A method for intelligently predicting the construction progress of a bent cap

Abstract

The application relates to the technical field of intelligent construction, and discloses a method for intelligently predicting the construction progress of a bent cap, which comprises the following steps: collecting multi-source real-time data of equipment, structures, personnel and environments in the construction process, and calculating construction entropy for measuring the uncertainty of a system; establishing a causal state evolution model to predict the evolution trend of the construction entropy in a future period; and when a construction progress disturbance risk is predicted, carrying out counterfactual reasoning based on the model or a sparse model obtained by dynamically pruning the model, and generating and recommending an optimized adaptive correction strategy. The application quantifies the overall uncertainty of a construction system as construction entropy, and combines the forward-looking reasoning capability of the causal state evolution model, so that the change from experience-dependent passive response to risk to data-driven proactive early warning and optimal decision recommendation is realized, and the scientificity, foresight and timeliness of construction risk management are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent construction, in particular to a method for intelligently predicting the construction progress of a bent cap. BACKGROUND

[0002] Bent cap intelligent lifting construction, as a key link of bridge and elevated structure upper structure installation, refers to the construction process of precisely and smoothly lifting the prefabricated or cast-in-place bent cap structure from the ground or low support to the design elevation by using an integrated control hydraulic synchronous lifting system. The process has high sensitivity to equipment synchronization, structure posture and construction environment.

[0003] The existing bent cap lifting construction progress monitoring technology mainly relies on the sensor array arranged at the key equipment and structure parts, acquires and displays the isolated physical quantity parameters such as the pressure, displacement of each jack, and the stress and inclination angle of the key section of the bent cap in real time, and alarms in combination with the preset single parameter safety threshold. The judgment of construction progress and risk state mainly relies on the manual interpretation and comprehensive experience of the on-site total control engineer on the discrete data.

[0004] Since the bent cap lifting construction is a complex dynamic system closely coupled by equipment, structure, personnel and environment, there is a complex nonlinear causal relationship between the monitoring data, which makes it difficult for the existing technology to understand the overall evolution trend of the system state from the massive and multi-source apparent data. Therefore, there are inherent defects such as serious lag in identifying construction risks, lack of forward-looking prediction ability of the future state of the system, and inability to quantitatively evaluate the overall uncertainty level of the system. This defect easily causes the gradual accumulation and amplification of minor construction disturbances due to the failure to be discovered and corrected in time, and eventually leads to serious lag in construction progress, structure damage and even safety accidents and other adverse consequences. SUMMARY

[0005] In view of the deficiencies of the prior art, the present application provides a method for intelligently predicting the construction progress of a bent cap intelligent lifting construction, aiming to solve the problem of lack of overall and forward-looking assessment of construction risks in the prior art, leading to lag in risk identification and lack of scientific correction decision basis.

[0006] To achieve the above purpose, the present application realizes the following technical solutions:

[0007] A method for intelligently predicting the construction progress of a bent cap intelligent lifting construction, comprising the following steps:

[0008] Collecting multi-source real-time data in the bent cap lifting construction process, and preprocessing the multi-source real-time data to obtain a standardized state data set;

[0009] constructing and calculating a construction entropy for measuring uncertainty of the construction system based on the standardized state dataset; the construction entropy is obtained by weighted summation of a device state entropy, a structure state entropy, a personnel state entropy and an environment state entropy through preset weight coefficients; the calculation method of any one of the device state entropy, the structure state entropy, the personnel state entropy and the environment state entropy comprises: in a sliding time window, for a plurality of parameters corresponding to the state entropy, calculating a deviation sequence of each parameter relative to a baseline value of the parameter; performing discretization processing on the deviation sequence to obtain a plurality of discrete state intervals; calculating a state probability of the deviation sequence in the plurality of discrete state intervals; and applying an information entropy formula to calculate a value of the state entropy according to the state probability;

[0010] establishing a causal state evolution model comprising observable variables, hidden variables and macro state variables, and using the model to deduce and predict an evolution trend of the construction entropy in a future period based on a current state of the construction system; the causal state evolution model is a directed acyclic graph, and a state transition function is used to describe a dynamic evolution mechanism of the graph, and the state transition function defines a specific conditional dependence function for each non-root node in the graph;

[0011] monitoring the value of the construction entropy and a change rate thereof in real time, and when the value of the construction entropy or the change rate thereof exceeds a preset threshold, performing dynamic pruning on the causal state evolution model to generate a sparse model focusing on a core causal path;

[0012] when the evolution trend of the construction entropy indicates a disturbance risk of the construction progress, performing counterfactual reasoning based on the causal state evolution model or the sparse model to generate an adaptive correction strategy capable of reducing the construction entropy in the future period, and the steps of generating the adaptive correction strategy comprise:

[0013] generating a candidate correction measure set matched with a current risk source from a preset correction measure knowledge base; performing forward reasoning on each measure in the candidate correction measure set using the causal state evolution model to respectively evaluate an expected evolution trend of the construction entropy after execution of the measure; and quantitatively evaluating expected correction effects and correction costs of the measures through a comprehensive utility function, and determining a candidate measure with a maximum comprehensive utility value as the adaptive correction strategy.

[0014] Preferably, the multi-source real-time data comprises:

[0015] device state data, structure state data, personnel operation data and environment state data.

[0016] Preferably, the steps of predicting and evaluating the disturbance risk of the construction progress comprise:

[0017] define a multi-dimensional composite discriminant criterion including the amplitude of entropy, the growth rate and the duration;

[0018] compare the construction entropy evolution trend with the multi-dimensional composite discriminant criterion to identify risks;

[0019] quantify the risk identification result into a progress disturbance probability value through a probability mapping model to determine the risk level.

[0020] An intelligent cap beam jacking construction progress intelligent prediction system comprises:

[0021] A data acquisition and preprocessing module is configured to acquire multi-source real-time data in a cap beam jacking construction process and preprocess the multi-source real-time data to obtain a standardized state data set.

[0022] A construction entropy calculation module is connected with the data acquisition and preprocessing module and configured to calculate a construction entropy for measuring construction system uncertainty based on the standardized state data set.

[0023] A model prediction module is connected with the construction entropy calculation module and configured to perform the construction entropy calculation step of claim 1, infer and predict a construction entropy evolution trend in a future period based on a current construction system state and the causal state evolution model.

[0024] A risk assessment module is connected with the model prediction module and configured to predict and assess a construction progress disturbance risk in the future period based on the construction entropy evolution trend.

[0025] A deviation correction decision module is connected with the risk assessment module and the model prediction module and configured to generate and recommend an optimized deviation correction decision based on the causal state evolution model when an assessment result of the construction progress disturbance risk exceeds a preset risk level.

[0026] The present application provides a cap beam intelligent jacking construction progress intelligent prediction method.

[0027] 1. The present application acquires four types of multi-source real-time data including equipment, structure, personnel and environment, and constructs a construction entropy index capable of comprehensively quantifying system uncertainty based on information entropy theory.

[0028] 2、The application predicts the construction entropy evolution trend of the future period by establishing a causal state evolution model containing observable variables, hidden variables and macro state variables, and using the model. This prediction mechanism based on causal relationship not only reveals the evolution path of the risk, but also identifies potential construction progress disturbance risks in advance, changes the risk management from passive response to proactive early warning, and saves valuable decision-making and intervention time for managers.

[0029] 3、When the construction progress disturbance risk is predicted, the causal state evolution model or the sparse model after dynamic pruning can be used to perform counterfactual reasoning to generate an adaptive correction strategy that can actively reduce the future construction entropy. This method replaces the emergency disposal mode that relies on artificial experience, and helps to improve the scientific nature, pertinence and effectiveness of the correction decision. BRIEF DESCRIPTION OF DRAWINGS

[0030] Figure 1 The method flowchart of the application is shown in the figure;

[0031] Figure 2 The construction entropy calculation process of the application is shown in the figure;

[0032] Figure 3 The causal state evolution model topology structure of the application is shown in the figure;

[0033] Figure 4 The system architecture of the application is shown in the figure. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the application will be described below with reference to the drawings in the application specification. Obviously, the described embodiments are only part of the embodiments of the application, not all embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application.

[0035] Referring to the drawings Figure 1 - the drawings Figure 3 , Figure 1 The cover beam intelligent lifting construction progress intelligent prediction method flowchart according to an embodiment of the application is shown in the figure. The application provides a cover beam intelligent lifting construction progress intelligent prediction method, which includes the following steps:

[0036] S10, collect multi-source real-time data in the cover beam lifting construction process, and pretreat the multi-source real-time data to obtain a standardized state data set;

[0037] S20, based on the standardized state data set, construct and calculate the construction entropy for measuring the uncertainty of the construction system;

[0038] S30, a causal state evolution model containing observable variables, latent variables and macro state variables is established, and based on the construction system state at the current moment, the model is used to deduce and predict the construction entropy evolution trend in the future period;

[0039] S40, the value of the construction entropy and its change rate are monitored in real time, and when the value of the construction entropy or its change rate exceeds the preset threshold, the causal state evolution model is dynamically pruned to generate a sparse model focusing on the core causal path;

[0040] S50, when the evolution trend of the construction entropy indicates that there is a disturbance risk in the construction progress, the counterfactual deduction is carried out based on the causal state evolution model or the sparse model, and an adaptive correction strategy capable of reducing the construction entropy in the future period is generated.

[0041] In order to make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described in detail below.

[0042] S10 step, that is, collecting multi-source real-time data in the process of lifting the cap beam, and preprocessing the multi-source real-time data to obtain a standardized state data set, specifically including the following sub-steps:

[0043] S101, through the data acquisition system deployed in the construction site, four types of original data reflecting the lifting construction state of the cap beam are obtained in real time. The multi-source real-time data specifically include but are not limited to:

[0044] Equipment state data: collected through sensors installed on the hydraulic pump station and each synchronous lifting jack. For example, the real-time pressure of the hydraulic main oil circuit and each branch oil circuit is obtained by using a pressure transmitter; the accurate extension amount of each jack piston is measured by using a linear variable differential transformer (LVDT) or a wire displacement sensor; and the temperature of the hydraulic oil and the key components of the equipment is monitored by using a thermocouple or a thermistor sensor.

[0045] Structure state data: collected through health monitoring sensors pre-deployed at key positions of the cap beam body. For example, the stress change of the key stress point of the cap beam in the lifting process is measured by using a resistance strain gauge; the attitude of the cap beam in space, including its absolute elevation, plane displacement and inclination, is monitored by using a static water level gauge or a laser range finder.

[0046] Personnel operation data: obtained by recording the operation log of the human-machine interface (HMI) or programmable logic controller (PLC) of the central control console. The data specifically include the timestamp of the operation instruction, the instruction type (such as start, pause, fine adjustment, stop), the instruction parameter (such as the target pressure value, the target displacement value) and the operator's cancellation or modification instruction record.

[0047] Environmental state data: collected by small weather stations or dedicated environmental sensors. For example, use anemometers to measure real-time wind speed and direction on site; use thermometers and hygrometers to measure ambient temperature and air humidity, respectively.

[0048] All the above raw data are continuously collected at a preset sampling frequency (e.g. 1 Hz) and transmitted to the central data server for storage through industrial wireless network or wired bus technology.

[0049] S102, perform preprocessing operations on the raw data stored in the central data server to generate standardized state data sets that can be directly used for subsequent entropy calculation and model input. The preprocessing operations include data cleaning, time series alignment and data normalization in turn.

[0050] Data cleaning aims to identify and process abnormal data in the raw data sequence. Specifically, the 3σ criterion can be used to judge the effectiveness of the data points, and the data points beyond the range of mean plus or minus three times the standard deviation are identified as outliers.

[0051] For the identified outliers or missing values caused by signal transmission interruption, linear interpolation or spline interpolation method can be used for filling to ensure the integrity of the data sequence.

[0052] Time series alignment aims to unify data streams from different sensors, with different sampling frequencies or transmission delays, to the same time reference. Specifically, a standard time interval (e.g. 1 second) is set, and all data sequences are aligned to the time points of the standard interval by resampling technology. For data with a sampling frequency higher than the standard interval, the mean or the last value within an interval can be taken as a representative; for data with a sampling frequency lower than the standard interval, the value of the previous valid data point can be used for filling.

[0053] Data normalization aims to eliminate the numerical differences caused by different physical units and dimensions of each state parameter, and map all data to a unified interval. Specifically, the min-max normalization method can be used to convert the original value of any parameter to a normalized value. The conversion formula is:

[0054] ;

[0055] In the formula, is the normalized parameter value; is the real-time measurement value of the parameter; is the minimum value of the parameter in historical data or the preset safe range; is the maximum value of the parameter in historical data or the preset safe range.

[0056] After normalization, the values of all parameters are mapped to the interval [0, 1] to form a final standardized state data set for subsequent steps S20 and S30.

[0057] In this embodiment, by systematically collecting four types of data of equipment, structure, personnel and environment on the construction site, and sequentially performing data cleaning, time alignment and normalization processing, the transformation of multi-source heterogeneous original monitoring data into standardized state data set is realized, which helps to lay a solid data foundation for the accurate quantification of subsequent construction entropy and reliable input of causal state evolution model.

[0058] S20, based on the standardized state data set, construction entropy is constructed and calculated to measure the uncertainty of the construction system, which includes the following sub-steps:

[0059] S201, define the composition of construction entropy. Construction entropy is a quantitative representation of the overall disorder or uncertainty of the construction system at a certain time. The construction entropy is obtained by weighting and summing the equipment state entropy, structure state entropy, personnel state entropy and environment state entropy through a preset weight coefficient. The relationship is determined by the following formula:

[0060] ;

[0061] In the formula, is the construction entropy; is the weight coefficient of the equipment state entropy; is the equipment state entropy; is the weight coefficient of the structure state entropy; is the structure state entropy; is the weight coefficient of the personnel state entropy; is the personnel state entropy; is the weight coefficient of the environment state entropy; is the environment state entropy.

[0062] The determination of the weight coefficients , , and is not arbitrary, but is determined by one or more systematic methods according to the risk characteristics of the specific project to ensure its objectivity and reasonableness.

[0063] One specific implementation is to use the analytic hierarchy process (AHP) to organize field experts to compare and score the contribution of equipment, structure, personnel and environment to the overall risk of construction, construct a judgment matrix, and obtain the weight of each factor by calculating the maximum eigenvalue and eigenvector of the matrix.

[0064] Another implementation is to quantify the contribution of each factor to the historical problem based on the failure or delay data of the historical similar projects through sensitivity analysis or regression analysis, and allocate the weight based on this.

[0065] S202, calculate each sub-state entropy. The calculation method of any one of the device state entropy, the structure state entropy, the personnel state entropy and the environment state entropy includes:

[0066] First, in the sliding time window, for the plurality of parameters corresponding to the state entropy, the deviation sequence of each parameter relative to its reference value is calculated. The reference value is determined according to the nature of the parameter, for example, for the pressure of the jack, the reference value is the target pressure set value under the current working condition; for the temperature of the hydraulic oil, the reference value is the median value of the ideal temperature interval of its normal working.

[0067] Second, the deviation sequence is discretized to obtain a plurality of discrete state intervals. That is, the continuous deviation value is mapped into k pre-set discrete state intervals. The specific implementation method of discretization includes but is not limited to: equal-width discretization, that is, the entire possible range of deviation value (for example, the normalized [0, 1] interval) is divided into k intervals with equal width; equal-frequency discretization, that is, the width of each interval is adjusted so that the number of data points falling into each interval is approximately equal; clustering algorithm-based discretization, for example, using K-means clustering algorithm, the deviation value data is automatically clustered into k clusters, and the range of each cluster is defined as a discrete state interval.

[0068] Third, the state probability of the deviation sequence in the plurality of discrete state intervals is calculated. That is, the frequency of the deviation value of each device parameter falling into the above K discrete state intervals in the time window is counted, and the state probability is calculated according to the frequency. For the i-th device parameter, the probability of the deviation value falling into the j-th state interval is determined by the frequency of the state divided by the total number of data points in the time window.

[0069] Finally, the information entropy formula is applied to calculate the value of the state entropy according to the state probability. That is, the information entropy of all device parameters in all discrete states is summed to obtain the total value of the device state entropy, and the formula is as follows:

[0070] ;

[0071] In the formula, is the device state entropy; is the index of the device parameter; is the total number of device monitoring parameters included in the calculation; is the index of the discrete state interval; is the total number of discrete state intervals; is the i-th device parameter; the probability of the deviation value of the equipment parameter falls in the first

[0072] For further clarification, the calculation process of other sub-state entropy also follows this methodology. For example, in the calculation of the structure state entropy, the reference value of the parameter deviation is derived from the theoretical stress or displacement calculation value of the finite element analysis (FEM) model for the current working condition.

[0073] In the calculation of the personnel state entropy, the deviation of the parameter (such as operation response time) is compared with the average response time of the operator executing the same type of instruction in normal, non-emergency state. In this way, the universality and effectiveness of the entropy calculation for various data sources are ensured.

[0074] S203, the four sub-state entropies calculated in S202 are substituted into the weighted summation formula defined in S201, thereby obtaining the construction entropy at the current time, which can comprehensively reflect the macro uncertainty level of the entire construction system. The construction entropy value will be a key dynamic indicator input into the subsequent S30 and S40 steps.

[0075] In this embodiment, by constructing multi-dimensional sub-state entropy and weighting and fusing it, a single, dynamic quantitative representation of the overall uncertainty of the complex construction system is achieved.

[0076] S30 step, i.e. establishing a causal state evolution model containing observable variables, hidden variables and macro state variables, and based on the current state of the construction system, using the model to deduce and predict the evolution trend of the construction entropy in the future period, which includes the following sub-steps:

[0077] S301, construct the static topology of the causal state evolution model. The causal state evolution model is mathematically defined as a directed acyclic graph, and the node set of the graph contains all key state variables representing the process of cap beam jacking construction. These variables are divided into three categories:

[0078] Observable variables, i.e. physical quantities that can be directly obtained by sensors, such as the pressure of a specific jack or the stress at a certain measuring point of the cap beam;

[0079] Hidden variables, i.e. potential factors that cannot be directly measured but have a key influence on the evolution of the system state, such as the cumulative wear degree of a specific device or the fatigue index of the operator, the value of these hidden variables can be estimated by weighted combination of multiple related observable variables or based on mechanism-based empirical model;

[0080] ​Macro state variables, i.e. the construction entropy and its four sub state entropies calculated in the preceding steps, which are used to represent the overall uncertainty of the system. The edge set of the graph represents the direct causal relationship between the node variables objectively existing. A directed edge from one node to another node represents that the former is the direct cause of the latter.

[0081] The topological structure of the causal graph can be combined in two ways:

[0082] Firstly, based on the knowledge of the field experts, the physical laws, process flow and management experience of the cap lifting construction are transformed into the initial causal network structure.

[0083] Secondly, the conditional independent relationship between variables is learned and verified from a large amount of state data accumulated in historical construction projects by applying causal discovery algorithms such as PC algorithm or LiNGAM algorithm, so as to modify and confirm the graph structure constructed by expert knowledge.

[0084] S302, define the dynamic evolution mechanism of the causal state evolution model. The causal state evolution model describes its dynamic evolution mechanism through a state transition function, which defines a specific conditional dependence function for each non-root node in the graph. The conditional dependence function includes at least one of an analytical model based on physical mechanism, a regression model based on data-driven or a conditional probability distribution based on probability theory, which defines the evolution law of the system state vector from the current time to the next time.

[0085] ;

[0086] In the formula, is the state vector of the system at the next time; is the state transition function; is the state vector containing the numerical values of all node variables in the graph at the current time; is the vector of external input or human intervention, such as a management instruction or a sudden environmental change; is the parameter set of the model.

[0087] The parameter set specifically defines the conditional dependence relationship of each node in the graph. For any node in the graph, its value at the next time is calculated by the values of all its parent nodes at the current time through a specific function. The specific function can be implemented in the following one or more ways according to the different properties of the causal relationship it describes:

[0088] Analytical model based on physical mechanism: for the causal relationship between variables with clear physical law, the function is an analytical expression. For example, in the calculation of the stress of the cap beam at a certain measuring point, the corresponding function can be a response surface model or a simplified mechanics equation based on structural mechanics theory, and the input of this equation is the real-time pressure of each jack, which is the parent node.

[0089] The above model can be simulated and calibrated in advance by finite element analysis software to obtain accurate function form and parameters.

[0090] Regression model based on data-driven: for the causal relationship with complex or difficult to accurately model physical mechanism, the function is a statistical regression model learned from historical data. For example, in the estimation of the hidden variable "operator fatigue index", the corresponding function can be a multivariate nonlinear regression model, such as a multilayer perceptron neural network with continuous working time of the operator, instruction modification frequency, etc. as input. The weights and biases of this neural network, that is, the model parameters obtained by training on historical operation log data.

[0091] Conditional probability distribution based on probability theory: when the model is constructed as a Bayesian network, the function is a conditional probability distribution. For example, the conditional probability distribution of the node "hydraulic system state" (which can take discrete states such as "normal", "mild abnormality", "serious abnormality", etc.) defines the probability of the node being in each of its discrete states given that its parent nodes "hydraulic oil temperature" and "main pump outlet pressure" are in different state intervals. In this case, the value of the node at the next time step will be determined by random sampling according to this conditional probability distribution.

[0092] S303, forward reasoning based on the causal state evolution model to predict the construction entropy evolution trend in the future period, and the prediction process takes the system state vector obtained after the aforementioned step as the initial condition.

[0093] Subsequently, by iteratively applying the state transition function defined in S302, the predicted state vector sequence at multiple future time steps is calculated in turn. Since the construction entropy is a component of the state vector, the construction entropy prediction value sequence at multiple future time steps is also obtained in the prediction sequence. This sequence is a quantitative prediction of the evolution trend of the construction system uncertainty in the future period, which will be passed to the subsequent step as the basis for risk judgment and correction decision.

[0094] By constructing a causal relationship network that combines expert knowledge and data-driven and defining a rigorous state transition function, the embodiment realizes the conversion of discrete and multi-dimensional construction state data into a system evolution model that can be dynamically and prospectively deduced, which helps to provide a solid model foundation for subsequent construction progress disturbance risk prediction and intelligent rectification decision-making.

[0095] S40, i.e., based on the construction entropy evolution trend, predicting and evaluating the construction progress disturbance risk in the future period, specifically including the following sub-steps:

[0096] S401, defining a composite criterion for construction progress disturbance risk. The criterion is not based on a single threshold, but is comprehensively judged by a multi-dimensional condition set including the amplitude, growth rate and duration of entropy.

[0097] Specifically, when the future construction entropy evolution trend predicted in S30 step meets any of the following conditions, it is determined that there is a construction progress disturbance risk in the future:

[0098] Amplitude over-limit criterion: the value of the predicted construction entropy at a certain time in the future exceeds the maximum safety entropy threshold representing the absolute unacceptable state of the system.

[0099] Growth rate over-limit criterion: the growth rate of the predicted construction entropy in a certain period in the future exceeds the critical growth rate threshold representing the rapid deterioration of system stability.

[0100] Continuous anomaly criterion: the value of the predicted construction entropy is continuously higher than a warning entropy threshold representing the non-ideal state of the system for a continuous period of time in the future, and the duration exceeds the maximum tolerance duration.

[0101] The maximum safety entropy threshold, critical growth rate threshold, warning entropy threshold and maximum tolerance duration are all pre-set according to the safety data statistics of similar historical projects, simulation experiment results and the experience of experts in the field, and stored in the system configuration library.

[0102] S402, based on the predicted construction entropy sequence, perform prospective risk identification, first, the system obtains the construction entropy prediction value sequence of multiple time steps in the future from S30 step.

[0103] Subsequently, the system analyzes each predicted value and its trend in the sequence one by one, and compares it with the composite discrimination criterion defined in S401 in real time. Once it is found that any one of the time points or time periods in the sequence meets any of the above amplitude overrun, growth rate overrun or continuous anomaly criteria, the system generates a construction progress disturbance risk warning signal. The signal not only identifies the existence of the risk, but also records the specific criterion type that triggered the warning and the future time point at which the risk is expected to occur; in this step, when the value of the construction entropy or its change rate exceeds the preset threshold, the causal state evolution model is dynamically pruned to generate a sparse model focusing on the core causal path.

[0104] S403, the identified risk is quantitatively evaluated to determine its severity level, in order to avoid the information loss caused by simple binary (yes / no risk) judgment, further introducing the calculation of progress disturbance probability to quantify the risk, which can be realized by a pre-trained probability mapping model, the formula is as follows:

[0105] ;

[0106] In the formula, is the predicted construction progress disturbance probability, whose value range is [0, 1]; is the index of the discrimination criterion, corresponding to the amplitude, growth rate and duration three criteria respectively; is the weight coefficient corresponding to the th criterion, reflecting the contribution of the criterion to the overall risk; is the normalized overrun amount of the th criterion, for example, for the amplitude criterion, the overrun amount is the degree of the predicted entropy value exceeding the maximum safe entropy threshold; is a calibration constant used to adjust the decision boundary of the function.

[0107] The progress disturbance probability value obtained by calculation can be used to classify the risk, for example, the probability value above 0.75 is defined as "high risk" and needs immediate intervention; the probability value between 0.5 and 0.75 is defined as "medium risk" and needs attention; the probability value below 0.5 is defined as "low risk" and only needs routine monitoring.

[0108] In this embodiment, by setting the multi-dimensional composite discrimination criterion of the amplitude, growth rate and duration of the entropy, and using the predicted construction entropy evolution trend for forward-looking evaluation, the automatic identification and quantitative evaluation of the future construction progress disturbance risk are realized, which helps to change the risk management from post-response to pre-warning, and provides accurate trigger time and risk level basis for subsequent rectification decision-making.

[0109] S50, when a construction progress disturbance risk is predicted, generating and recommending an optimized correction decision, including the following sub-steps:

[0110] S501, based on the pre-set correction measure knowledge base, generating a candidate correction measure set. The correction measure knowledge base is a structured database that pre-stores standardized operation procedures verified for different risk sources. The construction of this knowledge base is based on construction design specifications, emergency plans, and historical experience of field experts.

[0111] When S40 outputs a specific risk warning signal (for example, "high risk" warning caused by "specific jack pressure anomaly"), the system will automatically retrieve and match all correction measures related to the risk source from the knowledge base, generating a candidate correction measure set matched with the current risk source. For example, for pressure anomaly, candidate measures can include:

[0112] "Reduce the loading rate of all jacks by 20%", "suspend construction and check the pressure sensor", "perform a micro-unloading operation on the jack with pressure anomaly", etc.

[0113] S502, using the causal state evolution model, forward deduce each measure in the candidate correction measure set to evaluate the expected construction entropy evolution trend after its execution. For each candidate measure, the system inputs it as a new external intervention vector into the causal state evolution model established in S30.

[0114] Subsequently, with the current system state as the initial condition, the model will reiterate the calculation to generate a new construction entropy evolution prediction trajectory in the future period after the execution of the measure. This process is equivalent to a "virtual execution" or "digital twin" simulation of each candidate measure.

[0115] S503, through a comprehensive utility function, quantitatively evaluate the expected correction effect and correction cost of each measure, and determine the optimal correction decision. The comprehensive utility function aims to score each predicted entropy evolution trajectory from the pros and cons of the correction effect and the high and low of the correction cost. A specific utility function can be defined as:

[0116] ;

[0117] Where, is the comprehensive utility value of the candidate measure ; and are the weight coefficients representing the correction effect and the correction cost, respectively; is the predicted time range; a reference entropy value representing an ideal stable state (usually a small value close to zero); to execute the measure at a future time the predicted construction entropy value; to execute the measure the cost it will bring, which can comprehensively consider the time required for operation, resource consumption, and potential impact on the total construction period.

[0118] The system will calculate the corresponding comprehensive utility value for each candidate measure. The higher the utility value, the more theoretically capable the measure is to suppress the future uncertainty of the system (construction entropy) at a lower cost, faster and more effectively to the ideal level.

[0119] S504, the candidate measure with the maximum comprehensive utility value is output and recommended as an adaptive correction strategy, the system will calculate the measure with the highest utility value, package it into a clear and executable instruction, and present it to the operator in the field control room through the human-machine interface (HMI).

[0120] The recommended information not only contains specific operation content (for example, "it is recommended to reduce the loading rate of No. 2 and No. 3 jacks by 15%"), but also includes its expected correction effect (for example, "it is expected to reduce the construction entropy to below the warning threshold within 5 minutes") and the corresponding risk assessment (for example, "the operation has minimal impact on the total construction period"), thereby providing comprehensive and transparent decision support for the operator.

[0121] In this embodiment, by constructing a correction measure knowledge base and using the causal state evolution model to perform forward reasoning and utility evaluation on candidate measures, an intelligent and optimized correction decision recommendation from risk warning is realized, which helps to combine human experience with precise model calculation, improves the scientificity and effectiveness of emergency response, and ultimately forms a closed-loop control of construction risk management.

[0122] Referring to the accompanying Figure 4 , the present application provides a cap beam intelligent jacking construction progress intelligent prediction system, comprising:

[0123] A data acquisition and preprocessing module is used to acquire multi-source real-time data in the cap beam jacking construction process and preprocess the multi-source real-time data to obtain a standardized state data set.

[0124] A construction entropy calculation module is connected with the data acquisition and preprocessing module and is used to calculate the construction entropy for measuring the uncertainty of the construction system based on the standardized state data set.

[0125] The model prediction module is connected with the construction entropy calculation module, is used for establishing a causal state evolution model, and is used for deducing and predicting the construction entropy evolution trend in a future period based on the current time construction system state by using the causal state evolution model;

[0126] The risk assessment module is connected with the model prediction module, is used for predicting and evaluating the construction progress disturbance risk in the future period based on the construction entropy evolution trend;

[0127] The rectification decision module is connected with the risk assessment module and the model prediction module, is used for generating and recommending the optimized rectification decision based on the causal state evolution model when the evaluation result of the construction progress disturbance risk exceeds the preset risk level.

Claims

1. A method for intelligently predicting the progress of a bent cap intelligent jacking construction, characterized in that, The method comprises the following steps: Collecting multi-source real-time data in the process of the lifting of the bent cap, and preprocessing the multi-source real-time data to obtain a standardized state data set; Based on the standardized state data set, a construction entropy for measuring the uncertainty of the construction system is constructed and calculated; the construction entropy is obtained by weighting and summing the equipment state entropy, the structure state entropy, the personnel state entropy and the environment state entropy through a preset weight coefficient; The calculation method of any one of the equipment state entropy, the structure state entropy, the personnel state entropy and the environment state entropy comprises: in a sliding time window, for a plurality of parameters corresponding to the state entropy, calculating the deviation sequence of each parameter relative to its reference value; the deviation sequence is discretized to obtain a plurality of discrete state intervals; the state probability of the deviation sequence in the plurality of discrete state intervals is counted; the value of the state entropy is calculated according to the state probability by applying the information entropy formula; A causal state evolution model including observable variables, hidden variables and macro state variables is established, and the model is used to deduce and predict the evolution trend of the construction entropy in the future period based on the current state of the construction system; the causal state evolution model is a directed acyclic graph, and a state transition function is used to describe the dynamic evolution mechanism of the graph, and the state transition function defines a specific conditional dependence function for each non-root node in the graph; The value and the change rate of the construction entropy are monitored in real time, and when the value or the change rate of the construction entropy exceeds a preset threshold, the causal state evolution model is dynamically pruned to generate a sparse model focusing on the core causal path; When the evolution trend of the construction entropy indicates that there is a disturbance risk in the construction progress, an adaptive correction strategy is generated based on the causal state evolution model or the sparse model, which can reduce the construction entropy in the future period, and the steps of generating the adaptive correction strategy comprise: From a preset correction measure knowledge base, a set of candidate correction measures matching the current risk source is generated; the causal state evolution model is used to forward deduce each measure in the set of candidate correction measures to evaluate the expected evolution trend of the construction entropy after the execution of each measure; and through a comprehensive utility function, the expected correction effect and the correction cost of each measure are quantitatively evaluated, and the candidate measure with the maximum comprehensive utility value is determined as the adaptive correction strategy.

2. The method according to claim 1, characterized in that, The multi-source real-time data comprises: Equipment state data, structure state data, personnel operation data and environment state data.

3. The method of claim 1, wherein, The steps of predicting and evaluating the construction progress disturbance risk comprise: Defining a multi-dimensional composite discrimination criterion including the amplitude, growth rate and duration of the entropy; Comparing the evolution trend of the construction entropy with the multi-dimensional composite discrimination criterion to identify the risk; Through a probability mapping model, the risk identification result is quantified as a progress disturbance probability value to determine the risk level.

4. A system for intelligently predicting the progress of a top-up construction of a bent cap, according to any one of claims 1-3, characterized in that, The method comprises: A data acquisition and preprocessing module for collecting multi-source real-time data in the process of the lifting of the bent cap, and preprocessing the multi-source real-time data to obtain a standardized state data set; The construction entropy calculation module is connected with the data acquisition and preprocessing module, calculates the construction entropy for measuring the uncertainty of the construction system based on the standardized state data set; The model prediction module is connected with the construction entropy calculation module, is used for executing the construction entropy calculation step in claim 1, and deduces and predicts the construction entropy evolution trend in the future period by using the causal state evolution model based on the construction system state at the current time; The risk assessment module is connected with the model prediction module, is used for predicting and assessing the construction progress disturbance risk in the future period based on the construction entropy evolution trend; The rectification decision module is connected with the risk assessment module and the model prediction module, is used for generating and recommending the optimized rectification decision based on the causal state evolution model when the assessment result of the construction progress disturbance risk exceeds the preset risk level.

Images