CN117933495A - Comprehensive safety monitoring system and method for well wall structure by drilling method - Google Patents
Comprehensive safety monitoring system and method for well wall structure by drilling method Download PDFInfo
- Publication number
- CN117933495A CN117933495A CN202410325180.4A CN202410325180A CN117933495A CN 117933495 A CN117933495 A CN 117933495A CN 202410325180 A CN202410325180 A CN 202410325180A CN 117933495 A CN117933495 A CN 117933495A
- Authority
- CN
- China
- Prior art keywords
- well wall
- life
- safety
- safety feature
- well
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 103
- 238000012544 monitoring process Methods 0.000 title claims abstract description 62
- 238000005553 drilling Methods 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 136
- 238000012360 testing method Methods 0.000 claims description 89
- 238000001514 detection method Methods 0.000 claims description 21
- 238000002474 experimental method Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 15
- 239000013598 vector Substances 0.000 claims description 15
- 239000012530 fluid Substances 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 12
- 238000006073 displacement reaction Methods 0.000 claims description 11
- 230000035699 permeability Effects 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000000977 initiatory effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000013480 data collection Methods 0.000 claims description 6
- 230000035515 penetration Effects 0.000 claims description 4
- 239000011435 rock Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 239000003673 groundwater Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009172 bursting Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000003749 cleanliness Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002002 slurry Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
Landscapes
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a comprehensive safety monitoring system and method for a well wall structure by a drilling method, which relate to the technical field of well wall safety monitoring, and are used for pre-training a well wall life prediction model and a well wall life loss proportion prediction model, collecting actual safety feature data of all safety features of a well wall of a well to be monitored, obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and the well wall life prediction model, collecting real-time safety feature quantities of all the safety features of the well wall of the well to be monitored in real time, outputting a predicted well wall life loss proportion if any safety feature has potential safety hazards, and updating the expected life of the well wall based on the life loss proportion. The early warning of the safety of the well wall is realized, and the aim of safe and effective real-time monitoring of the quality of the well wall is fulfilled.
Description
Technical Field
The invention relates to the technical field of well wall safety monitoring, in particular to a comprehensive safety monitoring system and method for a well wall structure by a drilling method.
Background
The drilling method has wide application in the fields of offshore and mine construction engineering. In the construction and use process of a coal mine shaft group, the safety of a shaft wall structure is a critical problem. The well wall of the middle-deep coal mine can be influenced by various geological environment factors, such as water pressure, surrounding rock pressure, structural movement and the like, and the factors can lead to deformation and damage of the well wall structure and even serious accidents such as well bursting and water burst. The conventional drilling method never realizes safety monitoring through a prefabricated well wall, and the prefabricated safety control technology of the well wall is always blank. However, because the surrounding rock environment of the deep well wall is complex and changeable, the well wall safety monitoring means after well formation is often difficult to comprehensively evaluate and predict the potential risk, and development of a safety intelligent monitoring system and method prefabricated in the well wall is needed to realize safe and effective real-time monitoring of the well wall quality.
The Chinese patent with the grant bulletin number of CN110067551B discloses a method for quantitatively and real-time monitoring the borehole cleanliness and the borehole wall stability, which comprises the steps of actual returned rock debris volume calculation, theoretical returned rock debris volume calculation, real-time rock debris return rate calculation and setting a safe rock debris return rate window; 1. calculating the volume of the actual returned rock debris; 1) Calculating the mass m wet of returned rock debris per meter; 2) The method is used for eliminating quality errors caused by slurry adsorption, and the method considers quantitative calculation of the stability of the well wall, but fails to solve the problem of well wall safety risk prediction caused by the environmental change of the well wall;
therefore, the invention provides a comprehensive safety monitoring system and method for a well wall structure by a drilling method.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art. Therefore, the comprehensive safety monitoring system and method for the well wall structure of the well drilling method provided by the invention realize early warning of the well wall safety and achieve the purpose of safe and effective real-time monitoring of the well wall quality.
In order to achieve the above purpose, the invention provides a comprehensive safety monitoring method for a well wall structure of a drilling method, which comprises the following steps:
Step one: pre-collecting a security feature set; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment;
step two: training a well wall life prediction model by taking safety feature training data corresponding to each safety feature as input and well wall life time length label data as output;
training a well wall life loss proportion prediction model for each safety feature by taking the safety feature fluctuation training data as input and the safety feature life loss label data as output;
Step three: after the construction of the well to be monitored is completed by using a drilling method, collecting actual safety feature data of all safety features of the well wall of the well to be monitored, and obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and a well wall life prediction model;
step four: collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, turning to the fifth step; otherwise, turning to the step six;
step five: collecting fluctuation training data of the well wall of the well to be monitored, and outputting predicted well wall life loss proportion according to the fluctuation training data and a corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; executing the step six;
step six: calculating the time difference between the current time and the monitoring start time in real time, and if the time difference reaches the time of the expected service life, initiating a well wall safety alarm;
Each security feature in the set of security features includes displacement, stress, environment, and fluid penetration;
The collecting the well wall life time label data and the safety feature training data corresponding to each safety feature comprises the following steps:
pre-selecting N first test well walls, wherein N is the number of the selected first test well walls;
setting a parameter value of the displacement in the security feature of each first test borehole wall to 0;
setting the stress, environment and fluid permeability of each first test well wall to different parameter values respectively, and keeping the stress, environment and fluid permeability unchanged;
collecting service life time labels of each first test well wall; the life duration label may be a duration from the beginning of the test to the time the professional evaluates as having a security risk;
The stress, environment and fluid permeability parameters of each first test well wall form a safety feature vector, and the safety feature vectors of all the first test well walls form safety feature training data;
All the life time labels of the first test well wall form well wall life time label data;
the mode of collecting the security feature life loss label data and the security feature fluctuation training data corresponding to each security feature in advance is as follows:
collecting N second test well walls for each safety feature again, wherein each second test well wall corresponds to one first test well wall, and the safety feature vector of each second test well wall is consistent with the corresponding first test well wall;
for each security feature:
marking the safety feature as i, and marking the number of each second test borehole wall of the safety feature i as ij;
Marking a life time label of a first test well wall corresponding to the ij second test well wall as TZij;
For the ij second test well wall, arbitrarily selecting a time point as a disturbance time point, and continuously and incrementally changing the parameter value of the safety feature i in the safety feature vector; marking the time length of the selected disturbance time point from the life loss detection experiment starting time as TSij;
Presetting disturbance collection time length T1; collecting a safety feature parameter sequence formed by each safety feature parameter value in a disturbance collection time period T1 of each second test well wall after a disturbance time point according to a unit time sequence; the safety feature parameter sequences of all safety features form safety feature fluctuation training data;
collecting the final service life of each second testing well wall, and marking the service life of the ij second testing well wall as TRij;
calculating a well wall life loss proportion label Bij of the ij second test well wall; the calculation mode of the well wall life loss proportion label Bij is as follows The well wall life loss proportion labels corresponding to all the safety features of the second test well wall form safety feature life loss label data;
The mode of training the well wall life prediction model is as follows:
Taking the safety feature vector of each first test well wall as the input of a well wall life prediction model, taking a predicted value of the life time length of the first test well wall as output, taking a life time length label corresponding to the first test well wall as a prediction target, taking the difference value between the predicted value of the life time length and the life time length label as a first prediction error, and taking the sum of minimized first prediction errors as a training target; training the well wall life prediction model until the sum of the first prediction errors reaches convergence; the well wall life prediction model is a polynomial regression model; the sum of the first prediction errors is a mean square error;
the method for training the well wall life loss proportion prediction model for each safety feature comprises the following steps:
for each security feature:
Taking the safety feature fluctuation training data of each second test well wall as the input of a well wall life loss proportion prediction model, taking a predicted value of the well wall life loss proportion of the second test well wall as the output, taking a well wall life loss proportion label of the safety feature corresponding to the second test well wall as a prediction target, taking a difference value between the predicted value of the well wall life loss proportion and the well wall life loss proportion label as a second prediction error, and taking the sum of the minimized second prediction errors as a training target; training the well wall life loss proportion prediction model until the sum of the second prediction errors reaches convergence; the well wall life loss proportion prediction model is a time sequence prediction model; the sum of the second prediction errors is a mean square error;
the method for collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time comprises the following steps:
Installing physical sensors corresponding to each safety feature on the wall of the well to be monitored;
Each physical sensor collects real-time parameter values of corresponding safety features in real time as safety feature real-time quantities of the safety features;
the method for judging the potential safety hazard of any one safety feature comprises the following steps:
presetting a security feature variation threshold for each security feature;
if the variation of any safety feature is larger than the safety feature variation threshold, judging that potential safety hazards exist;
the method for collecting fluctuation training data of the well wall of the well to be monitored comprises the following steps:
Collecting and judging safety feature parameter sequences of all safety features within disturbance collection time T1 from the moment when potential safety hazards exist, and forming fluctuation training data;
The method for outputting the predicted well wall life loss proportion by using the fluctuation training data and the corresponding well wall life loss proportion prediction model comprises the following steps:
Marking the safety feature corresponding to the safety hidden danger as a dangerous feature;
Inputting the fluctuation training data into a well wall life loss proportion prediction model corresponding to the dangerous characteristics, and obtaining a predicted well wall life loss proportion output by the well wall life loss proportion prediction model;
The method for updating the expected life of the well wall comprises the following steps:
marking the expected life of the well wall before updating as Yq;
marking the predicted well wall life loss proportion as Bp;
marking the time length of the time distance monitoring starting time judged to have the potential safety hazard as Tr;
The updated life expectancy Yh of the well wall is calculated by the following steps: 。
The comprehensive safety monitoring system for the well wall structure of the well drilling method comprises a training data collection module, a model training module, a well wall life prediction module and a safety monitoring module; wherein, each module is electrically connected;
The training data collection module is used for collecting a safety feature set in advance; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment, and transmitting the well wall life time label data, the safety feature training data, the safety feature life loss label data and the safety feature fluctuation training data to a model training module;
the model training module is used for taking safety feature training data corresponding to each safety feature as input, taking the well wall life time length label data as output, training a well wall life prediction model, taking safety feature fluctuation training data as input, taking safety feature life loss label data as output, training a well wall life loss proportion prediction model for each safety feature, sending the well wall life prediction model to the well wall life prediction module, and sending the well wall life prediction model and the well wall life loss proportion prediction model to the safety monitoring module;
The well wall life prediction module is used for collecting actual safety feature data of each safety feature of the well wall of the well to be monitored after the construction of the well to be monitored is completed by using a drilling method, obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and the well wall life prediction model, and sending the expected life to the safety monitoring module;
The safety monitoring module is used for collecting the real-time quantity of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, collecting the fluctuation training data of the well wall of the well to be monitored, and outputting the predicted well wall life loss proportion according to the fluctuation training data and the corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; and judging whether the current time reaches the life expectancy in real time, and if so, initiating a well wall safety alarm.
An electronic device is proposed, comprising: a processor and a memory, wherein the memory stores a computer program for the processor to call;
And the processor executes the comprehensive safety monitoring method for the well wall structure of the drilling method by calling the computer program stored in the memory.
A computer-readable storage medium is proposed, on which a computer program is stored that is erasable;
when the computer program runs on the computer equipment, the computer equipment is caused to execute the comprehensive safety monitoring method for the well wall structure of the well drilling method.
Compared with the prior art, the invention has the beneficial effects that:
The invention collects the safety feature set in advance; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; the method comprises the steps of pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment, taking the safety feature training data corresponding to each safety feature as input, taking the well wall life time label data as output, training a well wall life prediction model, taking the safety feature fluctuation training data as input, taking the safety feature life loss label data as output, training a well wall life loss proportion prediction model for each safety feature, collecting actual safety feature data of each safety feature of the well wall of the well to be monitored after the construction of the well to be monitored is completed through a drilling method, obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and the well wall life prediction model, collecting the safety feature real-time quantity of each safety feature of the well wall of the well to be monitored in real time, if any safety feature has potential safety hazards, collecting the fluctuation training data of the well wall of the well to be monitored, and outputting the predicted well wall life loss proportion according to the fluctuation training data and the corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; and calculating the time difference between the current time and the monitoring start time in real time, and if the time difference reaches the time of the expected service life, initiating a well wall safety alarm. The life prediction model of the well wall is trained firstly to predict the life of the well wall according to the parameter values of each safety feature of the well to be monitored, and then the life of the well wall is adjusted by using the life loss proportion prediction model of the well wall after the well wall is subjected to excessive disturbance, so that the early warning of the safety of the well wall is realized, and the purpose of safe and effective real-time monitoring of the quality of the well wall is achieved.
Drawings
FIG. 1 is a flow chart of a method for comprehensive safety monitoring of a borehole wall structure in accordance with embodiment 1 of the present invention;
FIG. 2 is a diagram showing the connection relationship between modules of the comprehensive safety monitoring system for a well wall structure in a well drilling method according to the embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of an electronic device in embodiment 3 of the present invention;
Fig. 4 is a schematic diagram of a computer-readable storage medium according to embodiment 4 of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, the comprehensive safety monitoring method for the well wall structure of the well drilling method comprises the following steps:
Step one: pre-collecting a security feature set; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment;
step two: training a well wall life prediction model by taking safety feature training data corresponding to each safety feature as input and well wall life time length label data as output;
training a well wall life loss proportion prediction model for each safety feature by taking the safety feature fluctuation training data as input and the safety feature life loss label data as output;
Step three: after the construction of the well to be monitored is completed by using a drilling method, collecting actual safety feature data of all safety features of the well wall of the well to be monitored, and obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and a well wall life prediction model;
step four: collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, turning to the fifth step; otherwise, turning to the step six;
step five: collecting fluctuation training data of the well wall of the well to be monitored, and outputting predicted well wall life loss proportion according to the fluctuation training data and a corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; executing the step six;
step six: calculating the time difference between the current time and the monitoring start time in real time, and if the time difference reaches the time of the expected service life, initiating a well wall safety alarm;
Wherein each security feature in the set of security features includes displacement, stress, environment, and fluid penetration; displacement is generally caused by geologic structure changes (such as geologic factors of underground structure activities, structure movements, earthquakes and the like), and displacement is used for indirect characterization because the geologic structure changes are difficult to quantitatively observe; stress is a change in the distribution of underground stress, including vertical and horizontal stresses, which may be caused by formation variations or mining activities, which are difficult to quantitatively observe, and therefore characterized by collecting real-time stress using stress sensors; the environment comprises humidity, rainfall and the like, and the rapid change of the environmental conditions around the well wall can cause the loosening and fastening of rock and soil around the well wall; fluid penetration includes the rate of change of the groundwater level and the flow speed of groundwater flow, rapid changes in groundwater level may cause the well wall to be affected by uneven water pressure;
Further, through life detection experiments, collecting the life time label data of the well wall and the safety feature training data corresponding to each safety feature, including:
Pre-selecting N first test well walls, wherein N is the number of the selected first test well walls; the first test well wall can be the well wall of a well which meets the actual requirement after being constructed by using a drilling method, can be the well wall of a three-dimensional model of the well which is generated by digital twin modeling, and can be the well wall of a small well which has a certain proportion relation with the size of the well which is actually required after being constructed by using the drilling method, so that the experimental cost is saved;
setting a parameter value of the displacement in the security feature of each first test borehole wall to 0;
setting the stress, environment and fluid permeability of each first test well wall to different parameter values respectively, and keeping the stress, environment and fluid permeability unchanged;
collecting service life time labels of each first test well wall; the life duration label may be a duration from the beginning of the test to the time the professional evaluates as having a security risk;
The stress, environment and fluid permeability parameters of each first test well wall form a safety feature vector, and the safety feature vectors of all the first test well walls form safety feature training data;
All the life time labels of the first test well wall form well wall life time label data;
further, the method for collecting the life loss label data of the safety features and the safety feature fluctuation training data corresponding to each safety feature in advance through the life loss detection experiment is as follows:
collecting N second test well walls for each safety feature again, wherein each second test well wall corresponds to one first test well wall, and the safety feature vector of each second test well wall is consistent with the corresponding first test well wall;
for each security feature:
marking the safety feature as i, and marking the number of each second test borehole wall of the safety feature i as ij;
Marking a life time label of a first test well wall corresponding to the ij second test well wall as TZij;
For the ij second test well wall, arbitrarily selecting a time point as a disturbance time point, and continuously and incrementally changing the parameter value of the safety feature i in the safety feature vector; the specific increment degree and increment time can be determined or randomly generated according to the actual requirements; marking the time length of the selected disturbance time point from the life loss detection experiment starting time as TSij;
Presetting disturbance collection time length T1; collecting a safety feature parameter sequence formed by each safety feature parameter value in a disturbance collection time period T1 of each second test well wall after a disturbance time point according to a unit time sequence; for example, when the safety feature is a displacement, the safety feature parameter sequence may be [1,2,3,4,5], which respectively represents that the displacement of the well wall is 1,2,3,4,5 in five unit time; the safety feature parameter sequences of all safety features form safety feature fluctuation training data;
Collecting the final service life of each second testing well wall, and marking the service life of the ij second testing well wall as TRij; it can be understood that the life time of the second test well wall is smaller than that of the corresponding first test well wall because the life time is disturbed by the safety feature;
calculating a well wall life loss proportion label Bij of the ij second test well wall; the calculation mode of the well wall life loss proportion label Bij is as follows The well wall life loss proportion labels corresponding to all the safety features of the second test well wall form safety feature life loss label data; it will be appreciated that Bij measures the extent to which the life of the borehole wall is compromised due to disturbances in the security features;
further, the method for training the well wall life prediction model by taking the safety feature training data corresponding to each safety feature as input and the well wall life time length label data as output is as follows:
Taking the safety feature vector of each first test well wall as the input of a well wall life prediction model, taking a predicted value of the life time length of the first test well wall as output, taking a life time length label corresponding to the first test well wall as a prediction target, taking the difference value between the predicted value of the life time length and the life time length label as a first prediction error, and taking the sum of minimized first prediction errors as a training target; training the well wall life prediction model until the sum of the first prediction errors reaches convergence, stopping training, and training out parameter values according to each safety feature, and outputting the well wall life prediction model of the well wall with the predicted life duration; the well wall life prediction model is a polynomial regression model; the sum of the first prediction errors is a mean square error;
furthermore, the method for training the well wall life loss proportion prediction model for each safety feature by taking the safety feature fluctuation training data as input and the safety feature life loss label data as output comprises the following steps:
for each security feature:
Taking the safety feature fluctuation training data of each second test well wall as the input of a well wall life loss proportion prediction model, taking a predicted value of the well wall life loss proportion of the second test well wall as the output, taking a well wall life loss proportion label of the safety feature corresponding to the second test well wall as a prediction target, taking a difference value between the predicted value of the well wall life loss proportion and the well wall life loss proportion label as a second prediction error, and taking the sum of the minimized second prediction errors as a training target; training the well wall life loss proportion prediction model until the sum of the second prediction errors reaches convergence, stopping training, and outputting the well wall life loss proportion prediction model of the well wall life loss proportion caused by the disturbance of the safety features according to the parameter sequences of the safety features after the disturbance of the safety features occurs; the well wall life loss proportion prediction model is a time sequence prediction model; the time series prediction model includes, but is not limited to, an RNN network model and an LSTM network model; the sum of the second prediction errors is a mean square error;
further, after the construction of the well to be monitored is completed by using the drilling method, the method for collecting the actual safety feature data of each safety feature of the well wall of the well to be monitored is as follows:
The method comprises the steps of respectively using physical sensors corresponding to all safety features to obtain parameter values of all safety features of a well wall of a well to be monitored after construction is completed, and forming actual safety feature data from the parameter values of all the safety features collected at the moment; for example, a computer vision sensor (such as a camera) is used for capturing the displacement of the well wall, a humidity sensor is used for capturing the humidity of the environment where the well wall is positioned, and the like;
Further, the method for obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and the well wall life prediction model comprises the following steps:
inputting actual safety characteristic data into a well wall life prediction model to obtain a predicted value of the well wall life of the well to be monitored, which is output by the well wall life prediction model, and taking the predicted value as the expected life of the well wall of the well to be monitored;
Further, the manner of collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time is as follows:
Installing physical sensors corresponding to each safety feature on the wall of the well to be monitored;
Each physical sensor collects real-time parameter values of corresponding safety features in real time as safety feature real-time quantities of the safety features;
Further, the method for judging the potential safety hazard of any one safety feature is as follows:
presetting a security feature variation threshold for each security feature;
if the variation of any safety feature is larger than the safety feature variation threshold, judging that potential safety hazards exist;
the variation of the safety feature refers to the difference between the real-time quantity of the safety feature and the parameter value of the corresponding safety feature in the actual safety feature data;
further, the method for collecting the fluctuation training data of the well wall of the well to be monitored is as follows:
Collecting and judging safety feature parameter sequences of all safety features within disturbance collection time T1 from the moment when potential safety hazards exist, and forming fluctuation training data;
further, the method for outputting the predicted life loss ratio of the well wall by using the fluctuation training data and the corresponding life loss ratio prediction model of the well wall comprises the following steps:
Marking the safety feature corresponding to the safety hidden danger as a dangerous feature;
Inputting the fluctuation training data into a well wall life loss proportion prediction model corresponding to the dangerous characteristics, and obtaining a predicted well wall life loss proportion output by the well wall life loss proportion prediction model;
further, based on the life loss proportion, the method for updating the expected life of the well wall is as follows:
marking the expected life of the well wall before updating as Yq;
marking the predicted well wall life loss proportion as Bp;
marking the time length of the time distance monitoring starting time judged to have the potential safety hazard as Tr;
The updated life expectancy Yh of the well wall is calculated by the following steps: 。
Example 2
As shown in fig. 2, the comprehensive safety monitoring system for the well wall structure of the drilling method comprises a training data collection module, a model training module, a well wall life prediction module and a safety monitoring module; wherein, each module is electrically connected;
The training data collection module is mainly used for collecting a safety feature set in advance; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment, and transmitting the well wall life time label data, the safety feature training data, the safety feature life loss label data and the safety feature fluctuation training data to a model training module;
The model training module is mainly used for taking safety feature training data corresponding to each safety feature as input, taking well wall life time length label data as output, training a well wall life prediction model, taking safety feature fluctuation training data as input, taking safety feature life loss label data as output, training a well wall life loss proportion prediction model for each safety feature, sending the well wall life prediction model to the well wall life prediction module, and sending the well wall life prediction model and the well wall life loss proportion prediction model to the safety monitoring module;
The well wall life prediction module is mainly used for collecting actual safety feature data of various safety features of the well wall of the well to be monitored after the construction of the well to be monitored is completed by using a drilling method, obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and a well wall life prediction model, and sending the expected life to the safety monitoring module;
The safety monitoring module is mainly used for collecting real-time safety feature quantity of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, collecting fluctuation training data of the well wall of the well to be monitored, and outputting predicted well wall life loss proportion according to the fluctuation training data and the corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; and judging whether the current time reaches the life expectancy in real time, and if so, initiating a well wall safety alarm.
Example 3
Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 3, there is also provided an electronic device 100 according to yet another aspect of the present application. The electronic device 100 may include one or more processors and one or more memories. Wherein the memory has stored therein computer readable code which, when executed by the one or more processors, is capable of performing the method of integrated safety monitoring of a wellbore wall structure as described above.
The method or apparatus according to embodiments of the present application may also be implemented by means of the architecture of the electronic device shown in fig. 3. As shown in fig. 3, the electronic device 100 may include a bus 101, one or more CPUs 102, a ROM103, a RAM104, a communication port 105 connected to a network, an input/output component 106, a hard disk 107, and the like. A storage device in the electronic device 100, such as the ROM103 or the hard disk 107, may store the method for comprehensive safety monitoring of the well wall structure of the well drilling method provided by the present application. The method for comprehensively monitoring the safety of the well wall structure by the drilling method can comprise the following steps: step one: pre-collecting a security feature set; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment; step two: training a well wall life prediction model by taking safety feature training data corresponding to each safety feature as input and well wall life time length label data as output; training a well wall life loss proportion prediction model for each safety feature by taking the safety feature fluctuation training data as input and the safety feature life loss label data as output; step three: after the construction of the well to be monitored is completed by using a drilling method, collecting actual safety feature data of all safety features of the well wall of the well to be monitored, and obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and a well wall life prediction model; step four: collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, turning to the fifth step; otherwise, turning to the step six; step five: collecting fluctuation training data of the well wall of the well to be monitored, and outputting predicted well wall life loss proportion according to the fluctuation training data and a corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; executing the step six; step six: and calculating the time difference between the current time and the monitoring start time in real time, and if the time difference reaches the time of the expected service life, initiating a well wall safety alarm.
Further, the electronic device 100 may also include a user interface 108. Of course, the architecture shown in fig. 3 is merely exemplary, and one or more components of the electronic device shown in fig. 3 may be omitted as may be practical in implementing different devices.
Example 4
FIG. 4 is a schematic diagram of a computer-readable storage medium according to one embodiment of the present application. As shown in fig. 4, is a computer-readable storage medium 200 according to one embodiment of the application. The computer-readable storage medium 200 has stored thereon computer-readable instructions. The method for integrated safety monitoring of a wellbore wall structure according to the embodiments of the present application described with reference to the above figures may be performed when the computer readable instructions are executed by a processor. Computer-readable storage medium 200 includes, but is not limited to, for example, volatile memory and/or nonvolatile memory. Volatile memory can include, for example, random Access Memory (RAM), cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like.
In addition, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, the present application provides a non-transitory machine-readable storage medium storing machine-readable instructions executable by a processor to perform instructions corresponding to the method steps provided by the present application, which when executed by a Central Processing Unit (CPU), perform the functions defined above in the method of the present application.
The methods and apparatus, devices of the present application may be implemented in numerous ways. For example, the methods and apparatus, devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present application may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present application. Thus, the present application also covers a recording medium storing a program for executing the method according to the present application.
In addition, in the foregoing technical solutions provided in the embodiments of the present application, parts consistent with implementation principles of corresponding technical solutions in the prior art are not described in detail, so that redundant descriptions are avoided.
The purpose, technical scheme and beneficial effects of the invention are further described in detail in the detailed description. It is to be understood that the above description is only of specific embodiments of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The above preset parameters or preset thresholds are set by those skilled in the art according to actual conditions or are obtained by mass data simulation.
The above embodiments are only for illustrating the technical method of the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted with equivalents thereof without departing from the spirit and scope of the technical method of the present invention.
Claims (13)
1. The comprehensive safety monitoring method for the well wall structure of the well drilling method is characterized by comprising the following steps of:
Step one: pre-collecting a security feature set; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment;
Step two: training a well wall life prediction model by taking safety feature training data corresponding to each safety feature as input and well wall life time length label data as output; training a well wall life loss proportion prediction model for each safety feature by taking the safety feature fluctuation training data as input and the safety feature life loss label data as output;
Step three: after the construction of the well to be monitored is completed by using a drilling method, collecting actual safety feature data of all safety features of the well wall of the well to be monitored, and obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and a well wall life prediction model;
step four: collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, turning to the fifth step; otherwise, turning to the step six;
step five: collecting fluctuation training data of the well wall of the well to be monitored, and outputting predicted well wall life loss proportion according to the fluctuation training data and a corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; executing the step six;
step six: and calculating the time difference between the current time and the monitoring start time in real time, and if the time difference reaches the time of the expected service life, initiating a well wall safety alarm.
2. The method of comprehensive safety monitoring of a well wall structure according to claim 1, wherein each safety feature in the set of safety features comprises displacement, stress, environment, and fluid penetration.
3. The method for comprehensive safety monitoring of a well wall structure according to claim 2, wherein the collecting the well wall life time label data and the safety feature training data corresponding to each safety feature comprises:
pre-selecting N first test well walls, wherein N is the number of the selected first test well walls;
setting a parameter value of the displacement in the security feature of each first test borehole wall to 0;
setting the stress, environment and fluid permeability of each first test well wall to different parameter values respectively, and keeping the stress, environment and fluid permeability unchanged;
Collecting service life time labels of each first test well wall;
The stress, environment and fluid permeability parameters of each first test well wall form a safety feature vector, and the safety feature vectors of all the first test well walls form safety feature training data;
And all the life time labels of the first test well wall form well wall life time label data.
4. The method for comprehensively monitoring the safety of a well wall structure by a drilling method according to claim 3, wherein the mode of collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature in advance is as follows:
collecting N second test well walls for each safety feature again, wherein each second test well wall corresponds to one first test well wall, and the safety feature vector of each second test well wall is consistent with the corresponding first test well wall;
for each security feature:
marking the safety feature as i, and marking the number of each second test borehole wall of the safety feature i as ij;
Marking a life time label of a first test well wall corresponding to the ij second test well wall as TZij;
For the ij second test well wall, arbitrarily selecting a time point as a disturbance time point, and continuously and incrementally changing the parameter value of the safety feature i in the safety feature vector; marking the time length of the selected disturbance time point from the life loss detection experiment starting time as TSij;
Presetting disturbance collection time length T1; collecting a safety feature parameter sequence formed by each safety feature parameter value in a disturbance collection time period T1 of each second test well wall after a disturbance time point according to a unit time sequence; the safety feature parameter sequences of all safety features form safety feature fluctuation training data;
collecting the final service life of each second testing well wall, and marking the service life of the ij second testing well wall as TRij;
calculating a well wall life loss proportion label Bij of the ij second test well wall; the calculation mode of the well wall life loss proportion label Bij is as follows And all the well wall life loss proportion labels corresponding to the safety features of the second test well wall form safety feature life loss label data.
5. The method for comprehensively monitoring the safety of a well wall structure by a drilling method according to claim 4, wherein the mode of training a well wall life prediction model is as follows:
Taking the safety feature vector of each first test well wall as the input of a well wall life prediction model, taking a predicted value of the life time length of the first test well wall as output, taking a life time length label corresponding to the first test well wall as a prediction target, taking the difference value between the predicted value of the life time length and the life time length label as a first prediction error, and taking the sum of minimized first prediction errors as a training target; training the well wall life prediction model until the sum of the first prediction errors reaches convergence; the well wall life prediction model is a polynomial regression model; the sum of the first prediction errors is a mean square error.
6. The method for comprehensive safety monitoring of a well wall structure according to claim 5, wherein the training of the well wall life-loss ratio prediction model for each safety feature is as follows:
for each security feature:
Taking the safety feature fluctuation training data of each second test well wall as the input of a well wall life loss proportion prediction model, taking a predicted value of the well wall life loss proportion of the second test well wall as the output, taking a well wall life loss proportion label of the safety feature corresponding to the second test well wall as a prediction target, taking a difference value between the predicted value of the well wall life loss proportion and the well wall life loss proportion label as a second prediction error, and taking the sum of the minimized second prediction errors as a training target; training the well wall life loss proportion prediction model until the sum of the second prediction errors reaches convergence; the well wall life loss proportion prediction model is a time sequence prediction model; the sum of the second prediction errors is a mean square error.
7. The method for comprehensively monitoring the safety of a well wall structure by a drilling method according to claim 6, wherein the manner of collecting the real-time quantity of the safety features of each safety feature of the well wall of the well to be monitored in real time is as follows:
Installing physical sensors corresponding to each safety feature on the wall of the well to be monitored;
Each physical sensor collects real-time parameter values of a corresponding security feature in real-time as security feature real-time quantities of the security feature.
8. The method for comprehensively monitoring the safety of a well wall structure by a drilling method according to claim 7, wherein the method for judging the potential safety hazard of any one of the safety features is as follows:
presetting a security feature variation threshold for each security feature;
and if the variation of any safety feature is larger than the safety feature variation threshold, judging that the potential safety hazard exists.
9. The comprehensive safety monitoring method for a well wall structure according to claim 8, wherein the method for collecting fluctuation training data of the well wall of the well to be monitored is as follows:
and collecting and judging the safety feature parameter sequences of all the safety features within the disturbance collection time T1 from the moment when the potential safety hazards exist, and forming fluctuation training data.
10. The method for comprehensively monitoring the safety of a well wall structure by a drilling method according to claim 9, wherein the mode of outputting the predicted well wall life-loss ratio by using the fluctuation training data and the corresponding well wall life-loss ratio prediction model is as follows:
Marking the safety feature corresponding to the safety hidden danger as a dangerous feature;
Inputting the fluctuation training data into a well wall life loss proportion prediction model corresponding to the dangerous characteristics, and obtaining a predicted well wall life loss proportion output by the well wall life loss proportion prediction model;
The method for updating the expected life of the well wall comprises the following steps:
marking the expected life of the well wall before updating as Yq;
marking the predicted well wall life loss proportion as Bp;
marking the time length of the time distance monitoring starting time judged to have the potential safety hazard as Tr;
The updated life expectancy Yh of the well wall is calculated by the following steps: 。
11. The comprehensive safety monitoring system for the well wall structure of the well drilling method is used for realizing the comprehensive safety monitoring method for the well wall structure of the well drilling method according to any one of claims 1-10, and is characterized by comprising a training data collection module, a model training module, a well wall life prediction module and a safety monitoring module; wherein, each module is electrically connected;
The training data collection module is used for collecting a safety feature set in advance; collecting well wall service life time length label data and safety feature training data corresponding to each safety feature through a service life detection experiment; pre-collecting safety feature life loss label data and safety feature fluctuation training data corresponding to each safety feature through a life loss detection experiment, and transmitting the well wall life time label data, the safety feature training data, the safety feature life loss label data and the safety feature fluctuation training data to a model training module;
the model training module is used for taking safety feature training data corresponding to each safety feature as input, taking the well wall life time length label data as output, training a well wall life prediction model, taking safety feature fluctuation training data as input, taking safety feature life loss label data as output, training a well wall life loss proportion prediction model for each safety feature, sending the well wall life prediction model to the well wall life prediction module, and sending the well wall life prediction model and the well wall life loss proportion prediction model to the safety monitoring module;
The well wall life prediction module is used for collecting actual safety feature data of each safety feature of the well wall of the well to be monitored after the construction of the well to be monitored is completed by using a drilling method, obtaining the expected life of the well wall of the well to be monitored based on the actual safety feature data and the well wall life prediction model, and sending the expected life to the safety monitoring module;
The safety monitoring module is used for collecting the real-time quantity of each safety feature of the well wall of the well to be monitored in real time, and if any safety feature has potential safety hazards, collecting the fluctuation training data of the well wall of the well to be monitored, and outputting the predicted well wall life loss proportion according to the fluctuation training data and the corresponding well wall life loss proportion prediction model; updating the life expectancy of the well wall based on the life loss proportion; and judging whether the current time reaches the life expectancy in real time, and if so, initiating a well wall safety alarm.
12. An electronic device, comprising: a processor and a memory, wherein:
the memory stores a computer program which can be called by the processor;
The processor performs the method for comprehensive safety monitoring of a well wall structure of a well drilling method according to any one of claims 1-10 in the background by calling a computer program stored in the memory.
13. A computer readable storage medium having stored thereon a computer program that is erasable;
the computer program, when run on a computer device, causes the computer device to perform the method of comprehensive safety monitoring of a well wall structure of a well as claimed in any one of claims 1 to 10 in the background.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410325180.4A CN117933495B (en) | 2024-03-21 | 2024-03-21 | Comprehensive safety monitoring system and method for well wall structure by drilling method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410325180.4A CN117933495B (en) | 2024-03-21 | 2024-03-21 | Comprehensive safety monitoring system and method for well wall structure by drilling method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117933495A true CN117933495A (en) | 2024-04-26 |
| CN117933495B CN117933495B (en) | 2024-06-18 |
Family
ID=90765024
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410325180.4A Active CN117933495B (en) | 2024-03-21 | 2024-03-21 | Comprehensive safety monitoring system and method for well wall structure by drilling method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117933495B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234575A (en) * | 2013-03-26 | 2013-08-07 | 安徽理工大学 | Method for improving and detecting safety of mine shaft on basis of firefly algorithm |
| CN109829561A (en) * | 2018-11-15 | 2019-05-31 | 西南石油大学 | Accident forecast method based on smoothing processing Yu network model machine learning |
| CN111691873A (en) * | 2019-03-13 | 2020-09-22 | 中国石油化工股份有限公司 | Method and system for calculating borehole wall stability value for borehole wall stability prediction |
| CN113095593A (en) * | 2021-04-30 | 2021-07-09 | 中国石油大学(北京) | Method, device and equipment for determining well wall state of drilling well |
| CN113496302A (en) * | 2020-04-02 | 2021-10-12 | 中国石油化工股份有限公司 | Method and system for intelligently identifying and early warning drilling risks |
| CN114462662A (en) * | 2021-09-24 | 2022-05-10 | 中国海洋石油集团有限公司 | Drilling tool life big data prediction and analysis method |
| CN115324571A (en) * | 2022-08-02 | 2022-11-11 | 西南石油大学 | Method and device for quantitatively predicting complex stratum well wall collapse based on drilling and logging information |
| CN115438823A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability mechanism analysis and prediction method and system |
| US20230266500A1 (en) * | 2020-07-31 | 2023-08-24 | Hamed Soroush | Geomechanics and wellbore stability modeling using drilling dynamics data |
| CN116822971A (en) * | 2023-08-30 | 2023-09-29 | 长江大学武汉校区 | Well wall risk level prediction method |
| US20230316152A1 (en) * | 2022-03-31 | 2023-10-05 | Saudi Arabian Oil Company | Method to predict aggregate caliper logs using logging-while-drilling data |
| CN117627627A (en) * | 2023-11-27 | 2024-03-01 | 长江大学 | Intelligent detection method for oil-gas well shaft safety |
-
2024
- 2024-03-21 CN CN202410325180.4A patent/CN117933495B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103234575A (en) * | 2013-03-26 | 2013-08-07 | 安徽理工大学 | Method for improving and detecting safety of mine shaft on basis of firefly algorithm |
| CN109829561A (en) * | 2018-11-15 | 2019-05-31 | 西南石油大学 | Accident forecast method based on smoothing processing Yu network model machine learning |
| CN111691873A (en) * | 2019-03-13 | 2020-09-22 | 中国石油化工股份有限公司 | Method and system for calculating borehole wall stability value for borehole wall stability prediction |
| CN113496302A (en) * | 2020-04-02 | 2021-10-12 | 中国石油化工股份有限公司 | Method and system for intelligently identifying and early warning drilling risks |
| US20230266500A1 (en) * | 2020-07-31 | 2023-08-24 | Hamed Soroush | Geomechanics and wellbore stability modeling using drilling dynamics data |
| CN113095593A (en) * | 2021-04-30 | 2021-07-09 | 中国石油大学(北京) | Method, device and equipment for determining well wall state of drilling well |
| CN115438823A (en) * | 2021-06-02 | 2022-12-06 | 中国石油化工股份有限公司 | Borehole wall instability mechanism analysis and prediction method and system |
| CN114462662A (en) * | 2021-09-24 | 2022-05-10 | 中国海洋石油集团有限公司 | Drilling tool life big data prediction and analysis method |
| US20230316152A1 (en) * | 2022-03-31 | 2023-10-05 | Saudi Arabian Oil Company | Method to predict aggregate caliper logs using logging-while-drilling data |
| CN115324571A (en) * | 2022-08-02 | 2022-11-11 | 西南石油大学 | Method and device for quantitatively predicting complex stratum well wall collapse based on drilling and logging information |
| CN116822971A (en) * | 2023-08-30 | 2023-09-29 | 长江大学武汉校区 | Well wall risk level prediction method |
| CN117627627A (en) * | 2023-11-27 | 2024-03-01 | 长江大学 | Intelligent detection method for oil-gas well shaft safety |
Non-Patent Citations (2)
| Title |
|---|
| 吴超 等: "井壁稳定性实时预测方法", 《石油勘探与开发》, no. 01, 29 February 2008 (2008-02-29), pages 80 - 84 * |
| 陈勉, 金衍: "深井井壁稳定技术研究进展与发展趋势", 《石油钻探技术》, vol. 33, no. 05, 30 September 2005 (2005-09-30), pages 28 - 34 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117933495B (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11795814B2 (en) | Early warning and automated detection for lost circulation in wellbore drilling | |
| CN104452836A (en) | Monitoring and early warning method of the stability of a foundation pit supporting structure | |
| CN109033504B (en) | Oil-water well casing damage prediction method | |
| CN112031839B (en) | Mine pressure space-time bi-periodic prediction method, device and equipment under limited data condition | |
| CN111859712A (en) | Ground advanced pre-control method for coal mine rock burst | |
| CN111042866B (en) | Multi-physical-field cooperative water inrush monitoring method | |
| US20170306726A1 (en) | Stuck pipe prediction | |
| CN114991225B (en) | Deep foundation pit deformation monitoring method, device and server | |
| CN109902265B (en) | Underground early warning method based on hidden Markov model | |
| CN117933495B (en) | Comprehensive safety monitoring system and method for well wall structure by drilling method | |
| CN113221347B (en) | Well wall stability drilling optimization method, device and equipment | |
| Qin et al. | Prediction of longwall mining‐induced stress in roof rock using LSTM neural network and transfer learning method | |
| CN115455791B (en) | Method for improving landslide displacement prediction accuracy based on numerical simulation technology | |
| CN116777085A (en) | Coal mine water damage prediction system based on data analysis and machine learning technology | |
| CN110714754B (en) | Method, system and storage medium for determining height of fractured zone and height of caving zone | |
| CN112324505A (en) | Pressure-bearing water coal mining micro-seismic water inrush early warning method and device and terminal equipment | |
| CN113685166B (en) | Drilling accident early warning method and system | |
| CN112100796A (en) | Drilling track determination method and device for preventing casing in shale gas well from being damaged | |
| CN115639604B (en) | Quantitative analysis method and system for underground cavern deep and shallow layer surrounding rock damage | |
| CN218481100U (en) | Pipeline track detecting system | |
| CN109165480B (en) | Method and system for predicting pit water inflow based on clay stress path | |
| KR102675763B1 (en) | Smart sensor system for civil structure maintenance | |
| CN116050938B (en) | Coal mine transportation safety supervision system based on data analysis | |
| CN117291100A (en) | TBM cutter head card machine prediction method and system utilizing correlation of detection parameters and torque | |
| CN116777101A (en) | Liquid level change early warning method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |