Vertical shaft wall deformation real-time monitoring and safety early warning method

Abstract

The invention discloses a vertical shaft wall deformation real-time monitoring and safety early warning method, which is applied to a server side, and comprises the following steps: identifying received construction equipment data to obtain an interference type and interference intensity on well wall state data, and then respectively obtaining an initial repair strategy and a Kalman filtering gain; correcting the well wall state data by using the initial repair strategy, and introducing the process disturbance intensity corresponding to the current construction stage into the state equation of the Kalman filter to construct a target state equation; processing the corrected well wall state data based on the target state equation and the Kalman filtering gain to obtain target well wall state data; inputting the target well wall state data, the construction equipment data, the in-well environment data and the construction process data into the optimized LSTM model to obtain a predicted well wall deformation increment; and performing early warning on safety risks caused by well wall deformation based on the predicted well wall deformation increment and the multi-source data to obtain early warning information, and sending the early warning information to an underground terminal and a user terminal.

Description

Technical Field

[0001] This invention relates to the field of industrial safety monitoring technology, and relates to, but is not limited to, a method for real-time monitoring and safety early warning of vertical shaft wall deformation. Background Technology

[0002] In recent years, many mines have experienced shaft wall rupture problems, with the rupture locations concentrated near the interface between the topsoil and bedrock. As the water level in the mining area continues to decline, the vertical additional stress generated by formation consolidation and compression increases, leading to increased stress in the shaft wall concrete and reduced safety reserves, posing a significant threat to safe mine production. Therefore, real-time monitoring and early warning of shaft wall deformation are essential.

[0003] In related technologies, fiber optic grating sensors are installed circumferentially and vertically along the well wall. By detecting the drift change of the center wavelength of the reflected light, the changes in well wall strain and temperature are obtained. These changes are then processed using a single model to achieve real-time monitoring and early warning of well wall deformation. However, this method has the problem that the data are independent of each other and cannot establish an effective correlation, and the model is single, so it cannot efficiently and accurately monitor and warn of well wall deformation in vertical wells.

[0004] Therefore, how to efficiently and accurately monitor and provide early warning of wellbore deformation has become an urgent problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method for real-time monitoring and safety early warning of vertical shaft wall deformation, which at least solves the problem that related technologies cannot efficiently and accurately monitor and warn of vertical shaft wall deformation.

[0006] According to a first aspect of the present invention, a method for real-time monitoring and safety early warning of vertical shaft wall deformation is provided, applied to a server, comprising: The system receives multi-source data corresponding to the current construction stage of the vertical shaft, transmitted by the downhole terminal through a hybrid transmission method. The multi-source data includes wellbore status data, construction equipment data, well environment data, and construction procedure data. The construction equipment data is identified to obtain the type and intensity of interference to the wellbore status data; and the initial repair strategy and Kalman filter gain are obtained based on the type and intensity of interference. The wellbore condition data is corrected using the initial repair strategy to obtain corrected wellbore condition data; The process disturbance intensity corresponding to the current construction stage is introduced into the state equation of the Kalman filter to construct the target state equation; and the corrected wellbore state data is processed based on the target state equation and the Kalman filter gain to obtain the target wellbore state data. The target wellbore condition data, construction equipment data, well environment data, and construction procedure data are input into the optimized LSTM model to obtain the predicted wellbore deformation increment; the input gate of the optimized LSTM model incorporates the weight matrix corresponding to the construction procedure data. Based on the predicted wellbore deformation increment and multi-source data, early warning is issued for the safety risks caused by wellbore deformation, and the early warning information is sent to the downhole terminal and user terminal.

[0007] According to a second aspect of the present invention, an electronic device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform an operation corresponding to the method described in the first aspect.

[0008] According to a third aspect of the present invention, a computer storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0009] According to the solution provided in the embodiments of the present invention, multi-source data corresponding to the current construction stage of the vertical shaft is received from the downhole terminal via a hybrid transmission method. The multi-source data includes wellbore status data, construction equipment data, well environment data, and construction procedure data. The construction equipment data is identified to obtain the type and intensity of interference to the wellbore status data. An initial repair strategy and Kalman filter gain are obtained based on the interference type and intensity. The wellbore status data is corrected using the initial repair strategy to obtain corrected wellbore status data. The current construction procedure data is incorporated into the state equation of the Kalman filter. The target state equation is constructed based on the intensity of the disturbance. The corrected wellbore state data is then processed using the target state equation and Kalman filter gain to obtain the target wellbore state data. The target wellbore state data, construction equipment data, well environment data, and construction procedure data are input into an optimized LSTM model to obtain the predicted wellbore deformation increment. The input gate of the optimized LSTM model incorporates the weight matrix corresponding to the construction procedure data. Based on the predicted wellbore deformation increment and multi-source data, early warnings are issued for safety risks caused by wellbore deformation, and these warnings are sent to the downhole terminal and user terminal. In this process, the types and intensity of interference in the wellbore status data are quantified, and various complex uncertainties are transformed into modelable noise parameters, thus laying the foundation for accurate filtering. By dynamically calculating the Kalman filter gain, noise can be automatically suppressed and real signals can be extracted. Combined with an optimized LSTM model, efficient and high-precision estimation of wellbore deformation status is further achieved, improving the accuracy and reliability of monitoring wellbore deformation. Based on the predicted wellbore deformation increment and the collected multi-source data, early warning information is obtained, providing a stable and reliable data foundation for early warning and risk decision-making. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein: Figure 1 A flowchart illustrating a method for real-time monitoring and safety early warning of vertical shaft wall deformation provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0011] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0012] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0013] It should be noted that the terms "first, second, and third" used in the embodiments of the present invention are only used to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, and third" can be interchanged in a specific order or sequence where permitted, so that the embodiments of the present invention described herein can be implemented in an order other than that illustrated or described herein.

[0014] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which these embodiments of the invention pertain. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0015] Figure 1 This is a flowchart illustrating a method for real-time monitoring and safety early warning of vertical shaft wall deformation provided in an embodiment of the present invention. The method can be executed by an electronic device, such as a computer or server.

[0016] like Figure 1 As shown, the method for real-time monitoring and safety early warning of vertical shaft wall deformation includes: S101. Receive multi-source data corresponding to the current construction stage of the vertical shaft transmitted by the downhole terminal through a hybrid transmission method. The multi-source data includes wellbore status data, construction equipment data, well environment data, and construction procedure data.

[0017] In embodiments of the present invention, the well wall status data reflects the health and response status of the well structure itself. This data is acquired through various sensors installed on the well wall, such as distributed fiber optic sensors and miniature piezoelectric stress sensors. The collected data includes deformation data, stress data, and temperature data. Deformation data includes the opening and closing degree of concrete joints and radial deformation, stress data includes internal well wall stress and instantaneous impact stress caused by the scraping of the hoisting platform, and temperature data is the surface temperature of the well wall. The construction equipment data represents the working status and output parameters of various mechanical equipment during construction. This data is acquired through various sensors, such as hoisting platform tension sensors, hoisting platform acceleration sensors, hoisting platform tilt sensors, rock grabber load sensors, and metal template displacement encoders. The collected data includes the tension of the suspension ropes at the four hoisting points, the vibration acceleration caused by the blasting shock wave, the horizontal tilt angle of the hoisting platform, and data from the rock grabber and metal template. The well environment data describes the natural conditions and status inside the well, mainly including well water inflow, well ambient temperature, and well ambient humidity. Construction process data consists of logical data that identifies macroscopic construction stages and parameters, including process switching nodes, such as the start or end of the tunneling stage, as well as process parameter data, mainly the amount of explosives, concrete pouring speed, and grouting pressure.

[0018] Furthermore, the downhole terminal transmits the collected data using a hybrid transmission method. Specifically, the main transmission utilizes wired transmission, such as flame-retardant armored optical fiber, to transmit wellbore status data, well environment data, construction procedure data, and data from fixed, non-mobile equipment to the server. Wireless transmission is used to transmit construction equipment data from mobile devices such as hoists and rock grabbers to the server. All data carries timestamps, sensor IDs, and monitoring unit numbers during transmission. The monitoring unit number indicates the specific location on the wellbore from which the data originated.

[0019] S102. Identify the construction equipment data to obtain the type and intensity of interference to the wellbore status data; and obtain the initial repair strategy and Kalman filter gain based on the type and intensity of interference.

[0020] In some embodiments of the present invention, an interference type identification model is constructed. Construction equipment data is input into the interference type identification model to obtain the interference type and intensity on the well wall condition data. The interference type can be classified as hoisting platform interference, rock grabber interference, and formwork interference. Hoisting platform interference is caused by the operation of the hoisting platform, such as scraping during hoisting and lowering, generating transient and localized impact stress on the well wall surface. Rock grabber interference is caused by the rock grabber's operating actions, such as grabbing impacts and swinging collisions. Formwork interference is caused by the assembly and pouring process of the metal formwork, such as interference generated by pouring side pressure and formwork shrinkage. The interference intensity can be classified as weak, medium, or strong interference.

[0021] Furthermore, after identifying the interference type, the interference intensity is determined through the interference's characteristic values. Then, the interference type and intensity are compared with a pre-built strategy library to find the initial repair strategy corresponding to a specific interference type and intensity. Simultaneously, the interference type and intensity are compared with a pre-built filter gain library to find the Kalman filter gain corresponding to a specific interference type and intensity.

[0022] S103. Correct the wellbore condition data using the initial repair strategy to obtain corrected wellbore condition data.

[0023] In some embodiments of the present invention, the initial repair strategy includes how to correct the wellbore status data when the interference type is medium or strong. Regardless of the type of interference, no correction is made when the interference intensity is weak, and the original wellbore status data remains unchanged. When the interference type is a hoisting platform type and the interference intensity is medium, it is determined whether the hoisting platform's swing angle and the peak value of the impact stress received by the wellbore are synchronized. If they are not synchronized, no correction is made. If they are synchronized, a pre-set swing threshold is obtained. When the hoisting platform's swing angle exceeds the swing threshold, the peak value of the impact stress in the wellbore status data is reduced according to a preset ratio to the peak value of the impact stress synchronized with the swing angle. When the interference intensity is strong, and the hoisting platform's swing angle and the peak value of the impact stress received by the wellbore are synchronized, the correction logic is the same as for medium interference. When the interference type is a rock grabber type and the interference intensity is medium, if the vibration frequency of the rock grabber and the high-frequency vibration time of the stress in the wellbore status data are synchronized, the low-frequency deformation trend is retained after removing high-frequency noise. In the case of strong interference, all synchronous high-frequency stress abrupt changes within this time period are removed, and only smooth low-frequency trends are retained. When the interference type is template-type interference and the interference intensity is medium interference, it is determined whether the displacement and pressure in the wellbore status data exceed their respective set thresholds. If they exceed them, the corresponding spurious deformations are removed according to the proportion of displacement exceeding the limit. When the interference intensity is strong interference, the correction logic is the same as for medium interference.

[0024] S104. Introduce the process disturbance intensity corresponding to the current construction stage into the state equation of the Kalman filter to construct the target state equation; and process the corrected wellbore state data based on the target state equation and the Kalman filter gain to obtain the target wellbore state data.

[0025] In an embodiment of the present invention, during the current construction phase, process parameters are obtained from the construction procedure data. Then, the process disturbance intensity is calculated based on these parameters. This disturbance intensity is used as a known external disturbance input and, along with the original control input, is written into the state equation to obtain the improved state equation, i.e., the target state equation. The corrected wellbore state data is then input into a Kalman filter. Based on the constructed target state equation and the Kalman filter gain, the corrected wellbore state data is processed until the target wellbore state data is obtained.

[0026] S105. Input the target wellbore condition data, construction equipment data, well environment data, and construction procedure data into the optimized LSTM model to obtain the predicted wellbore deformation increment; the input gate of the optimized LSTM model introduces the weight matrix corresponding to the construction procedure data.

[0027] In an embodiment of the present invention, the target wellbore status data, construction equipment data, well environment data, and construction procedure data are aligned in dimensions and then spliced ​​together to obtain a spliced ​​vector. The spliced ​​vector is then input into an optimized LSTM model. When the LSTM unit in the optimized LSTM model processes the data, the activation vector output by the input gate of the LSTM unit is calculated based on the spliced ​​vector, the spliced ​​vector, the construction procedure data, and the weight matrix corresponding to the construction procedure data.

[0028] S106. Based on the predicted wellbore deformation increment and multi-source data, early warning is issued for the safety risks caused by wellbore deformation, and the early warning information is sent to the downhole terminal and user terminal.

[0029] In embodiments of this invention, the predicted wellbore deformation increment is an estimate of the amount of deformation that may occur in the wellbore over a future period. Combining the predicted wellbore deformation increment with the original multi-source data, a warning level is assigned to address the safety risks caused by wellbore deformation, resulting in warning levels such as blue, yellow, and red. These warning levels are then marked in a constructed 3D wellbore panoramic view, and a trend analysis and prediction comparison chart is added to the 3D wellbore panoramic view. This chart describes which sensor data is problematic and explains the principle behind the warning level assignment. Finally, based on the marked 3D wellbore panoramic view and the added trend analysis and prediction comparison chart, warning information is generated and sent to the downhole terminal and user terminal.

[0030] Yellow alerts indicate no immediate risk and require continuous monitoring. Blue alerts indicate medium risk and require manual intervention. It is recommended to stop non-critical processes, such as auxiliary grouting, and have the electromechanical team check water inflow points and adjust the hoisting platform angle to within the preset angle, reporting data every 10 minutes. Red alerts indicate high risk and require emergency intervention. It is recommended to shut down the entire well, evacuate all personnel immediately, and activate the emergency drainage system and other corresponding measures.

[0031] Upon receiving the early warning information, the downhole terminal and user terminal immediately take corresponding measures. The downhole terminal can perform operations such as continuing work or emergency evacuation based on the content of the early warning information, or take pictures of the situation inside the well and send them to the user terminal to wait for further instructions. The user terminal can accurately locate the risk location in the three-dimensional panoramic view of the wellbore based on the early warning information, deploy response strategies, trace the causes of deformation, and dynamically adjust and issue disposal instructions based on the information transmitted back by the downhole terminal.

[0032] The server can also coordinate with construction equipment based on early warning information, and the construction equipment can receive instructions and execute corresponding measures. For example, when a red warning is issued and the tilt angle of the hoisting platform exceeds the preset range, the top support will be automatically activated to fix it, prioritizing the adjustment of the lower side. If it is not lowered below the preset range within 10 seconds, the backup top support will be triggered, and a manual intervention reminder will be sent.

[0033] It is understood that, in the embodiments of the present invention, the downhole terminal receives multi-source data corresponding to the current construction stage of the vertical shaft transmitted via a hybrid transmission method. This multi-source data includes wellbore status data, construction equipment data, well environment data, and construction procedure data. The construction equipment data is identified to obtain the type and intensity of interference to the wellbore status data. An initial repair strategy and Kalman filter gain are obtained based on the interference type and intensity. The wellbore status data is corrected using the initial repair strategy to obtain corrected wellbore status data. The state equation of the Kalman filter is then incorporated with the data corresponding to the current construction stage. The intensity of process disturbance is used to construct the target state equation; the corrected wellbore state data is then processed based on the target state equation and Kalman filter gain to obtain the target wellbore state data; the target wellbore state data, construction equipment data, well environment data, and construction procedure data are input into an optimized LSTM model to obtain the predicted wellbore deformation increment; the input gate of the optimized LSTM model incorporates the weight matrix corresponding to the construction procedure data; based on the predicted wellbore deformation increment and multi-source data, early warning is issued for the safety risks caused by wellbore deformation, and the early warning information is sent to the downhole terminal and user terminal. In this process, the types and intensity of interference in the wellbore status data are quantified, and various complex uncertainties are transformed into modelable noise parameters, thus laying the foundation for accurate filtering. By dynamically calculating the Kalman filter gain, noise can be automatically suppressed and real signals can be extracted. Combined with an optimized LSTM model, efficient and high-precision estimation of wellbore deformation status is further achieved, improving the accuracy and reliability of monitoring wellbore deformation. Based on the predicted wellbore deformation increment and the collected multi-source data, early warning information is obtained, providing a stable and reliable data foundation for early warning and risk decision-making.

[0034] In some embodiments of the present invention, obtaining the initial repair strategy and Kalman filter gain based on the interference type and interference intensity in S102 can be achieved by S121 and S1023, which will be explained by the following steps. S1021 and S1022 do not have a specific order.

[0035] S1021. When it is a single type of interference, the interference characteristic value is compared with the preset interference range to obtain the comparison result; and the initial repair strategy and Kalman filter gain are obtained from the preset strategy library and the preset filter gain library respectively according to the comparison result.

[0036] In some embodiments of the present invention, when the interference is of a single type, i.e., any one of the three types: hanging platform interference, rock grabber interference, and template interference, its interference characteristic value is obtained. Thresholds are set for weak, medium, and strong interference conditions. The interference characteristic value is compared with the set threshold to obtain a comparison result of the interference intensity. The comparison result is matched with a preset strategy library to find the initial repair strategy corresponding to the interference intensity under that type of interference, and the corresponding filter gain is obtained from a preset filter gain library.

[0037] Among them, when the interference is of the hanging platform type, the interference characteristic value can be the tilt angle characteristic value and the tension difference characteristic value, etc. When the interference is of the rock grabber, the interference characteristic value can be the rock grabber impact force and frequency, etc. When the interference is of the template type, the interference characteristic value can be the template pressure and displacement, etc.

[0038] S1022. When it is a mixed type of interference, obtain the single repair strategy corresponding to each type of interference, sort the single repair strategies according to priority to obtain the initial repair strategy; and obtain the highest level of interference intensity in the mixed type of interference; the priority of hanging platform interference, rock grabber interference and template interference decreases in sequence.

[0039] In some embodiments of the present invention, when there is a mixed type of interference, that is, when there are at least two types of interference, the repair strategy corresponding to each type of interference is first obtained through S1021, and then the corresponding repair strategies are sorted according to the priority of the hanging platform interference, the rock grabber interference and the template interference, and the final sorting result is used as the initial repair strategy.

[0040] In the process of repairing wellbore status data, the repair strategies corresponding to each type of interference are applied sequentially according to the sorting results.

[0041] S1023. Obtain the corresponding Kalman filter gain from the preset filter gain library based on the highest level of interference intensity.

[0042] In some embodiments of the present invention, when the interference type is mixed, such as the interference of the hoisting platform and the rock grabber, if the interference intensity of the hoisting platform interference is weak and the interference intensity of the rock grabber interference is strong, the corresponding filter gain is obtained from the preset filter gain library based on the rock grabber interference and the interference intensity. If the interference intensity of the hoisting platform interference is weak and the interference intensity of the rock grabber interference is also weak, since the priority of the hoisting platform interference, the rock grabber interference and the template interference decreases in that order, the corresponding filter gain can be obtained from the preset filter gain library based on the hoisting platform interference and the interference intensity.

[0043] In some embodiments of the present invention, S10 to S12 are included before S104. S10 to S12 have no sequential relationship and will be explained through the following steps.

[0044] S10. When it is the tunneling stage, the product of the explosive charge and the impact coefficient shall be used as the process disturbance intensity.

[0045] S11. When it is the wall-building stage, the difference between the pouring speed and the pressure transmission rate of the formwork is taken as the process disturbance strength.

[0046] S12. When it is the grouting stage, the product of the grouting pressure and the rebound correction coefficient is used as the process disturbance strength.

[0047] In some embodiments of the present invention, the current construction stage includes a tunneling stage, a wall-building stage, and a grouting stage. When it is the tunneling stage, the process parameters in the construction process data, such as the explosive charge and the impact coefficient, are multiplied to obtain the process disturbance intensity. When it is the wall-building stage, the process parameters in the construction process data, such as the pouring speed and the formwork pressure transmission rate, are calculated by difference, and the difference result is used as the process disturbance intensity. When it is the grouting stage, the process parameters in the construction process data, such as the grouting pressure and the rebound correction coefficient, are multiplied, and the product result is used as the process disturbance intensity. Then, in different construction stages, the process disturbance intensity is used as a known external disturbance input and written into the state equation together with the original control input to obtain the optimized state equation.

[0048] The impact coefficient increases linearly with the amount of explosive charge, increasing by 0.15 for every 100kg increase in explosive charge. The formwork pressure transmittance is related to the pouring speed; when the pouring speed exceeds 2 m / h, the formwork pressure transmittance is set to 0.8. The rebound correction coefficient increases linearly with the grouting pressure, increasing by 0.08 for every 1MPa increase in grouting pressure.

[0049] In some embodiments of the present invention, the input of target wellbore state data, construction equipment data, well environment data and construction procedure data into the optimized LSTM model in S105 to obtain the predicted wellbore deformation increment can be achieved through S1051 and S1052, which will be explained through the following steps.

[0050] S1051. The target wellbore condition data, construction equipment data, well environment data, and construction procedure data are spliced ​​together to obtain a splicing vector.

[0051] S1052. Input the spliced ​​vector into the input gate of the optimized LSTM model, obtain the activation vector through the improved activation vector formula, and obtain the predicted wellbore deformation increment based on the activation vector.

[0052] In some embodiments of the present invention, the target wellbore condition data, construction equipment data, well environment data, and construction procedure data are aligned dimensionally and then stitched together to obtain a stitched vector. The input gate in the optimized LSTM model has been improved. In the above formula, Let be the input gate activation vector at time step t. Let be the process encoding vector for the construction process data at step t. This is the weight matrix corresponding to the process coding vector. It is the Sigmoid activation function. Let be the hidden state vector at step t-1. Let t be the concatenated input vector at time step t. For the bias term of the input gate, This is the weight matrix specific to the input gate.

[0053] The optimized LSTM model is trained before use. During training, the loss function is constructed using root mean square error and process change constraint term. The process change constraint term is implemented by penalizing the model's prediction error of deformation trend or acceleration when switching processes.

[0054] In some embodiments of the present invention, S106 can be implemented by S1061 to S1063, as described in the following steps.

[0055] S1061. Obtain the predicted deformation rate and the actual deformation rate based on the predicted wellbore deformation increment and wellbore state data, respectively; and obtain the first score by using the predicted deformation rate, the actual deformation rate and the first preset rule.

[0056] In some embodiments of the present invention, the first preset rule can be different intervals, including three comparison intervals corresponding to the predicted deformation rate and three intervals corresponding to the actual deformation rate. After calculating the predicted deformation rate by the predicted wellbore deformation increment and calculating the actual deformation rate by the collected original wellbore state data, the predicted deformation rate and the actual deformation rate and their respective intervals are compared to obtain a first score.

[0057] For example, if the actual deformation rate is not greater than 0.5 and the predicted deformation rate is not greater than 0.8, the first score is 40. If the actual deformation rate is greater than 0.5 and not greater than 1.0, or the predicted deformation rate is greater than 0.8 and not greater than 1.2, the score is 20. If the actual deformation rate is greater than 1.0 and not greater than 2.0, or the predicted deformation rate is greater than 1.2 and not greater than 2.0, the score is 10. If the actual deformation rate is greater than 2.0, or the predicted deformation rate is greater than 2.0, the score is 0.

[0058] S1062. Obtain a second score based on well environment data, construction procedure data, and preset multi-level risk assessment rules; and obtain a third score based on the deviation value of process parameters in the construction equipment data.

[0059] In some embodiments of the present invention, the well environment data, well wall condition data and construction procedure data are first judged according to the preset multi-level risk judgment rules. First, it is judged whether the high-risk condition is met. If it is met, the corresponding second score is obtained. If it is not met, it is judged whether the medium-risk condition is met. If it is met, the corresponding second score is obtained. If it is not met, the next stage of judgment is continued.

[0060] Furthermore, process parameters from the construction equipment data, such as the lifting platform tilt angle, lifting point tension difference, and rock grabber impact value, are obtained and compared with preset standard values ​​to obtain deviation values. Then, the deviation values ​​are compared with preset score thresholds to obtain a third score.

[0061] For example, if the construction process data shows that the well wall deformation rate is still greater than the preset 1.5 within 2 hours of blasting, or the grouting pressure drops by more than the preset 30%, it is considered high risk. If the water inflow in the well wall condition data is greater than the preset 20, or the number of masonry joints is greater than the preset 5, it is considered medium risk. If the water inflow in the well wall condition data is less than 20, and the process parameters in the construction process data are normal, it is considered low risk.

[0062] S1063. Early warning information is obtained based on the first score, second score, third score and the correction coefficient corresponding to the predicted wellbore deformation increment.

[0063] In some embodiments of the present invention, a correction coefficient corresponding to the predicted wellbore deformation increment is used to correct the wellbore deformation increment. After calculating the first score, the second score, and the third score, a safety threshold for the wellbore deformation increment is used to determine whether to use the correction coefficient to correct the predicted wellbore deformation increment, and finally, an early warning information is obtained.

[0064] In some embodiments of the present invention, S1063 can be implemented by S201 to S202, as described in the following steps.

[0065] S201. The first score, the second score, and the third score are weighted and summed according to preset weights to obtain the initial comprehensive score.

[0066] S202. Obtain the deformation increment safety threshold. When the predicted wellbore deformation increment is greater than the deformation increment safety threshold, the initial comprehensive score is reduced by a correction coefficient according to a preset ratio to obtain the target comprehensive score. Based on the target comprehensive score and the preset classification threshold, different levels of early warning information are obtained.

[0067] In some embodiments of the present invention, according to preset weights, the weight of the first score is greater than that of the second and third scores. The first, second, and third scores are weighted and summed according to preset weights to obtain an initial comprehensive score. A deformation increment safety threshold is set, which is the maximum allowable increase in deformation. If the predicted wellbore deformation increment is not greater than the deformation increment safety threshold, the initial comprehensive score is used as the target comprehensive score. If the predicted wellbore deformation increment is greater than the deformation increment safety threshold, the initial comprehensive score is reduced using a correction coefficient to obtain the target comprehensive score.

[0068] Furthermore, a preset threshold is set, and different levels of early warning information are obtained based on the matching results of the target comprehensive score and the preset interval.

[0069] For example, a score of 80 or higher is considered to have no urgent risk, a score of 50 or higher but less than 80 is considered to have medium risk, and a score of less than 50 is considered to have high risk.

[0070] Reference Figure 2 The diagram shows a structural schematic of an electronic device according to an embodiment of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the electronic device.

[0071] like Figure 2 As shown, the electronic device may include: a processor 502, a communications interface 504, a memory 506, and a communications bus 508.

[0072] in: The processor 502, communication interface 504, and memory 506 communicate with each other via communication bus 508.

[0073] Communication interface 504 is used to communicate with other electronic devices or servers.

[0074] The processor 502 is used to execute program 510, specifically the relevant steps in the above method embodiments.

[0075] Specifically, program 510 may include program code that includes computer operation instructions.

[0076] Processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The smart device may include one or more processors of the same type, such as one or more CPUs; or it may include processors of different types, such as one or more CPUs and one or more ASICs.

[0077] Memory 506 is used to store program 510. Memory 506 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0078] Specifically, program 510 can be used to cause processor 502 to perform the operations corresponding to the methods described in the above method embodiments.

[0079] The specific implementation of each step in program 510 can be found in the corresponding descriptions of the steps and units in the above method embodiments, and will not be repeated here. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the devices and modules described above can be referred to the corresponding process descriptions in the foregoing method embodiments, and will not be repeated here.

[0080] It should be noted that, depending on the implementation needs, the various components / steps described in the embodiments of the present invention can be broken down into more components / steps, or two or more components / steps or parts of the operation of components / steps can be combined into new components / steps to achieve the purpose of the embodiments of the present invention.

[0081] The methods described above according to embodiments of the present invention can be implemented in hardware, firmware, or as software or computer code that can be stored in a recording medium (such as a CD-ROM, RAM, floppy disk, hard disk, or magneto-optical disk), or as computer code originally stored on a remote recording medium or a non-transitory machine-readable medium and subsequently stored on a local recording medium, downloaded via a network. Thus, the methods described herein can be processed by software stored on a recording medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware (such as an ASIC or FPGA). It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components (e.g., RAM, ROM, flash memory, etc.) capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods described herein. Furthermore, when a general-purpose computer accesses code used to implement the methods shown herein, the execution of the code transforms the general-purpose computer into a dedicated computer for executing the methods shown herein.

[0082] Those skilled in the art will recognize that the units and method steps of the various examples 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 implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the embodiments of the present invention.

[0083] The above embodiments are only used to illustrate the embodiments of the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the embodiments of the present invention. Therefore, all equivalent technical solutions also fall within the scope of the embodiments of the present invention, and the patent protection scope of the embodiments of the present invention should be defined by the claims.

Claims

1. A method for real-time monitoring and safety early warning of vertical shaft wall deformation, applied to a server, characterized in that, include: The system receives multi-source data corresponding to the current construction stage of the vertical shaft, transmitted by the downhole terminal through a hybrid transmission method. The multi-source data includes wellbore status data, construction equipment data, well environment data, and construction procedure data. The construction equipment data is identified to obtain the type and intensity of interference to the wellbore status data; and the initial repair strategy and Kalman filter gain are obtained based on the type and intensity of interference. The wellbore condition data is corrected using the initial repair strategy to obtain corrected wellbore condition data; The process disturbance intensity corresponding to the current construction stage is introduced into the state equation of the Kalman filter to construct the target state equation; and the corrected wellbore state data is processed based on the target state equation and the Kalman filter gain to obtain the target wellbore state data. The target wellbore condition data, construction equipment data, well environment data, and construction procedure data are input into the optimized LSTM model to obtain the predicted wellbore deformation increment; the input gate of the optimized LSTM model incorporates the weight matrix corresponding to the construction procedure data. Based on the predicted wellbore deformation increment and multi-source data, early warning is issued for the safety risks caused by wellbore deformation, and the early warning information is sent to the downhole terminal and user terminal.

2. The method according to claim 1, characterized in that, The interference types include interference from hanging platforms, interference from rock grabbers, and interference from templates; The process of obtaining the initial repair strategy and Kalman filter gain based on interference type and interference intensity includes: When it is a single type of interference, the interference feature value is compared with the preset interference range to obtain the comparison result; and the initial repair strategy and Kalman filter gain are obtained from the preset strategy library and the preset filter gain library respectively according to the comparison result. When the interference type is mixed, obtain the single repair strategy corresponding to each type of interference, sort the single repair strategies according to priority to obtain the initial repair strategy; and obtain the highest level of interference intensity in the mixed interference type; the priority of hanging platform interference, rock grabber interference and template interference decreases in that order. The corresponding Kalman filter gain is obtained from the preset filter gain library based on the highest level of interference intensity.

3. The method according to claim 1, characterized in that, The current construction phases include the tunneling phase, the wall-building phase, and the grouting phase; Before introducing the process disturbance intensity corresponding to the current construction stage into the state equation of the Kalman filter to construct the target state equation, the method further includes: When it is the tunneling stage, the product of the explosive charge and the impact coefficient is used as the process disturbance intensity. When it is the wall-building stage, the difference between the pouring speed and the pressure transmission rate of the formwork is taken as the process disturbance strength; When it is the grouting stage, the product of the grouting pressure and the rebound correction coefficient is used as the process disturbance strength.

4. The method according to claim 1, characterized in that, The process of inputting target wellbore condition data, construction equipment data, well environment data, and construction procedure data into an optimized LSTM model to obtain the predicted wellbore deformation increment includes: The target wellbore condition data, construction equipment data, well environment data, and construction procedure data are spliced ​​together to obtain a spliced ​​vector. The concatenated vector is input into the input gate of the optimized LSTM model. An improved activation vector formula is used to obtain the activation vector, and the predicted wellbore deformation increment is obtained based on this activation vector. The improved activation vector formula is as follows: In the above formula, Let be the input gate activation vector at time step t. Let be the process encoding vector for the construction process data at step t. This is the weight matrix corresponding to the process coding vector. It is the Sigmoid activation function. Let be the hidden state vector at time step t-1. Let t be the concatenated input vector at time step t. For the bias term of the input gate, This is the weight matrix specific to the input gate.

5. The method according to claim 1, characterized in that, The method uses predicted wellbore deformation increments and multi-source data to provide early warnings of safety risks caused by wellbore deformation, resulting in early warning information including: The predicted deformation rate and the actual deformation rate are obtained based on the predicted wellbore deformation increment and wellbore state data, respectively; and the first score is obtained by using the predicted deformation rate, the actual deformation rate and the first preset rule. The second score is obtained by using well environment data, construction procedure data, and pre-set multi-level risk assessment rules; and the third score is obtained based on the deviation value of process parameters in the construction equipment data. Early warning information is obtained based on the first score, second score, third score, and the correction coefficient corresponding to the predicted wellbore deformation increment.

6. The method according to claim 5, characterized in that, The method of obtaining early warning information based on the first score, second score, third score, and the correction coefficient corresponding to the predicted wellbore deformation increment includes: The first score, second score, and third score are weighted and summed according to preset weights to obtain the initial comprehensive score; Obtain the deformation increment safety threshold. When the predicted wellbore deformation increment exceeds the deformation increment safety threshold, use a correction coefficient to reduce the initial comprehensive score according to a preset ratio to obtain the target comprehensive score. Then, obtain early warning information of different levels based on the target comprehensive score and the preset classification threshold.

Images