Method, device and equipment for stable control of risk preference parameter and medium

Abstract

The application relates to a risk preference parameter stability control method and device, equipment and medium. The method comprises the following steps: obtaining a risk utility value of a current support scheme and construction state information; determining a parameter boundary and a minimum update time interval currently applicable according to the construction state information; judging whether a preset trigger condition is met or not according to the risk utility value, the construction state information and the minimum update time interval; calculating a first adjustment amount of a first risk preference parameter for the current risk utility value, limiting the first adjustment amount in a preset amplitude range to obtain a second adjustment amount; adding the second adjustment amount to the first risk preference parameter and limiting the addition result in the parameter boundary to obtain a second risk preference parameter; and outputting the second risk preference parameter as a target risk preference parameter after stability control when a stability check passes. The application solves the problem of oscillation or drift of the risk preference parameter of the rock mass support system in the adjustment process.

Description

Technical Field

[0001] This application relates to the field of geotechnical engineering support technology, and in particular to a method, device, equipment and medium for the stable control of risk preference parameters. Background Technology

[0002] In intelligent support systems for rock mass engineering, risk preference parameters are used to quantify the decision-making body's tendency to weigh the risk of surrounding rock instability against support costs. These parameters directly influence the selection of support timing, strength, and method. Currently, risk preference parameters are typically set to a fixed set of values ​​during system initialization, or adjusted based on simple feedback from a single monitoring indicator (e.g., displacement, stress) during operation. However, jointed rock mass engineering presents complex construction conditions, frequent geological changes, and fluctuating sample data. Fixed parameters cannot adapt to dynamic changes in working conditions, while simple feedback adjustments lacking system constraints easily lead to frequent parameter fluctuations or continuous unidirectional drift. This parameter instability directly causes contradictions or discontinuities in support decisions across different periods, affecting system reliability and engineering safety. Therefore, preventing oscillations or drifts in the risk preference parameters of rock mass support systems during adjustment is a problem that needs to be addressed.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and medium for the stable control of risk preference parameters, in order to solve the technical problem of oscillation or drift of risk preference parameters in the above-mentioned rock mass support system during the adjustment process.

[0005] According to one aspect of the embodiments of this application, this application provides a method for stable control of risk preference parameters, applied to a rock mass support system, comprising: obtaining the risk utility value of the current support scheme and construction status information, wherein the risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on construction monitoring samples, and the risk utility value is used to characterize the risk level of the current support scheme; determining the currently applicable parameter boundary and minimum update time interval based on the construction status information; determining whether a preset triggering condition is met based on the risk utility value, construction status information, and minimum update time interval; if the preset triggering condition is met, calculating a first adjustment amount for the current first risk preference parameter based on the risk utility value, and limiting the first adjustment amount within a preset range to obtain a second adjustment amount; adding the second adjustment amount to the first risk preference parameter, and limiting the addition result within the parameter boundary to obtain a second risk preference parameter; performing a stability verification on the second risk preference parameter, and outputting the second risk preference parameter as the target risk preference parameter after stable control if the stability verification passes.

[0006] Optionally, obtaining the risk utility value of the current support scheme includes: collecting construction monitoring data during the construction process, wherein the construction monitoring data is multi-dimensional raw data used to evaluate the implementation effect of the support scheme; quantifying the construction monitoring data to obtain a set of return samples; using a piecewise power function to convert the return values ​​of each return sample in the set of return samples into subjective utility values ​​to obtain a set of subjective utility values; and performing discrete approximation calculations on the set of subjective utility values ​​to obtain the risk utility value.

[0007] Optionally, a discrete approximation calculation is performed on the set of subjective utility values ​​to obtain the risk utility value, including: sorting each subjective utility value in the set of subjective utility values ​​in ascending order, using each sorted subjective utility value as a segment node, wherein two adjacent segment nodes constitute a segment interval, and each segment interval corresponds to the segment node at its left endpoint; for each segment node, calculating the proportion of each subjective utility value greater than the segment node to determine the empirical probability corresponding to the segment node; performing nonlinear distortion processing on each empirical probability to obtain the weighted probability corresponding to each segment node; and multiplying the weighted probability of each segment node by the length of the corresponding segment interval and summing the results to obtain the risk utility value.

[0008] Optionally, the applicable parameter boundaries and minimum update interval are determined based on the construction status information, including: reading the current construction stage label and the current risk level label from the construction status information; determining the lower limit value, upper limit value, and minimum update interval of the parameters based on the current construction stage label and the current risk level label through a preset mapping rule, wherein the mapping rule defines the correspondence between the construction stage and risk level and the lower limit value, upper limit value, and minimum update interval of the parameters; and configuring the lower limit value and upper limit value of the parameters as parameter boundaries.

[0009] Optionally, the lower limit value, upper limit value, and minimum update time interval of the parameters are determined by a preset mapping rule, including: determining whether the current construction stage label belongs to the target stage label set to obtain a first determination result, and determining whether the current risk level label belongs to the high-risk level label set to obtain a second determination result, wherein the target stage label set includes labels for high-risk stages and important process stages; when the first determination result is yes and / or the second determination result is yes, the first lower limit value is used as the lower limit value of the parameters, the first upper limit value is used as the upper limit value of the parameters, and the first time interval is used as the minimum update time interval; when the first determination result is no and the second determination result is no, the second lower limit value is used as the lower limit value of the parameters, the second upper limit value is used as the upper limit value of the parameters, and the second time interval is used as the minimum update time interval, wherein the first lower limit value is greater than the second lower limit value, the first upper limit value is less than the second upper limit value, and the first time interval is greater than the second time interval.

[0010] Optionally, based on the risk utility value, construction status information, and minimum update interval, it is determined whether the current situation meets the preset triggering conditions, including: reading the historical risk utility value of the previous period and calculating the change range of the risk utility value compared to the historical risk utility value, and obtaining the risk level change and abnormal monitoring signals from the construction status information; determining whether the content triggering conditions are met based on the change range, risk level change, and abnormal monitoring signals, wherein meeting the content triggering conditions means that at least one of the following situations occurs: the change range is greater than or equal to a preset threshold, the risk level change indication level changes, and the abnormal monitoring signal indicates that there is an abnormality in the construction process; if the content triggering conditions are met, the last parameter update time is read, and it is determined whether the time triggering conditions are met based on the current time and the parameter update time, wherein the time triggering condition is that the time interval between the current time and the parameter update time is greater than or equal to the minimum update interval; if the time triggering conditions are determined to be met, it is determined that the current situation meets the preset triggering conditions.

[0011] Optionally, after performing stability verification on the second risk preference parameter, the method further includes: if the stability verification fails, outputting the first risk preference parameter as the target risk preference parameter; recording the reason for the stability verification failure and the value of the second risk preference parameter, generating an anomaly record, and storing the anomaly record in the database.

[0012] According to another aspect of the embodiments of this application, this application provides a stable control device for risk preference parameters, applied to a rock mass support system, comprising: an acquisition module, used to acquire the risk utility value of the current support scheme and construction status information, wherein the risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on construction monitoring samples, and the risk utility value is used to characterize the risk level of the current support scheme; a determination module, used to determine the currently applicable parameter boundary and minimum update time interval based on the construction status information; a judgment module, used to determine whether the current situation meets the preset triggering conditions based on the risk utility value, construction status information, and minimum update time interval; a calculation module, used to calculate a first adjustment amount for the current first risk preference parameter based on the risk utility value when the preset triggering conditions are determined to be met, and limit the first adjustment amount within a preset range to obtain a second adjustment amount; a processing module, used to add the second adjustment amount to the first risk preference parameter, and limit the addition result within the parameter boundary to obtain a second risk preference parameter; and an output module, used to perform stability verification on the second risk preference parameter, and output the second risk preference parameter as the target risk preference parameter after stable control when the stability verification passes.

[0013] According to another aspect of the embodiments of this application, this application provides an electronic device, including a memory, a processor, a communication interface and a communication bus. The memory stores a computer program that can run on the processor. The memory and the processor communicate with each other through the communication bus and the communication interface. When the processor executes the computer program, it implements the steps of the above method.

[0014] According to another aspect of the embodiments of this application, this application also provides a computer-readable medium having processor-executable non-volatile program code that causes the processor to perform the above-described method.

[0015] Compared with related technologies, the technical solutions provided in this application have the following advantages: This application provides a method for stable control of risk preference parameters, applied to rock mass support systems, comprising: acquiring the risk utility value of the current support scheme and construction status information, wherein the risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on construction monitoring samples, and the risk utility value is used to characterize the risk level of the current support scheme; determining the applicable parameter boundaries and minimum update time interval based on the construction status information; determining whether the current situation meets the preset triggering conditions based on the risk utility value, construction status information, and minimum update time interval; if the current situation meets the preset triggering conditions, calculating a first adjustment amount for the current first risk preference parameter based on the risk utility value, and limiting the first adjustment amount within a preset range to obtain a second adjustment amount; adding the second adjustment amount to the first risk preference parameter, and limiting the sum to the parameter boundaries to obtain a second risk preference parameter; performing stability verification on the second risk preference parameter, and outputting the second risk preference parameter as the target risk preference parameter after stable control if the stability verification passes. By preventing parameter oscillations through the magnitude of single adjustment, and by limiting the parameter value range through dynamically determined parameter boundaries based on construction status information, the problem of oscillations or drifts in the risk preference parameters of the rock mass support system during adjustment is solved. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram illustrating the diversity of rock mass support selection under complex geological conditions according to the embodiments of this application; Figure 2 This is a flowchart of an optional method for stabilizing risk preference parameters according to an embodiment of this application; Figure 3 This is a flowchart of another optional method for stabilizing risk preference parameters provided according to an embodiment of this application; Figure 4 This is a block diagram of an optional risk preference parameter stabilization control device provided according to an embodiment of this application; Figure 5 This is a schematic diagram of an optional electronic device structure provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustration and has no specific meaning in itself. Therefore, "module" and "part" may be used interchangeably.

[0021] In intelligent support systems for rock mass engineering, risk preference parameters are used to quantify the decision-making body's tendency to weigh the risk of surrounding rock instability against support costs. Risk preference parameters directly affect the selection of support timing, support strength, and support methods.

[0022] Figure 1 This is a schematic diagram illustrating the diversity of rock mass support options under complex geological conditions, such as... Figure 1 As shown, the support schemes used in the same rock mass project vary significantly across different geological sections. In the sandstone area, a combination of systematic anchor bolts and prestressed anchor cables is used; in the granite area, a combination of random anchor bolts and wire mesh is used; in the fault zone, a combination of grid arch frames and steel fiber reinforced shotcrete is used; and in the underground powerhouse cavern area, systematic anchor bolts are used for support.

[0023] The aforementioned differences indicate that the selection of support schemes for jointed rock mass engineering is highly scenario-dependent and stage-specific, with varying surrounding rock stability, support requirements, and risk control priorities in different sections. Existing methods typically employ fixed configurations or simple feedback adjustments for risk preference parameters, which are ill-suited to adapting to these scenario changes and prone to oscillations or drifts during adjustment.

[0024] To address the problems mentioned in the background art, according to one aspect of the embodiments of this application, an embodiment of a method for stabilizing and controlling risk preference parameters is provided, applied to a rock mass support system, such as... Figure 2 As shown, it includes: Step 201: Obtain the risk utility value and construction status information of the current support scheme. The risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on the construction monitoring samples. The risk utility value is used to characterize the risk level of the current support scheme. Step 202: Determine the applicable parameter boundaries and minimum update interval based on the construction status information; Step 203: Determine whether the preset triggering conditions are met based on the risk utility value, construction status information, and minimum update interval. Step 204: If the preset triggering conditions are met, calculate the first adjustment amount for the current first risk preference parameter based on the risk utility value, and limit the first adjustment amount within a preset range to obtain the second adjustment amount; Step 205: Add the second adjustment amount to the first risk preference parameter, and restrict the sum to within the parameter boundary to obtain the second risk preference parameter; Step 206: Perform stability verification on the second risk preference parameter, and if the stability verification passes, output the second risk preference parameter as the target risk preference parameter after stable control.

[0025] The risk preference parameter stabilization control method provided in this application is applicable to geotechnical engineering scenarios with well-developed joints, complex geological conditions, and significant differences in the stability state of surrounding rock in different construction sections, such as water conservancy and hydropower tunnels, transportation tunnels, and underground powerhouses. This application utilizes a scenario-adaptive parameter boundary dynamic adjustment mechanism during the execution of support schemes to adaptively adjust the risk preference parameters according to changes in construction stages and risk levels, thereby meeting the differentiated control requirements of support schemes in different geological sections.

[0026] Risk preference parameters are used to characterize the asymmetric sensitivity of engineering decision-makers to gains and losses, specifically including the gain curvature parameter. Loss curvature parameters and loss aversion coefficient , can be represented as The revenue curvature parameter is the exponent of the power function of the revenue interval, used to control the rate of decrease in marginal sensitivity of revenue. The loss curvature parameter is the exponent of the power function of the loss interval, used to control the rate of decrease in marginal sensitivity of loss. The loss aversion coefficient is the magnification factor of the loss interval, used to reflect the multiple relationship between the decision-maker's aversion to loss and their preference for gain.

[0027] This application suppresses parameter instability by introducing multiple constraint mechanisms during parameter updates. Specifically, it first obtains a risk utility value characterizing the risk level of the current support scheme, and determines the applicable parameter boundaries and minimum update interval based on construction status information. When an update is triggered, a first adjustment amount is calculated based on the risk utility value for the current first risk preference parameter, and this first adjustment amount is limited within a preset range to obtain a second adjustment amount, thereby preventing parameter oscillations caused by excessively large single update amplitudes. Subsequently, the second adjustment amount is added to the first risk preference parameter, and the result is limited within the parameter boundaries determined based on construction status information to obtain a second risk preference parameter, thereby preventing the parameter from gradually deviating from a reasonable range during long-term operation, i.e., suppressing parameter drift. Finally, the stability of the second risk preference parameter is verified, and only when the verification passes is the second risk preference parameter output as the target risk preference parameter after stable control. Through the coordinated operation of multiple operations such as amplitude limiting, boundary truncation, and stability verification, while allowing parameters to adjust with changes in working conditions, it ensures that the result of each update is always within a controllable and stable range.

[0028] As an optional embodiment, obtaining the risk utility value of the current support scheme includes: collecting construction monitoring data during the construction process, wherein the construction monitoring data is multi-dimensional raw data used to evaluate the implementation effect of the support scheme; quantifying the construction monitoring data to obtain a set of return samples; using a piecewise power function to convert the return values ​​of each return sample in the set of return samples into subjective utility values ​​to obtain a set of subjective utility values; and performing discrete approximation calculations on the set of subjective utility values ​​to obtain the risk utility value.

[0029] During construction and operation, the following multi-dimensional raw data are collected from the on-site monitoring system and construction management system using a pre-set fixed evaluation cycle as the basic statistical unit: surrounding rock displacement monitoring results, which reflect the degree of surrounding rock deformation; microseismic activity records, which reflect the degree of surrounding rock fracturing activity; support structure stress data, which characterize the working status of the support system; construction progress information, which measures the execution efficiency of the support scheme; and cost consumption, which measures the economic efficiency of the support scheme.

[0030] The evaluation cycle can be determined based on the construction organization, the frequency of monitoring data updates, and the requirements of project management. For example, it can be divided according to the excavation cycle, shift cycle, or phased construction nodes.

[0031] The collected data on surrounding rock displacement monitoring, microseismic activity records, support structure stress data, construction progress information, and cost consumption are preprocessed, normalized, and subjected to unified scaling. Indicators with different dimensions and value ranges are mapped to unified return or loss values, and compiled into a return sample set, represented as follows: , For object In the In this evaluation, the return value is B, which represents the number of valid samples.

[0032] The return sample obtained by quantifying construction monitoring data is the construction monitoring sample mentioned above.

[0033] The sample collection of returns is stored in the project database, and the corresponding construction section number, process stage type, and risk level label are simultaneously marked.

[0034] The return values ​​of each return sample in the return sample set are transformed into subjective utility values ​​using a piecewise power function, resulting in a set of subjective utility values. Specifically, this involves using a utility function in the form of a piecewise power function from cumulative prospect theory to convert each return value... Substitute into the following formula to calculate the subjective utility value : Equation (1) Where α is the return curvature parameter, β is the loss curvature parameter, and λ is the loss aversion coefficient. This function is used to characterize the diminishing marginal sensitivity and loss aversion characteristics. Through equation (1), the objective return is transformed into a subjective utility value reflecting the risk attitude of engineering decision-making, thus obtaining a set of subjective utility values.

[0035] The risk utility value is obtained by sorting, segmenting, probability-weighting, and summing the set of subjective utility values.

[0036] This embodiment transforms multi-source data such as surrounding rock displacement, microseismic activity, support stress, construction progress, and cost consumption generated during construction into a unified risk utility calculation process. This reduces evaluation bias caused by sample fluctuations, differences in implementation methods, and discrete calculation errors, resulting in better consistency of evaluation results across different time periods, sections, and data batches.

[0037] As an optional embodiment, a discrete approximation calculation is performed on the set of subjective utility values ​​to obtain a risk utility value, including: sorting each subjective utility value in the set of subjective utility values ​​in ascending order, using each sorted subjective utility value as a segment node, wherein two adjacent segment nodes constitute a segment interval, and each segment interval corresponds to a segment node at its left endpoint; for each segment node, calculating the proportion of each subjective utility value greater than the segment node to determine the empirical probability corresponding to the segment node; performing nonlinear distortion processing on each empirical probability to obtain a weighted probability corresponding to each segment node; and multiplying the weighted probability of each segment node by the length of the corresponding segment interval and summing the results to obtain the risk utility value.

[0038] Specifically, if the set of subjective utility values ​​contains B sample values, the sequence obtained after sorting in ascending order is: , with each As a segment node Adjacent nodes and The interval between [ , () is a segmented interval, and this segmented interval is related to its left endpoint. Correspondingly.

[0039] For each segment node, the proportion of subjective utility values ​​greater than that segment node is calculated to determine the empirical probability corresponding to that segment node. Specifically, this includes: for each segment node... The set of statistical subjective utility values ​​is greater than The empirical probability is obtained by dividing the number of samples by the total number of samples B, and the calculation formula is as follows: Equation (2) in, , Represents empirical probability; This represents an indicator function. It takes the value 1 when the condition within the parentheses is true and 0 when the condition within the parentheses is false. Summing the indicator function values ​​of all samples gives the number of samples greater than the segment node.

[0040] The empirical probabilities are nonlinearly distorted to obtain weighted probabilities corresponding to each segment node. Specifically, this involves introducing a probability weighting function from cumulative prospect theory (including a probability weighting function for the payoff interval). Probability weighting function of loss interval We can obtain weighted probabilities by performing a nonlinear mapping on empirical probabilities. Calculating weighted probabilities can adjust the sensitivity to low-probability and high-probability events, making the calculation results closer to the risk judgment characteristics of engineering managers in actual decision-making.

[0041] The risk utility value is obtained by multiplying the weighted probability of each segment node by the length of its corresponding segment interval and then summing the results. Specifically, for each segment node, its weighted probability is multiplied by the length of its corresponding segment interval, and all multiplications are summed. This summation is a numerical approximation of the cumulative prospect theory integral expression, calculated using the following formula: Equation (3) in, For risk utility value, and These are probability weighted functions for the profit and loss intervals, respectively. For theoretical probability, Represents subjective utility value Less than or equal to the utility threshold The theoretical probability, Represents subjective utility value Greater than the threshold The theoretical probability.

[0042] Since the true probability distribution cannot be obtained in actual engineering, this embodiment uses empirical probability for discrete approximation calculation to numerically solve the above integral expression.

[0043] Utility threshold It is an integral variable, and its range of values ​​covers the entire domain of subjective utility values. When, the corresponding loss interval (utility value is negative), when At that time, the corresponding benefit range (utility value is positive).

[0044] Specifically, the approximate values ​​of the revenue portion are calculated according to the following formulas. and approximate value of loss : Equation (4) Equation (5) in, This indicates that the subjective utility value is greater than the segment node. The empirical probability, This indicates that the subjective utility value is less than or equal to the segment node. The empirical probability can be derived from ( ) was calculated to be This represents the length of the j-th segment interval.

[0045] The risk utility value is obtained by adding the approximate values ​​of the gains and losses, as shown in the following formula: Equation (6) This embodiment employs empirical probability estimation based on sample sorting and piecewise summation approximation, which eliminates the need to assume that the sample data follows a certain theoretical distribution. This enables the numerical calculation of the cumulative prospect theory integral expression, reducing evaluation bias caused by sample fluctuations, differences in implementation methods, and discrete calculation errors.

[0046] As an optional embodiment, determining the currently applicable parameter boundaries and minimum update time interval based on construction status information includes: reading the current construction stage label and the current risk level label from the construction status information; determining the lower limit value, upper limit value, and minimum update time interval of the parameters based on the current construction stage label and the current risk level label through a preset mapping rule, wherein the mapping rule defines the correspondence between the construction stage and risk level and the lower limit value, upper limit value, and minimum update time interval of the parameters; and configuring the lower limit value and upper limit value of the parameters as parameter boundaries.

[0047] Construction status information comes from the construction planning system and the risk warning system. The construction planning system dynamically divides construction into different stages (e.g., excavation, support, monitoring, etc.) based on the overall project progress and phased objectives, and generates corresponding construction stage labels. The risk warning system assesses the risk level of the current construction stage (e.g., low risk, medium risk, high risk) by monitoring real-time changes in the stability of the surrounding rock, the stress state of the support structure, and other environmental factors, and generates corresponding risk level labels.

[0048] Based on the current construction stage label and the current risk level label, the lower limit value, upper limit value, and minimum update interval of parameters are determined through preset mapping rules. The mapping rules define the correspondence between the construction stage and risk level and the lower limit value, upper limit value, and minimum update interval of parameters. For example, in high-risk stages or key process stages (such as fault zone crossings or excavation of underground powerhouse cavern groups), the surrounding rock conditions are complex and the construction uncertainty is high. The mapping rules output tightened parameter boundaries (i.e., higher lower limit values ​​and lower upper limit values) and larger minimum update intervals, allowing the risk preference parameters to be adjusted within a conservative range and avoiding overly risky support decisions. In normal construction stages (such as conventional excavation in stable surrounding rock areas), the surrounding rock stability is high and the construction conditions are ideal. The mapping rules output relaxed parameter boundaries (i.e., lower lower limit values ​​and higher upper limit values) and smaller minimum update intervals, improving construction efficiency while ensuring safety.

[0049] Configure the lower and upper limits of the parameters as parameter boundaries, and use the minimum update interval as the time interval threshold for subsequent trigger condition judgments. The parameter boundaries are used to truncate the updated parameter values, and the minimum update interval is used to control the minimum frequency of parameter updates.

[0050] By establishing mapping rules between construction stages, risk levels, parameter boundaries, and minimum update intervals, parameter configuration no longer adopts a static and uniform mode, but can be adjusted in a targeted manner according to different procedures, different surrounding rock conditions, and different safety requirements.

[0051] As an optional embodiment, the lower limit value, upper limit value, and minimum update time interval of the parameters are determined by a preset mapping rule, including: determining whether the current construction stage label belongs to the target stage label set to obtain a first determination result, and determining whether the current risk level label belongs to the high-risk level label set to obtain a second determination result, wherein the target stage label set includes labels for high-risk stages and important process stages; when the first determination result is yes and / or the second determination result is yes, the first lower limit value is used as the lower limit value of the parameters, the first upper limit value is used as the upper limit value of the parameters, and the first time interval is used as the minimum update time interval; when the first determination result is no and the second determination result is no, the second lower limit value is used as the lower limit value of the parameters, the second upper limit value is used as the upper limit value of the parameters, and the second time interval is used as the minimum update time interval, wherein the first lower limit value is greater than the second lower limit value, the first upper limit value is less than the second upper limit value, and the first time interval is greater than the second time interval.

[0052] The target stage label set includes high-risk stage labels and important process stage labels. The high-risk stage labels correspond to the fault zone crossing stage and the high ground stress stage, while the important process stage labels correspond to the excavation of the tunnel intersection and the support of the key block.

[0053] After obtaining the current construction stage label from the construction planning system, the label is compared with the preset target stage label set: if the current construction stage label exists in the set, the first judgment result is yes; otherwise, the first judgment result is no.

[0054] Determine whether the current risk level label belongs to the set of high-risk level labels to obtain a second judgment result. Specifically, after obtaining the current risk level label from the risk warning system, compare the label with the preset set of high-risk level labels: if the current risk level label exists in the set, the second judgment result is yes; otherwise, the second judgment result is no.

[0055] When the first judgment result is yes, and / or the second judgment result is yes, it indicates that the current construction stage belongs to a high-risk or important process stage, or the current risk level belongs to a high-risk level. In this case, the first lower limit value is used as the lower limit value of the parameter, the first upper limit value is used as the upper limit value of the parameter, and the first time interval is used as the minimum update time interval. The values ​​taken at this time correspond to the tightened parameter boundaries and the larger update time interval, which is suitable for high-risk scenarios.

[0056] When both the first and second judgments are negative, it indicates that the current construction phase is not a high-risk or critical process phase, and the current risk level is not high-risk. The second lower limit is used as the lower limit of the parameter, the second upper limit as the upper limit of the parameter, and the second time interval as the minimum update interval. Since the first lower limit is greater than the second lower limit, the first upper limit is less than the second upper limit, and the first time interval is greater than the second time interval, the values ​​in this case correspond to relaxed parameter boundaries and a smaller update interval, suitable for normal construction scenarios.

[0057] The first lower limit, the first upper limit, the first time interval, the second lower limit, the second upper limit, and the second time interval are all preset values. The specific values ​​can be determined based on engineering experience or historical data.

[0058] By treating the construction phase and risk level as two independent judgment dimensions, the system can flexibly respond to risk control needs in different scenarios. Through differentiated configurations where the first lower limit is greater than the second lower limit and the first upper limit is less than the second upper limit, the parameter boundaries are automatically tightened in high-risk scenarios and automatically relaxed in normal scenarios. Furthermore, through differentiated configurations where the first time interval is greater than the second time interval, the update frequency is automatically reduced in high-risk scenarios and automatically increased in normal scenarios.

[0059] As an optional embodiment, determining whether the current situation meets the preset triggering conditions based on the risk utility value, construction status information, and minimum update time interval includes: reading the historical risk utility value of the previous period and calculating the change range of the risk utility value compared to the historical risk utility value, and obtaining the risk level change and abnormal monitoring signals from the construction status information; determining whether the content triggering conditions are met based on the change range, risk level change, and abnormal monitoring signals, wherein meeting the content triggering conditions means that at least one of the following situations occurs: the change range is greater than or equal to a preset threshold, the risk level change indicates a change in the level, and the abnormal monitoring signal indicates that there is an abnormality in the construction process; if the content triggering conditions are met, reading the last parameter update time and determining whether the time triggering conditions are met based on the current time and the parameter update time, wherein the time triggering condition is that the time interval between the current time and the parameter update time is greater than or equal to the minimum update time interval; if the time triggering conditions are met, determining that the current situation meets the preset triggering conditions.

[0060] The change magnitude is obtained by subtracting the risk utility value calculated for the current period from the risk utility value stored in the database for the previous period and taking the absolute value.

[0061] The risk level label obtained from the risk warning system in the current period is compared with the risk level label in the previous period to determine whether there has been a change.

[0062] The system obtains surrounding rock displacement monitoring results, microseismic activity records, and support structure stress data from the field monitoring system to determine whether there are any abnormal signals exceeding the preset safety threshold.

[0063] The content triggering condition is met if at least one of the following conditions is met: the magnitude of the change is greater than or equal to a preset threshold (i.e., a significant change in the risk level); the risk level changes (i.e., the risk level changes from low risk to medium risk, high risk, etc.); or anomaly monitoring signals indicate anomalies during construction (e.g., sudden changes in surrounding rock displacement, increased microseismic activity, excessive support stress, etc.). If any one of these three conditions is met, the content triggering condition is deemed satisfied.

[0064] If the content triggering condition is met, the system reads the last parameter update time from the database and compares the current time with the last parameter update time to determine if the time triggering condition is met. The time triggering condition is that the time interval between the current time and the last parameter update time is greater than or equal to the minimum update interval. The time triggering condition is used to prevent parameters from being frequently adjusted within a short period, which could affect system stability.

[0065] If the time-triggered condition is met, the current preset trigger condition is also met, and the parameter update process can proceed. If the content-triggered condition is not met, or the content-triggered condition is met but the time-triggered condition is not met, the current preset trigger condition is not met, and parameter update is not performed.

[0066] This embodiment uses a dual judgment mechanism that combines content-triggered conditions and time-triggered conditions to ensure that parameter updates can respond promptly to changes in risks at the construction site, while avoiding frequent parameter adjustments due to local sample fluctuations or short-term anomalies.

[0067] In this embodiment, the limiting operation is implemented using the following formula: Equation (7) in, This is a truncation function. The preset maximum adjustment range It refers to the preset amplitude range.

[0068] In this embodiment, the boundary truncation operation is implemented using the following formula: Equation (8) in, and These are the lower limit and upper limit of the parameter, respectively. First, set the current parameter... Adjustment amount after limiting Add them together, and then restrict the result to... Within the interval: If The calculation result is greater than Then As The value; if the calculation result is less than Then As The value; if the calculation result is located in Within the interval, it remains unchanged, that is .

[0069] As an optional embodiment, after performing stability verification on the second risk preference parameter, the method further includes: if the stability verification fails, outputting the first risk preference parameter as the target risk preference parameter; recording the reason information for the failure of the stability verification and the value of the second risk preference parameter, generating an anomaly record, and storing the anomaly record in the database.

[0070] The second risk preference parameter includes the updated return curvature parameter, loss curvature parameter, and loss aversion coefficient. Only if all three parameters pass the stability check can the second risk preference parameter be considered to have passed the stability check.

[0071] Stability checks include timing consistency checks, cross-parameter collaborative consistency checks, and output consistency checks. If any one of these checks is not met, the stability check will fail.

[0072] The temporal consistency check includes comparing the second risk preference parameter with the first risk preference parameter to verify whether the direction of change of the second risk preference parameter relative to the first risk preference parameter is consistent with the risk evolution trend of the current construction phase. The temporal consistency check dynamically correlates the parameter update results with the risk evolution trend of the construction scenario to ensure that the parameter adjustment direction meets the engineering requirements of the current stage.

[0073] For example, the value of the first risk preference parameter is read from the engineering database, the direction of change of the second risk preference parameter relative to the first risk preference parameter is calculated, and the risk evolution trend of the current construction stage is determined based on the current construction stage label. If the current construction stage is a high-risk stage or an important process stage, the surrounding rock conditions are complex, construction uncertainty is high, and the risk shows an upward trend. It is expected that the risk preference parameter should be adjusted in the direction of increasing risk aversion, specifically: the loss aversion coefficient increases relative to the previous parameter value, and the revenue curvature parameter decreases relative to the previous parameter value. If the second risk preference parameter shows the opposite direction of change, that is, the loss aversion coefficient decreases relative to the previous parameter value or the revenue curvature parameter increases relative to the previous parameter value, then the time series consistency check is determined to be unsatisfactory. If the current construction stage is a normal construction stage, the surrounding rock stability is high, and the risk shows a stable or decreasing trend. It is not mandatory to adjust the parameter in a conservative direction, and the time series consistency check automatically passes.

[0074] Cross-parameter collaborative consistency checks include verifying whether the numerical relationships among the return curvature parameter, loss curvature parameter, and loss aversion coefficient in the second risk preference parameter meet the preset collaborative constraints.

[0075] For example, the updated return curvature parameter, loss curvature parameter, and loss aversion coefficient are read from the second risk preference parameter, and the following collaborative constraints are verified in sequence: Verify whether both the return curvature parameter and the loss curvature parameter belong to the open interval (0, 1); verify whether the loss aversion coefficient is greater than 1, which reflects the psychological characteristic that the decision-maker's aversion to loss is higher than their preference for gain; verify whether the absolute value of the difference between the return curvature parameter and the loss curvature parameter is less than a preset threshold, which ensures that the curvature of the return interval and the loss interval are basically symmetrical, avoiding extremely uneven utility function shapes; verify whether the combination relationship of the return curvature parameter, loss curvature parameter, and loss aversion coefficient satisfies the rationality inequality derived from the cumulative prospect theory. If the return curvature parameter, loss curvature parameter, and loss aversion coefficient in the second risk preference parameter satisfy all the above constraints, the cross-parameter collaborative consistency check is deemed to have passed; if any one of the constraints is not satisfied, the cross-parameter collaborative consistency check is deemed to have failed.

[0076] Cross-parameter coherence check utilizes the inherent physical relationship between risk preference parameters for coherence verification, overcoming the limitation of conventional single-parameter range check in failing to verify the coherence relationship between parameters.

[0077] Output consistency checks include verifying whether the second risk preference parameter complies with the engineering safety specifications for the current construction phase.

[0078] For example, the engineering safety specifications for the current construction phase are retrieved from the construction management system. If the current construction phase is a high-risk phase or a critical process phase, the engineering safety specifications require a loss aversion coefficient not lower than the first safety threshold (e.g., 2.0) and a revenue curvature parameter not higher than the second safety threshold (e.g., 0.5). If the current construction phase is a normal construction phase, the engineering safety specifications require a loss aversion coefficient not lower than the third safety threshold (e.g., 1.5) and a revenue curvature parameter not higher than the fourth safety threshold (e.g., 0.8). The updated revenue curvature parameter and loss aversion coefficient are read from the second risk preference parameter, and each parameter is verified to meet the corresponding specification requirements for the current phase. If the second risk preference parameter meets all the engineering safety specification requirements for the current construction phase, the output consistency check is considered passed; if any parameter does not meet the corresponding specification requirements, the output consistency check is considered unsatisfactory.

[0079] Output consistency checks directly link parameter verification with engineering safety specifications during the construction phase, ensuring that the final output target risk preference parameters meet the actual safety management requirements of the project.

[0080] When the second risk preference parameter fails the stability check, the check result is determined to be unsatisfactory. The second risk preference parameter obtained in this update is not adopted. Instead, the system reverts to the stable state before the update. In other words, the first risk preference parameter before the update is output as the target risk preference parameter for support decision-making.

[0081] Record the specific reasons for the failure of this verification, such as: the direction of change of the second risk preference parameter is inconsistent with the risk evolution trend of the current construction stage, or the synergistic constraints between risk preference parameters are not met. Also, record the value of the second risk preference parameter so that engineers can analyze the causes of the anomaly.

[0082] After the abnormal records are associated with the current construction section number, process stage type and risk level label, they are stored in the project database to form a traceable historical record, which is used for fault tracing and system optimization.

[0083] By automatically reverting to the previous stable parameter state when the stability check fails, abnormal parameters are prevented from entering the operating system and causing continuous impact on subsequent support decisions, thereby enhancing the system's safety assurance capability during long-term continuous operation.

[0084] The database involved in this application is an engineering database used to store the return sample set and a complete record of each parameter update process. The return sample set includes the return value or loss value formed in each evaluation cycle and the corresponding construction section number, process stage type and risk level label. The parameter update record includes the triggering conditions, sample source, update range and verification results, as well as the record of abnormal reasons when the stability verification fails.

[0085] This application provides a method for stable control of risk preference parameters, applied to rock mass support systems, comprising: acquiring the risk utility value of the current support scheme and construction status information, wherein the risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on construction monitoring samples, and the risk utility value is used to characterize the risk level of the current support scheme; determining the applicable parameter boundaries and minimum update time interval based on the construction status information; determining whether the current situation meets the preset triggering conditions based on the risk utility value, construction status information, and minimum update time interval; if the current situation meets the preset triggering conditions, calculating a first adjustment amount for the current first risk preference parameter based on the risk utility value, and limiting the first adjustment amount within a preset range to obtain a second adjustment amount; adding the second adjustment amount to the first risk preference parameter, and limiting the sum to the parameter boundaries to obtain a second risk preference parameter; performing stability verification on the second risk preference parameter, and outputting the second risk preference parameter as the target risk preference parameter after stable control if the stability verification passes. By preventing parameter oscillations through the magnitude of single adjustment, and by limiting the parameter value range through dynamically determined parameter boundaries based on construction status information, the problem of oscillations or drifts in the risk preference parameters of the rock mass support system during adjustment is solved.

[0086] Figure 3 A flowchart illustrating another risk preference parameter stabilization control method provided in this application embodiment includes the following steps: Step 301, Engineering Data Acquisition and Sample Construction: Collect multi-source monitoring and management data such as surrounding rock displacement, microseismic activity, support structure stress, construction progress and cost, preprocess and normalize the raw data to form a uniform scale of return and loss sample set, and store it in the engineering database. Step 302, Utility Transformation and Subjective Utility Modeling: Based on the cumulative prospect theory, utility function mapping is performed on the return and loss samples to transform the objective engineering results into subjective utility values ​​that reflect risk attitude, providing a basic input for subsequent risk utility calculation; Step 303, Construction of the risk utility integral model: Based on the cumulative prospect theory, construct a probability-weighted expression for the risk utility integral, and weight the tail probabilities of the utility distribution to form a risk utility theoretical calculation model; Step 304, Empirical probability estimation and numerical approximation calculation: The utility distribution is empirically estimated using a small batch of historical samples, and the risk utility integral is numerically approximated by sorting, segmenting and discrete summation to obtain the risk utility value that the project can achieve. Step 305, Construction Scenario Mapping and Parameter Adaptation: Based on the construction stage division results and risk level assessment information, the value boundaries and update strategies of the risk preference parameters are configured for scenario mapping to achieve dynamic matching between parameters and the engineering environment; Step 306, Stable update control of risk preference parameters: Using the risk utility calculation results as input, combined with the triggering conditions and time interval constraint mechanism, the risk preference parameters are periodically adjusted, and the update magnitude and value range are limited to ensure the stability of parameter evolution; Step 307, Stability verification and rollback: Perform stability verification on the updated parameters. If the test results do not meet the stability or safety requirements, automatically roll back to the previous stable parameter state. Step 308, Parameter Issuance and Decision Execution: The final confirmed risk preference parameters are issued to the support decision or control module to guide the configuration of support parameters and the adjustment of construction plans, and to execute the corresponding control strategies; Step 309, Operational Feedback and Closed-Loop Update: Collect operational performance data after the implementation of the scheme, update the sample library and parameter record information, provide feedback support for risk utility calculation and parameter update in the next evaluation cycle, and form a closed-loop operation mechanism.

[0087] By constructing calculable risk utility values ​​for engineering through multi-source data acquisition and cumulative prospect theory, and combining the dynamic adaptation of parameter boundaries, amplitude constraints, and stability verification backoff mechanisms of scenario mapping, the oscillation and drift of risk preference parameters in the rock mass support system during the adjustment process is effectively suppressed.

[0088] According to another aspect of the embodiments of this application, this application provides a device for stabilizing and controlling risk preference parameters, applied to rock mass support systems, such as... Figure 4 As shown, it includes: The acquisition module 401 is used to acquire the risk utility value of the current support scheme and construction status information. The risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on the construction monitoring samples. The risk utility value is used to characterize the risk level of the current support scheme. The determination module 402 is used to determine the currently applicable parameter boundaries and minimum update time interval based on the construction status information; The judgment module 403 is used to determine whether the preset triggering conditions are met based on the risk utility value, construction status information and minimum update time interval. The calculation module 404 is used to calculate a first adjustment amount for the current first risk preference parameter based on the risk utility value when it is determined that the current preset triggering condition is met, and to limit the first adjustment amount within a preset range to obtain a second adjustment amount; Processing module 405 is used to add the second adjustment amount to the first risk preference parameter, and restrict the addition result within the parameter boundary to obtain the second risk preference parameter; The output module 406 is used to perform stability verification on the second risk preference parameter, and if the stability verification passes, output the second risk preference parameter as the target risk preference parameter after stability control.

[0089] It should be noted that the acquisition module 401 in this embodiment can be used to execute step 201 in this application embodiment, the determination module 402 in this embodiment can be used to execute step 202 in this application embodiment, the judgment module 403 in this embodiment can be used to execute step 203 in this application embodiment, the calculation module 404 in this embodiment can be used to execute step 204 in this application embodiment, the processing module 405 in this embodiment can be used to execute step 205 in this application embodiment, and the output module 406 in this embodiment can be used to execute step 206 in this application embodiment.

[0090] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments.

[0091] According to another aspect of the embodiments of this application, this application provides an electronic device, such as... Figure 5 As shown, the system includes a memory 501, a processor 502, a communication interface 503, and a communication bus 504. The memory 501 stores a computer program that can run on the processor 502. The memory 501 and the processor 502 communicate through the communication interface 503 and the communication bus 504. When the processor 502 executes the computer program, it implements the steps of the above method.

[0092] The memory and processor in the aforementioned electronic devices communicate with each other via a communication bus and a communication interface. The communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0093] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0094] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0095] According to another aspect of the embodiments of this application, a computer-readable medium having processor-executable non-volatile program code is also provided.

[0096] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0097] In specific implementation, the embodiments of this application can be referred to the above embodiments and have corresponding technical effects.

[0098] It is understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described herein, or combinations thereof.

[0099] For software implementation, the techniques described herein can be implemented by units that perform the functions described herein. The software code can be stored in memory and executed by a processor. The memory can be implemented in the processor or external to the processor.

[0100] 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 in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0101] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0102] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0103] 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; that is, 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.

[0104] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0105] If the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks. It should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. In the absence of further restrictions, an element defined by the phrase "comprising a..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0106] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A method for stabilizing and controlling risk preference parameters, applied to rock mass support systems, characterized in that, include: Obtain the risk utility value and construction status information of the current support scheme, wherein the risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on construction monitoring samples, and the risk utility value is used to characterize the risk level of the current support scheme; The applicable parameter boundaries and minimum update time interval are determined based on the construction status information. Based on the risk utility value, the construction status information, and the minimum update time interval, determine whether the preset triggering conditions are met. If the preset triggering condition is met, a first adjustment amount is calculated for the current first risk preference parameter based on the risk utility value, and the first adjustment amount is limited to a preset range to obtain a second adjustment amount. The second adjustment amount is added to the first risk preference parameter, and the result is restricted within the parameter boundary to obtain the second risk preference parameter; The second risk preference parameter is subjected to stability verification, and if the stability verification passes, the second risk preference parameter is output as the target risk preference parameter after stability control.

2. The method according to claim 1, characterized in that, The process of obtaining the risk utility value of the current support plan includes: Collect construction monitoring data during the construction process, wherein the construction monitoring data is multi-dimensional raw data used to evaluate the implementation effect of the support scheme; The construction monitoring data is quantified to obtain a return sample set; The return values ​​of each return sample in the return sample set are converted into subjective utility values ​​using a piecewise power function, resulting in a set of subjective utility values. The risk utility value is obtained by performing discrete approximation calculations on the set of subjective utility values.

3. The method according to claim 2, characterized in that, The step of performing discrete approximation calculations on the set of subjective utility values ​​to obtain the risk utility value includes: The subjective utility values ​​in the set of subjective utility values ​​are sorted in ascending order, and the sorted subjective utility values ​​are used as segmentation nodes. A segmentation interval is formed between two adjacent segmentation nodes, and each segmentation interval corresponds to the segmentation node at its left endpoint. For each segment node, the proportion of subjective utility values ​​that are greater than the segment node is counted to determine the empirical probability corresponding to the segment node; The empirical probabilities are nonlinearly distorted to obtain the weighted probabilities corresponding to each segment node. The risk utility value is obtained by multiplying the weighted probability of each segment node by the length of the corresponding segment interval and summing the results.

4. The method according to claim 1, characterized in that, The step of determining the currently applicable parameter boundaries and minimum update time interval based on the construction status information includes: Read the current construction stage label and the current risk level label from the construction status information; Based on the current construction stage label and the current risk level label, the lower limit value of the parameter, the upper limit value of the parameter, and the minimum update time interval are determined by a preset mapping rule, wherein the mapping rule defines the correspondence between the construction stage and risk level and the lower limit value of the parameter, the upper limit value of the parameter, and the minimum update time interval; Configure the lower limit value and the upper limit value of the parameter as the parameter boundary.

5. The method according to claim 4, characterized in that, The step of determining the lower limit value of the parameter, the upper limit value of the parameter, and the minimum update time interval through a preset mapping rule includes: Determine whether the current construction stage label belongs to the target stage label set to obtain a first determination result, and determine whether the current risk level label belongs to the high risk level label set to obtain a second determination result, wherein the target stage label set includes labels for high risk stages and important process stages; When the first judgment result is yes, and / or the second judgment result is yes, the first lower limit value is used as the lower limit value of the parameter, the first upper limit value is used as the upper limit value of the parameter, and the first time interval is used as the minimum update time interval; When the first judgment result is negative and the second judgment result is negative, the second lower limit value is used as the lower limit value of the parameter, the second upper limit value is used as the upper limit value of the parameter, and the second time interval is used as the minimum update time interval, wherein the first lower limit value is greater than the second lower limit value, the first upper limit value is less than the second upper limit value, and the first time interval is greater than the second time interval.

6. The method according to claim 1, characterized in that, The step of determining whether the preset triggering condition is met based on the risk utility value, the construction status information, and the minimum update time interval includes: Read the historical risk utility value of the previous period, calculate the change of the risk utility value compared with the historical risk utility value, and obtain the risk level change and abnormal monitoring signals from the construction status information; Based on the change range, the change in risk level, and the abnormal monitoring signal, it is determined whether the content triggering condition is met. The content triggering condition is met when at least one of the following situations occurs: the change range is greater than or equal to a preset threshold, the change in risk level indicates a change in the risk level, and the abnormal monitoring signal indicates that there is an abnormality during the construction process. If the content triggering condition is met, the last parameter update time is read, and the current time and the parameter update time are compared to determine whether the time triggering condition is met. The time triggering condition is that the time interval between the current time and the parameter update time is greater than or equal to the minimum update time interval. If the time triggering condition is met, then the preset triggering condition is determined to be met.

7. The method according to claim 1, characterized in that, After performing a stability check on the second risk preference parameter, the method further includes: If the stability check fails, the first risk preference parameter will be output as the target risk preference parameter. Record the reason why the stability check failed and the value of the second risk preference parameter, generate an anomaly record, and store the anomaly record in the database.

8. A risk preference parameter stabilization control device, applied to a rock mass support system, characterized in that, include: The acquisition module is used to acquire the risk utility value of the current support scheme and construction status information. The risk utility value is obtained by nonlinear mapping and discrete approximation calculation based on construction monitoring samples. The risk utility value is used to characterize the risk level of the current support scheme. The determination module is used to determine the currently applicable parameter boundaries and minimum update time interval based on the construction status information; The judgment module is used to determine whether the preset triggering conditions are met based on the risk utility value, the construction status information, and the minimum update time interval. The calculation module is used to calculate a first adjustment amount for the current first risk preference parameter based on the risk utility value when it is determined that the preset triggering condition is met, and to limit the first adjustment amount within a preset range to obtain a second adjustment amount; The processing module is used to add the second adjustment amount to the first risk preference parameter, and restrict the addition result within the parameter boundary to obtain the second risk preference parameter; The output module is used to perform stability verification on the second risk preference parameter, and if the stability verification passes, output the second risk preference parameter as the target risk preference parameter after stability control.

9. An electronic device comprising a memory, a processor, a communication interface, and a communication bus, wherein the memory stores a computer program executable on the processor, and the memory and the processor communicate via the communication bus and the communication interface, characterized in that... When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable medium having processor-executable non-volatile program code, characterized in that, The program code causes the processor to execute the method of any one of claims 1 to 7.

Images