Intelligent grouting progress monitoring and control method and system

Abstract

The invention discloses an intelligent grouting progress monitoring management and control method and system, and relates to the technical field of intelligent grouting, and the method comprises the steps: obtaining a preset video monitoring frequency range and a preset video monitoring duration range, and obtaining a plurality of random video monitoring vectors based on a random number generation method; analyzing monitoring redundant data and monitoring load data of grouting progress monitoring under different video monitoring vectors; constructing a progress monitoring effect evaluation model based on machine learning according to the monitoring redundant data and the monitoring load data; constructing a video monitoring vector effect display model based on the three-dimensional model according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, and performing data analysis on the video monitoring vector effect display model to obtain an optimal video monitoring vector which is used for managing and controlling the monitoring process of the grouting progress; the method is used for solving the problem of poor monitoring caused by shooting disorder during grouting progress monitoring in the prior art.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent grouting, and more specifically, to an intelligent grouting progress monitoring and control method and system. Background Art

[0002] The operating principle of intelligent grouting is based on real-time monitoring and data collection of the construction site. The key parameters of the grouting process (such as pressure, flow, time, grouting status, etc.) are automatically monitored through installed sensors and cameras. The system analyzes the collected data and determines in real time whether the grouting meets the predetermined standards. If an abnormality is found, an alarm is immediately issued and feedback is given to the construction personnel so that timely measures can be taken. At the same time, the intelligent grouting system generates grouting records and video files that cannot be tampered with to ensure traceability of the entire process and guarantee grouting quality and construction safety.

[0003] National standards and local specifications have set strict quality requirements for the construction process of steel sleeve grouting in prefabricated buildings. Construction units must record the entire construction process on video. However, the current filming of construction sites is often casual, lacking standardized monitoring standards, and recorded video materials are easily edited and tampered with, making it difficult to provide reliable evidence support when problems arise. In this case, the traceability of the grouting process and construction safety are difficult to guarantee, increasing the risk of project quality.

[0004] Some grouting video detection management systems have begun to be introduced. Such systems can perform real-time quality monitoring and problem feedback on the grouting construction process by extracting and analyzing key variables from videos shot at the construction site. The system can promptly detect abnormal phenomena in grouting construction, such as the lack of grouting from the grouting holes and illegal blocking, and can quickly formulate corresponding solutions. However, although the existing systems have certain monitoring and analysis functions, their video records may still be at risk of modification or loss, and cannot fully meet the needs of project quality management and construction process traceability.

[0005] For example, the grouting unit flowmeter calibration device and method disclosed in the invention patent with announcement number CN108801404B includes initializing the flowmeter calibration mark and the flowmeter full value; when the recorder storage interval is reached, recording the amount of slurry injected within the storage interval; judging whether the slurry mixing system is activated within the storage interval, if the slurry mixing system is activated, initializing the initial slurry amount of the slurry mixing system and returning to step two; judging whether the system slurry injection rate is a small injection rate, if it is not a small injection rate, returning to step two, if it is a small injection rate, calibrating the flowmeter full value and setting the flowmeter calibration mark. The present invention can automatically measure the slurry amount in the slurry barrel with a machine and automatically calibrate the flowmeter, which can improve the automation level of the site, reduce supervision intervention and work intensity; control key quality points of grouting, improve grouting quality; reduce unnecessary grouting time, and improve grouting progress.

[0006] For example, the invention patent with announcement number CN117906825A discloses a cloud platform-based remote transmission method and system for grouting monitoring data. First, the change characteristic value corresponding to each data point in the total set of pressure time series data is obtained; in the process of binary partitioning the data set to be processed, an isolated tree is constructed, and the noise degree value of each pressure data segmentation set is obtained according to the set continuous value, set correlation value and number of elements of the pressure data segmentation set; the actual segmentation value of the data set to be processed is determined; and then all noise data in the total set of pressure time series data is corrected to obtain the grouting monitoring transmission data of the total set of pressure time series data. In the embodiment of the present invention, the selection of the actual segmentation value is optimized to improve the accuracy of identifying noise data and real data, thereby improving the efficiency of remote transmission data of grouting pressure.

[0007] The above disclosed technical solutions have at least the following technical problems: There are many quality and management problems in the existing steel sleeve grouting construction process, especially in the monitoring and control of construction progress. At present, manual monitoring and traditional video recording are often used in grouting construction. However, traditional methods have many limitations, especially in the construction process, which is prone to human operation errors and grouting quality risks.

[0008] If you shoot videos too frequently during multiple construction phases, although it can reflect the progress in more detail, it will lead to data redundancy and increase the burden of video processing and storage. At the same time, frequent switching of shooting may interfere with the normal construction progress;

[0009] If the shooting time intervals are too far apart, some important operation links or quality issues in the grouting process may be missed, such as blockage of the grouting holes or the solidification stage of the grouting materials, and the entire construction progress cannot be fully reflected.

[0010] In view of the above problems, the present invention proposes a solution. Summary of the invention

[0011] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an intelligent grouting progress monitoring and control method and system, which solves the problem of poor monitoring caused by chaotic shooting during existing grouting progress monitoring by analyzing the optimal duration and time period of video shooting.

[0012] To achieve the above object, the present invention provides the following technical solutions:

[0013] An intelligent grouting progress monitoring and control method and system, comprising the following steps: obtaining a preset video monitoring frequency range and a video monitoring time range, and obtaining a number of random video monitoring vectors based on a random number generation method, wherein the video monitoring vectors include a video monitoring frequency and a video monitoring time; analyzing the monitoring redundant data and the monitoring load data of the grouting progress monitoring under different video monitoring vectors; constructing a progress monitoring effect evaluation model based on machine learning according to the monitoring redundant data and the monitoring load data; constructing a video monitoring vector effect display model based on a three-dimensional model according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, and performing data analysis on the video monitoring vector effect display model to obtain the optimal video monitoring vector, which is used to control the monitoring process of the grouting progress.

[0014] In a preferred embodiment, the random number generation method is based on which a number of random video monitoring vectors are obtained, specifically: obtaining a preset video monitoring frequency range and a video monitoring duration range; randomly extracting a number of video monitoring frequency values ​​from the set frequency range based on a random number generation library in a computer language; and randomly generating a number of video monitoring duration values ​​from the set duration range; randomly combining the generated random video monitoring frequency values ​​and video monitoring duration values ​​into a video monitoring vector; filtering and storing the video monitoring vectors through a set data structure, and each time a new video monitoring vector is formed, checking whether the video monitoring vector already exists in the set, and if so, regenerating it until a unique video monitoring vector is formed.

[0015] In a preferred embodiment, the monitoring redundant data includes a video review effectiveness coefficient and an abnormal tracing influence coefficient; the specific method for obtaining the video review effectiveness coefficient is as follows: obtain video data for video review, the video data includes a standard reference video and a historical review video, and classify the historical review videos into stage types according to the standard reference video; calculate the effective proportion of each video data category in the video data; calculate the video effective information entropy of the video data according to the effective proportion; and normalize the video effective information entropy to the video review effectiveness coefficient.

[0016] In a preferred embodiment, the specific method for obtaining the abnormal tracing influence coefficient is as follows: collect abnormal positioning data, the abnormal positioning data includes each abnormal feedback and positioning accuracy; classify the collected abnormal feedback according to type, and assign abnormal weights to different types of abnormalities; calculate the abnormal impact coefficient according to the type and weight of the abnormal feedback; obtain the abnormal feedback accuracy and abnormal range affected by the project abnormality and the duration of the video interval occupied, and calculate the abnormal feedback effectiveness coefficient; obtain the type of grouting machine progress in the monitoring process, the type of grouting machine progress in the monitoring process includes the grouting start-up stage, the initial grouting stage, the stable grouting stage, the final pressure stage and the solidification stage, and set the stage score for the type of grouting machine progress according to the proportion of abnormal feedback accuracy, and the total stage score remains unchanged; calculate the abnormal tracing influence coefficient in combination with the abnormal feedback effectiveness coefficient, the abnormal influence coefficient and the stage score.

[0017] In a preferred embodiment, the monitored load data includes a system load influence coefficient, and a specific method for obtaining the system load influence coefficient is as follows: real-time monitoring of the computing resource consumption rate and the video transmission bit rate corresponding to the time interval E within the P time when monitoring the grouting progress, and numbering the computing resource consumption rate and the video transmission bit rate; calculating the system load standard deviation and the system load average value by the computing resource consumption rate and the video transmission bit rate corresponding to the time interval E within the P time when monitoring the grouting progress; calculating the system load variation coefficient based on the system load standard deviation and the system load average value; calculating the system load influence coefficient based on the system load variation coefficient.

[0018] In a preferred embodiment, according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, a video monitoring vector effect display model is constructed based on a three-dimensional model, specifically: the video monitoring frequency and video monitoring duration of each video monitoring vector are marked as the x-axis and y-axis on the rectangular coordinate system respectively, the marked rectangular coordinate system is used as the base, and the output of the progress monitoring effect evaluation model corresponding to each video monitoring vector mark is used as the z-axis of the video monitoring vector effect display model; and each evaluation vector is used as a data point to update the marked video monitoring vector effect display model; each data point of the video monitoring vector effect display model is connected to draw a three-dimensional effect-video monitoring vector curve.

[0019] In a preferred embodiment, the video monitoring vector effect display model is subjected to data analysis to obtain the best video monitoring vector, which is used to control the monitoring process of the grouting progress. Specifically, a corresponding mathematical function is established according to the effect-video monitoring vector curve; each peak value in the effect-video monitoring vector curve is obtained, and the secondary derivative of the corresponding peak value in the mathematical function is calculated, and the video monitoring vector corresponding to the peak value whose secondary derivative is closest to zero is taken as the best video monitoring vector, which is used to control the monitoring process of the grouting progress.

[0020] A system for an intelligent grouting progress monitoring and control method includes a monitoring vector generation module, a data analysis module, a data evaluation module and a monitoring vector screening module, and there is a connection between the modules; the monitoring vector generation module is used to obtain a preset video monitoring frequency range and a video monitoring time range, and obtain a number of random video monitoring vectors based on a random number generation method, wherein the video monitoring vectors include a video monitoring frequency and a video monitoring time; the data analysis module is used to analyze the monitoring redundant data and the monitoring load data of the grouting progress monitoring under different video monitoring vectors; the data evaluation module is used to construct a progress monitoring effect evaluation model based on machine learning according to the monitoring redundant data and the monitoring load data; the monitoring vector screening module is used to construct a video monitoring vector effect display model based on a three-dimensional model according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, and perform data analysis on the video monitoring vector effect display model to obtain the best video monitoring vector, which is used to control the monitoring process of the grouting progress.

[0021] Technical effects and advantages of an intelligent grouting progress monitoring and control method and system of the present invention:

[0022] 1. The present invention proposes a solution for optimizing grouting progress monitoring by using a monitoring vector method based on random number generation, randomly combining the video monitoring frequency and duration and evaluating its monitoring effect. Its technical effects include effectively improving the monitoring accuracy and system resource utilization by calculating the video review effectiveness coefficient, the abnormal tracing influence coefficient and the system load influence coefficient. First, the video review effectiveness coefficient analyzes the effective information entropy in the video to screen out monitoring clips containing important information, thereby avoiding data redundancy and invalid information processing, and improving monitoring efficiency and information value. Secondly, the abnormal tracing influence coefficient can ensure that key abnormal events are captured and traced in time during the grouting process, enhancing the timeliness of monitoring and the accuracy of problem location. Finally, the system load influence coefficient helps to evaluate the balance between monitoring frequency and system resources, and avoid system load problems caused by excessively high frequency shooting.

[0023] 2. The present invention has obvious technical advantages and effects by constructing a progress monitoring effect evaluation model based on monitoring redundant data and monitoring load data combined with machine learning. First, by introducing the video review effectiveness coefficient, the abnormal tracing influence coefficient and the system load influence coefficient, the progress monitoring effect can be evaluated more comprehensively and accurately. Secondly, the progress monitoring effect evaluation coefficient is generated by a formulated evaluation model, which ensures the accuracy and objectivity of the evaluation process. In addition, based on the display method of the three-dimensional model, the video monitoring vector is combined with the monitoring effect evaluation, and further through the optimization analysis of mathematical functions, the optimal video monitoring vector can be accurately identified and selected. This method not only improves the accuracy of grouting progress monitoring, but also effectively reduces data redundancy in monitoring, optimizes monitoring efficiency, and achieves more efficient process control. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a structural schematic diagram of an intelligent grouting progress monitoring and control method of the present invention.

[0025] Figure 2 This is a structural schematic diagram of an intelligent grouting progress monitoring and control system of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] Embodiment 1, Figure 1 The present invention provides an intelligent grouting progress monitoring and control method, comprising the following steps:

[0028] S1, obtaining a preset video monitoring frequency range and a video monitoring duration range, and obtaining a number of random video monitoring vectors based on a random number generation method, wherein the video monitoring vectors include a video monitoring frequency and a video monitoring duration;

[0029] In this embodiment, the random number generation method is used to obtain a number of random video monitoring vectors, specifically:

[0030] Get the preset video monitoring frequency range and video monitoring duration range;

[0031] A random number generation library based on computer language randomly extracts a number of video monitoring frequency values ​​from a set frequency range;

[0032] And randomly generate several video monitoring duration values ​​from the set duration range;

[0033] Randomly combine the generated random video monitoring frequency value and video monitoring duration value into a video monitoring vector;

[0034] The video monitoring vectors are filtered and stored through the set data structure. Each time a new video monitoring vector is formed, it is checked whether the video monitoring vector already exists in the set. If so, it is regenerated until a unique video monitoring vector is formed.

[0035] It should be noted that the preset video monitoring frequency range and video monitoring duration range are determined according to the actual needs and process characteristics of the grouting construction. During the grouting process, a frequency that is too high may lead to increased redundancy in monitoring data and excessive resource consumption, while a frequency that is too low may miss key issues. Usually, the frequency range is set between a few seconds and a few minutes to ensure that important stages of the grouting process can be captured in a timely manner. The range of video monitoring duration needs to comprehensively consider the duration of each monitoring to avoid the data processing burden caused by too long video clips. The duration range can be set from a few minutes to more than ten minutes so that the key grouting links can be covered to ensure the integrity and traceability of the entire construction process.

[0036] S2, analyzing the monitoring redundancy data and monitoring load data of grouting progress monitoring under different video monitoring vectors;

[0037] The monitoring redundancy data includes a video review effectiveness coefficient and an abnormality tracing influence coefficient, and the monitoring load data includes a system load influence coefficient;

[0038] The video review effectiveness coefficient is a key indicator for measuring the value of information contained in each shot video, usually expressed in the form of video effective information entropy; this coefficient reflects the richness of actual useful information in the video content, and can help evaluate the effectiveness of different video monitoring vectors; during the grouting process, if the parameters change relatively slowly, the videos obtained by frequent shooting may contain a large amount of redundant information, resulting in a decrease in the video review effectiveness coefficient, thereby increasing the cost of data processing; therefore, by calculating the video review effectiveness coefficient, it is possible to effectively determine whether the video obtained at a certain monitoring frequency has sufficient value, thereby providing a basis for optimizing the video monitoring vector and ensuring the efficiency of the monitoring process and the effectiveness of information.

[0039] Analyzing the video review effectiveness coefficient has the following advantages for selecting the best video monitoring vector to solve the problem of poor monitoring caused by chaotic shooting during existing grouting progress monitoring:

[0040] Improve information utilization: By calculating the video review effectiveness coefficient, monitoring videos with high information content and outstanding value can be screened out to avoid the impact of invalid or redundant data, ensuring that each monitoring segment can provide meaningful feedback for the grouting progress.

[0041] Optimize monitoring frequency and duration: Effectiveness coefficient analysis can help determine the optimal combination of monitoring frequency and duration, thereby avoiding information overload caused by frequent shooting, while ensuring that sufficient information can be obtained at critical stages. This optimization can improve the quality and efficiency of overall monitoring.

[0042] Enhance the accuracy of data analysis: When the video review effectiveness coefficient is high, it means that the changes and problems captured in the video can more accurately reflect the actual construction situation. By screening out videos with high effectiveness coefficients, the accuracy of subsequent data analysis can be enhanced, helping to identify and solve potential problems in a timely manner.

[0043] Reduce data processing costs: Screening out videos with high validity coefficients can reduce the amount of data that needs to be processed and analyzed, thereby reducing the cost of data storage and processing. After reducing redundant data, subsequent analysis work will be more efficient, saving time and resources.

[0044] Improve traceability: By analyzing the effectiveness coefficient of video review, it is possible to ensure that the selected video clips provide sufficient information support when tracing problems, thereby improving the traceability of the monitoring system and helping construction units to quickly locate the causes and make effective rectifications when problems arise.

[0045] Improve construction quality assurance: Comprehensive use of the video review effectiveness coefficient can enhance the control ability of grouting progress monitoring, thereby improving construction quality assurance, ensuring that the key parameters of each link can be effectively monitored, and ultimately improving the overall safety and stability of the project.

[0046] Through these advantages, the video review effectiveness coefficient provides a scientific basis for optimizing grouting progress monitoring, helps to solve the problem of poor monitoring due to chaotic shooting, and thus achieves more efficient and accurate construction monitoring.

[0047] The specific method for obtaining the video review effectiveness coefficient is as follows:

[0048] Obtain video data for video review, including standard reference videos and historical review videos, and classify the historical review videos into stage types according to the standard reference videos;

[0049] Calculate the effective proportion of each video data category in the video data;

[0050] Calculate the video effective information entropy of the video data according to the effective proportion;

[0051] The video effective information entropy is normalized into a video review effectiveness coefficient.

[0052] The calculation formula of the effective ratio is as follows: , The specific calculation formula of the effective information entropy of the video is as follows: , The specific calculation formula of the video review effectiveness coefficient is: , In the formula, is the effective proportion, is the number of historical videos with the value X in the video data, N is the total number of historical videos, is the possible value of the video data, is the effective information entropy of the video data, The validity coefficient of the video review.

[0053] The abnormal tracing impact coefficient is an important indicator used to evaluate the ability of video monitoring to capture key abnormal events during the grouting process. It reflects that low-frequency or discontinuous monitoring may lead to the omission of key issues during the monitoring process, especially abnormal situations that occur instantaneously during grouting (such as blockage of the grouting hole or insufficient grouting pressure). Low-frequency monitoring may not only miss these details, but also lead to feedback lags, affecting the timely implementation of countermeasures, and may ultimately endanger the quality of the project. In addition, when the video monitoring data is not detailed enough, it is impossible to accurately locate the time point when the problem occurred, making it more difficult to trace and solve the problem. Therefore, the abnormal tracing impact coefficient can help evaluate the effectiveness of different monitoring vectors in tracing problems and ensure that the monitoring process is both timely and complete.

[0054] Analyzing the abnormal tracing influence coefficient has the following advantages for selecting the best video monitoring vector to solve the problem of poor monitoring caused by chaotic shooting during the existing grouting progress monitoring: The specific method for obtaining the abnormal tracing influence coefficient is as follows: Improve the ability to capture abnormalities: The abnormal tracing impact coefficient can evaluate the effect of monitoring frequency on capturing abnormal situations, ensure that the shooting frequency and duration are high enough, avoid missing important instantaneous abnormal problems, such as blockage of the slurry hole or insufficient pressure, so as to timely discover and deal with potential risks in the construction process.

[0055] Improve the timeliness of monitoring: By analyzing the abnormal tracing influence coefficient, the video shooting frequency can be optimized to ensure that once an abnormality occurs during the grouting process, the system can provide timely feedback to avoid the delayed response caused by low-frequency monitoring, and ensure the real-time and safety of the construction process.

[0056] Enhance the accuracy of problem tracing: When the surveillance video has sufficient time accuracy, the abnormal tracing impact coefficient can help accurately locate the time point and specific link of the problem, improve the accuracy of problem tracing, ensure the effectiveness of subsequent decision-making and problem solving, and reduce analysis errors caused by missing information.

[0057] Reduce risk hazards: By reasonably adjusting the monitoring frequency and reducing the probability of missing key issues, the abnormal tracing impact coefficient can maximize the prevention of construction quality hazards and provide support for the rapid response mechanism to ensure that construction safety and quality meet standards.

[0058] Optimize data redundancy and burden: By analyzing the impact coefficient of abnormal tracing, we can find the balance point of too high or too low monitoring frequency, avoid data redundancy caused by frequent shooting, and prevent the problem of ineffective tracing due to too low monitoring frequency. Ultimately, we can optimize data load and redundancy and improve monitoring efficiency.

[0059] Improve the reliability and traceability of monitoring: The abnormal tracing impact coefficient helps to design a more reasonable video monitoring vector, so that video records can be better used for problem tracing, enhance the reliability of monitoring records, ensure that each link can be clearly tracked when problems occur, and provide comprehensive and accurate grouting process monitoring.

[0060] In summary, the abnormal tracing impact coefficient improves the ability to capture abnormal problems, the timeliness of monitoring feedback, and the accuracy of problem tracing by optimizing the monitoring frequency and video duration. It can effectively solve the problem of poor monitoring caused by chaotic shooting in traditional grouting progress monitoring, and ensure the controllability of the construction process and the safety of project quality.

[0061] The specific method for obtaining the abnormal tracing influence coefficient is as follows: Collect abnormal location data, which includes various abnormal feedback and location accuracy; Classify the collected exception feedback by type and assign exception weights to different types of exceptions; Calculate the abnormal impact coefficient according to the type and weight of abnormal feedback; Obtain the abnormal feedback accuracy and abnormal range affected by the project abnormality and the duration of the video interval occupied, and calculate the abnormal feedback effectiveness coefficient; The type of grouting machine progress in the monitoring process is obtained. The types of grouting machine progress in the monitoring process include grouting start-up stage, initial grouting stage, stable grouting stage, final pressure stage and solidification stage. The stage score is set for the type of grouting machine progress according to the proportion of abnormal feedback accuracy, and the total stage score remains unchanged; The abnormality tracing impact coefficient is calculated by combining the abnormality feedback effectiveness coefficient, abnormality impact coefficient and stage score.

[0062] The specific calculation formula of the abnormal influence coefficient is as follows: , The specific calculation formula of the abnormal feedback effectiveness coefficient is as follows: , The specific calculation formula of the abnormal tracing impact coefficient is as follows: , In the formula, is the abnormal influence coefficient, is the weight of the i-th type of anomaly, is the number of times the i-th abnormality occurs, is the number of times the exception type occurs, V is the total number of exceptions, is the effective coefficient of abnormal feedback, is the number of stages affected, is the abnormal feedback accuracy, is the interval time from the abnormal stage to the project monitoring video, P is the stage score, is the abnormal tracing impact coefficient.

[0063] The system load impact coefficient is an important indicator for evaluating resource usage during video monitoring, reflecting the impact of high-frequency video monitoring on system storage, bandwidth transmission, and server processing capabilities. Frequent video shooting generates a large amount of data, occupies a large amount of storage space, increases the transmission burden, and places higher requirements on server computing and processing capabilities, which may lead to problems such as slow system processing speed and network congestion. Excessive load not only increases system maintenance and operating costs, but may also affect the real-time and stability of monitoring. By analyzing the system load impact coefficient, the rationality of video monitoring frequency and duration can be effectively evaluated, and the monitoring vector with the least impact on system resources while ensuring monitoring results can be found, thereby optimizing monitoring efficiency and system performance.

[0064] Analyzing the system load influence coefficient has the following advantages for selecting the best video monitoring vector to solve the problem of poor monitoring caused by chaotic shooting during existing grouting progress monitoring: Optimize system resource allocation: The system load impact coefficient can effectively evaluate the relationship between monitoring frequency and system resource usage, avoid problems such as waste of storage resources and network congestion caused by frequent shooting, and ensure stable operation of the system under normal load by reasonably balancing shooting frequency and duration, thereby improving data processing efficiency.

[0065] Reduce transmission and storage pressure: Although high-frequency monitoring provides more data, it also increases the pressure on transmission bandwidth and storage. By analyzing the system load impact coefficient, it is possible to reduce unnecessary data volume while ensuring key data collection, reduce storage and transmission costs, optimize system operation efficiency, and avoid network freezes or video upload delays.

[0066] Improve the real-time and reliability of monitoring: Reasonable system load management helps to improve data processing speed, ensure that the real-time video monitoring system can quickly respond to changes in the grouting process, avoid monitoring delays and blind spots caused by system overload, and ensure real-time monitoring of the grouting progress.

[0067] Avoid the risk of system overload: Frequent generation and transmission of surveillance videos may cause system overload. Analysis of the system load impact coefficient can help design a more reasonable monitoring frequency, reduce the risk of system failure or crash, ensure the reliability and stability of the monitoring system, and avoid monitoring failure at critical moments due to system failure.

[0068] Improve the utilization of video data: By analyzing the system load impact coefficient, the most effective monitoring frequency and duration can be screened out to ensure that each video can provide valuable information, reduce redundant data caused by excessive shooting frequency, optimize the utilization of video data, and reduce the burden of subsequent data processing and analysis.

[0069] Balance monitoring effect and system cost: The system load impact coefficient helps to weigh the relationship between monitoring accuracy and system cost. By screening out video monitoring vectors that can meet monitoring needs without excessively occupying resources, it solves the problems of resource waste and monitoring failure caused by chaotic shooting in traditional grouting monitoring, and improves the overall efficiency and economy of the system.

[0070] In summary, the system load impact coefficient can effectively screen out the best video monitoring vector that can both ensure monitoring quality and reduce system pressure by optimizing resource utilization, reducing redundant data and preventing system overload, solve problems such as shooting confusion and system overload in grouting progress monitoring, and improve monitoring efficiency and reliability.

[0071] The specific method for obtaining the system load influence coefficient is as follows: Real-time monitoring of the computing resource consumption rate and video transmission bit rate corresponding to the time interval E within the P time when monitoring the grouting progress, and numbering the computing resource consumption rate and video transmission bit rate; The system load standard deviation and system load average are calculated by calculating the resource consumption rate and video transmission bit rate corresponding to the time interval E within the P time when monitoring the grouting progress; Calculate the coefficient of variation of system load based on the standard deviation of system load and the average value of system load; The system load impact coefficient is calculated based on the system load variation coefficient.

[0072] The specific calculation formula of the system load standard deviation is as follows: , The specific calculation formula of the system load average value is as follows: , The specific calculation formula of the system load influence coefficient is as follows: , In the formula, is the system load standard deviation, is the average system load, The total number of numbers for calculating resource consumption rate and video transmission bit rate, The number for calculating resource consumption rate and video transmission bit rate, To calculate the resource consumption rate, is the video transmission bit rate, is the system load influence coefficient.

[0073] This embodiment proposes a solution for optimizing grouting progress monitoring by using a monitoring vector method based on random number generation, randomly combining the video monitoring frequency and duration and evaluating its monitoring effect. Its technical effects include effectively improving the monitoring accuracy and system resource utilization by calculating the video review effectiveness coefficient, the abnormal tracing influence coefficient and the system load influence coefficient. First, the video review effectiveness coefficient analyzes the effective information entropy in the video to screen out monitoring clips containing important information, thereby avoiding data redundancy and invalid information processing, and improving monitoring efficiency and information value. Secondly, the abnormal tracing influence coefficient can ensure that key abnormal events are captured and traced in time during the grouting process, enhancing the timeliness of monitoring and the accuracy of problem location. Finally, the system load influence coefficient helps to evaluate the balance between monitoring frequency and system resources, and avoid system load problems caused by excessively high frequency shooting.

[0074] Embodiment 2, S3, constructs a progress monitoring effect evaluation model based on machine learning according to monitoring redundant data and monitoring load data.

[0075] The progress monitoring effect evaluation model is constructed based on machine learning according to the monitoring redundant data and the monitoring load data, specifically: The obtained video review effectiveness coefficient, abnormal tracing influence coefficient and system load influence coefficient are used to construct a progress monitoring effect evaluation model to generate a progress monitoring effect evaluation coefficient; The specific calculation formula of the progress monitoring effect evaluation coefficient is as follows: , In the formula, is the progress monitoring effect evaluation coefficient, The preset proportional coefficient for the video review effectiveness coefficient. is the preset proportional coefficient of the abnormal tracing impact coefficient, is the preset proportional coefficient of the system load influence coefficient, is the video review effectiveness coefficient, is the abnormal tracing influence coefficient, is the system load influence coefficient.

[0076] S4, according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, a video monitoring vector effect display model is constructed based on the three-dimensional model, and data analysis is performed on the video monitoring vector effect display model to obtain the optimal video monitoring vector, which is used to control the monitoring process of the grouting progress.

[0077] According to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, a video monitoring vector effect display model is constructed based on the three-dimensional model, specifically: The video monitoring frequency and video monitoring duration of each video monitoring vector are marked as the x-axis and y-axis on the rectangular coordinate system respectively, the marked rectangular coordinate system is used as the base, and the output of the progress monitoring effect evaluation model corresponding to each video monitoring vector mark is used as the z-axis of the video monitoring vector effect display model; Each evaluation vector is used as a data point to update the label video monitoring vector effect display model; Connect the various data points of the video monitoring vector effect display model to draw a three-dimensional effect-video monitoring vector curve.

[0078] The video monitoring vector effect display model is analyzed for data to obtain the best video monitoring vector, which is used to control the monitoring process of the grouting progress, specifically: Establish corresponding mathematical functions according to the effect-video monitoring vector curve; Obtain each peak value in the effect-video monitoring vector curve, and calculate the secondary derivative of the corresponding peak value in the mathematical function. The video monitoring vector corresponding to the peak value whose secondary derivative is closest to zero is taken as the optimal video monitoring vector, and is used to control the monitoring process of the grouting progress.

[0079] This embodiment has obvious technical advantages and effects by building a progress monitoring effect evaluation model based on monitoring redundant data and monitoring load data combined with machine learning. First, by introducing the video review effectiveness coefficient, abnormal tracing influence coefficient and system load influence coefficient, the progress monitoring effect can be evaluated more comprehensively and accurately. Secondly, the progress monitoring effect evaluation coefficient is generated through a formulated evaluation model, which ensures the accuracy and objectivity of the evaluation process. In addition, based on the display method of the three-dimensional model, the video monitoring vector is combined with the monitoring effect evaluation, and further through the optimization analysis of mathematical functions, the optimal video monitoring vector can be accurately identified and selected. This method not only improves the accuracy of grouting progress monitoring, but also effectively reduces data redundancy in monitoring, optimizes monitoring efficiency, and achieves more efficient process control.

[0080] Embodiment 3, Figure 2 A system for an intelligent grouting progress monitoring and control method includes a monitoring vector generation module, a data analysis module, a data evaluation module and a monitoring vector screening module, and there are connections between the modules; A monitoring vector generation module, used to obtain a preset video monitoring frequency range and a video monitoring duration range, and obtain a number of random video monitoring vectors based on a random number generation method, wherein the video monitoring vectors include a video monitoring frequency and a video monitoring duration; A data analysis module is used to analyze the monitoring redundancy data and monitoring load data of grouting progress monitoring under different video monitoring vectors; A data evaluation module is used to build a progress monitoring effect evaluation model based on machine learning according to monitoring redundancy data and monitoring load data; The monitoring vector screening module is used to build a video monitoring vector effect display model based on the three-dimensional model according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, and perform data analysis on the video monitoring vector effect display model to obtain the optimal video monitoring vector, which is used to control the monitoring process of the grouting progress.

[0081] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0082] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0083] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0085] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0086] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent grouting progress monitoring and control method, characterized in that: The steps include: Obtaining a preset video monitoring frequency range and a video monitoring duration range, and obtaining a number of random video monitoring vectors based on a random number generation method, wherein the video monitoring vectors include a video monitoring frequency and a video monitoring duration; Analyze the monitoring redundancy data and monitoring load data of grouting progress monitoring under different video monitoring vectors; Construct a progress monitoring effect evaluation model based on machine learning according to monitoring redundancy data and monitoring load data; According to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, a video monitoring vector effect display model is constructed based on the three-dimensional model. Data analysis is performed on the video monitoring vector effect display model to obtain the optimal video monitoring vector, which is used to control the grouting progress monitoring process.

2. According to claim 1, a smart grouting progress monitoring and control method is characterized in that: The method of obtaining a plurality of random video monitoring vectors based on a random number generation method is specifically as follows: Get the preset video monitoring frequency range and video monitoring duration range; A random number generation library based on computer language randomly extracts a number of video monitoring frequency values ​​from a set frequency range; And randomly generate several video monitoring duration values ​​from the set duration range; Randomly combine the generated random video monitoring frequency value and video monitoring duration value into a video monitoring vector; The video monitoring vectors are filtered and stored through the set data structure. Each time a new video monitoring vector is formed, it is checked whether the video monitoring vector already exists in the set. If so, it is regenerated until a unique video monitoring vector is formed.

3. According to claim 2, an intelligent grouting progress monitoring and control method is characterized in that: The monitoring redundant data includes the video review effectiveness coefficient and the abnormal tracing influence coefficient; the specific method for obtaining the video review effectiveness coefficient is as follows: Obtain video data for video review, including standard reference videos and historical review videos, and classify the historical review videos into stage types according to the standard reference videos; Calculate the effective proportion of each video data category in the video data; Calculate the video effective information entropy of the video data according to the effective proportion; The video effective information entropy is normalized into a video review effectiveness coefficient.

4. The intelligent grouting progress monitoring and control method according to claim 3 is characterized in that: The specific method for obtaining the abnormal tracing influence coefficient is as follows: Collect abnormal location data, which includes various abnormal feedback and location accuracy; Classify the collected exception feedback by type and assign exception weights to different types of exceptions; Calculate the abnormal impact coefficient according to the type and weight of abnormal feedback; Obtain the abnormal feedback accuracy and abnormal range affected by the project abnormality and the duration of the video interval occupied, and calculate the abnormal feedback effectiveness coefficient; The type of grouting machine progress in the monitoring process is obtained. The types of grouting machine progress in the monitoring process include grouting start-up stage, initial grouting stage, stable grouting stage, final pressure stage and solidification stage. The stage score is set for the type of grouting machine progress according to the proportion of abnormal feedback accuracy, and the total stage score remains unchanged; The abnormality tracing impact coefficient is calculated by combining the abnormality feedback effectiveness coefficient, abnormality impact coefficient and stage score.

5. The intelligent grouting progress monitoring and control method according to claim 4 is characterized in that: The monitoring load data includes a system load influence coefficient, and a specific method for obtaining the system load influence coefficient is as follows: Real-time monitoring of the computing resource consumption rate and video transmission bit rate corresponding to the time interval E within the P time when monitoring the grouting progress, and numbering the computing resource consumption rate and video transmission bit rate; The system load standard deviation and system load average are calculated by calculating the resource consumption rate and video transmission bit rate corresponding to the time interval E within the P time when monitoring the grouting progress; Calculate the coefficient of variation of system load based on the standard deviation of system load and the average value of system load; The system load impact coefficient is calculated based on the system load variation coefficient.

6. The intelligent grouting progress monitoring and control method according to claim 5 is characterized in that: According to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, a video monitoring vector effect display model is constructed based on the three-dimensional model, specifically: The video monitoring frequency and video monitoring duration of each video monitoring vector are marked as the x-axis and y-axis on the rectangular coordinate system respectively, the marked rectangular coordinate system is used as the base, and the output of the progress monitoring effect evaluation model corresponding to each video monitoring vector mark is used as the z-axis of the video monitoring vector effect display model; Each evaluation vector is used as a data point to update the label video monitoring vector effect display model; Connect the various data points of the video monitoring vector effect display model to draw a three-dimensional effect-video monitoring vector curve.

7. The intelligent grouting progress monitoring and control method according to claim 6 is characterized in that: The video monitoring vector effect display model is analyzed for data to obtain the best video monitoring vector, which is used to control the monitoring process of the grouting progress, specifically: Establish corresponding mathematical functions according to the effect-video monitoring vector curve; Obtain each peak value in the effect-video monitoring vector curve, and calculate the secondary derivative of the corresponding peak value in the mathematical function. The video monitoring vector corresponding to the peak value whose secondary derivative is closest to zero is taken as the optimal video monitoring vector, and is used to control the monitoring process of the grouting progress.

8. The intelligent grouting progress monitoring and control method according to claim 7 is characterized in that: The calculation formula of the effective ratio is as follows: , The specific calculation formula of the effective information entropy of the video is as follows: , The specific calculation formula of the video review effectiveness coefficient is: , In the formula, is the effective proportion, is the number of historical videos with the value X in the video data, N is the total number of historical videos, is the possible value of the video data, is the effective information entropy of the video data, The validity coefficient of the video review.

9. The intelligent grouting progress monitoring and control method according to claim 8 is characterized in that: The specific calculation formula of the abnormal influence coefficient is as follows: , The specific calculation formula of the abnormal feedback effectiveness coefficient is as follows: , The specific calculation formula of the abnormal tracing impact coefficient is as follows: , In the formula, is the abnormal influence coefficient, is the weight of the i-th type of anomaly, is the number of times the i-th abnormality occurs, is the number of times the exception type occurs, V is the total number of exceptions, is the effective coefficient of abnormal feedback, is the number of stages affected, is the abnormal feedback accuracy, is the interval time from the abnormal stage to the project monitoring video, P is the stage score, is the abnormal tracing impact coefficient.

10. A system using the intelligent grouting progress monitoring and control method according to any one of claims 1 to 9, characterized in that: It includes a monitoring vector generation module, a data analysis module, a data evaluation module and a monitoring vector screening module, and there are connections between the modules; A monitoring vector generation module, used to obtain a preset video monitoring frequency range and a video monitoring duration range, and obtain a number of random video monitoring vectors based on a random number generation method, wherein the video monitoring vectors include a video monitoring frequency and a video monitoring duration; A data analysis module is used to analyze the monitoring redundancy data and monitoring load data of grouting progress monitoring under different video monitoring vectors; A data evaluation module is used to build a progress monitoring effect evaluation model based on machine learning according to monitoring redundancy data and monitoring load data; The monitoring vector screening module is used to build a video monitoring vector effect display model based on the three-dimensional model according to the output of the progress monitoring effect evaluation model and the corresponding video monitoring vector, and perform data analysis on the video monitoring vector effect display model to obtain the optimal video monitoring vector, which is used to control the monitoring process of the grouting progress.

Images