A tunnel surrounding rock intelligent grading and risk early warning three-dimensional visualization platform

Abstract

This invention provides a 3D visualization platform for intelligent grading and risk early warning of tunnel surrounding rock, relating to the field of tunnel engineering technology. It includes the following functional modules: a data integrity verification module (calculating a data integrity index to assess the completeness of geological sketch feedback data in each tunneling cycle); a feedback timeliness management module (calculating a feedback timeliness index to assess the timeliness of on-site data feedback); a prediction deviation verification module (calculating a prediction deviation index to quantify the degree of deviation between system prediction results and on-site measured results); and a closed-loop accountability and handling module (calculating an accountability execution index to comprehensively determine the management responsibility attribution and handling level for the current tunneling cycle). This invention achieves closed-loop management of data acquisition, system evolution, early warning correction, and responsibility tracing, promoting the upgrade of tunnel construction 3D visualization platforms from information display to intelligent control.

Description

Technical Field

[0001] This invention relates to the field of tunnel engineering technology, specifically to a three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock. Background Technology

[0002] The Intelligent Rock Mass Grading and Risk Early Warning 3D Visualization Platform for Tunnels is a comprehensive digital management system for tunnel engineering, integrating intelligent rock mass perception, automatic data analysis, dynamic risk early warning, and 3D visual decision-making. It aims to solve the problems of traditional tunnel construction, such as reliance on manual rock mass grading, strong subjectivity, and delayed risk early warning. However, current platform systems cannot achieve continuous dynamic evolution and self-optimization based on measured data, and the platform outputs cannot be effectively linked to construction management behaviors. Therefore, a method can be constructed to continuously improve the accuracy of intelligent grading and risk early warning, while deeply binding the platform outputs with construction management behaviors, effectively enhancing the level of intelligent control in tunnel construction.

[0003] In the prior art, patent publication number CN119962054A discloses a method and system for intelligent classification of tunnel surrounding rock based on engineering information modeling and virtual simulation technology. This technology includes the following steps: Step S1: Environmental data collection and establishment of a geotechnical engineering BIM model; Step S2: Intelligent classification and simulation optimization of tunnel surrounding rock; Step S3: Construction plan output and dynamic management of on-site implementation; Step S4: Visual monitoring and feedback loop; Step S5: Data analysis and predictive early warning. This solution, through the integration of BIM and virtual simulation technologies and the application of intelligent classification algorithms, can quickly acquire and process large amounts of surrounding rock data in a short time, thus greatly shortening the classification time. Furthermore, based on objective data collection and scientific algorithm analysis, it can more accurately assess the properties and state of the surrounding rock, providing a reliable classification basis for tunnel engineering.

[0004] However, in the aforementioned existing technologies, the completeness and timeliness of on-site feedback data lack systematic quantitative control, which may affect the effective support of measured data for the closed-loop verification of the intelligent grading and early warning system; the intelligent grading and early warning system can be further improved in terms of automatic updates and continuous evolution based on measured deviations; the post-event verification and differentiated handling mechanism for false alarms and missed alarms needs to be established to improve the closed-loop correction capability of early warning accuracy; the quantitative attribution mechanism for management responsibility is not yet clear, making it difficult to effectively distinguish between system prediction deviations and personnel operation deviations; the degree of integration between the output results of the 3D visualization platform and management behaviors such as construction approval, data submission, and responsibility tracing can still be strengthened to further reduce the disconnect between information display and actual control.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock, thereby addressing the problems mentioned in the background section. This invention ensures effective feedback of measured data through quantitative threshold control, driving the system to continuously evolve with tunneling progress; it achieves early warning correction and precise accountability through differentiated penalties and attribution judgments; and it upgrades the three-dimensional visualization platform from passive display to proactive control by deeply integrating platform output with construction approval, effectively improving the level of intelligent management in tunnel construction.

[0007] To achieve the above objectives, the present invention provides the following technical solution: A three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock includes the following functional modules: Data integrity verification module: Obtains the actual number of standardized feedback forms submitted by on-site personnel and the total number that should be submitted, as well as the number of valid forms after system verification. It is used to calculate the data integrity index, which is used to evaluate the integrity of geological sketch feedback data in each tunneling cycle. When it is determined that the data integrity does not meet the construction permit requirements, the construction approval process for the next tunneling cycle is frozen. Feedback Timeliness Management Module: Obtains the excavation completion timestamp and the submission timestamp of the standardized feedback form submitted by on-site personnel for each tunneling cycle, as well as the system's preset allowable delay time, to calculate the feedback timeliness index. The feedback timeliness index is used to evaluate the timeliness of on-site data feedback. When it is determined that the feedback timeliness does not meet the update timeliness requirements of the intelligent grading system, the feedback data of the tunneling cycle will not be included in the system analysis and the responsible person must submit a written explanation. Prediction Deviation Verification Module: Acquires the predicted surrounding rock grade output by the intelligent grading system and the actual measured surrounding rock grade on site, and the predicted risk probability value output by the early warning system and the actual measured risk status on site, and uses it to calculate the prediction deviation index. The prediction deviation index is used to quantify the degree of deviation between the system prediction result and the actual measured result on site. When it is determined that the prediction deviation exceeds the allowable range, a system failure alarm is triggered and the tunneling cycle data is forcibly included in the system training set. Closed-loop accountability and handling module: Acquires data integrity index, feedback timeliness index, prediction deviation index, and the historical cumulative number of violations by the responsible person to calculate the accountability execution index. The accountability execution index is used to comprehensively determine the management responsibility attribution and handling level of the current tunneling cycle, and to implement step-by-step handling measures according to the numerical range in which it is located. After the handling is completed, the next tunneling cycle begins.

[0008] Furthermore, the data integrity index is calculated using the following formula: ; in: For data completeness index; This represents the actual number of submissions. The total number to be submitted; This represents the number of valid forms. For submission rate; For efficiency; The weighting coefficient for the submission rate. The weighting coefficients are for efficiency.

[0009] Furthermore, the data integrity index takes a value between [0,1]. After calculating the data integrity index, it is compared with the system's preset integrity threshold to determine whether the integrity of the current tunneling cycle feedback data meets the construction permit requirements. ; in, The system's preset integrity threshold, ; when When the data integrity of the tunneling cycle is deemed satisfactory, the system allows entry into the next module; when If the system determines that the data integrity of the tunneling cycle does not meet the construction permit requirements, it freezes the construction approval process for the next tunneling cycle and continues to send reminder notices until the on-site personnel complete the data and submit a valid feedback form.

[0010] Furthermore, the timely feedback index is calculated using the following formula: ; in: To provide timely feedback index; Submission time; Allowed delay time; This refers to the time when the excavation was completed; This is the actual delay time; The attenuation coefficient is an adjustment parameter that controls the rate of exponential decline.

[0011] Furthermore, the feedback timeliness index ranges from (0,1). After calculating the feedback timeliness index, it is compared with the system's preset timeliness threshold to determine the timeliness qualification of the current tunneling cycle feedback data. ; in, The time threshold preset by the system, ; when When the feedback data of the tunneling cycle is deemed to be within acceptable timeframes, the system allows entry into the next module; when If the feedback data of the current tunneling cycle is deemed untimely, the data will not be included in subsequent system analysis. The system will automatically record the violation and notify the responsible person to submit a written explanation.

[0012] Furthermore, the prediction deviation index is calculated using the following formula: ; in: For prediction deviation index; To predict the surrounding rock grade; This is based on the measured surrounding rock grade; To predict the probability value of risk; This is a test of the actual risk status; This is a penalty item for risk deviation; This is a graded deviation term; This is a risk deviation item; These are the weighting coefficients for the graded deviation term; This is the weighting coefficient for the risk deviation term.

[0013] Furthermore, after calculating the prediction deviation index, the prediction deviation index is compared with the system's preset allowable deviation threshold to determine whether the system prediction deviation of the current tunneling cycle is within an acceptable range. ; in, The system's preset allowable deviation threshold, ; when When the system prediction deviation of the current tunneling cycle is determined to be within the allowable range, the system is operating normally; when If the system prediction deviation of the current tunneling cycle exceeds the allowable range, the system will trigger a failure alarm and forcibly include the measured data of the current tunneling cycle into the system training set.

[0014] Furthermore, the accountability enforcement index is calculated using the following formula: ; in: To ensure accountability and implementation index; The cumulative number of historical violations by the responsible person; Responsibility for missing data; For feedback on delayed responsibility items; These are the weighting coefficients for data missing responsibility, feedback delay responsibility, prediction bias index, and the historical cumulative number of violations by the responsible person. .

[0015] Furthermore, after calculating the accountability enforcement index, tiered measures are implemented based on the numerical range of the accountability enforcement index: when If the current tunneling cycle is determined to be operating normally, only a record is made, and no further action is required; when When a minor anomaly is detected, the system automatically sends a notification to the responsible person and their supervisor; when When the condition is determined to be moderately abnormal, the responsible person must submit a written rectification report; when If the situation is deemed a serious anomaly, the intelligent system's command output privileges will be suspended, the decision will be reverted to manual review, and the responsible person's performance bonus will be reduced. The system's preset processing thresholds meet the requirements. After the treatment is completed, the next tunneling cycle begins.

[0016] Furthermore, when the accountability execution index is at a level of mild abnormality or higher, the system initiates attribution determination: when and The sum of the two items accounts for The proportion of the total value is greater than When the primary issue was determined to be related to the data submission process by on-site personnel, the rectification target was the on-site personnel; Single item The proportion of the total value is greater than When the main problem is determined to be the prediction accuracy of the intelligent grading system or early warning system, the rectification target is the system itself, triggering a forced update of the system's training set; when Single item The proportion of the total value is greater than When the primary problem is determined to be repeated violations by the responsible party, the severity of the punishment for that party will be increased; among other things, The system's preset attribution thresholds are all greater than 0 and less than 1.

[0017] Compared with existing technologies, the beneficial effects of this invention are as follows: by controlling the quantitative threshold of the integrity and timeliness of feedback data, the effective transmission of measured data is ensured; by the forced update mechanism triggered by prediction deviation, the system is driven to continuously evolve with tunneling; by differentiated penalties for false alarms and missed alarms and post-event verification, the accuracy of early warnings is corrected in a closed loop; by attribution judgment of the accountability execution index, differentiated accountability for people and the system is achieved; and by deeply binding the platform output with construction approval, the 3D visualization platform is upgraded from passive display to active control, effectively improving the level of intelligent management of tunnel construction. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the principle of a three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock according to the present invention; Figure 2 This is a schematic diagram of the operation process of a three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock according to the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0020] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0021] Example: Please see Figures 1-2 The present invention provides the following technical solutions: A three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock includes the following functional modules: The data integrity verification module: This module obtains the total number of standardized feedback forms that should be submitted during the current tunneling cycle. These standardized feedback forms include at least three mandatory fields: face lithology photographs, joint development records, and seepage status records. It also obtains the total number of feedback forms actually submitted by on-site personnel after the current tunneling cycle is completed. This actual submission count is automatically generated by the system backend based on uploaded records. Finally, it obtains the number of valid forms after system verification. This verification includes image quality verification of photograph clarity, content verification of the completeness of mandatory fields, and threshold verification of the reasonableness of the entered data. Only forms that pass all three verifications are considered valid. These three data points are used to calculate the data integrity index.

[0022] The data completeness index is calculated using the following formula: ; in: For data completeness index; This represents the actual number of submissions. The total number to be submitted; This represents the number of valid forms. Submission rate reflects the completeness of the submitted feedback forms; To be efficient, it reflects the quality level of information in submitted forms; The weighting coefficient for the submission rate. The weighting coefficients are set in advance by the system according to the project management requirements, and are used to balance the contribution of the number and quality of submissions to the data integrity index.

[0023] After calculating the data integrity index, the data integrity index is compared with the system's preset integrity threshold to determine whether the integrity of the current tunneling cycle feedback data meets the construction permit requirements. The specific comparison method is as follows: ; in, The preset integrity threshold, .

[0024] when If the system determines that the data integrity of the current tunneling cycle is qualified and meets the construction permit requirements, the system will allow the system to proceed to the next module to execute the calculations of the feedback timeliness management module.

[0025] when If the system determines that the data integrity of the current tunneling cycle does not meet the requirements for a construction permit, it freezes the construction approval process for the next tunneling cycle and continuously sends reminders to on-site personnel until the on-site personnel complete and submit all feedback forms that have been verified as valid by the system, at which point the system will lift the freeze.

[0026] The data integrity index is used to screen feedback data that meets the required level of completeness for subsequent analysis, ensuring that every piece of feedback data participating in the system analysis is complete and intact. This avoids distortion of subsequent prediction and verification results due to missing data, thereby achieving quantitative control over the integrity of feedback data.

[0027] The feedback timeliness management module obtains the excavation completion timestamp of the current tunneling cycle. This timestamp is the moment when blasting and muck removal are completed and the tunnel face is fully exposed, recorded in the construction log or automatically generated by intelligent equipment. It also obtains the submission timestamp of standardized feedback forms submitted by on-site personnel. This timestamp is automatically recorded by the system when on-site personnel complete the form and upload it to the platform. Finally, it obtains the system-preset allowed delay time. This allowed delay time is the maximum duration allowed for on-site personnel to submit feedback forms, calculated from the excavation completion time, and is preset by the management system according to project management requirements. These three data points are used to calculate the feedback timeliness index.

[0028] The timely feedback index is calculated using the following formula. ; in: To provide timely feedback index; Submission time; Allowed delay time; This refers to the time when the excavation was completed; This represents the actual delay time, reflecting the response speed of on-site personnel from the completion of excavation to the submission of feedback; The attenuation coefficient is an adjustment parameter that controls the rate of exponential descent and is preset by the system. The larger the value, the faster the exponent decreases as the delay time increases.

[0029] After calculating the feedback timeliness index, the feedback timeliness index is compared with the system's preset timeliness threshold to determine the timeliness qualification of the current tunneling cycle feedback data. The specific comparison method is as follows: ; in, The time threshold preset by the system, .

[0030] when When the system determines that the feedback data of the current tunneling cycle is timely and meets the system update timeliness requirements, the system allows the system to proceed to the next module to execute the calculation of the prediction deviation verification module; when If the system determines that the feedback data of the current tunneling cycle is not timely enough and does not meet the system update timeliness requirements, the feedback data of this tunneling cycle will not be included in subsequent system analysis. The system will automatically record this violation and send a notification to the responsible person, requiring them to submit a written explanation explaining the reason for the delay.

[0031] Through the above comparison and judgment, the feedback timeliness index is used to screen timely and qualified feedback data to enter the subsequent analysis stage, ensuring that every piece of feedback data participating in the system analysis is submitted within the valid time window, avoiding the distortion of system analysis results due to data expiration, thereby realizing the quantitative control of the timeliness of feedback data.

[0032] Prediction Deviation Verification Module: This module acquires the predicted surrounding rock grade output by the intelligent grading system. The predicted surrounding rock grade is automatically determined and output by the intelligent grading system before the current tunneling cycle begins excavation, based on multi-source sensing data such as drilling parameters, face images, and 3D laser scanning. It is quantified into grades I to V, corresponding to values ​​1 to 5. It also acquires the actual surrounding rock grade measured on-site. The actual surrounding rock grade is the real surrounding rock grade determined by on-site geological engineers based on on-site observation and geological sketching of the excavation face after the current tunneling cycle is completed. This grade is also quantified into grades I to V, corresponding to values ​​1 to 5.

[0033] The system acquires the predicted risk probability value output by the early warning system. This predicted risk probability value is automatically calculated and output by the early warning system based on the surrounding rock classification results and real-time monitoring data before the current tunneling cycle begins excavation, and its value ranges from 0 to 1. It also acquires the actual on-site measured risk status. This actual on-site measured risk status is the actual occurrence of a hazard confirmed by the construction safety record after the current tunneling cycle's excavation and support are completed; 0 represents no hazard occurring, and 1 represents a hazard occurring. These four data points are used to calculate the prediction deviation index.

[0034] The prediction deviation index is calculated using the following formula: ; in: For prediction deviation index; To predict the surrounding rock grade; This is based on the measured surrounding rock grade; To predict the probability value of risk; This is a test of the actual risk status; This is a penalty item for risk deviation; This is the graded deviation term. This term is normalized by dividing the absolute value of the deviation of the surrounding rock grade by the maximum possible difference of the surrounding rock grade, which is 4. The maximum difference of the surrounding rock grade is the difference between grade I and grade V, which is 5-1=4. Dividing by 4 normalizes this term to between 0 and 1. This is the risk deviation term, reflecting the absolute deviation between the predicted risk probability and the actual risk status. These are the weighting coefficients for the graded deviation term; The risk deviation item weighting coefficient; both are preset by the system according to engineering management requirements, and are used to balance the contribution of classification deviation and risk deviation to the prediction deviation index.

[0035] When the predicted risk probability value is lower than the system's preset low-risk threshold, but the actual measured risk status is that a hazard has occurred, it is determined to be a missed report, and the system assigns a first penalty value. When the predicted risk probability value is higher than the system's preset high-risk threshold, but the actual measured risk status is that a hazard has not occurred, it is determined to be a false alarm, and the system assigns a second penalty value. In other cases, if there is no significant deviation between the predicted risk probability value and the actual measured risk status, the system assigns a value of zero. The first penalty value is greater than the second penalty value, and the penalty for a missed report is higher than the penalty for a false alarm, reflecting the management logic that the consequences of a missed disaster report are more severe.

[0036] Both the first and second penalty values ​​are preset by the system according to engineering management requirements, and the first penalty value must be greater than the second penalty value. The reason for setting the penalty for missed reporting higher than that for false reporting is that: a missed report means the system failed to identify an actual disaster risk, and the construction team excavated without warning, directly exposing personnel and equipment to danger with serious consequences; a false report means the system issued a false alarm, which, while affecting construction efficiency and system reliability, does not directly endanger safety. The specific penalty value is preset by the system based on engineering experience and expert review, and remains fixed during construction.

[0037] After calculating the prediction deviation index, the prediction deviation index is compared with the system's preset allowable deviation threshold to determine whether the system prediction deviation of the current tunneling cycle is within an acceptable range. The specific comparison method is as follows: ; in, The system's preset allowable deviation threshold, .

[0038] when If the system prediction deviation of the current tunneling cycle is determined to be within the allowable range, and the deviation between the prediction results of the intelligent grading system and the early warning system and the actual on-site measurement results is at an acceptable level, the system is operating normally and no additional handling measures are required.

[0039] when If the system prediction deviation for the current tunneling cycle exceeds the allowable range, indicating that the prediction accuracy of the intelligent grading system or early warning system can no longer meet the construction requirements, the system automatically triggers a failure alarm and forcibly incorporates the measured surrounding rock grade and measured risk status of the current tunneling cycle into the system training set. This is used to drive the parameter correction and model update of the intelligent grading system and early warning system. The system training set consists of the measured surrounding rock grade and measured risk status of all tunneling cycles completed in the current project, and is used to support the parameter correction and update of the intelligent grading system and early warning system.

[0040] Through the above comparison and judgment, the prediction deviation index is used to quantify the degree of deviation between the system prediction results and the actual on-site measurement results. When the deviation exceeds the allowable range, the system self-correction mechanism is triggered to ensure that the prediction accuracy of the intelligent grading system and the early warning system is continuously optimized in the construction process, thereby realizing closed-loop control of the system prediction accuracy.

[0041] The closed-loop accountability and handling module acquires the following: a data integrity index, reflecting the completeness of feedback data in the current tunneling cycle; a feedback timeliness index, reflecting the timeliness of feedback data in the current tunneling cycle; a prediction deviation index, reflecting the degree of deviation between the system's prediction results and the actual on-site measurement results in the current tunneling cycle; and the historical cumulative number of violations by the responsible person, automatically generated by the system platform, with the statistical range being the total number of violations recorded against the same responsible person within a preset number of consecutive tunneling cycles prior to the current tunneling cycle. These four data points are used to calculate the accountability execution index.

[0042] The accountability enforcement index is calculated using the following formula: ; in: To ensure accountability and implementation index; The cumulative number of historical violations by the responsible person; This is a data incompleteness liability item used to quantify the degree of responsibility arising from on-site personnel failing to fulfill their data submission obligations. This is based on the data integrity index. Reflecting the completeness of the feedback data, A higher value indicates more complete data. The lower the value, the less responsibility there is for missing data; conversely, The lower the value, the more severe the data missing. The higher the value, the greater the responsibility due to missing data; This feedback delay liability item quantifies the degree of responsibility incurred by on-site personnel for failing to fulfill their data submission obligations within the permitted timeframe. This is due to the timeliness index of the feedback. Reflecting the timeliness of feedback data, A higher value indicates more timely feedback. The lower the value, the less responsibility is due to delayed feedback; conversely, The lower the value, the more severe the feedback delay. The higher the value, the greater the responsibility due to delayed feedback; These are the weighting coefficients for data missing responsibility, feedback delay responsibility, prediction bias index, and the historical cumulative number of violations by the responsible person. .

[0043] After calculating the accountability enforcement index, tiered measures are implemented based on the numerical range of the accountability enforcement index. when If the current tunneling cycle is determined to be operating normally, it indicates that the data integrity, feedback timeliness, prediction accuracy, and historical compliance are all at an acceptable level. The system only records the data for filing and no further action is required.

[0044] when If a minor anomaly is detected in the current tunneling cycle, the system will automatically send a reminder notification to the person in charge and their superiors, prompting them to pay attention to any deviations in data submission or system predictions during the current tunneling cycle.

[0045] when If a moderate anomaly is determined in the current tunneling cycle, the person in charge must submit a written rectification report within the specified period, detailing the cause of the problem and the proposed improvement measures.

[0046] when If a serious anomaly is detected in the current tunneling cycle, the system suspends the command output permissions of the intelligent grading system and the early warning system, reverts construction decisions to manual execution, and deducts performance bonuses from the responsible personnel. The system's preset processing thresholds meet the requirements. .

[0047] After the problem is resolved, the system enters the next tunneling cycle and re-executes the calculations and judgments of the four modules to achieve continuous operation of closed-loop management in the time dimension.

[0048] When the accountability enforcement index is at a level of mild abnormality or above, that is... When this happens, the system automatically initiates attribution determination to accurately pinpoint the primary source of responsibility for the anomaly.

[0049] The attribution determination is performed according to the following rules: when and The sum of the two items accounts for a proportion of the total value of the accountability execution index that exceeds the first attribution threshold preset by the system. At that time, it was determined that the main problem in the current tunneling cycle was related to the data submission process of the on-site personnel, and the on-site personnel were the target of rectification.

[0050] when The proportion of a single item in the total accountability execution index exceeds the second attribution threshold preset by the system. If the main problem in the current tunneling cycle is determined to be the prediction accuracy of the intelligent grading system or the early warning system, the rectification target is the system itself, triggering a forced update of the system training set.

[0051] when The proportion of a single item in the total accountability execution index exceeds the third attribution threshold preset by the system. At that time, it was determined that the main problem in the current tunneling cycle was due to repeated violations by the responsible person, and the level of punishment was increased by one level based on the measures already taken against that person. The attribution thresholds preset for the system are all greater than 0 and less than 1. Through the above attribution logic, the accountability execution index can achieve differentiated closed-loop management of tracing individual problems back to individuals and system problems back to the system, ensuring that the direction of rectification is accurate and traceable.

[0052] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0053] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0054] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0055] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock, characterized in that, Includes the following functional modules: Data integrity verification module: Obtains the actual number of standardized feedback forms submitted by on-site personnel and the total number that should be submitted, as well as the number of valid forms after system verification. It is used to calculate the data integrity index, which is used to evaluate the integrity of geological sketch feedback data in each tunneling cycle. When it is determined that the data integrity does not meet the construction permit requirements, the construction approval process for the next tunneling cycle is frozen. Feedback Timeliness Management Module: Obtains the excavation completion timestamp and the submission timestamp of the standardized feedback form submitted by on-site personnel for each tunneling cycle, as well as the system's preset allowable delay time, to calculate the feedback timeliness index. The feedback timeliness index is used to evaluate the timeliness of on-site data feedback. When it is determined that the feedback timeliness does not meet the update timeliness requirements of the intelligent grading system, the feedback data of the tunneling cycle will not be included in the system analysis and the responsible person must submit a written explanation. Prediction Deviation Verification Module: Acquires the predicted surrounding rock grade output by the intelligent grading system and the actual measured surrounding rock grade on site, and the predicted risk probability value output by the early warning system and the actual measured risk status on site, and uses it to calculate the prediction deviation index. The prediction deviation index is used to quantify the degree of deviation between the system prediction result and the actual measured result on site. When it is determined that the prediction deviation exceeds the allowable range, a system failure alarm is triggered and the tunneling cycle data is forcibly included in the system training set. Closed-loop accountability and handling module: Acquires data integrity index, feedback timeliness index, prediction deviation index, and the historical cumulative number of violations by the responsible person to calculate the accountability execution index. The accountability execution index is used to comprehensively determine the management responsibility attribution and handling level of the current tunneling cycle, and to implement step-by-step handling measures according to the numerical range in which it is located. After the handling is completed, the next tunneling cycle begins.

2. The intelligent classification and risk early warning three-dimensional visualization platform for tunnel surrounding rock according to claim 1, characterized in that: The data completeness index is calculated using the following formula: ； in: For data completeness index; This represents the actual number of submissions. The total number to be submitted; This represents the number of valid forms. For submission rate; For efficiency; The weighting coefficient for the submission rate. The weighting coefficients are for efficiency.

3. The intelligent classification and risk early warning three-dimensional visualization platform for tunnel surrounding rock according to claim 2, characterized in that: The data integrity index ranges from [0,1]. After calculating the data integrity index, it is compared with the system's preset integrity threshold to determine whether the integrity of the current tunneling cycle feedback data meets the construction permit requirements. ； in, The system's preset integrity threshold, ; when When the data integrity of the tunneling cycle is deemed satisfactory, the system allows entry into the next module; when If the system determines that the data integrity of the tunneling cycle does not meet the construction permit requirements, it freezes the construction approval process for the next tunneling cycle and continues to send reminder notices until the on-site personnel complete the data and submit a valid feedback form.

4. The three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock according to claim 2, characterized in that: The timely feedback index is calculated using the following formula: ； in: To provide timely feedback index; Submission time; Allowed delay time; This refers to the time when the excavation was completed; This is the actual delay time; The attenuation coefficient is an adjustment parameter that controls the rate of exponential decline.

5. The intelligent classification and risk early warning three-dimensional visualization platform for tunnel surrounding rock according to claim 4, characterized in that: The feedback timeliness index ranges from (0,1). After calculating the feedback timeliness index, it is compared with the system's preset timeliness threshold to determine the timeliness qualification of the current tunneling cycle feedback data. ； in, The time threshold preset by the system, ; when When the feedback data of the tunneling cycle is deemed to be within acceptable timeframes, the system allows entry into the next module; when If the feedback data of the current tunneling cycle is deemed untimely, the data will not be included in subsequent system analysis. The system will automatically record the violation and notify the responsible person to submit a written explanation.

6. The intelligent classification and risk early warning three-dimensional visualization platform for tunnel surrounding rock according to claim 4, characterized in that: The prediction deviation index is calculated using the following formula: ； in: For prediction deviation index; To predict the surrounding rock grade; The measured surrounding rock grade; To predict the probability value of risk; This is a test of the actual risk status; This is a penalty item for risk deviation; This is a graded deviation term; This is a risk deviation item; These are the weighting coefficients for the grading deviation term; This is the weighting coefficient for the risk deviation term.

7. The intelligent classification and risk early warning three-dimensional visualization platform for tunnel surrounding rock according to claim 6, characterized in that: After calculating the prediction deviation index, the prediction deviation index is compared with the system's preset allowable deviation threshold to determine whether the system prediction deviation of the current tunneling cycle is within an acceptable range. ； in, The system's preset allowable deviation threshold, ; when When the system prediction deviation of the current tunneling cycle is determined to be within the allowable range, the system is operating normally; when If the system prediction deviation of the current tunneling cycle exceeds the allowable range, the system will trigger a failure alarm and forcibly include the measured data of the current tunneling cycle into the system training set.

8. The three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock according to claim 6, characterized in that: The accountability enforcement index is calculated using the following formula: ； in: To ensure accountability and implementation index; The cumulative number of historical violations by the responsible person; Responsibility for missing data; For feedback on delayed responsibility items; These are the weighting coefficients for data missing responsibility, feedback delay responsibility, prediction bias index, and the historical cumulative number of violations by the responsible person. .

9. A three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock according to claim 8, characterized in that: After calculating the accountability enforcement index, tiered measures are implemented based on the index's value range: when... If the current tunneling cycle is determined to be operating normally, only a record is made, and no further action is required; when When a minor anomaly is detected, the system automatically sends a notification to the responsible person and their supervisor; when When the condition is determined to be moderately abnormal, the responsible person must submit a written rectification report; when If the situation is deemed a serious anomaly, the intelligent system's command output privileges will be suspended, the decision will be reverted to manual review, and the responsible person's performance bonus will be reduced. The system's preset processing thresholds meet the requirements. After the treatment is completed, the next tunneling cycle begins.

10. A three-dimensional visualization platform for intelligent classification and risk early warning of tunnel surrounding rock according to claim 9, characterized in that: When the accountability execution index is at a level of mild abnormality or above, the system initiates attribution determination: when and The sum of the two items accounts for The proportion of the total value is greater than When the primary issue was determined to be related to the data submission process by on-site personnel, the rectification target was the on-site personnel; when Single item The proportion of the total value is greater than When the main problem is determined to be the prediction accuracy of the intelligent grading system or early warning system, the rectification target is the system itself, triggering a forced update of the system's training set; when Single item The proportion of the total value is greater than When the primary problem is determined to be due to repeated violations by the responsible party, the severity of the punishment for that party will be increased; among other things, The system's preset attribution thresholds are all greater than 0 and less than 1.

Images