Method and system for evaluating vibration isolation effect of existing building in subway operation area

Abstract

The invention discloses a subway operation area existing building vibration isolation effect evaluation method and system, and particularly relates to the technical field of building vibration isolation. A monitoring area is divided according to the density of existing buildings in a metro operation area, vibration signals in a fixed time period are captured in real time, nonlinear characteristics in the vibration signals and response characteristics of the buildings under vibration are analyzed, and when abnormal vibration is detected, the reverse vibration wave error change condition calculated by a control algorithm is analyzed, so that the abnormal vibration is detected. Comprehensively analyzing an abnormal vibration behavior and a reverse vibration wave error change condition based on fuzzy logic, performing quality division on a vibration isolation effect in a monitoring area, generating an evaluation report, and taking corresponding improvement measures; the vibration condition of the building can be comprehensively mastered, abnormal vibration can be accurately diagnosed, the precision and adaptability of a control system can be improved, scientific vibration isolation effect evaluation can be provided, and effective improvement measures can be formulated, so that the overall vibration isolation quality can be improved, and the structural safety and the use comfort of the building can be ensured.

Description

Technical Field

[0001] The invention relates to the technical field of building vibration isolation, and in particular to a method and system for evaluating the vibration isolation effect of existing buildings in a subway operation area. Background Art

[0002] Vibration isolation of existing buildings in subway operation areas refers to taking technical measures to reduce the impact of vibrations generated by subway trains on surrounding existing buildings. By installing vibration isolation devices or improving the building structure, the intensity of vibrations transmitted to the building is reduced, thereby protecting the structural integrity and living comfort of the building. This vibration isolation measure includes installing vibration isolation pads, shock absorbers and other equipment at key locations such as the building foundation and floor slab, or improving the building design to improve its vibration resistance. The evaluation of the vibration isolation effect requires the measurement and analysis of vibration data to determine whether additional measures are needed to ensure the safety of the building and the comfort of the use environment.

[0003] As a commonly used vibration isolation device, the active vibration isolation system effectively reduces the intensity of vibration transmitted to the building through real-time monitoring and feedback control. It is particularly suitable for environments with extremely high requirements for vibration control. By real-time monitoring of vibration signals, using sensors to detect external vibrations, and calculating the corresponding reverse vibration wave parameters through the controller, the brake is driven to generate reverse vibration waves, thereby actively offsetting the original vibration waves and achieving the effect of efficient vibration reduction and stable environment. However, when a building is subjected to strong vibrations, its vibration response characteristics will change, causing the vibration behavior to become abnormal. Traditional control algorithms based on linear assumptions may not be able to accurately calculate the reverse vibration waves, resulting in the failure of the vibration isolation effect, and the building will continue to be affected by the vibration generated by the subway operation. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for evaluating the vibration isolation effect of existing buildings in a subway operation area, so as to solve the shortcomings of the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a method for evaluating the vibration isolation effect of existing buildings in a subway operation area, comprising the following steps:

[0006] S1: Divide the subway operation area into several monitoring areas according to the density of existing buildings. Install n vibration sensors at different locations of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period.

[0007] S2: After preprocessing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the building's signal under vibration are analyzed to identify abnormal vibration behavior of the building;

[0008] S3: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results;

[0009] S4: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

[0010] Preferably, the subway operation area is divided into several monitoring areas according to the density of existing buildings, and is divided into high-density monitoring areas, medium-density monitoring areas and low-density monitoring areas according to the density of buildings.

[0011] Preferably, the phase amplitude coupling index is generated according to the nonlinear characteristics in the vibration signal, and the method for obtaining the phase amplitude coupling index is:

[0012] The original vibration signal is preprocessed, and the preprocessed signal is decomposed into frequency bands. A bandpass filter is used to decompose the signal into components of different frequency bands. Each frequency band component is Hilbert transformed to obtain a complex Hilbert signal. The signal xi(t) after Hilbert transformation is expressed as: xi(t) = Ai(t)e jθi(t) ; Where Ai(t) is the instantaneous amplitude of the signal, θi(t) is the instantaneous phase of the signal, e and j are constants, the instantaneous phase θlow(t) of the low-frequency component and the instantaneous amplitude Ahigh(t) of the high-frequency component are selected, and the instantaneous phase and amplitude of each frequency band component are obtained through the initial Hilbert transform;

[0013] Perform Hilbert transform on the instantaneous amplitude Ahigh(t) of the high-frequency component to obtain the instantaneous phase θAhigh(t) of its envelope, and calculate the phase difference Δθ(t) between the low-frequency phase θlow(t) and the instantaneous phase θAhigh(t) of the high-frequency amplitude. The phase difference Δθ(t) is expressed as: Δθ(t) = θlow(t) - θAhigh(t); calculate the phase amplitude coupling index PACI. The phase difference Δθ(t) is used to calculate the phase amplitude coupling index PACI. The specific calculation expression is: Where N is the number of time points and Δθ(t) is the phase difference at the t-th time point.

[0014] Preferably, the vibration signal amplitude distribution anomaly index is generated according to the real-time signal response characteristics of the building under vibration, and the method for obtaining the vibration signal amplitude distribution anomaly index is:

[0015] The vibration signals x(t) of various parts of the building are denoised and filtered, and then wavelet transform is performed to obtain wavelet coefficients at different scales. The wavelet transform is expressed as: Wj,k = ∫x(t)ψj,k(t)dt; where Wj,k is the wavelet coefficient, which represents the intensity of the signal at scale j and time position k, and ψj,k(t) is the wavelet basis function. The amplitude of the wavelet coefficient at each scale and time position is calculated to obtain the local amplitude: Aj,k = |Wj,k|; where Aj,k is the local amplitude, which represents the intensity of the vibration signal at a specific scale and time position. The detection threshold λ is set, and the abnormal points in the local amplitude Aj,k that are greater than or equal to the detection threshold λ are identified, and an abnormal point set Ω is established, which includes all amplitude points identified as abnormal, and the vibration signal amplitude distribution abnormality index is calculated. The specific calculation expression is: M is the total number of detection points, and TMCK is the vibration signal amplitude distribution anomaly index.

[0016] Preferably, the phase amplitude coupling index and the vibration signal amplitude distribution anomaly index are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the building vibration behavior assessment coefficient label for each group of first eigenvectors as a prediction target, and minimizes the sum of prediction errors for all building vibration behavior assessment coefficient labels as a training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The building vibration behavior assessment coefficient is determined according to the model output results.

[0017] Preferably, the acquired building vibration behavior assessment coefficient is compared with a preset building vibration behavior assessment coefficient reference threshold value. If the building vibration behavior assessment coefficient is greater than or equal to the preset building vibration behavior assessment coefficient reference threshold value, the building has abnormal vibration behavior; if the building vibration behavior assessment coefficient is less than the preset building vibration behavior assessment coefficient reference threshold value, the building does not have abnormal vibration behavior.

[0018] Preferably, when abnormal vibration behavior occurs in the building, vibration data is recorded in real time according to vibration sensors installed at different parts of the building, and the vibration data includes original vibration signals and reverse vibration wave signals; the reverse vibration wave calculated according to the control algorithm is compared with the actually measured vibration signal to define an error index;

[0019] Use the error indicator as a label to generate a corresponding label for each set of input data;

[0020] Divide the collected data into training set and test set;

[0021] Use the training set data to train the random forest model, with the input being the vibration signal features and the output being the error index;

[0022] Use the test set data to evaluate the performance of the model;

[0023] Input the real-time collected vibration signal features into the trained random forest model to predict the error value of the current control algorithm;

[0024] According to the error value of the control algorithm output by the model over a period of time, the error change of the reverse vibration wave calculated by the control algorithm is determined.

[0025] Preferably, a dynamic adjustment strategy is designed to adjust the reverse vibration wave parameters according to the error change. The error formula is: Among them, Y x is the actual vibration value, EY x is the vibration value predicted by the model, and H is the number of samples;

[0026] According to the change of error, the reverse vibration wave parameters are gradually adjusted, the error values ​​of the control algorithm output by the model within a period of time are collected, and the corresponding data set is established. The standard deviation of the data set is calculated, that is, the error fluctuation index is calculated. When the calculated error fluctuation index is greater than or equal to the preset threshold, the parameters are adjusted according to the fixed increment. The specific calculation expression is: Pnew=Pcurrent+ΔP; wherein ΔP is the fixed increment value, Pnew is the reverse vibration wave parameter after adjustment, and Pcurrent is the reverse vibration wave parameter before adjustment.

[0027] Preferably, the building vibration behavior evaluation coefficient and the error fluctuation index of the control algorithm are used as input items, and the vibration isolation effect in each monitoring area is used as an output item;

[0028] Convert the evaluation coefficient, error fluctuation index and vibration isolation effect into fuzzy sets;

[0029] Convert the actually measured vibration evaluation coefficient and error fluctuation index into member values ​​in the fuzzy set;

[0030] According to the fuzzy rule base, the input fuzzy set is matched with rules to obtain the corresponding fuzzy output;

[0031] Using fuzzy reasoning methods, the input items are mapped to output items through fuzzy rules to generate fuzzy output results;

[0032] The fuzzy output is converted into specific vibration isolation effect through the central value method.

[0033] The present invention also provides a vibration isolation effect evaluation system for existing buildings in a subway operation area, comprising a vibration signal acquisition module, an abnormal vibration identification module, a control algorithm analysis module and a vibration isolation effect evaluation module;

[0034] Vibration signal acquisition module: The subway operation area is divided into several monitoring areas according to the density of existing buildings. n vibration sensors are installed at different locations of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period;

[0035] Abnormal vibration identification module: After pre-processing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the building's signal under vibration are analyzed to identify the abnormal vibration behavior of the building;

[0036] Control algorithm analysis module: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results;

[0037] Vibration isolation effect evaluation module: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

[0038] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0039] 1. The present invention divides the building density into monitoring areas and installs vibration sensors to capture vibration signals in real time and perform preprocessing and analysis to identify abnormal vibration behavior of the building. When abnormal vibration is detected, the control algorithm dynamically adjusts the reverse vibration wave parameters, comprehensively analyzes the abnormal vibration behavior and the reverse vibration wave error changes through fuzzy logic, divides the vibration isolation effect in the monitoring area by quality, generates an evaluation report and formulates improvement measures. This method can fully grasp the vibration conditions of the building, accurately diagnose abnormal vibration behavior, improve the accuracy and adaptability of the control system, provide a scientific vibration isolation effect evaluation, thereby effectively improving the overall vibration isolation quality and ensuring the structural safety and comfort of the building.

[0040] 2. Through nonlinear feature analysis, machine learning model prediction and error dynamic adjustment strategy, the system can maintain efficient vibration isolation effect when the building is subjected to strong vibration. In particular, the comprehensive analysis based on fuzzy logic can accurately evaluate the vibration isolation effect in each monitoring area, generate a detailed evaluation report, and take effective improvement measures based on the evaluation results. Overall, the invention has significant advantages in solving the limitations of traditional vibration isolation control systems, effectively reducing the impact of subway vibration on buildings, and improving the scientificity and practicality of vibration isolation control. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0042] Figure 1 The figure is a flow chart of the method of the present invention.

[0043] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] Example 1

[0046] See also Figure 1 As shown, the vibration isolation effect evaluation method of existing buildings in a subway operation area described in this embodiment includes the following steps:

[0047] S1: Divide the subway operation area into several monitoring areas according to the density of existing buildings. Install n vibration sensors at different locations of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period.

[0048] S2: After preprocessing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the building's signal under vibration are analyzed to identify abnormal vibration behavior of the building;

[0049] S3: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results;

[0050] S4: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

[0051] Among them, in S1, the subway operation area is divided into several monitoring areas according to the density of existing buildings, and n vibration sensors are installed at different positions of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period.

[0052] According to the density of existing buildings in the subway operation area, it is divided into several monitoring areas, and divided into high-density monitoring areas, medium-density monitoring areas and low-density monitoring areas according to the density of buildings. Specifically:

[0053] High-density monitoring area: areas with dense buildings within the subway operation area, such as commercial centers, residential areas, etc. The monitoring areas here are divided into smaller areas to ensure that each building has sufficient monitoring coverage.

[0054] Medium-density monitoring area: an area where buildings are relatively dispersed but still have a certain density, such as a comprehensive office area or light industrial area. The size of the monitoring area is moderate to ensure that all important buildings can be covered.

[0055] Low-density monitoring area: an area with fewer buildings, such as parks, open spaces, warehouse areas, etc. The monitoring area here is divided into larger areas, but it is still necessary to ensure that key buildings are covered.

[0056] In order to effectively monitor the vibration impact of subway operation on existing buildings, sensors should be installed at key locations. Sensors should be installed at the foundation and base of the building in each monitoring area to monitor the vibration transmitted from the ground; sensors should be installed at key structural support points such as load-bearing walls, columns, and beams to monitor the vibration response of the structure; sensors should be installed on the floor slabs and ceilings of each floor to capture vertical vibration and the response of the overall structure.

[0057] In addition, sensors should be arranged at different heights. Dense sensors should be installed on the ground floor, because the ground floor is most directly affected by subway vibration; sensors should be installed on the middle floors to understand the propagation and attenuation of vibration inside the building; sensors should be installed on the top floor to monitor the response of vibration at high levels, ensuring comprehensive coverage of vibration monitoring and accuracy of data.

[0058] In order to accurately capture the vibration impact of subway operation on buildings, fixed time period monitoring should be carried out. Sensors need to capture and record vibration signals in real time to achieve uninterrupted monitoring; at the same time, the signals should be processed in segments, such as hourly, daily, and weekly vibration signals, so as to carry out detailed analysis and comparison.

[0059] In addition, to improve monitoring accuracy, the sensor should adopt a high sampling rate (such as 100 times per second or more) to ensure that high-frequency vibrations and subtle changes can be captured. Ensure that the data of all sensors are collected synchronously so that the data at different locations can be compared and analyzed in time series, thereby providing comprehensive and accurate vibration monitoring information.

[0060] S2: After preprocessing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the signal of the building under vibration are analyzed to identify the abnormal vibration behavior of the building.

[0061] The captured vibration signal is preprocessed, including noise removal, filtering and smoothing, to improve signal quality and accuracy. The preprocessed signal is purer, eliminating interference factors, and providing a reliable basis for subsequent analysis.

[0062] After the signal is preprocessed, the signal is feature extracted. Through spectrum analysis, time domain analysis and wavelet transform, the key features of the vibration signal, such as frequency components, amplitude, energy density, etc., are extracted to provide detailed data information for evaluating the impact of subway vibration on buildings.

[0063] The phase amplitude coupling index is generated according to the nonlinear characteristics in the vibration signal. The method for obtaining the phase amplitude coupling index is:

[0064] Preprocess the original vibration signal and decompose the preprocessed signal into frequency bands. Usually, a bandpass filter is used to decompose the signal into components of different frequency bands.

[0065] Perform Hilbert transform on each frequency band component to obtain the complex Hilbert signal. The signal xi(t) after Hilbert transform is expressed as: xi(t) = Ai(t)e jθi(t) ; Where Ai(t) is the instantaneous amplitude of the signal, θi(t) is the instantaneous phase of the signal, e and j are constants, the instantaneous phase θlow(t) of the low-frequency component and the instantaneous amplitude Ahigh(t) of the high-frequency component are selected, and the instantaneous phase and amplitude of each frequency band component are obtained through the initial Hilbert transform;

[0066] Perform Hilbert transform on the instantaneous amplitude Ahigh(t) of the high-frequency component to obtain the instantaneous phase θAhigh(t) of its envelope, and calculate the phase difference Δθ(t) between the low-frequency phase θlow(t) and the instantaneous phase θAhigh(t) of the high-frequency amplitude. The phase difference Δθ(t) is expressed as: Δθ(t) = θlow(t) - θAhigh(t); calculate the phase amplitude coupling index PACI. The phase difference Δθ(t) is used to calculate the phase amplitude coupling index PACI. The specific calculation expression is: Where N is the number of time points and Δθ(t) is the phase difference at the t-th time point.

[0067] The larger the phase amplitude coupling index (PACI), the higher the coupling between the low-frequency phase and high-frequency amplitude in the vibration signal. This means that the phase change of the low-frequency vibration significantly affects the amplitude change of the high-frequency vibration, showing a strong phase modulation phenomenon. Such a phenomenon usually indicates that the vibration behavior of the system is more complex and nonlinear, and there may be strong nonlinear effects or resonance phenomena.

[0068] High phase-amplitude coupling index values ​​indicate significant abnormal vibration behaviors in the vibration signal, such as resonance, harmonic amplification, etc. These abnormal vibration behaviors can make the vibration response of the system more unpredictable and difficult to accurately describe using a linear model. Especially in buildings in subway operation areas, strong phase-amplitude coupling may cause greater vibration shocks to the building structure, increasing the risk of structural damage.

[0069] Therefore, by monitoring and analyzing the phase-amplitude coupling index, abnormal behaviors in vibration signals can be identified and quantified, thus providing an important basis for taking targeted vibration isolation measures. High phase-amplitude coupling index values ​​indicate that these strong nonlinear vibration effects need special attention and treatment to ensure the structural safety and user comfort of the building.

[0070] The vibration signal amplitude distribution anomaly index is generated according to the real-time signal response characteristics of the building under vibration. The method for obtaining the vibration signal amplitude distribution anomaly index is as follows:

[0071] The vibration signals x(t) of various parts of the building are denoised and filtered, and then wavelet transform is performed to obtain wavelet coefficients at different scales. The wavelet transform is expressed as: Wj,k = ∫x(t)ψj,k(t)dt; where Wj,k is the wavelet coefficient, which represents the intensity of the signal at scale j and time position k, and ψj,k(t) is the wavelet basis function. The amplitude of the wavelet coefficient at each scale and time position is calculated to obtain the local amplitude: Aj,k = |Wj,k|; where Aj,k is the local amplitude, which represents the intensity of the vibration signal at a specific scale and time position. The detection threshold λ is set to identify abnormal amplitudes, and the abnormal points in the local amplitude Aj,k that are greater than or equal to the detection threshold λ are identified, and an abnormal point set Ω is established, which includes all amplitude points identified as abnormal. The vibration signal amplitude distribution abnormality index is calculated. The specific calculation expression is: M is the total number of detection points, and TMCK is the vibration signal amplitude distribution anomaly index.

[0072] When the vibration signal amplitude distribution anomaly index is large, it means that there are a large number of vibration points with abnormally high amplitudes in the vibration signal. These high-amplitude vibrations may cause the structural components of the building, such as beams, columns and walls, to be subjected to stress and strain far exceeding the design standards, increasing the possibility of structural damage. High-amplitude vibrations may also cause secondary structures (such as glass windows and interior walls) to break or fall off, affecting the safety and use function of the building.

[0073] When the vibration signal amplitude distribution abnormality index is large, not only the amplitude of the vibration points with abnormal amplitude is high, but also the number is greater. This means that the frequency of vibration abnormalities is high, indicating that the vibration source impacts the building more frequently. Frequent abnormal vibrations can cause structural fatigue, increase the risk of material aging and damage, and shorten the service life of the building. If the building is in a high-frequency abnormal vibration environment for a long time, structural problems such as cracks and settlement may occur.

[0074] A high value of the vibration signal amplitude distribution anomaly index also indicates that the vibration signal contains complex nonlinear characteristics, and the vibration behavior becomes difficult to predict. This complexity may be due to factors such as the superposition effect of multiple vibration sources and the nonlinear response of the structure itself. Complex vibration behavior makes traditional linear vibration isolation and vibration reduction methods difficult to work, and more advanced nonlinear analysis methods and intelligent control technologies are needed to ensure the safety and stability of buildings in complex vibration environments.

[0075] The phase-amplitude coupling index and the vibration signal amplitude distribution anomaly index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the building vibration behavior assessment coefficient label for each group of first eigenvectors as the prediction target, and minimizes the sum of prediction errors of all building vibration behavior assessment coefficient labels as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The building vibration behavior assessment coefficient is determined according to the model output results.

[0076] The method for obtaining the building vibration behavior evaluation coefficient is as follows: from the first eigenvector training data of the trained machine learning model, the corresponding function expression is obtained: CT = f1(PACI, TMCK); where f1 is the output function of the model, PACI is the phase amplitude coupling index, TMCK is the vibration signal amplitude distribution anomaly index, and CT is the building vibration behavior evaluation coefficient.

[0077] The obtained building vibration behavior assessment coefficient is compared with the pre-set building vibration behavior assessment coefficient reference threshold. If the building vibration behavior assessment coefficient is greater than or equal to the pre-set building vibration behavior assessment coefficient reference threshold, it means that the building has abnormal vibration behavior; if the building vibration behavior assessment coefficient is less than the pre-set building vibration behavior assessment coefficient reference threshold, it means that the building does not have abnormal vibration behavior.

[0078] S3: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results.

[0079] When a building exhibits abnormal vibration behavior, vibration sensors installed in different parts of the building will record vibration data in real time. The vibration data includes the original vibration signal and the reverse vibration wave signal. Vibration data is continuously collected to ensure coverage of various operating conditions and environmental conditions.

[0080] De-noise and filter the collected vibration signals to remove random noise and interference signals. Extract key features such as frequency, amplitude, phase, acceleration, etc. from the pre-processed signals.

[0081] The reverse vibration wave calculated by the control algorithm is compared with the actual measured vibration signal, and error indicators (such as mean square error, correlation coefficient, etc.) are defined.

[0082] Using the error indicator as a label, generate corresponding labels for each set of input data.

[0083] The collected data is divided into training and test sets, usually in an 80 / 20 ratio.

[0084] The random forest model is trained using the training set data, with the input being the vibration signal features and the output being the error indicator.

[0085] Use the test set data to evaluate the performance of the model and calculate the model's accuracy, recall, F1 score and other indicators.

[0086] The vibration signal features collected in real time are input into the trained random forest model to predict the error value of the current control algorithm.

[0087] According to the error value of the control algorithm output by the model over a period of time, the error change of the reverse vibration wave calculated by the control algorithm is determined.

[0088] Design a dynamic adjustment strategy to adjust the reverse vibration wave parameters according to the error changes. The error formula is: Among them, Y x is the actual vibration value, EY x is the vibration value predicted by the model, and H is the number of samples;

[0089] According to the change of error, the reverse vibration wave parameters are gradually adjusted, the error values ​​of the control algorithm output by the model within a period of time are collected, and the corresponding data set is established to calculate the standard deviation of the data set, that is, the error fluctuation index is calculated. When the calculated error fluctuation index is greater than or equal to the preset threshold, the parameters are adjusted according to the fixed increment. The specific calculation expression is: Pnew = Pcurrent + ΔP; where ΔP is the fixed increment value, Pnew is the adjusted reverse vibration wave parameter, and Pcurrent is the reverse vibration wave parameter before adjustment. The adjusted parameters are immediately fed back to the control system, the reverse vibration wave signal is updated in real time, the adjusted vibration response is continuously monitored, and the effect of the parameter adjustment is recorded.

[0090] S4: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

[0091] The building vibration behavior evaluation coefficient and the error fluctuation index of the control algorithm are used as input items, and the vibration isolation effect in each monitoring area is used as the output item;

[0092] The evaluation coefficients are converted into fuzzy sets. For example, the evaluation coefficients are divided into three levels: "low", "medium" and "high".

[0093] The error fluctuation index is converted into a fuzzy set. For example, the error is divided into three levels: "stable", "fluctuating" and "violent".

[0094] The vibration isolation effect of the building in each monitoring area, including vibration reduction rate, structural stability, resident comfort, etc. The vibration isolation effect is converted into a fuzzy set, for example, the vibration isolation effect is divided into three levels: "poor", "average", and "good".

[0095] Fuzzy rules are formulated based on different combinations of input items. For example: If the vibration evaluation coefficient is "high" and the error fluctuation index is "severe", the vibration isolation effect is "poor". If the vibration evaluation coefficient is "medium" and the error fluctuation index is "fluctuating", the vibration isolation effect is "average". If the vibration evaluation coefficient is "low" and the error fluctuation index is "stable", the vibration isolation effect is "good".

[0096] The actually measured vibration evaluation coefficient and error fluctuation index are converted into member values ​​in the fuzzy set.

[0097] According to the fuzzy rule base, the input fuzzy set is matched with rules to obtain the corresponding fuzzy output.

[0098] Using fuzzy reasoning methods (such as Mamdani reasoning or Sugeno reasoning), the input items are mapped to output items through fuzzy rules to generate fuzzy output results.

[0099] The fuzzy output is converted into specific vibration isolation effect through the central value method.

[0100] Display vibration evaluation coefficient, error fluctuation index and fuzzy classification results. Provide vibration isolation effect evaluation results of each monitoring area, including charts and data analysis.

[0101] Install more vibration isolation pads, shock absorbers and other equipment in monitoring areas with poor vibration isolation to reduce vibration transmission. Strengthen the building structure to enhance its vibration resistance.

[0102] According to the error fluctuation index in the evaluation report, the parameters of the control algorithm are adjusted to make the generation of reverse vibration waves more accurate. The adaptive control algorithm is introduced to enable the system to automatically optimize the reverse vibration wave parameters based on real-time vibration data. Vibration data is collected and analyzed regularly to evaluate the effects of improvement measures, and vibration isolation facilities and control algorithms are dynamically adjusted to ensure the long-term stability and safety of the building.

[0103] In this embodiment, the subway operation area is divided into several monitoring areas according to the density of existing buildings, and n vibration sensors are installed at different positions of the buildings in the monitoring area to capture the vibration signal in a fixed time period in real time; after preprocessing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the signal of the building under vibration are analyzed to identify the abnormal vibration behavior of the building; when the building has abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results; based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed, and the vibration isolation effect in each monitoring area is divided by quality according to the analysis results, and an evaluation report is generated, and corresponding improvement measures are taken according to the evaluation report. It can fully grasp the vibration situation of the building, accurately diagnose abnormal vibration behavior, improve the accuracy and adaptability of the control system, provide scientific vibration isolation effect evaluation, and formulate effective improvement measures, thereby improving the overall vibration isolation quality and ensuring the structural safety and comfort of the building.

[0104] Example 2

[0105] See also Figure 2 As shown, the vibration isolation effect evaluation of existing buildings in a subway operation area described in this embodiment includes a vibration signal acquisition module, an abnormal vibration identification module, a control algorithm analysis module and a vibration isolation effect evaluation module;

[0106] Vibration signal acquisition module: The subway operation area is divided into several monitoring areas according to the density of existing buildings. n vibration sensors are installed at different locations of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period;

[0107] Abnormal vibration identification module: After pre-processing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the building's signal under vibration are analyzed to identify the abnormal vibration behavior of the building;

[0108] Control algorithm analysis module: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results;

[0109] Vibration isolation effect evaluation module: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

[0110] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0111] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0112] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0113] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0114] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0115] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for evaluating the vibration isolation effect of existing buildings in a subway operation area, characterized in that: The steps include: S1: Divide the subway operation area into several monitoring areas according to the density of existing buildings. Install n vibration sensors at different locations of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period. S2: After preprocessing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the building's signal under vibration are analyzed to identify abnormal vibration behavior of the building; S3: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results; S4: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

2. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 1 is characterized in that: The subway operation area is divided into several monitoring areas according to the density of existing buildings, and divided into high-density monitoring areas, medium-density monitoring areas and low-density monitoring areas according to the density of buildings.

3. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 1 is characterized in that: The phase amplitude coupling index is generated according to the nonlinear characteristics in the vibration signal. The method for obtaining the phase amplitude coupling index is: The original vibration signal is preprocessed, and the preprocessed signal is decomposed into frequency bands. A bandpass filter is used to decompose the signal into components of different frequency bands. Each frequency band component is Hilbert transformed to obtain a complex Hilbert signal. The signal xi(t) after Hilbert transformation is expressed as: xi(t) = Ai(t)e jθi(t) ; Where Ai(t) is the instantaneous amplitude of the signal, θi(t) is the instantaneous phase of the signal, e and j are constants, the instantaneous phase θlow(t) of the low-frequency component and the instantaneous amplitude Ahigh(t) of the high-frequency component are selected, and the instantaneous phase and amplitude of each frequency band component are obtained through the initial Hilbert transform; Perform Hilbert transform on the instantaneous amplitude Ahigh(t) of the high-frequency component to obtain the instantaneous phase θAhigh(t) of its envelope, and calculate the phase difference Δθ(t) between the low-frequency phase θlow(t) and the instantaneous phase θAhigh(t) of the high-frequency amplitude. The phase difference Δθ(t) is expressed as: Δθ(t) = θlow(t) - θAhigh(t); calculate the phase amplitude coupling index PACI. The phase difference Δθ(t) is used to calculate the phase amplitude coupling index PACI. The specific calculation expression is: Where N is the number of time points and Δθ(t) is the phase difference at the t-th time point.

4. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 3 is characterized by: The vibration signal amplitude distribution anomaly index is generated according to the real-time signal response characteristics of the building under vibration. The method for obtaining the vibration signal amplitude distribution anomaly index is as follows: The vibration signals x(t) of various parts of the building are denoised and filtered, and then wavelet transform is performed to obtain wavelet coefficients at different scales. The wavelet transform is expressed as: Wj,k = ∫x(t)ψj,k(t)dt; where Wj,k is the wavelet coefficient, which represents the intensity of the signal at scale j and time position k, and ψj,k(t) is the wavelet basis function. The amplitude of the wavelet coefficient at each scale and time position is calculated to obtain the local amplitude: Aj,k = |Wj,k|; where Aj,k is the local amplitude, which represents the intensity of the vibration signal at a specific scale and time position. The detection threshold λ is set, and the abnormal points in the local amplitude Aj,k that are greater than or equal to the detection threshold λ are identified, and an abnormal point set Ω is established, which includes all amplitude points identified as abnormal, and the vibration signal amplitude distribution abnormality index is calculated. The specific calculation expression is: M is the total number of detection points, and TMCK is the vibration signal amplitude distribution anomaly index.

5. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 4 is characterized in that: The phase-amplitude coupling index and the vibration signal amplitude distribution anomaly index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model predicts the building vibration behavior assessment coefficient label for each group of first eigenvectors as the prediction target, and minimizes the sum of prediction errors of all building vibration behavior assessment coefficient labels as the training target. The machine learning model is trained until the sum of prediction errors converges, and the model training is stopped. The building vibration behavior assessment coefficient is determined according to the model output results.

6. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 5 is characterized by: The obtained building vibration behavior assessment coefficient is compared with the pre-set building vibration behavior assessment coefficient reference threshold. If the building vibration behavior assessment coefficient is greater than or equal to the pre-set building vibration behavior assessment coefficient reference threshold, the building has abnormal vibration behavior; if the building vibration behavior assessment coefficient is less than the pre-set building vibration behavior assessment coefficient reference threshold, the building does not have abnormal vibration behavior.

7. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 1 is characterized by: When abnormal vibration occurs in a building, vibration sensors installed in different parts of the building record vibration data in real time. The vibration data includes the original vibration signal and the reverse vibration wave signal. The reverse vibration wave calculated by the control algorithm is compared with the actual measured vibration signal to define the error index. Use the error indicator as a label to generate a corresponding label for each set of input data; Divide the collected data into training set and test set; Use the training set data to train the random forest model, with the input being the vibration signal features and the output being the error index; Use the test set data to evaluate the performance of the model; Input the real-time collected vibration signal features into the trained random forest model to predict the error value of the current control algorithm; According to the error value of the control algorithm output by the model over a period of time, the error change of the reverse vibration wave calculated by the control algorithm is determined.

8. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 7 is characterized by: Design a dynamic adjustment strategy to adjust the reverse vibration wave parameters according to the error changes. The error formula is: Among them, Y x is the actual vibration value, EY x is the vibration value predicted by the model, and H is the number of samples; According to the change of error, the reverse vibration wave parameters are gradually adjusted, the error values ​​of the control algorithm output by the model within a period of time are collected, and the corresponding data set is established. The standard deviation of the data set is calculated, that is, the error fluctuation index is calculated. When the calculated error fluctuation index is greater than or equal to the preset threshold, the parameters are adjusted according to the fixed increment. The specific calculation expression is: Pnew=Pcurrent+ΔP; wherein ΔP is the fixed increment value, Pnew is the reverse vibration wave parameter after adjustment, and Pcurrent is the reverse vibration wave parameter before adjustment.

9. The method for evaluating vibration isolation effect of existing buildings in a subway operation area according to claim 1 is characterized by: The building vibration behavior evaluation coefficient and the error fluctuation index of the control algorithm are used as input items, and the vibration isolation effect in each monitoring area is used as the output item; Convert the evaluation coefficient, error fluctuation index and vibration isolation effect into fuzzy sets; Convert the actually measured vibration evaluation coefficient and error fluctuation index into member values ​​in the fuzzy set; According to the fuzzy rule base, the input fuzzy set is matched with rules to obtain the corresponding fuzzy output; Using fuzzy reasoning methods, the input items are mapped to output items through fuzzy rules to generate fuzzy output results; The fuzzy output is converted into specific vibration isolation effect through the central value method.

10. A vibration isolation effect evaluation system for existing buildings in a subway operation area, used to implement a vibration isolation effect evaluation method for existing buildings in a subway operation area as claimed in any one of claims 1 to 9, characterized in that: It includes vibration signal acquisition module, abnormal vibration identification module, control algorithm analysis module and vibration isolation effect evaluation module; Vibration signal acquisition module: The subway operation area is divided into several monitoring areas according to the density of existing buildings. n vibration sensors are installed at different locations of the buildings in the monitoring area to capture vibration signals in real time within a fixed time period; Abnormal vibration identification module: After pre-processing the captured vibration signal, the nonlinear characteristics in the vibration signal and the real-time response characteristics of the building's signal under vibration are analyzed to identify the abnormal vibration behavior of the building; Control algorithm analysis module: When the building exhibits abnormal vibration behavior, the error change of the reverse vibration wave calculated by the control algorithm is analyzed, and the reverse vibration wave parameters are dynamically adjusted according to the analysis results; Vibration isolation effect evaluation module: Based on fuzzy logic, the abnormal vibration behavior of the building and the error change of the reverse vibration wave calculated by the control algorithm are comprehensively analyzed. According to the analysis results, the vibration isolation effect in each monitoring area is divided into quality, and an evaluation report is generated. According to the evaluation report, corresponding improvement measures are taken.

Images