) to adapt to the time series characteristics and nonlinear changes of the flow state of geothermal wells.

[0063] Once the model is trained, it has strong generalization capabilities and can process new input data in practical applications. For example, the vortex formation index and flow direction deviation index generated within the monitoring window can be identified and analyzed in the machine learning model as input features. Based on these inputs, the model calculates the water flow dynamic coefficient in real time and predicts the current or upcoming flow pattern, such as whether there will be violent fluctuations, flow direction deviation or increased turbulence. This real-time prediction provides a scientific basis for the exposure time and parameter adjustment of the camera, enabling the camera to flexibly respond to the challenges of foreign object identification in dynamic environments. At the same time, the model can also continuously absorb new data over time, and further improve its prediction accuracy and robustness through online learning or periodic retraining. This machine learning method has greatly improved the intelligence level and response efficiency of geothermal well foreign object identification and salvage systems.

[0064] When the formation frequency and intensity of the eddy current in the geothermal well are relatively high, it indicates that the hot water in the well is in a continuous dynamic fluctuation state. The frequent generation and enhancement of the eddy current mean that the direction and speed of the water flow change continuously in a short period of time, and the flow pattern changes from a stable laminar flow to a turbulent flow. This dynamic fluctuation not only increases the energy exchange and disturbance inside the water body, but also reflects the instability of the fluid environment in the geothermal well. In this case, the identification and positioning of foreign objects will become more complicated because the eddy current will interfere with the objects within the camera's field of view, making it difficult to capture their shapes and positions.

[0065] The specific steps for generating the eddy current formation index through anomaly analysis and processing of the formation frequency and intensity of the eddy current in the geothermal well within the set monitoring window are as follows:

[0066] Within the monitoring window, first collect the instantaneous velocity of the hot water flow and the change rate of the pressure gradient. The instantaneous velocity of the hot water flow and the change rate of the pressure gradient are closely related to the formation of the eddy current. The preliminary expressions for the eddy current formation frequency and the eddy current intensity are: In the formula, v(t) represents the instantaneous flow velocity of the hot water at time t, represents the change rate of the pressure gradient at time t, T represents the time length of the monitoring window, f vortex represents the eddy current formation frequency, which represents the frequency of fluctuations in the water flow velocity within the monitoring window, and S vortex represents the eddy current intensity, which represents the combined effect of the velocity and the pressure gradient;

[0067] After identifying the eddy current formation frequency and the eddy current intensity, perform a weighting process on the eddy current formation frequency and the eddy current intensity, calculate their comprehensive influence within the monitoring window, and use a non-linear weight function for the weighting calculation. The calculation expression is: In the formula, α and β are the weight coefficients of the eddy current formation frequency and the eddy current intensity respectively, which can be set according to the actual situation of the geothermal well and are not specifically limited here. W(f, S) is a non-linear weight function used to comprehensively evaluate the combined influence of the eddy current formation frequency and the eddy current intensity of the water flow in the geothermal well on the water flow state;

[0068] is a non-linear transformation used to amplify the influence of high-frequency fluctuations, and exp(S vortex ) represents exponential function processing, which is used to reflect the exacerbation of the system instability caused by strong eddy currents.

[0069] Further generate the final eddy current formation index through the non-linear weight function. The eddy current formation index combines the eddy current formation frequency, the eddy current intensity, and their non-linear influence, providing an accurate assessment of the degree of water flow turbulence and instability. The specific expression is:

[0070]

[0071] , where γ represents the suppression coefficient, which is used to control the impact of drastic acceleration changes, represents the cumulative acceleration change, which is used to capture the drastic changes in flow velocity over time, I vortex is the eddy formation index.

[0072] From the eddy formation index, it can be seen that within the set monitoring window, the larger the value of the eddy formation index generated after abnormal analysis of the formation frequency and intensity of eddies in the geothermal well, the higher the degree of water turbulence, the more frequent and intense the fluctuations in flow velocity and direction, indicating that the hot water in the geothermal well is in a significant dynamic fluctuation state. At this time, the disturbance of the water flow will be more complex, which may cause greater interference to the foreign object recognition and positioning of the camera. On the contrary, if the value of the eddy formation index is small, it indicates that the changes in the frequency and intensity of the water flow are not obvious, and the flow of the hot water tends to be stable, belonging to a relatively stable state.

[0073] When the deviation amplitude of the water flow direction in the geothermal well is large, it usually indicates that the hot water is constantly fluctuating dynamically. The deviation amplitude of the flow direction reflects the degree of change of the water flow direction relative to the original path, and this deviation is often caused by factors such as eddies, local pressure changes, or unstable hot water flow velocity. If the flow direction deviates frequently and significantly, it means that the water flow is disturbed by external forces or environmental factors, resulting in the flow pattern of the water body in the well changing from a stable state to an irregular fluctuating state.

[0074] Within the set monitoring window, the specific steps for generating the flow direction deviation index after abnormal analysis of the deviation amplitude of the water flow direction in the geothermal well are as follows:

[0075] Within the set monitoring window, collect the instantaneous direction vector of the hot water flow direction, compare it with the originally set flow direction vector, calculate the deviation angle of the flow direction, and the calculation expression is:

[0076]

[0077] , where θ(t) represents the water flow deviation angle at time t (unit: degree or radian), v t represents the water flow direction vector at time t, v0 represents the original reference direction vector (the expected water flow direction of the geothermal well), · represents the vector dot product operator, and ||*|| represents the modulus of the vector, which is used to calculate the magnitude of the direction vector;

[0078] This step calculates the deviation angle of the water flow relative to the reference direction at each time point. The larger the angle, the more serious the deviation of the water flow direction.

[0079] Within the monitoring window, accumulate the deviation angles at all time points and adjust the contribution of the deviation in combination with the flow velocity weight coefficient to prevent the deviation at low speeds from having too much impact on the index. The calculation expression is: in,

[0080]

[0081] , where ΔΘ is the cumulative deviation angle within the monitoring window, w(t) is the velocity weight coefficient at time t, which is used to amplify the impact of high-speed water flow deviation, and δ is the velocity weight factor, which is used to adjust the sensitivity of the weight (usually a positive number, such as 1.5 or 2);

[0082] This step ensures that when the water velocity is high, the corresponding directional offset has a greater impact on the final index, while the offset at low velocity has a smaller impact.

[0083] The flow direction deviation index is generated by using the cumulative deviation angle and the time span within the monitoring window. The flow direction deviation index reflects the overall deviation trend of the water flow within the monitoring window. The calculation expression is:

[0084]

[0085] , where I 偏移 Represents the flow deviation index, which is used to measure the magnitude of the change in the direction of the water flow. 偏移 Indicates the effective area where the offset occurs within the monitoring window, A 井 represents the total cross-sectional area of the geothermal well;

[0086] The effective area where the deviation occurs refers to the spatial area covered by the area where the geothermal well water flow direction is deviated within the monitoring window. This area reflects the size of the area where the water flow actually deviates during the flow, that is, the part of the water flow that deviates from the original set flow direction. The calculation of the effective area usually combines factors such as the deviation angle of the water flow, the flow velocity, and the cross-sectional area of the well. If the water flow deviates in multiple areas, the areas of these areas will be calculated cumulatively. The larger the effective area of the deviation, the more significant the instability and dynamic fluctuation of the water flow. This indicator plays a key role in quantifying the degree of water flow anomaly and determining the exposure adjustment strategy of the camera.

[0087] It can be seen from the flow deviation index that within the set monitoring window, the larger the performance value of the flow deviation index generated after abnormal analysis of the deviation amplitude of the water flow direction in the geothermal well, the more frequent and drastic changes in the flow direction of the hot water have occurred during this period of time, reflecting that the dynamic fluctuations of the water flow are more obvious. This means that the hot water is greatly affected by external interference (such as eddy currents, pressure changes, or structural obstructions in the well), and the water flow tends to be unstable. On the contrary, when the value of the flow deviation index is small, it means that the water flow direction is relatively consistent and the flow direction changes are small, indicating that the hot water is in a relatively stable state and the dynamic fluctuations are not obvious.

[0088] The machine learning model is not specifically limited here, and can realize the eddy current formation index Ivortex and the flow direction offset index I 偏移 are comprehensively analyzed to generate the water flow dynamic coefficient Water Flow Any machine learning model can be used. To implement the technical solution of the present invention, the present invention provides a specific implementation manner; the water flow dynamic coefficient Water Flow The calculation formula generated is as follows:

[0089]

[0090] , where r1 and r2 are respectively the eddy current formation index I vortex and the flow direction offset index I 偏移 of the preset proportionality coefficient, and both r1 and r2 are greater than 0.

[0091] It can be seen from the water flow dynamic coefficient that within the set monitoring window, the larger the value of the eddy current formation index generated after abnormal analysis and processing of the formation frequency and intensity of the eddy current in the geothermal well, and the larger the value of the flow direction offset index generated after abnormal analysis and processing of the offset amplitude of the water flow direction in the geothermal well. That is, when predicting the water flow situation in the geothermal well through the machine learning model in the monitoring window, the larger the value of the water flow dynamic coefficient generated, the more obvious the water flow dynamic fluctuation is, and vice versa, it indicates that the water flow dynamic fluctuation is less obvious.

[0092] The flow state classification module divides the water flow situation of the hot water in the monitoring window into two categories: dynamic fluctuation type and static stability type based on the prediction results of the machine learning model;

[0093] The water flow dynamic coefficient generated when predicting the water flow situation of the hot water in the geothermal well through the machine learning model in the monitoring window is compared and analyzed with the pre-set water flow dynamic coefficient reference threshold to divide the water flow situation of the hot water in the monitoring window. The specific division steps are as follows:

[0094] If the water flow dynamic coefficient is greater than or equal to the water flow dynamic coefficient reference threshold, the water flow situation of the hot water in the monitoring window is divided into the dynamic fluctuation type;

[0095] If the water flow dynamic coefficient is less than the water flow dynamic coefficient reference threshold, the water flow situation of the hot water in the monitoring window is divided into the static stability type.

[0096] The dynamic fluctuation type refers to the situation where the hot water flow rate and direction change significantly, the eddy current is obvious, and the flow is unstable; the static stability type refers to the situation where the hot water flow rate is constant, the flow direction is consistent, and the flow is stable. Through clear classification, corresponding foreign object recognition strategies can be formulated for different flow states, improving the accuracy and efficiency of recognition.

[0097] The stable flow identification module, for the hot water flow of geothermal wells classified as static stable type, continues to use a high-resolution camera to identify and locate foreign objects with a set starting exposure time;

[0098] For the hot water flow of geothermal wells classified as static stable type, it means that the flow rate and direction of the hot water remain relatively constant, without obvious eddies, flow rate fluctuations or direction offsets. In such a stable environment, the water flow dynamics are relatively controllable, which will not interfere with the camera's field of view, nor cause motion blur or image distortion. Therefore, in this state, the system does not need to adjust the exposure time or image acquisition parameters of the camera, and can continue to use the preset starting exposure time to identify and locate foreign objects.

[0099] The set starting exposure time is usually optimized to suit the lighting conditions and imaging requirements in the stable environment of the well. This exposure time can ensure that the images captured by the camera have high clarity and low noise, enabling the edge and detail features of foreign objects to be clearly presented. Due to the stable water flow, the position of foreign objects will not move or blur due to the disturbance of the water flow, and the camera can efficiently complete the identification and positioning tasks.

[0100] By maintaining the initial exposure time in a static stable environment, the system avoids unnecessary frequent adjustments, improves the efficiency and accuracy of foreign object identification. At the same time, this strategy reduces the computational load and equipment wear of the camera, helps to extend the service life of the equipment, and optimizes the execution of the fishing task. Ultimately, this method ensures that the system continuously provides reliable foreign object identification and accurate positioning services in the stable flow state of the geothermal well.

[0101] The dynamic flow optimization module, for the hot water flow of geothermal wells classified as dynamic fluctuation type, optimizes and adjusts the exposure time of the high-resolution camera according to the predicted dynamic flow of the hot water. Specifically, it shortens the exposure time of the camera to reduce the motion blur caused by the rapid flow and eddies of the hot water;

[0102] Optimize and adjust the exposure time of the high-resolution camera according to the predicted dynamic flow of the hot water. The specific steps are as follows:

[0103] Calculate the exposure time adjustment coefficient using the water flow dynamic coefficient and the water flow dynamic coefficient reference threshold to quantify the intensity of the fluctuation and determine the degree of shortening of the exposure time. The calculation formula is:

[0104]

[0105] where, K a is the exposure time adjustment coefficient, 0 < K a < 1, Water Flow represents the currently predicted water flow dynamic coefficient, Cr is the reference threshold of the water flow dynamic coefficient;

[0106] Based on the starting exposure time and the exposure time adjustment coefficient, calculate the adjusted actual exposure time. The calculation formula is: T d = K a ·T s , where T d represents the actual exposure time after dynamic adjustment, and T s represents the starting exposure time, which is the initial set value in the stable state;

[0107] When the water flow dynamic coefficient is significantly higher than the water flow dynamic coefficient reference threshold, the adjusted actual exposure time will be shortened to reduce image blurring caused by water flow fluctuations.

[0108] According to the change rate of the water flow dynamic coefficient, the actual exposure time is optimized in real time to ensure that the system responds quickly to environmental changes. Calculate the final exposure time. The calculation formula is:

[0109]

[0110] , where T f represents the final exposure time after real-time feedback. λ is the feedback weight factor, which controls the sensitivity of time adjustment, is the change rate of the water flow dynamic coefficient with respect to time.

[0111] Shortening the exposure time can capture instantaneous images faster, freeze foreign objects in dynamic scenes, and ensure that their shapes and edges are clearly presented. At the same time, it may be necessary to enhance the light source illumination or increase the camera's sensitivity to make up for the lack of brightness caused by the shortened exposure time. Through this dynamic adjustment, the camera can adapt to the complex and changeable underground environment, continuously provide high-precision foreign object recognition and positioning, and ensure the success rate of the fishing operation and the safe operation of the geothermal well.

[0112] The present invention uses a high-resolution camera for initial recognition, combines with the measurement module built in the camera to collect real-time flow data of hot water, establishes a comprehensive data set, and through in-depth analysis and prediction of the machine learning model, dynamically adjusts the exposure time of the camera, so that it can maintain high-precision image acquisition under static stable flow, and under dynamic fluctuating flow, by shortening the exposure time, effectively reduce the motion blur caused by water flow vortices, not only improve the accuracy and efficiency of foreign object recognition, reduce the risk of missed detection, but also optimize the camera's response speed and parameter settings, enabling the system to flexibly adapt to dynamic changes in complex environments. In addition, it reduces repeated detections and equipment load caused by environmental changes, extends the service life of the equipment, avoids the risks of wellbore blockage and equipment damage caused by failure to fish key foreign objects in time, and ensures the safe operation of the geothermal well and the maximization of economic benefits.

[0113] The above formulas are all dimensionless and only take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulations to get a formula that is closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0114] Only some exemplary embodiments of the present invention have been described above by way of illustration. Without doubt, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of the claims of the present invention.

[0115] It should be noted that in this text, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0116] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution is prior or subsequent. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0117] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this text can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0118] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0119] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0120] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, in each embodiment of the present application, the functional units can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0122] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0123] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A rapid identification and recovery control system for foreign objects inside a geothermal well, characterized in that, It includes an initial recognition and positioning module, a real-time data acquisition module, a data analysis and flow prediction module, a flow state classification module, a stable flow recognition module, and a dynamic flow optimization module; The initial recognition and positioning module deploys a high-resolution camera inside the geothermal well to perform initial foreign object recognition and positioning operations at a set starting exposure time; The real-time data acquisition module, while performing foreign object recognition and positioning, uses the measurement module built into the high-resolution camera to obtain the flow data of the hot water in the geothermal well in real time and establish a comprehensive data set; The data analysis and flow prediction module deeply analyzes the collected data set, extracts the key features reflecting the flow state of the hot water in the geothermal well, performs anomaly analysis on the extracted key features within a set monitoring window, and inputs the feature data after anomaly analysis into a pre-trained machine learning model to predict the flow of the hot water in the geothermal well in real time; The flow state classification module divides the hot water flow situation within the monitoring window into two categories: dynamic fluctuation type and static stability type based on the prediction results of the machine learning model; The stable flow recognition module continues to use the high-resolution camera to perform foreign object recognition and positioning at the set starting exposure time for the hot water flow in the geothermal well classified as static stability type; The dynamic flow optimization module, for the hot water flow in the geothermal well classified as dynamic fluctuation type, optimizes and adjusts the exposure time of the high-resolution camera according to the predicted dynamic flow situation of the hot water, specifically by shortening the exposure time of the camera to reduce the motion blur caused by the rapid flow and eddy current of the hot water.

2. The quick identification and fishing control system for foreign objects inside a geothermal well according to claim 1, characterized in that The set starting exposure time is optimized according to the lighting conditions of the geothermal well and the expected static flow environment to ensure that the high-resolution camera can capture high-quality images.

3. The rapid identification and fishing control system for foreign objects inside a geothermal well according to claim 1, characterized in that The measurement module built into the high-resolution camera is a sensing unit integrated inside the high-resolution camera, which is used to detect and analyze the physical parameters of the environment inside the geothermal well in real time.

4. The quick identification and fishing control system for foreign objects inside a geothermal well according to claim 1, characterized in that Extract the key features reflecting the flow state of the hot water in the geothermal well. Among them, the extracted key features include the formation frequency, intensity of the eddy current in the geothermal well, and the deviation amplitude of the water flow direction in the geothermal well. After performing anomaly analysis on the formation frequency, intensity of the eddy current in the geothermal well, and the deviation amplitude of the water flow direction in the geothermal well within a set monitoring window, an eddy current formation index and a flow direction deviation index are generated respectively. The eddy current formation index is used to measure the occurrence frequency and intensity of the eddy current in the geothermal well, reflecting the turbulence degree and instability of the water flow in the well, and the flow direction deviation index is used to measure the change amplitude of the water flow direction in the geothermal well, reflecting the degree of deviation of the water flow from the original direction.

5. The rapid identification and fishing control system for foreign objects inside a geothermal well according to claim 4, wherein Input the eddy current formation index and the flow direction deviation index generated after anomaly analysis within the monitoring window into a pre-trained machine learning model to generate a water flow dynamic coefficient, and use the water flow dynamic coefficient to predict the flow of the hot water in the geothermal well in real time.

6. The quick identification and fishing control system for foreign objects inside a geothermal well according to claim 4, characterized in that, The specific steps for generating the eddy current formation index after performing anomaly analysis on the formation frequency and intensity of the eddy current in the geothermal well within a set monitoring window are as follows: In the monitoring window, first collect the instantaneous velocity of the hot water flow and the rate of change of the pressure gradient. The instantaneous velocity of the hot water flow and the rate of change of the pressure gradient are closely related to the formation of eddy currents. The preliminary expressions for the eddy current formation frequency and eddy current intensity are as follows: In the formula, v(t) represents the instantaneous flow velocity of the hot water at time t, represents the rate of change of the pressure gradient at time t, T represents the time length of the monitoring window, f vortex represents the eddy current formation frequency, which represents the frequency of fluctuations in the water flow velocity within the monitoring window, S vortex represents the eddy current intensity, which represents the combined effect of velocity and pressure gradient; After identifying the eddy current formation frequency and eddy current intensity, perform a weighting process on the eddy current formation frequency and eddy current intensity, calculate their comprehensive influence within the monitoring window, and use a non-linear weight function for weighted calculation. The calculation expression is as follows: In the formula, α and β are the weight coefficients of the eddy current formation frequency and eddy current intensity respectively. W(f, S) is a non-linear weight function used to comprehensively evaluate the combined influence of the eddy current formation frequency and eddy current intensity of the water flow in the geothermal well on the water flow state; The final vortex formation index is further generated through a non-linear weight function. The vortex formation index combines the vortex formation frequency and intensity and their non-linear effects to provide an accurate assessment of the degree of water flow turbulence and instability. The specific expression is as follows: ， In the formula, γ represents the suppression coefficient, which is used to control the influence of drastic acceleration changes. represents the accumulation of acceleration changes and is used to capture drastic changes in the flow velocity over time. I vortex is the eddy formation index.

7. The quick identification and fishing control system for foreign objects inside a geothermal well according to claim 6, wherein The specific steps for generating the flow direction offset index through anomaly analysis of the offset amplitude of the water flow direction in the geothermal well within the set monitoring window are as follows: Within the set monitoring window, collect the instantaneous direction vector of the hot water flow direction, compare it with the originally set flow direction vector, and calculate the offset angle of the flow direction. The calculation expression is: ， where, θ(t) represents the water flow deflection angle at time t, v t represents the water flow direction vector at time t, v0 represents the original reference direction vector, · represents the vector dot product operator, and ||*|| represents the magnitude of the vector, which is used to calculate the magnitude of the direction vector; In the monitoring window, the offset angles at all time points are accumulated, and the contribution of the offset is adjusted in combination with the flow velocity weight coefficient. The calculation expression is as follows: where ， In the formula, ΔΘ is the cumulative offset angle within the monitoring window, w(t) is the flow velocity weight coefficient at time t, which is used to amplify the influence of the high-speed water flow offset, and δ is the flow velocity weight factor, which is used to adjust the sensitivity of the weight; Use the cumulative offset angle and the time span within the monitoring window to generate the flow direction offset index. The flow direction offset index reflects the overall offset trend of the water flow within the monitoring window. The calculation expression is: ， Where, I 偏移 represents the flow direction deviation index, which is used to measure the amplitude of the change in the water flow direction, and S 偏移 represents the effective area where deviation occurs within the monitoring window, and A 井 represents the total cross-sectional area of the geothermal well.

8. The rapid identification and fishing control system for foreign objects inside a geothermal well according to claim 5, characterized in that Compare and analyze the water flow dynamic coefficient generated when predicting the water flow situation in the geothermal well through a machine learning model within the monitoring window with the pre-set reference threshold of the water flow dynamic coefficient to classify the water flow situation within the monitoring window. The specific classification steps are as follows: If the water flow dynamic coefficient is greater than or equal to the reference threshold of the water flow dynamic coefficient, classify the water flow situation within the monitoring window as the dynamic fluctuation type; If the water flow dynamic coefficient is less than the reference threshold of the water flow dynamic coefficient, classify the water flow situation within the monitoring window as the static stability type.

9. The rapid identification and fishing control system for foreign objects inside a geothermal well according to claim 8, characterized in that Optimize and adjust the exposure time of the high-resolution camera according to the predicted hot water dynamic flow situation. The specific steps are as follows: Calculate the exposure time adjustment coefficient using the water flow dynamic coefficient and the reference threshold of the water flow dynamic coefficient, which is used to quantify the intensity of the fluctuation and determine the degree of shortening of the exposure time. The calculation expression is: ， Where, K a is the exposure time adjustment coefficient, 0 < K a < 1, Water Flow represents the currently predicted water flow dynamic coefficient, C r is the reference threshold of the water flow dynamic coefficient; Based on the starting exposure time and the exposure time adjustment coefficient, calculate the adjusted actual exposure time. The calculation expression is: T d = K a ·T s , where T d represents the actual exposure time after dynamic adjustment, and T s represents the starting exposure time, which is the initial set value in the stable state; According to the change rate of the water flow dynamic coefficient, optimize the actual exposure time in real time to ensure the system responds quickly to environmental changes and calculate the final exposure time. The calculation expression is: ， Where, T f represents the final exposure time after real-time feedback, λ is the feedback weight factor, which controls the sensitivity of time adjustment, is the rate of change of the water flow dynamic coefficient with respect to time.

Images