Foundation pit support performance evaluation method and system based on data analysis
By filtering and feature extraction of real-time monitoring data of foundation pit support structure, optimizing parameters, and establishing a dynamic evaluation model, the problem of difficult analysis of data noise and nonlinear features in the existing technology is solved, and more accurate performance evaluation and Structural optimization improves construction efficiency and safety.
Patent Information
- Application Number
- CN202410305284.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-18
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-03-18
AI Technical Summary
The existing foundation pit support performance evaluation technology is difficult to effectively analyze when there are noise and complex nonlinear features in the data, which affects the accuracy and reliability of the evaluation results, and makes it difficult to optimize parameters targeted, limiting structural performance and construction efficiency. Improvement.
Using data analysis-based methods, through real-time monitoring of data filtering and denoising processing, signal characteristics are extracted, evaluation rules are designed, key parameters are optimized, dynamic evaluation models are established, and evaluation parameters are adjusted. Strategy.
It improves the accuracy and efficiency of performance evaluation of foundation pit support structures, can effectively identify periodic changes and abnormal fluctuations, optimize key parameters, improve structural performance, and provide real-time performance evaluation and safety monitoring to predict future risks and performance changes.
Smart Images

Figure CN118133672B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of foundation pit support performance evaluation, and in particular to a foundation pit support performance evaluation method and system based on data analysis. Background Art
[0002] The technical field of foundation pit support performance evaluation involves the systematic evaluation of the support structure of the foundation pit in civil engineering to ensure construction safety and engineering stability. The field includes the analysis and evaluation of the stability of the foundation pit slope, the strength and durability of the support structure, and the impact of the surrounding environment. The current foundation pit support performance evaluation not only relies on traditional engineering experience and physical testing, but also includes the collection and analysis of complex data to provide more accurate and real-time evaluation results.
[0003] The foundation pit support performance evaluation method based on data analysis is a method that uses data analysis techniques, such as machine learning, big data analysis, etc., to improve the accuracy and efficiency of foundation pit support performance evaluation. The purpose is to identify potential risk points and weaknesses of support structures by analyzing batch data collected from multiple sources (including geological data, construction process data, real-time monitoring data, etc.), and prevent accidents and problems from occurring in the early stages of construction.
[0004] Although existing technologies have improved the accuracy and efficiency of foundation pit support performance evaluation through complex data collection and analysis methods, it is difficult to effectively analyze the data when the data contains a lot of noise or needs to process complex nonlinear characteristics, which affects the accuracy and reliability of the evaluation results. In addition, although existing technologies use data analysis technology to improve the efficiency of foundation pit support performance evaluation, in actual applications, even if potential risk points or weaknesses in the support structure are identified, it is difficult to effectively optimize parameters in a targeted manner, which limits the ability to improve structural performance and construction efficiency. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings existing in the prior art and to propose a foundation pit support performance evaluation method and system based on data analysis.
[0006] In order to achieve the above-mentioned object, the present invention adopts the following technical scheme: a foundation pit support performance evaluation method based on data analysis, comprising the following steps;
[0007] S1: Collect real-time monitoring data of foundation pit support structures, including displacement, stress and temperature, filter and denoise the data, analyze the time series characteristics of the data, and obtain the processed monitoring data set;
[0008] S2: performing waveform analysis on the processed monitoring data set, extracting characteristic frequency and amplitude in the signal, identifying periodic changes and abnormal fluctuations in the data, and obtaining signal feature extraction results;
[0009] S3: Based on the signal feature extraction results, an evaluation rule is designed, including monitoring data change trends and threshold settings, to determine the state of the foundation pit support structure and obtain an initial state evaluation result;
[0010] S4: using the initial state assessment result, by simulating the performance of the support structure under various working conditions, adjusting key parameters, optimizing the parameters, and obtaining optimized parameter settings;
[0011] S5: combining the optimized parameter settings and the real-time monitoring data of the foundation pit support structure, analyzing and matching various environments and state changes, adjusting the evaluation criteria and logic, and performing real-time performance evaluation and safety monitoring to obtain a dynamic evaluation model;
[0012] S6: Apply the dynamic assessment model to continuously monitor and evaluate the foundation pit support structure, combine real-time data analysis with historical data comparison, predict the future performance of the structure, and adjust the assessment parameters and strategies accordingly to obtain performance prediction and assessment results.
[0013] The present invention has improvements in that the processed monitoring data set includes processed displacement amplitude, stress change value after removing environmental interference, and corrected temperature fluctuation data; the signal feature extraction result includes key frequency points of the vibration mode, amplitude spectrum of energy distribution, and identified non-periodic abnormal vibration sequence; the initial state evaluation result includes stability level based on change trend analysis, risk area exceeding a predetermined threshold and sensitive indicator set that needs to be monitored again; the optimized parameter setting includes adjusted support wall thickness, improved soil pressure distribution model, and selected temperature adjustment measures; the dynamic evaluation model includes adaptively adjusted evaluation frequency, safety threshold updated according to real-time data, and performance rating standard for multi-environment matching; the performance prediction and evaluation results include predicted displacement trend curve, location map of potential risk points and estimated value of effect of improvement measures.
[0014] The present invention is improved in that the specific steps of collecting real-time monitoring data of the foundation pit support structure, including displacement, stress and temperature, filtering and denoising the data, analyzing the time series characteristics of the data, and obtaining the processed monitoring data set are as follows;
[0015] S101: collecting real-time monitoring data of the foundation pit support structure, including displacement, stress and temperature data, filtering data beyond the measurement range and breakpoint data, and obtaining a filtered monitoring data set;
[0016] S102: filtering and denoising the screened monitoring data set to remove interference caused by the external environment or measurement errors, reflecting the current physical condition of the foundation pit support structure, and obtaining a denoised monitoring data set;
[0017] S103: Analyze the denoised monitoring data set to identify time series features in the data, including long-term trends, periodic changes and emergencies, and obtain a processed monitoring data set.
[0018] The present invention is improved in that the specific steps of performing waveform analysis on the processed monitoring data set, extracting characteristic frequency and amplitude in the signal, identifying periodic changes and abnormal fluctuations in the data, and obtaining the signal feature extraction result are as follows;
[0019] S201: Based on the processed monitoring data set, an empirical mode decomposition method is used to perform waveform analysis on the data, decompose multiple frequency components and quantify their amplitudes, and a fuzzy reasoning method is combined to identify key frequencies and energy distributions of structural responses to obtain frequency and amplitude analysis results;
[0020] The empirical mode decomposition method is based on the formula:
[0021] Formula I
[0022] Calculate each intrinsic mode function and its corresponding trend term, combine fuzzy reasoning method, process the data generated by empirical mode decomposition, identify the key frequency and energy distribution of structural response, and generate frequency and amplitude analysis results;
[0023] in, is the total number of oscillation modes in the data set, For the Oscillation mode, is the frequency adjustment coefficient, which dynamically adjusts the frequency component of each intrinsic mode function according to the frequency characteristics of the signal. is the amplitude adjustment coefficient, which is adjusted according to the statistical characteristics of the signal amplitude. is the trend item, It is a data adaptive parameter that automatically adjusts according to the nonlinear characteristics and complexity of the data;
[0024] S202: extracting key frequency and amplitude values from the frequency and amplitude analysis results, identifying periodic changes and abnormal fluctuations in the data, marking abnormal data points indicating structural problems, and obtaining periodicity and abnormal fluctuation analysis results;
[0025] S203: Comprehensively utilizing the periodicity and abnormal fluctuation analysis results, re-analyze the periodic changes and abnormal fluctuations in the monitoring data set, identify structural performance changes or damage indicators, evaluate the stability and safety of the structure in combination with historical monitoring data, and obtain signal feature extraction results.
[0026] The present invention is improved in that, based on the signal feature extraction result, an evaluation rule is designed, including monitoring data change trend and threshold setting, to judge the state of the foundation pit support structure, and the specific steps of obtaining the initial state evaluation result are as follows;
[0027] S301: Based on the signal feature extraction result, a safety range of the monitoring index of the foundation pit support structure is selected, including the normal fluctuation range of displacement, stress and temperature, and a safety threshold of the index is set to obtain a safety threshold setting result;
[0028] S302: applying the safety threshold setting result, analyzing the processed monitoring data set, comparing the measured value of each indicator with its safety threshold, identifying the indicator that exceeds the safety range, classifying the current status of the foundation pit support structure, including normal, warning or over-limit, and obtaining the status classification analysis result;
[0029] S303: Based on the results of the condition classification analysis, the overall performance of the foundation pit support structure is comprehensively judged to reflect the stability and risk level of the structure under the current monitoring conditions, and an initial state assessment result is obtained.
[0030] The present invention is improved in that the initial state evaluation result is used to simulate the performance of the support structure under various working conditions, and the parameters are optimized for adjusting key parameters. The specific steps for obtaining the optimized parameter settings are as follows;
[0031] S401: using the initial state assessment result as a reference, designing a multi-condition simulation test, including simulating the influence of various loads, temperature changes and water level changes on the support structure, monitoring the response of the structure through the simulation test, and obtaining the simulation test result;
[0032] S402: using a sensitivity analysis method to analyze the sensitivity of the support structure to various conditions from the simulation test results, identifying parameters that affect the structural performance, including the thickness of the support structure, the type of materials used, and the construction method, using a differential evolution algorithm to refine and adjust the parameters, and re-simulating and testing the effect of the adjustment to obtain sensitivity analysis results of key parameters;
[0033] The sensitivity analysis method is based on the formula:
[0034] Formula II
[0035] Calculate the impact of each input parameter on the output result and generate a sensitivity index based on the complexity and priority of the parameters;
[0036] in, is the sensitivity index, Var\left [ {E(Y\left | {{X}_{i}} \right |)} \right ] For a given input parameter Output results The conditional expected variance of is the weight coefficient of parameter complexity scoring, which is determined through statistical analysis of parameter complexity scoring and expert experience. For parameters The complexity score of is the weight coefficient of the parameter performance priority, which is determined by comprehensive evaluation of the parameter's historical performance data. The performance priority of the parameter in the previous project, To output the result The total variance of
[0037] The differential evolution algorithm is based on the formula:
[0038] Formula III
[0039] Adjust key parameters with reference to dynamic adjustment factors to obtain optimized parameter settings;
[0040] in, For the next generation The parameter vector of each individual, For the current generation The parameter vector of each individual, is the scaling factor, is the parameter vector of two difference individuals randomly selected from the current generation, is the weight coefficient of the dynamic adjustment factor, which is determined by analyzing the dynamic change trend of the parameter. Based on the current parameters Dynamic adjustment factor of
[0041] S403: Based on the sensitivity analysis results of the key parameters, the parameter settings are optimized through iterative simulation and analysis, and the influence of each indicator on the structural stability and safety is comprehensively referred to, and the parameter configuration is adjusted and selected to obtain the optimized parameter settings.
[0042] The present invention is improved in that the specific steps of combining the optimized parameter settings and the real-time monitoring data of the foundation pit support structure, analyzing and matching a variety of environmental and state changes, adjusting the evaluation criteria and logic, and performing real-time performance evaluation and safety monitoring to obtain a dynamic evaluation model are as follows;
[0043] S501: combining the optimized parameter settings and the real-time monitoring data of the foundation pit support structure, analyzing the performance of the foundation pit support structure in the current environment and multiple states, matching the impact of environmental changes on structural performance, and obtaining environmental impact analysis results;
[0044] S502: According to the environmental impact analysis results, the evaluation criteria and logic are adjusted to match the performance changes of the foundation pit support structure shown by the monitoring data, reflect the structural status, and obtain the adjusted evaluation criteria;
[0045] S503: Apply the adjusted evaluation standard to conduct real-time performance evaluation and safety monitoring of the foundation pit support structure, update the evaluation results in real time to reflect the current structural status and safety situation, and obtain a dynamic evaluation model.
[0046] The present invention is improved in that the dynamic evaluation model is applied to continuously monitor and evaluate the foundation pit support structure, and the future performance of the structure is predicted by combining real-time data analysis with historical data comparison, and the evaluation parameters and strategies are adjusted accordingly. The specific steps of obtaining the performance prediction and evaluation results are as follows;
[0047] S601: Utilizing the dynamic evaluation model, continuously monitoring and evaluating the foundation pit support structure, analyzing real-time data and historical data, identifying the change trend of structural performance and potential problem points, and obtaining performance change trend analysis results;
[0048] S602: Based on the performance change trend analysis results, predict the future performance of the foundation pit support structure, including future risks and changes in structural performance, perform risk assessment and performance prediction, and obtain risk and performance prediction analysis results;
[0049] S603: According to the risk and performance prediction analysis results, the evaluation parameters and strategies are adjusted to cope with future environmental changes and structural status, the dynamic evaluation model is cyclically updated, and continuous performance monitoring and risk evaluation are performed to obtain performance prediction and evaluation results.
[0050] A foundation pit support performance evaluation system based on data analysis, the system comprising a data acquisition and processing module, a waveform analysis module, an evaluation rule design module, a parameter optimization simulation module, a dynamic evaluation logic adjustment module, a performance monitoring and prediction module, and an evaluation parameter adjustment module;
[0051] The data acquisition and processing module collects monitoring data of the foundation pit support structure, performs data screening to exclude data beyond the measurement range and breakpoint data, performs data filtering and denoising, reflects the physical condition of the foundation pit support structure, analyzes the time series characteristics of the data, and obtains the processed monitoring data set;
[0052] The waveform analysis module performs waveform analysis on the processed monitoring data set, decomposes multiple frequency components and quantifies their amplitudes, identifies key frequencies and energy distributions of structural responses, extracts characteristic frequencies and amplitude values therefrom, marks periodic changes and abnormal fluctuations in the data, and generates signal feature extraction results;
[0053] The evaluation rule design module uses the signal feature extraction results to select the safety range of the monitoring indicators, set the safety threshold, analyze the processed monitoring data set, identify the indicators that exceed the safety range, classify the current status of the foundation pit support structure, and construct the initial state evaluation results;
[0054] The parameter optimization simulation module designs multi-condition simulation tests based on the initial state assessment results, including the effects of load, temperature change and water level change, monitors the response of the structure through simulation tests, analyzes the sensitivity of the support structure from the simulation test results, adjusts key parameters, and establishes optimized parameter settings;
[0055] The dynamic evaluation logic adjustment module combines the optimized parameter settings and the monitoring data of the foundation pit support structure to analyze the performance of the foundation pit support structure in various environments and states, adjust the evaluation criteria and logic, and generate a dynamic evaluation model;
[0056] The performance monitoring and prediction module applies a dynamic evaluation model, combines real-time data and historical data analysis, identifies the changing trend of structural performance and potential problem points, conducts risk assessment and performance prediction, and obtains performance prediction and evaluation results;
[0057] The evaluation parameter adjustment module adjusts the evaluation parameters and strategies according to the performance prediction and evaluation results, copes with future environmental changes and structural states, and constructs updated evaluation parameters and strategies.
[0058] Compared with the prior art, the advantages and positive effects of the present invention are:
[0059] In the present invention, through the use of technologies such as empirical mode decomposition and fuzzy reasoning, periodic changes and abnormal fluctuations can be effectively identified, and the evaluation of the performance changes of the foundation pit support structure is more accurate. The key parameters affecting the performance of the foundation pit support are identified and optimized through sensitivity analysis, which not only improves the structural performance but also optimizes the construction efficiency. In addition, through the dynamic evaluation model, combined with real-time and historical monitoring data, it not only provides instant performance evaluation and safety monitoring, but also predicts future risks and performance changes, providing a basis for adjusting evaluation parameters and strategies. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 A flow chart of a foundation pit support performance evaluation method based on data analysis is proposed for the present invention;
[0061] Figure 2 A schematic diagram of a detailed flow chart of step S1 in a foundation pit support performance evaluation method based on data analysis proposed in the present invention;
[0062] Figure 3 A schematic diagram of a detailed process of step S2 in a foundation pit support performance evaluation method based on data analysis proposed in the present invention;
[0063] Figure 4 A detailed flow chart of step S3 in the foundation pit support performance evaluation method based on data analysis proposed in the present invention;
[0064] Figure 5 A detailed flow chart of step S4 in the foundation pit support performance evaluation method based on data analysis proposed in the present invention;
[0065] Figure 6 A detailed flow chart of step S5 in the foundation pit support performance evaluation method based on data analysis proposed in the present invention;
[0066] Figure 7 A detailed flow chart of step S6 in the foundation pit support performance evaluation method based on data analysis proposed in the present invention;
[0067] Figure 8 A module diagram of a foundation pit support performance evaluation system based on data analysis is proposed for the present invention. DETAILED DESCRIPTION
[0068] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0069] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example
[0070] See also Figure 1 ,The present invention provides a technical solution: a foundation pit support performance evaluation method based on data analysis, comprising the following steps;
[0071] S1: Collect real-time monitoring data of foundation pit support structures, including displacement, stress and temperature, filter and denoise the data, analyze the time series characteristics of the data, and obtain the processed monitoring data set;
[0072] S2: Perform waveform analysis on the processed monitoring data set, extract characteristic frequency and amplitude in the signal, identify periodic changes and abnormal fluctuations in the data, and obtain signal feature extraction results;
[0073] S3: Based on the signal feature extraction results, the evaluation rules are designed, including monitoring data change trends and threshold settings, to judge the state of the foundation pit support structure and obtain the initial state evaluation results;
[0074] S4: Using the initial state assessment results, by simulating the performance of the support structure under various working conditions, the key parameters are adjusted and optimized to obtain the optimized parameter settings;
[0075] S5: Combine the optimized parameter settings with the real-time monitoring data of the foundation pit support structure, analyze and match various environments and state changes, adjust the evaluation criteria and logic, and conduct real-time performance evaluation and safety monitoring to obtain a dynamic evaluation model;
[0076] S6: Apply the dynamic assessment model to continuously monitor and evaluate the foundation pit support structure, combine real-time data analysis with historical data comparison to predict the future performance of the structure, and adjust the assessment parameters and strategies accordingly to obtain performance prediction and assessment results.
[0077] The processed monitoring data set includes the processed displacement amplitude, stress change value after removing environmental interference, and corrected temperature fluctuation data. The signal feature extraction results include the key frequency points of the vibration mode, the amplitude spectrum of the energy distribution, and the identified non-periodic abnormal vibration sequence. The initial state assessment results include the stability level based on the change trend analysis, the risk area exceeding the predetermined threshold, and the sensitive indicator set that needs to be monitored again. The optimized parameter settings include the adjusted support wall thickness, the improved soil pressure distribution model, and the selected temperature adjustment measures. The dynamic evaluation model includes the adaptively adjusted evaluation frequency, the safety threshold updated according to the real-time data, and the performance rating standard for multi-environment matching. The performance prediction and evaluation results include the predicted displacement trend curve, the location map of potential risk points, and the estimated effect of the improvement measures.
[0078] See also Figure 2 ,The specific steps of collecting real-time monitoring data of foundation pit support ,structure, including displacement, stress and temperature, filtering and denoising the data, analyzing the time series ,characteristics of the data, and obtaining the processed monitoring data set are as follows;
[0079] S101: collect real-time monitoring data of foundation pit support structure, including displacement, stress and temperature data, filter out data beyond the measurement range and breakpoint data, and obtain the specific process of the filtered monitoring data set as follows;
[0080] Sub-step S101 uses a data screening algorithm based on the data collected by the real-time monitoring instrument, uses the Python programming language combined with the Pandas library for data processing, organizes the data through DataFrame, uses the query method to screen the displacement, stress, and temperature data, sets the screening conditions to the data value within the set measurement range and without breakpoints, and generates a screened monitoring data set.
[0081] S102: filtering and denoising the screened monitoring data set to remove interference caused by the external environment or measurement errors, reflecting the current physical condition of the foundation pit support structure, and obtaining the denoised monitoring data set. The specific process is as follows;
[0082] In sub-step S102, based on the screened monitoring data set, signal processing methods are used, and the Python language is used in conjunction with the SciPy library to perform filtering and denoising operations. The Butterworth low-pass filter in the signal module is called, and filter parameters such as cutoff frequency and filter order are set. The filter is applied using the lfilter function to remove interference caused by the external environment or measurement errors, and generate a denoised monitoring data set.
[0083] S103: Analyze the denoised monitoring data set, identify the time series characteristics in the data, including long-term trends, periodic changes and emergencies, and obtain the processed monitoring data set. The specific process is as follows;
[0084] Sub-step S103 uses a time series analysis method based on the denoised monitoring data set, uses Python language combined with NumPy and Statsmodels libraries to perform operations, calls the ARIMA model to analyze the time series characteristics in the data, sets model parameters such as autoregressive terms, number of differences, and moving average terms, fits the model through the fit method, identifies long-term trends, cyclical changes, and emergencies in the data, and generates a processed monitoring data set.
[0085] See also Figure 3 ,The specific steps of performing waveform analysis on the processed monitoring data set to extract the characteristic frequency and amplitude in the signal, identifying the periodic changes and abnormal fluctuations in the data, and obtaining the signal feature extraction results are as follows;
[0086] S201: Based on the processed monitoring data set, the empirical mode decomposition method is used to perform waveform analysis on the data, decompose multiple frequency components and quantify their amplitudes, and combine the fuzzy reasoning method to identify the key frequencies and energy distribution of the structural response, and the specific process of obtaining the frequency and amplitude analysis results is as follows;
[0087] In sub-step S201, based on the processed monitoring data set, the empirical mode decomposition method is adopted. The Python language is used in conjunction with the NumPy library to perform empirical mode decomposition of the data. The data is decomposed into multiple intrinsic mode functions through the emd function, and a frequency range is set for each IMF. The instantaneous frequency and amplitude of each IMF are calculated using the Hilbert transform, and then multiple frequency components are decomposed and their amplitudes are quantified. The fuzzy reasoning method is adopted, and the fuzzy logic reasoning model is established using Matlab's FuzzyLogicToolbox. The membership function and rule set are defined, and the key frequency points and energy distribution obtained by the EMD method are analyzed. The key frequency and energy distribution of the structural response are judged through fuzzy logic reasoning, and the frequency and amplitude analysis results are generated.
[0088] The empirical mode decomposition method is based on the formula:
[0089] Formula I
[0090] Calculate each intrinsic mode function and its corresponding trend term, combine fuzzy reasoning method, process the data generated by empirical mode decomposition, identify the key frequency and energy distribution of structural response, and generate frequency and amplitude analysis results;
[0091] in, is the total number of oscillation modes in the data set, that is, the total number of intrinsic mode functions decomposed from the original signal. For the An oscillation mode represents a specific frequency component in the original signal. Combining the oscillation modes can reconstruct the original signal. The frequency adjustment coefficient is used to dynamically adjust the frequency component of each intrinsic mode function according to the frequency characteristics of the signal to improve the accuracy and adaptability of frequency analysis. It is the amplitude adjustment coefficient, which is adjusted according to the statistical characteristics of the signal amplitude. It is used to accurately represent the amplitude of the modal function and enhance the expressiveness of the amplitude analysis. It is the trend term, which represents the remaining part in the signal decomposition process and represents the long-term trend or low-frequency component of the signal. It is a data adaptive parameter that is automatically adjusted according to the nonlinear characteristics and complexity of the data. It is used to optimize the expression of trend terms and make the modal decomposition closer to the dynamic changes and structural characteristics of the actual signal.
[0092] The execution process is as follows:
[0093] Collect relevant signal data, including physical measurement displacement, velocity, acceleration, etc. Preprocess the signal, including filtering and denoising, to ensure data quality.
[0094] The preprocessed signal is decomposed into a series of intrinsic mode functions and a residual trend term using the empirical mode decomposition method to extract the different frequency components of the signal.
[0095] Determine adjustment parameters based on signal characteristics and requirements. , improving the accuracy and adaptability of signal analysis.
[0096] Further analysis of the adjusted intrinsic mode function and residual trend term, including amplitude and frequency analysis, is performed to identify key features in the signal.
[0097] The fuzzy reasoning method is used to analyze the results of empirical mode decomposition, and the key frequency points and energy distribution obtained are processed. The key frequency and energy distribution of the structural response are determined through fuzzy logic reasoning to generate frequency and amplitude analysis results.
[0098] S202: extract key frequency and amplitude values from the frequency and amplitude analysis results, identify periodic changes and abnormal fluctuations in the data, mark abnormal data points indicating structural problems, and obtain the specific process of periodicity and abnormal fluctuation analysis results as follows;
[0099] Based on the frequency and amplitude analysis results, sub-step S202 adopts a peak detection algorithm, uses Python language combined with the find_peaks function of the SciPy library, performs peak detection on the analysis results, sets minimum height and distance parameters to extract key frequency and amplitude values, identifies periodic changes and abnormal fluctuations in the data through peaks, marks abnormal data points indicating structural problems, and generates periodic and abnormal fluctuation analysis results.
[0100] S203: Comprehensively utilize the periodicity and abnormal fluctuation analysis results to re-analyze the periodic changes and abnormal fluctuations in the monitoring data set, identify structural performance changes or damage indicators, and evaluate the stability and safety of the structure in combination with historical monitoring data. The specific process of obtaining the signal feature extraction result is as follows;
[0101] Based on the results of periodicity and abnormal fluctuation analysis, sub-step S203 adopts time series analysis method, uses Python language combined with ARIMA model of Statsmodels library, and re-analyzes periodic changes and abnormal fluctuations. It sets the parameters of ARIMA model such as difference times, autoregressive terms and moving average terms, and combines historical monitoring data to evaluate the stability and safety of the structure by predicting future values through the model, identify changes in structural performance or damage indications, and generate signal feature extraction results.
[0102] See also Figure 4,Based on the signal feature extraction results, the evaluation rules are designed, including monitoring data change trends and threshold setting, to judge the state of the foundation pit support structure, and the specific steps to obtain the initial state evaluation results are as follows;
[0103] S301: Based on the signal feature extraction results, the safety range of the monitoring indicators of the foundation pit support structure is selected, including the normal fluctuation range of displacement, stress and temperature, and the safety threshold of the indicator is set. The specific process of obtaining the safety threshold setting result is as follows;
[0104] In sub-step S301, the safety threshold is set based on the signal feature extraction results. The data set is operated using Python language combined with the Pandas library. The distribution characteristics of displacement, stress and temperature, including mean and standard deviation, are statistically analyzed through the describe method of DataFrame. Based on the statistical results and engineering experience, the safety range of the monitoring indicators is set. The apply function of DataFrame is used to apply the safety range to each monitoring indicator, set the maximum and minimum safety thresholds for displacement, stress and temperature, and generate the safety threshold setting results.
[0105] S302: Apply the safety threshold setting result to analyze the processed monitoring data set, compare the measured value of each indicator with its safety threshold, identify the indicator that exceeds the safety range, and classify the current status of the foundation pit support structure, including normal, warning or over-limit. The specific process of obtaining the status classification analysis result is as follows;
[0106] Based on the safety threshold setting results, sub-step S302 analyzes the processed monitoring data set, uses Python language combined with the Numpy library to perform conditional judgment, compares the measured value of each indicator with its safety threshold through the logical_and and logical_or functions, identifies those indicators that exceed the safety range, and uses Pandas' groupby method to classify the monitoring data according to the situation that exceeds the safety range, classifies the current status of the foundation pit support structure as normal, warning or over-limit, and generates status classification analysis results.
[0107] S303: Based on the results of the condition classification analysis, the overall performance of the foundation pit support structure is comprehensively judged to reflect the stability and risk level of the structure under the current monitoring conditions. The specific process of obtaining the initial condition assessment result is as follows;
[0108] Based on the results of the condition classification analysis, sub-step S303 comprehensively judges the overall performance of the foundation pit support structure, uses Python language and Matplotlib library for visual analysis, and uses the plot function to draw a trend chart of the changes in each monitoring indicator over time. Combined with the threshold setting results and the condition classification analysis results, the stability and risk level of the structure under the current monitoring conditions are judged through logical reasoning, and a risk assessment chart is drawn to generate the initial state assessment results.
[0109] See also Figure 5 ,Using the initial state assessment results, by simulating the performance of the support structure under various working conditions, the key parameters are adjusted and the parameters are optimized. The specific steps for obtaining the optimized parameter settings are as follows;
[0110] S401: Using the initial state assessment results as a reference, design a multi-condition simulation test, including simulating the impact of various loads, temperature changes and water level changes on the support structure, and monitor the response of the structure through simulation tests. The specific process of obtaining the simulation test results is as follows;
[0111] Based on the initial state assessment results, sub-step S401 conducts multi-condition simulation test design, uses ANSYS software for structural simulation, sets up projects through the Workbench platform, introduces Geometry and StaticStructural analysis systems, configures material properties and boundary conditions, simulates the effects of various loads, temperature changes, and water level changes on the support structure, runs simulation tests through the Solution module, monitors the displacement, stress, and temperature data of the structural response, and generates simulation test results.
[0112] S402: Use sensitivity analysis method to analyze the sensitivity of the support structure to various conditions from the simulation test results, identify the parameters that affect the structural performance, including the thickness of the support structure, the type of materials used, and the construction method, use the differential evolution algorithm to refine and adjust the parameters, and re-simulate and test the effect of the adjustment. The specific process of obtaining the sensitivity analysis results of key parameters is as follows;
[0113] Based on the simulation test results, sub-step S402 adopts the sensitivity analysis method, uses MATLAB software to perform sensitivity analysis, calls the Sobol sequence functions sbolset and gSobol to perform global sensitivity analysis, analyzes the sensitivity of the support structure to various conditions, identifies key parameters affecting structural performance such as the thickness of the support structure, the type of materials used, and the construction method, uses the differential evolution algorithm, calls MATLAB's deoptim function to perform parameter optimization, sets differential evolution parameters such as population size and crossover probability, refines and adjusts key parameters, re-simulates to test the effect of the adjustment, and generates key parameter sensitivity analysis results.
[0114] Sensitivity analysis method, according to the formula:
[0115] Formula II
[0116] Calculate the impact of each input parameter on the output result and generate a sensitivity index based on the complexity and priority of the parameters;
[0117] in, is the sensitivity index, Var\left [ {E(Y\left | {{X}_{i}} \right |)} \right ] For a given input parameter Output results The conditional expected variance of , which represents the variability of the output with respect to specific parameters. The weight coefficient of the parameter complexity score is determined through statistical analysis of the parameter complexity score and expert experience, and is used to adjust the complexity score. Effects in the sensitivity index. For parameters The complexity score reflects the complexity or difficulty of adjusting the parameters in the model. The weight coefficient of the parameter performance priority is determined by comprehensive evaluation of the parameter's historical performance data and is used to adjust the performance priority. Effects in the sensitivity index. Prioritize the performance of parameters in previous projects based on an assessment of the parameter's historical performance or expected importance. To output the result The total variance of , which represents the total variability of the output results.
[0118] Differential evolution algorithm, according to the formula:
[0119] Formula III
[0120] Adjust key parameters with reference to dynamic adjustment factors to obtain optimized parameter settings;
[0121] in, For the next generation The parameter vector of each individual represents the new parameter set after adjustment and optimization. For the current generation The parameter vector of each individual represents the current parameter configuration. is a scaling factor, which is used to adjust the influence of the differential vector. is the parameter vector of two difference individuals randomly selected from the current generation, used to generate the difference vector. It is the weight coefficient of the dynamic adjustment factor, which is determined by analyzing the dynamic change trend of the parameter and is used to adjust the dynamic adjustment factor. The impact on parameter updating. Based on the current parameters The dynamic adjustment factor also refers to the impact of the current state of the parameter or environmental changes on the optimization direction.
[0122] The execution process is as follows:
[0123] Collect necessary input parameter data from real-time monitoring and historical data of foundation pit support structures, such as the thickness of the support structure, the type of material used, construction method, etc.
[0124] Each parameter is evaluated using Equation II Output (e.g. pit stability), with reference to the complexity score of the parameter , performance priority , and the corresponding weight coefficients and , identify the parameters that are most sensitive to the output results.
[0125] Determine the weight coefficients and in the sensitivity analysis method based on parameter complexity and historical performance.
[0126] Based on the sensitivity analysis results, the key parameters identified were optimized using Formula III.
[0127] The iterative process of the differential evolution algorithm is repeated until the set convergence criterion or the upper limit of the number of iterations is reached. In each iteration, the impact of the parameter setting on the performance of the foundation pit support structure is evaluated to ensure that the optimal parameter combination is found.
[0128] After the final parameter settings are determined, they are applied to the design or adjustment of the foundation pit support structure, the effect is monitored in real time, and the evaluation model is adjusted according to the actual performance to further improve the stability and safety of the foundation pit support structure.
[0129] S403: Based on the results of sensitivity analysis of key parameters, the optimization of parameter settings is performed through iterative simulation and analysis, and the influence of each indicator on structural stability and safety is comprehensively referred to, and the parameter configuration is adjusted and selected. The specific process of obtaining the optimized parameter settings is as follows;
[0130] In sub-step S403, based on the results of sensitivity analysis of key parameters, the optimal parameter settings are searched. The parameter optimization is performed using Python language combined with the minimize function in the SciPy library. The objective function is set to minimize the maximum displacement difference in the structural response. The Nelder-Mead method is used for iterative simulation and analysis. By adjusting parameters such as the thickness of the support structure, the type of material used, and the construction method, the impact of each indicator on the stability and safety of the structure is comprehensively evaluated. The optimal parameter configuration is adjusted and selected to generate the optimized parameter settings.
[0131] See also Figure 6 ,Combining the optimized parameter settings and the real-time monitoring data of the foundation pit support structure, analyzing and matching various environments and state changes, adjusting the evaluation criteria and logic, and conducting real-time performance evaluation and safety monitoring, the specific steps to obtain the dynamic evaluation model are as follows;
[0132] S501: Combine the optimized parameter settings and the real-time monitoring data of the foundation pit support structure, analyze the performance of the foundation pit support structure in the current environment and multiple states, match the impact of environmental changes on structural performance, and obtain the specific process of environmental impact analysis results;
[0133] In sub-step S501, based on the optimized parameter settings and real-time monitoring data of the foundation pit support structure, the environment and state changes are analyzed. The data are operated using Python language combined with Pandas and NumPy libraries. DataFrame is used to filter and analyze data sets under different environmental conditions, such as load, temperature changes, and water level changes. Conditional filtering technology is used to match the impact of environmental changes on structural performance. Linear regression analysis is performed to determine the correlation between environmental changes and structural performance, and environmental impact analysis results are generated.
[0134] S502: According to the results of the environmental impact analysis, the evaluation criteria and logic are adjusted to match the performance changes of the foundation pit support structure shown by the monitoring data, reflect the structural status, and obtain the specific process of the adjusted evaluation criteria;
[0135] The S502 sub-step adjusts the evaluation criteria and logic based on the results of the environmental impact analysis, uses the R language in conjunction with the Shiny application to build a dynamic evaluation tool, allows users to input different environmental change parameters through the UI interface, and the back-end logic adjusts the evaluation criteria and logic based on the input to match the performance changes of the foundation pit support structure shown by the monitoring data. The dynamic threshold adjustment algorithm is executed to automatically update the evaluation criteria to reflect the structural status and generate the adjusted evaluation criteria.
[0136] S503: Apply the adjusted evaluation criteria to conduct real-time performance evaluation and safety monitoring of the foundation pit support structure, update the evaluation results in real time to reflect the current structural status and safety situation, and obtain the specific process of the dynamic evaluation model as follows;
[0137] In sub-step S503, the adjusted evaluation criteria are applied to conduct real-time performance evaluation and safety monitoring of the foundation pit support structure. The real-time data analysis script is executed using MATLAB software, and the real-time monitoring data stream is read through the Simulink module. In combination with the adjusted evaluation criteria, dynamic system simulation is performed to analyze the current structural status and safety situation. The evaluation results are updated in real time using event listeners to generate a dynamic evaluation model.
[0138] See also Figure 7 ,The dynamic evaluation model is applied to continuously monitor and evaluate the foundation pit support structure, and the future performance of the structure is predicted by combining real-time data analysis with historical data comparison, and the evaluation parameters and strategies are adjusted accordingly. The specific steps to obtain the performance prediction and evaluation results are as follows;
[0139] S601: Use the dynamic assessment model to continuously monitor and evaluate the foundation pit support structure, analyze real-time data and historical data, identify the change trend of structural performance and potential problem points, and obtain the specific process of performance change trend analysis results as follows;
[0140] Based on the dynamic evaluation model, sub-step S601 continuously monitors and evaluates the foundation pit support structure, uses Python language combined with the Pandas library to process real-time data and historical data, merges real-time and historical data sets through the merge method of DataFrame, and uses rolling and expanding window functions to calculate moving average and cumulative average, identifies the changing trends and potential problem points of structural performance, performs linear regression analysis to predict performance change trends, and generates performance change trend analysis results.
[0141] S602: Based on the performance change trend analysis results, predict the future performance of the foundation pit support structure, including future risks and changes in structural performance, conduct risk assessment and performance prediction, and obtain the specific process of risk and performance prediction analysis results as follows;
[0142] Based on the performance change trend analysis results, sub-step S602 predicts the future performance of the foundation pit support structure, uses R language with the forecast package to perform time series forecasting, automatically selects the optimal ARIMA model parameters through the auto.arima function, combines historical and real-time monitoring data for model training, uses the forecast function to predict future risks and structural performance changes, conducts risk assessment and performance forecasting, and generates risk and performance forecast analysis results.
[0143] S603: According to the risk and performance prediction analysis results, the evaluation parameters and strategies are adjusted to cope with future environmental changes and structural status, the dynamic evaluation model is cyclically updated, and continuous performance monitoring and risk evaluation are performed to obtain the specific process of performance prediction and evaluation results;
[0144] In sub-step S603, the evaluation parameters and strategies are adjusted according to the risk and performance prediction analysis results. The Simulink module in the MATLAB software is used to build a feedback control system for the dynamic evaluation model. The parameter adjustment module is set to cope with future environmental changes and structural states. Parameter optimization algorithms such as the particle swarm optimization algorithm are executed. The optimal evaluation parameter configuration is searched through algorithm iterations. The dynamic evaluation model is cyclically updated to perform continuous performance monitoring and risk assessment, and generate performance prediction and evaluation results.
[0145] See also Figure 8 , a foundation pit support performance evaluation system based on data analysis, the system includes data acquisition and processing module, waveform analysis module, evaluation rule design module, parameter optimization simulation module, dynamic evaluation logic adjustment module, performance monitoring and prediction module, and evaluation parameter adjustment module;
[0146] The data acquisition and processing module collects the monitoring data of the foundation pit support structure, performs data screening to exclude data beyond the measurement range and breakpoint data, performs data filtering and denoising, reflects the physical condition of the foundation pit support structure, analyzes the time series characteristics of the data, and obtains the processed monitoring data set;
[0147] The waveform analysis module performs waveform analysis on the processed monitoring data set, decomposes multiple frequency components and quantifies their amplitudes, identifies the key frequencies and energy distribution of the structural response, extracts characteristic frequencies and amplitude values, marks periodic changes and abnormal fluctuations in the data, and generates signal feature extraction results;
[0148] The evaluation rule design module uses the signal feature extraction results to select the safety range of the monitoring indicators, set the safety threshold, analyze the processed monitoring data set, identify the indicators that exceed the safety range, classify the current status of the foundation pit support structure, and construct the initial state evaluation results;
[0149] The parameter optimization simulation module designs multi-condition simulation tests based on the initial state assessment results, including the effects of load, temperature change and water level change. The response of the structure is monitored through simulation tests, the sensitivity of the support structure is analyzed from the simulation test results, key parameters are adjusted, and the optimized parameter settings are established.
[0150] The dynamic evaluation logic adjustment module combines the optimized parameter settings and the monitoring data of the foundation pit support structure to analyze the performance of the foundation pit support structure under various environments and conditions, adjust the evaluation criteria and logic, and generate a dynamic evaluation model;
[0151] The performance monitoring and prediction module applies a dynamic evaluation model, combines real-time data and historical data analysis, identifies the changing trends and potential problems of structural performance, conducts risk assessment and performance prediction, and obtains performance prediction and evaluation results;
[0152] The evaluation parameter adjustment module adjusts the evaluation parameters and strategies according to the performance prediction and evaluation results, copes with future environmental changes and structural status, and constructs updated evaluation parameters and strategies.
[0153] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. The foundation pit support performance evaluation method based on data analysis is characterized by: The steps include: Collect real-time monitoring data of foundation pit support structures, including displacement, stress and temperature, filter and denoise the data, analyze the time series characteristics of the data, and obtain the processed monitoring data set; The specific steps of performing waveform analysis on the processed monitoring data set, extracting characteristic frequency and amplitude in the signal, identifying periodic changes and abnormal fluctuations in the data, and obtaining signal feature extraction results are as follows; Based on the processed monitoring data set, an empirical mode decomposition method is used to perform waveform analysis on the data, decompose multiple frequency components and quantify their amplitudes, and a fuzzy reasoning method is combined to identify the key frequencies and energy distribution of the structural response to obtain frequency and amplitude analysis results; The empirical mode decomposition method is based on the formula: , Calculate each intrinsic mode function and its corresponding trend term, combine fuzzy reasoning method, process the data generated by empirical mode decomposition, identify the key frequency and energy distribution of structural response, and generate frequency and amplitude analysis results; in, is the total number of oscillation modes in the data set, For the Oscillation mode, is the frequency adjustment coefficient, which dynamically adjusts the frequency component of each intrinsic mode function according to the frequency characteristics of the signal. is the amplitude adjustment coefficient, which is adjusted according to the statistical characteristics of the signal amplitude. is the trend item, It is a data adaptive parameter that automatically adjusts according to the nonlinear characteristics and complexity of the data; Extract key frequency and amplitude values from the frequency and amplitude analysis results, identify periodic changes and abnormal fluctuations in the data, mark abnormal data points indicating structural problems, and obtain periodicity and abnormal fluctuation analysis results; Comprehensively utilizing the periodicity and abnormal fluctuation analysis results, reanalyzing the periodic changes and abnormal fluctuations in the monitoring data set, identifying structural performance changes or damage indicators, and evaluating the stability and safety of the structure in combination with historical monitoring data to obtain signal feature extraction results; Based on the signal feature extraction results, an evaluation rule is designed, including monitoring data change trends and threshold settings, to judge the state of the foundation pit support structure and obtain an initial state evaluation result; By using the initial state assessment results, the performance of the support structure under various working conditions is simulated, and the parameters are optimized for adjusting key parameters to obtain optimized parameter settings; Combining the optimized parameter settings with the real-time monitoring data of the foundation pit support structure, analyzing and matching various environments and state changes, adjusting the evaluation criteria and logic, and performing real-time performance evaluation and safety monitoring to obtain a dynamic evaluation model; The dynamic assessment model is applied to continuously monitor and evaluate the foundation pit support structure. The future performance of the structure is predicted by combining real-time data analysis with historical data comparison. The assessment parameters and strategies are adjusted accordingly to obtain performance prediction and assessment results.
2. The method for evaluating foundation pit support performance based on data analysis according to claim 1, characterized in that: The processed monitoring data set includes the processed displacement amplitude, the stress change value after removing environmental interference, and the corrected temperature fluctuation data. The signal feature extraction results include the key frequency points of the vibration mode, the amplitude spectrum of the energy distribution, and the identified non-periodic abnormal vibration sequence. The initial state assessment results include the stability level based on the change trend analysis, the risk area exceeding the predetermined threshold and the sensitive indicator set that needs to be monitored again. The optimized parameter settings include the adjusted support wall thickness, the improved soil pressure distribution model, and the selected temperature adjustment measures. The dynamic evaluation model includes the adaptively adjusted evaluation frequency, the safety threshold updated according to the real-time data, and the performance rating standard for multi-environment matching. The performance prediction and evaluation results include the predicted displacement trend curve, the location map of the potential risk points and the estimated value of the effect of the improvement measures.
3. The method for evaluating foundation pit support performance based on data analysis according to claim 1, characterized in that: The specific steps of collecting real-time monitoring data of foundation pit support structures, including displacement, stress and temperature, filtering and denoising the data, analyzing the time series characteristics of the data, and obtaining the processed monitoring data set are as follows; Collect real-time monitoring data of foundation pit support structures, including displacement, stress and temperature data, filter out data beyond the measurement range and breakpoint data, and obtain the filtered monitoring data set; Filtering and denoising the screened monitoring data set to remove interference caused by the external environment or measurement errors, reflecting the current physical condition of the foundation pit support structure, and obtaining a denoised monitoring data set; The denoised monitoring data set is analyzed to identify time series features in the data, including long-term trends, periodic changes and emergencies, to obtain a processed monitoring data set.
4. The method for evaluating foundation pit support performance based on data analysis according to claim 1, characterized in that: Based on the signal feature extraction results, the evaluation rules are designed, including monitoring data change trends and threshold settings, to determine the state of the foundation pit support structure, and the specific steps for obtaining the initial state evaluation results are as follows; Based on the signal feature extraction result, a safety range of the monitoring index of the foundation pit support structure is selected, including the normal fluctuation range of displacement, stress and temperature, and a safety threshold of the index is set to obtain a safety threshold setting result; Applying the safety threshold setting result, analyzing the processed monitoring data set, comparing the measured value of each indicator with its safety threshold, identifying indicators that exceed the safety range, classifying the current status of the foundation pit support structure, including normal, warning or over-limit, and obtaining status classification analysis results; According to the results of the condition classification analysis, the overall performance status of the foundation pit support structure is comprehensively judged to reflect the stability and risk level of the structure under the current monitoring conditions, and the initial status assessment results are obtained.
5. The method for evaluating foundation pit support performance based on data analysis according to claim 1, characterized in that: Using the initial state assessment results, by simulating the performance of the support structure under various working conditions, the key parameters are adjusted and the parameters are optimized. The specific steps for obtaining the optimized parameter settings are as follows; Using the initial state assessment results as a reference, design a multi-condition simulation test, including simulating the effects of various loads, temperature changes, and water level changes on the support structure, monitor the response of the structure through the simulation test, and obtain the simulation test results; The sensitivity analysis method is used to analyze the sensitivity of the support structure to various conditions from the simulation test results, and the parameters affecting the structural performance are identified, including the thickness of the support structure, the type of materials used, and the construction method. The differential evolution algorithm is used to refine the parameters and re-simulate the effect of the adjustment to obtain the sensitivity analysis results of key parameters. The sensitivity analysis method is based on the formula: Formula II, Calculate the impact of each input parameter on the output result and generate a sensitivity index based on the complexity and priority of the parameters; in, is the sensitivity index, For a given input parameter Output results The conditional expected variance of is the weight coefficient of parameter complexity scoring, which is determined through statistical analysis of parameter complexity scoring and expert experience. For parameters The complexity score of is the weight coefficient of the parameter performance priority, which is determined by comprehensive evaluation of the parameter's historical performance data. The performance priority of the parameters in the previous project, To output the result The total variance of The differential evolution algorithm is based on the formula: Formula III, Adjust key parameters with reference to dynamic adjustment factors to obtain optimized parameter settings; in, For the next generation The parameter vector of each individual, For the current generation The parameter vector of each individual, is the scaling factor, is the parameter vector of two difference individuals randomly selected from the current generation, is the weight coefficient of the dynamic adjustment factor, which is determined by analyzing the dynamic change trend of the parameter. Based on the current parameters Dynamic adjustment factor of Based on the results of the sensitivity analysis of the key parameters, the parameter settings are optimized through iterative simulation and analysis. The influence of each indicator on the structural stability and safety is comprehensively referred to, and the parameter configuration is adjusted and selected to obtain the optimized parameter settings.
6. The method for evaluating foundation pit support performance based on data analysis according to claim 1, characterized in that: The specific steps of combining the optimized parameter settings and the real-time monitoring data of the foundation pit support structure, analyzing and matching various environments and state changes, adjusting the evaluation criteria and logic, and performing real-time performance evaluation and safety monitoring to obtain a dynamic evaluation model are as follows; Combining the optimized parameter settings with the real-time monitoring data of the foundation pit support structure, analyzing the performance of the foundation pit support structure in the current environment and multiple states, matching the impact of environmental changes on structural performance, and obtaining environmental impact analysis results; According to the environmental impact analysis results, the assessment criteria and logic are adjusted to match the performance changes of the foundation pit support structure shown by the monitoring data, reflect the structural status, and obtain the adjusted assessment criteria; The adjusted evaluation standard is applied to conduct real-time performance evaluation and safety monitoring of the foundation pit support structure, and the evaluation results are updated in real time to reflect the current structural status and safety situation, thereby obtaining a dynamic evaluation model.
7. The method for evaluating foundation pit support performance based on data analysis according to claim 1, characterized in that: The dynamic assessment model is applied to continuously monitor and evaluate the foundation pit support structure, and the future performance of the structure is predicted by combining real-time data analysis with historical data comparison, and the assessment parameters and strategies are adjusted accordingly. The specific steps for obtaining performance prediction and assessment results are as follows; The dynamic evaluation model is used to continuously monitor and evaluate the foundation pit support structure, analyze real-time data and historical data, identify the change trend and potential problem points of the structural performance, and obtain the performance change trend analysis results; Based on the performance change trend analysis results, predict the future performance of the foundation pit support structure, including future risks and changes in structural performance, conduct risk assessment and performance prediction, and obtain risk and performance prediction analysis results; According to the risk and performance prediction analysis results, the evaluation parameters and strategies are adjusted to cope with future environmental changes and structural states, the dynamic evaluation model is cyclically updated, continuous performance monitoring and risk evaluation are performed, and performance prediction and evaluation results are obtained.
8. The foundation pit support performance evaluation system based on data analysis is characterized by: According to the method for evaluating foundation pit support performance based on data analysis according to any one of claims 1 to 7, the system includes a data acquisition and processing module, a waveform analysis module, an evaluation rule design module, a parameter optimization simulation module, a dynamic evaluation logic adjustment module, a performance monitoring and prediction module, and an evaluation parameter adjustment module; The data acquisition and processing module collects monitoring data of the foundation pit support structure, performs data screening to exclude data beyond the measurement range and breakpoint data, performs data filtering and denoising, reflects the physical condition of the foundation pit support structure, analyzes the time series characteristics of the data, and obtains the processed monitoring data set; The waveform analysis module performs waveform analysis on the processed monitoring data set, decomposes multiple frequency components and quantifies their amplitudes, identifies key frequencies and energy distributions of structural responses, extracts characteristic frequencies and amplitude values therefrom, marks periodic changes and abnormal fluctuations in the data, and generates signal feature extraction results; The evaluation rule design module uses the signal feature extraction results to select the safety range of the monitoring indicators, set the safety threshold, analyze the processed monitoring data set, identify the indicators that exceed the safety range, classify the current status of the foundation pit support structure, and construct the initial state evaluation results; The parameter optimization simulation module designs multi-condition simulation tests based on the initial state assessment results, including the effects of load, temperature change and water level change, monitors the response of the structure through simulation tests, analyzes the sensitivity of the support structure from the simulation test results, adjusts key parameters, and establishes optimized parameter settings; The dynamic evaluation logic adjustment module combines the optimized parameter settings and the monitoring data of the foundation pit support structure to analyze the performance of the foundation pit support structure in various environments and states, adjust the evaluation criteria and logic, and generate a dynamic evaluation model; The performance monitoring and prediction module applies a dynamic evaluation model, combines real-time data and historical data analysis, identifies the changing trend of structural performance and potential problem points, conducts risk assessment and performance prediction, and obtains performance prediction and evaluation results; The evaluation parameter adjustment module adjusts the evaluation parameters and strategies according to the performance prediction and evaluation results, copes with future environmental changes and structural states, and constructs updated evaluation parameters and strategies.
Citation Information
Cited By
Foundation pit supporting performance evaluation method and system based on data analysis and storage medium
CN121365495A
