Control system for quickly identifying and salvaging foreign matters in geothermal well

Abstract

The invention discloses a geothermal well internal foreign matter rapid identification and salvage control system, and relates to the technical field of geothermal well internal foreign matter identification and salvage control. Comprising 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. And the initial recognition and positioning module is used for deploying a high-resolution camera in the geothermal well and carrying out initial foreign matter recognition and positioning operation according to the set initial exposure time. The high-resolution camera and the built-in measurement module are used for collecting hot water flow data in real time, the exposure time is dynamically adjusted in combination with a machine learning model, high-precision recognition under static flow is achieved, the exposure time is shortened under dynamic fluctuation so as to reduce motion blur, the recognition accuracy and efficiency are effectively improved, the missing detection risk is reduced, and the recognition efficiency is improved. And the response speed and parameter setting of the camera are optimized, so that the camera can flexibly cope with complex environment changes.

Description

Technical Field

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

[0002] Foreign body identification and salvage in geothermal wells refers to the use of professional technology to identify and remove foreign bodies that may exist in the well, such as mud, gravel, metal parts or biological debris, in order to ensure the smooth flow of the well and the safety of equipment during the operation of the geothermal well. This process usually uses downhole video detection equipment or sensors to locate foreign bodies, combined with mechanical salvage tools (such as salvage claws, magnetic absorbers or steel cable nets) to accurately capture and remove foreign bodies to prevent them from affecting the water 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 life of the equipment and improves the utilization efficiency of geothermal resources.

[0003] In the process of identifying and salvaging foreign objects inside geothermal wells, high-resolution cameras are a common and effective positioning device. This type of camera has high-definition imaging capabilities and is equipped with a strong light illumination system, which can provide clear images inside the well in low-light or turbid environments. Operators use real-time video feedback to accurately observe the type, size and specific location of foreign objects in the well to ensure that the salvage tools can effectively aim at the foreign objects. Some high-resolution cameras also support optical zoom and remote control, allowing them to be flexibly used at different depths and in complex environments. The high-temperature and pressure-resistant design makes it suitable for the high-temperature and high-pressure environment of geothermal wells, providing important guarantees for accurate identification of foreign objects and safe salvage.

[0004] The prior art has the following deficiencies:

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

[0006] However, the flow speed and direction of hot water in geothermal wells are often unstable, which can easily cause fluctuations in the camera's field of view, making it more difficult to observe foreign objects. If a fixed exposure time is continued, in this highly dynamic environment, the images captured 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 that are small in size or have unclear surface features may be completely unrecognizable, resulting in missing the best time to salvage them, directly affecting the success rate of the mission and even endangering the safe operation of the geothermal well.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

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

[0009] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a control system for rapid identification and salvage of foreign bodies inside a geothermal well, comprising 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 in 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 identifying and locating foreign objects, uses the built-in measurement module of the high-resolution camera to obtain the flow data of hot water in the geothermal well in real time and establish a comprehensive data set;

[0012] The data analysis and flow prediction module conducts in-depth analysis on the collected data set, extracts key features that reflect the flow status of hot water in geothermal wells, performs abnormal analysis on the extracted key features within the set monitoring window, and inputs the feature data that has undergone abnormal analysis into the pre-trained machine learning model to make real-time predictions on the flow status of hot water in geothermal wells;

[0013] The flow state classification module divides the hot water flow conditions in the monitoring window into two types: dynamic fluctuation type and static stability type based on the prediction results of the machine learning model;

[0014] The stable flow identification module, for geothermal well hot water flows classified as static stable, continues to use a high-resolution camera to identify and locate foreign objects with a set initial exposure time;

[0015] The dynamic flow optimization module optimizes the exposure time of the high-resolution camera based on the predicted dynamic flow of hot water in geothermal wells classified as dynamically fluctuating. Specifically, the camera exposure time is shortened to reduce motion blur caused by rapid flow of hot water and eddies.

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

[0017] Preferably, the built-in measurement module of the high-resolution camera is a sensor unit integrated inside the high-resolution camera, which is used for real-time detection and analysis of physical parameters of the environment inside the geothermal well.

[0018] Preferably, key features reflecting the flow state of hot water in a geothermal well are extracted, wherein the extracted key features include the formation frequency and intensity of vortices in the geothermal well and the deviation amplitude of the flow direction of water in the geothermal well. Within a set monitoring window, after abnormal analysis and processing of the formation frequency and intensity of vortices in the geothermal well and the deviation amplitude of the flow direction of water in the geothermal well, a vortex formation index and a flow direction deviation index are generated respectively. The vortex formation index is used to measure the occurrence frequency and intensity of vortices in the geothermal well, reflecting the degree of turbulence 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.

[0019] Preferably, the vortex formation index and flow direction deviation index generated after abnormal analysis processing within the monitoring window are input into a pre-trained machine learning model to generate a 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.

[0020] Preferably, within a set monitoring window, the specific steps of generating a vortex formation index after abnormal analysis of the formation frequency and intensity of the vortex in the geothermal well are as follows:

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

[0022] After identifying the eddy current formation frequency and eddy current intensity, the eddy current formation frequency and eddy current intensity are weighted to calculate their comprehensive impact within the monitoring window. The nonlinear weight function is used for weighted calculation. The calculation expression is: Where α and β are the weight coefficients of vortex formation frequency and vortex intensity, respectively, and W(f, S) is a nonlinear weight function used to comprehensively evaluate the joint influence of vortex formation frequency and vortex intensity on the water flow state in geothermal wells;

[0023] The final vortex formation index is further generated through the nonlinear weight function. The vortex formation index combines the vortex formation frequency and vortex intensity and their nonlinear effects to provide an accurate assessment of the turbulence degree and instability of the water flow. The specific expression is:

[0024] , where γ represents the suppression coefficient, which is used to control the impact of drastic acceleration changes. It represents the accumulation of acceleration changes and is used to capture the drastic changes in flow velocity over time. vortex is the vortex formation index.

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

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

[0028] , where θ(t) represents the water flow deviation 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, ∥*∥ represents the vector modulus, which is used to calculate the magnitude of the direction vector;

[0030] In the monitoring window, the offset angles at all time points are accumulated, and the contribution of the velocity weight coefficient to the offset is adjusted. The calculation expression is: in,

[0031] , 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;

[0033] 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:

[0034] , 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.

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

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

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

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

[0040] The exposure time adjustment coefficient is calculated using the water flow dynamic coefficient and the water flow dynamic coefficient reference threshold, 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] , where K a is the exposure time adjustment factor, 0 <K a <1, Water Flow Represents the current predicted water flow dynamic coefficient, C r is the reference threshold of water flow dynamic coefficient;

[0043] Based on the initial exposure time and the exposure time adjustment coefficient, the adjusted actual exposure time is calculated. The calculation expression is: T d =K a ·T s , where T d Indicates the actual exposure time after dynamic adjustment, T s Indicates 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] , where Tf 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 and establish a comprehensive data set. After in-depth analysis and prediction by a machine learning model, the camera's exposure time is dynamically adjusted to maintain high-precision image acquisition under static stable flow, and to 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 1 A geothermal well internal foreign body rapid identification and salvage control system is shown, comprising 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;

[0053] The initial identification and positioning module deploys a high-resolution camera in 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 initial 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 identifying and locating foreign objects, uses the built-in measurement module of the high-resolution camera to obtain the flow data of hot water in the geothermal well in real time and establish a comprehensive data set;

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

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

[0059] The data analysis and flow prediction module conducts in-depth analysis on the collected data set, extracts key features that reflect the flow status of hot water in geothermal wells, performs abnormal analysis on the extracted key features within the set monitoring window, and inputs the feature data that has undergone abnormal analysis into the pre-trained machine learning model to make real-time predictions on the flow status of hot water in geothermal wells;

[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 frequency and intensity of vortex formation in a geothermal well are high, it indicates that the hot water is in a state of continuous dynamic fluctuation in the well. The frequent generation and enhancement of vortices means that the direction and speed of the water flow are constantly changing in a short period of time, and the flow pattern changes from smooth laminar flow to 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, foreign object identification and positioning will become more complicated because the vortex will interfere with the objects in the camera's field of view, making their shape and position difficult to capture.

[0065] The specific steps for generating the vortex formation index after abnormal analysis of the frequency and intensity of vortex formation in the geothermal well within the set monitoring window are as follows:

[0066] In the monitoring window, the instantaneous velocity and pressure gradient change rate of the hot water flow are first collected. The instantaneous velocity and pressure gradient change rate of the hot water flow are closely related to the vortex formation. The preliminary expression of the vortex formation frequency and vortex intensity is: In the formula, v(t) represents the instantaneous flow rate of hot water at time t, represents the pressure gradient change rate at time t, T represents the time length of the monitoring window, and f vortex Indicates the frequency of vortex formation, representing the frequency of water flow velocity fluctuations within the monitoring window, S vortex represents the eddy strength, representing the combined effect of velocity and pressure gradients;

[0067] After identifying the eddy current formation frequency and eddy current intensity, the eddy current formation frequency and eddy current intensity are weighted to calculate their comprehensive impact within the monitoring window. The nonlinear weight function is used for weighted calculation. The calculation expression is: Wherein, α and β are weight coefficients of vortex formation frequency and vortex 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 nonlinear weight function used to comprehensively evaluate the joint influence of vortex formation frequency and vortex intensity of water flow in the geothermal well on the water flow state;

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

[0069] The final vortex formation index is further generated through the nonlinear weight function. The vortex formation index combines the vortex formation frequency and vortex intensity and their nonlinear effects to provide an accurate assessment of the turbulence degree and instability of the water flow. The specific expression is:

[0070] , where γ represents the suppression coefficient, which is used to control the impact of drastic acceleration changes. It represents the accumulation of acceleration changes and is used to capture the drastic changes in flow velocity over time. vortex is the vortex formation index.

[0072] It can be seen from the vortex formation index that within the set monitoring window, the larger the performance value of the vortex formation index generated after abnormal analysis of the formation frequency and intensity of the vortex in the geothermal well, the higher the turbulence of the water flow, the more frequent and intense the fluctuations in flow velocity and direction, indicating that the hot water in the geothermal well is in a state of significant dynamic fluctuation. At this time, the disturbance of the water flow will be more complex, which may cause greater interference to the camera's foreign body identification and positioning. On the contrary, if the vortex formation index value is small, it means that the frequency and intensity of the water flow do not change significantly, the flow of hot water tends to be stable, and it is a relatively stable state.

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

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

[0075] In the set monitoring window, the instantaneous direction vector of the hot water flow is collected and compared with the original set flow direction vector to calculate the deviation angle of the flow direction. 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, ∥*∥ represents the vector modulus, 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] 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 velocity weight coefficient to prevent the offset at low speed from having too great an 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 I vortex and flow deviation index I 偏移 Perform comprehensive analysis to generate the water flow dynamic coefficient Water Flow In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; the water flow dynamic coefficient Water Flow The resulting calculation formula is:

[0089] , where r1 and r2 are the eddy current formation index I vortex and flow deviation index I 偏移 The preset proportional coefficient, and r1 and r2 are both greater than 0.

[0091] It can be seen from the water flow dynamic coefficient that, within the set monitoring window, the greater the performance value of the vortex formation index generated after the abnormal analysis and processing of the formation frequency and intensity of the vortex in the geothermal well, the greater the performance value of the flow direction deviation index generated after the abnormal analysis and processing of the deviation amplitude of the water flow direction in the geothermal well, that is, the greater the performance value of the water flow dynamic coefficient generated when the flow conditions of hot water in the geothermal well are predicted by the machine learning model in the monitoring window, the more obvious the water flow dynamic fluctuation is, and vice versa.

[0092] The flow state classification module divides the hot water flow conditions in the monitoring window into two types: 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 flow of 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, and the hot water flow in the monitoring window is divided. 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 hot water flow condition in the monitoring window is classified as a dynamic fluctuation type;

[0095] If the water flow dynamic coefficient is less than the water flow dynamic coefficient reference threshold, the hot water flow condition in the monitoring window is classified as a static stable type.

[0096] Dynamic fluctuation refers to the situation where the hot water flow rate and direction have significant changes, eddy currents are obvious, and the flow is unstable; static stability refers to the situation where the hot water flow rate is constant, the flow direction is consistent, and the flow is smooth. Through clear classification, corresponding foreign body recognition strategies can be formulated for different flow states to improve the accuracy and efficiency of recognition.

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

[0098] For geothermal well hot water flow that is classified as static stable, it means that the flow rate and direction of the hot water remain relatively constant, without obvious eddies, flow rate fluctuations or direction deviations. In this stable environment, the water flow dynamics are relatively controllable and 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 camera's exposure time or image acquisition parameters, and can continue to use the preset starting exposure time for foreign object identification and positioning.

[0099] The set starting exposure time is usually optimized to suit the lighting conditions and imaging requirements in a stable environment in the well. This exposure time ensures that the images captured by the camera have high clarity and low noise, so that the edges and details of the foreign objects can be clearly presented. Since the water flow is stable, the position of the foreign object will not move or blur due to the disturbance of the water flow, and the camera can efficiently complete the recognition and positioning tasks.

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

[0101] The dynamic flow optimization module optimizes the exposure time of the high-resolution camera based on the predicted dynamic flow of hot water in geothermal wells classified as dynamic fluctuations. Specifically, the camera exposure time is shortened to reduce motion blur caused by the rapid flow of hot water and eddies.

[0102] According to the predicted dynamic flow of hot water, the exposure time of the high-resolution camera is optimized and adjusted. The specific steps are as follows:

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

[0104] , where K a is the exposure time adjustment factor, 0 <K a <1, Water Flow Represents the current predicted water flow dynamic coefficient, C r is the reference threshold of water flow dynamic coefficient;

[0106] Based on the initial exposure time and the exposure time adjustment coefficient, the adjusted actual exposure time is calculated. The calculation expression is: T d =K a ·T s , where T d Indicates the actual exposure time after dynamic adjustment, T s Indicates the starting exposure time, the initial setting value under 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 blur caused by water flow fluctuations.

[0108] 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:

[0109] , 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.

[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 sensitivity of the camera to compensate for the lack of brightness caused by the shortened exposure time. Through this dynamic adjustment, the camera can adapt to the complex and changing underground environment, continuously provide high-precision foreign object identification and positioning, and ensure the success rate of salvage missions and the safe operation of geothermal wells.

[0112] The present invention uses a high-resolution camera for initial recognition, and in combination with the camera's built-in measurement module, collects hot water flow data in real time, establishes a comprehensive data set, and dynamically adjusts the camera's exposure time after in-depth analysis and prediction of the 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, which 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. In addition, it reduces repeated detection and equipment load caused by environmental changes, extends the service life of the equipment, avoids the risk of well blockage and equipment damage caused by the failure to salvage key foreign objects in time, and ensures the safe operation of geothermal wells and the maximization of economic benefits.

[0113] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0114] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0115] It should be noted that, in this article, if there are first and second, etc., relational terms 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 terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0116] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0117] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this 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 aforementioned method embodiments and will not be repeated here.

[0119] In the several embodiments provided in 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 only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

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

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

[0122] If the functions are implemented in the form of software functional 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 can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0123] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A control system for rapid identification and salvage of foreign objects inside a geothermal well, characterized in that: It includes initial identification and positioning module, real-time data acquisition module, data analysis and flow prediction module, flow state classification module, stable flow identification module and dynamic flow optimization module; The initial identification and positioning module deploys a high-resolution camera in the geothermal well to perform initial foreign object identification and positioning operations with a set starting exposure time; The real-time data acquisition module, while identifying and locating foreign objects, uses the built-in measurement module of the high-resolution camera to obtain the flow data of hot water in the geothermal well in real time and establish a comprehensive data set; The data analysis and flow prediction module conducts in-depth analysis on the collected data set, extracts key features that reflect the flow status of hot water in geothermal wells, performs abnormal analysis on the extracted key features within the set monitoring window, and inputs the feature data that has undergone abnormal analysis into the pre-trained machine learning model to make real-time predictions on the flow status of hot water in geothermal wells; The flow state classification module divides the hot water flow conditions in the monitoring window into two types: dynamic fluctuation type and static stability type based on the prediction results of the machine learning model; The stable flow identification module, for geothermal well hot water flows classified as static stable, continues to use a high-resolution camera to identify and locate foreign objects with a set initial exposure time; The dynamic flow optimization module optimizes the exposure time of the high-resolution camera based on the predicted dynamic flow of hot water in geothermal wells classified as dynamically fluctuating. Specifically, the camera exposure time is shortened to reduce motion blur caused by rapid flow of hot water and eddies.

2. The geothermal well internal foreign body rapid identification and salvage control system according to claim 1 is characterized in that: The set initial exposure time is optimized based on the lighting conditions of the geothermal well and the expected static flow environment, ensuring that the high-resolution camera can capture high-quality images.

3. The geothermal well internal foreign body rapid identification and salvage control system according to claim 1 is characterized in that: The built-in measurement module of the high-resolution camera is a sensor 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 geothermal well internal foreign body rapid identification and salvage control system according to claim 1, characterized in that: 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.

5. The geothermal well internal foreign body rapid identification and salvage control system according to claim 4 is characterized in that: 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.

6. The geothermal well internal foreign body rapid identification and salvage control system according to claim 4, characterized in that: The specific steps for generating the vortex formation index after abnormal analysis of the frequency and intensity of vortex formation in the geothermal well within the set monitoring window are as follows: In the monitoring window, the instantaneous velocity and pressure gradient change rate of the hot water flow are first collected. The instantaneous velocity and pressure gradient change rate of the hot water flow are closely related to the vortex formation. The preliminary expression of the vortex formation frequency and vortex intensity is: In the formula, v(t) represents the instantaneous flow rate of hot water at time t, represents the pressure gradient change rate at time t, T represents the time length of the monitoring window, and f vortex Indicates the frequency of vortex formation, representing the frequency of water flow velocity fluctuations within the monitoring window, S vortex represents the eddy strength, representing the combined effect of velocity and pressure gradients; After identifying the eddy current formation frequency and eddy current intensity, the eddy current formation frequency and eddy current intensity are weighted to calculate their comprehensive impact within the monitoring window. The nonlinear weight function is used for weighted calculation. The calculation expression is: Where α and β are the weight coefficients of vortex formation frequency and vortex intensity, respectively, and W(f, S) is a nonlinear weight function used to comprehensively evaluate the joint influence of vortex formation frequency and vortex intensity on the water flow state in geothermal wells; The final vortex formation index is further generated through the nonlinear weight function. The vortex formation index combines the vortex formation frequency and vortex intensity and their nonlinear effects to provide an accurate assessment of the turbulence degree and instability of the water flow. The specific expression is: , where γ represents the suppression coefficient, which is used to control the impact of drastic acceleration changes. It represents the accumulation of acceleration changes and is used to capture the drastic changes in flow velocity over time. vortex is the vortex formation index.

7. The geothermal well internal foreign body rapid identification and salvage control system according to claim 6, characterized in that: The specific steps of generating the flow direction deviation index after abnormal analysis of the deviation amplitude of the water flow direction in the geothermal well within the set monitoring window are as follows: In the set monitoring window, the instantaneous direction vector of the hot water flow is collected and compared with the original set flow direction vector to calculate the deviation angle of the flow direction. The calculation expression is: , where θ(t) represents the water flow deviation 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, ∥*∥ represents the vector modulus, 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 velocity weight coefficient to the offset is adjusted. The calculation expression is: in, , 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; 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: , 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.

8. The geothermal well internal foreign body rapid identification and salvage control system according to claim 5, characterized in that: The water flow dynamic coefficient generated when predicting the flow of 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, and the hot water flow in the monitoring window is divided. The specific division steps are as follows: If the water flow dynamic coefficient is greater than or equal to the water flow dynamic coefficient reference threshold, the hot water flow condition in the monitoring window is classified as a dynamic fluctuation type; If the water flow dynamic coefficient is less than the water flow dynamic coefficient reference threshold, the hot water flow condition in the monitoring window is classified as a static stable type.

9. The geothermal well internal foreign body rapid identification and salvage control system according to claim 8, characterized in that: According to the predicted dynamic flow of hot water, the exposure time of the high-resolution camera is optimized and adjusted. The specific steps are as follows: The exposure time adjustment coefficient is calculated using the water flow dynamic coefficient and the water flow dynamic coefficient reference threshold, 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 factor, 0 <K a <1, Water Flow Represents the current predicted water flow dynamic coefficient, C r is the reference threshold of water flow dynamic coefficient; Based on the initial exposure time and the exposure time adjustment coefficient, the adjusted actual exposure time is calculated. The calculation expression is: T d =K a ·T s , where T d Indicates the actual exposure time after dynamic adjustment, T s Indicates the starting exposure time, the initial setting value under stable state; 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: , 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