Building structure deformation real-time monitoring method and system

By installing nanotechnology sensors and photonic crystal sensors in the building structure, combining quantum sensing and communication technology, combining multi-sensor data fusion algorithm and blockchain technology, an intelligent adaptive early warning and visualization platform is established, and the building structure is solved. The problems of insufficient accuracy, delay, safety and prediction capabilities in deformation monitoring have achieved efficient and intelligent monitoring and early warning systems.

CN119022871AInactive Publication Date: 2024-11-26FOSHAN ANGUZHI HOUSE INSPECTION & TESTING APPRAISAL CO LTD
View PDF 0 Cites 6 Cited by

Patent Information

Application Number
CN202411115847.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-14
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing building structure deformation monitoring system has problems such as insufficient monitoring accuracy, delay in data transmission, low data processing efficiency, lack of intelligent analysis and early warning mechanisms, data security problems, and lack of visual analysis and prediction capabilities.

Method used

Nanotechnical sensors and photonic crystal sensors are used for deformation data acquisition, combining quantum sensing technology, quantum communication technology, multi-sensor data fusion algorithm, dynamic environmental compensation algorithm, intelligent adaptive early warning mechanism, blockchain technology and mixed reality visualization platform. Carry out real-time data processing and analysis to achieve efficient data transmission and secure storage, and make predictions through machine learning and big data analysis.

Benefits of technology

It improves monitoring accuracy, reduces data transmission delay, enhances data processing capabilities, realizes intelligent early warning and data security, provides intuitive visual analysis and future deformation prediction, and improves the intelligence and foresight of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119022871A_ABST
    Figure CN119022871A_ABST
Patent Text Reader

Abstract

The invention relates to a building structure deformation real-time monitoring method and system. The method comprises the following steps: S1, installing a nanotechnology sensor and a photonic crystal sensor at a key structure position of a building; s2, processing and analyzing the data by a quantum walking technology and a variational auto-encoder; s3, transmitting the data to a central processing unit by using a quantum communication technology; s4, performing real-time analysis in the central processing unit in combination with a multi-sensor data fusion algorithm and a dynamic environment compensation algorithm, and identifying and detecting an abnormal deformation condition; s5, detecting nano-scale micro deformation through interference fringes by a quantum sensing technology; s6, setting an intelligent self-adaptive early warning mechanism; s7, generating a deformation monitoring report; s8, establishing a visual platform based on mixed reality; and S9, on the basis of the generated deformation monitoring report, prediction is carried out by using a multi-dimensional data analysis technology, high-precision, real-time and intelligent building structure deformation monitoring can be realized, and the safety and stability of a building are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of analytical sensing technology, and in particular to a real-time monitoring method and system for building structure deformation. Background Art

[0002] The specific defects are as follows:

[0003] 1. Insufficient monitoring accuracy. Traditional sensors have limited accuracy when monitoring tiny deformations and cannot detect tiny deformations at the nanometer level, resulting in the inability to detect early tiny deformation problems in a timely manner.

[0004] 2. Data transmission delay. The data acquisition system usually has the problem of data transmission delay, which cannot reflect the structural changes of the building in real time, affecting the timeliness and accuracy of monitoring.

[0005] 3. Low data processing efficiency. The existing system has deficiencies in data processing efficiency and is unable to quickly process large amounts of real-time monitoring data, resulting in an inability to respond in a timely manner in emergency situations.

[0006] 4. Lack of intelligent analysis and early warning mechanisms. Traditional monitoring methods lack intelligent analysis and early warning mechanisms, making it impossible to conduct in-depth analysis and prediction of monitoring data, and it is difficult to issue early warnings in a timely manner and take corresponding emergency measures.

[0007] 5. Data security issues. The existing monitoring system has security issues during data storage and transmission. Data is easily tampered with or lost, affecting the reliability of monitoring results.

[0008] 6. Lack of visual analysis. Traditional monitoring systems lack intuitive visual analysis methods, making it difficult for engineers to quickly understand and diagnose deformation conditions, which affects the efficiency of monitoring and maintenance.

[0009] 7. Insufficient prediction capability. The existing system lacks the ability to predict future deformation, making it difficult to take preventive measures in advance, which reduces the system's predictability and prevention capabilities.

[0010] Therefore, how to provide a real-time monitoring method and system for building structure deformation is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0011] One object of the present invention is to propose a real-time monitoring method and system for building structure deformation, which aims to solve the defects of the prior art, such as insufficient monitoring accuracy, data transmission delay, low data processing efficiency, lack of intelligent analysis and early warning mechanism, data security issues, lack of visual analysis and insufficient prediction ability.

[0012] A method and system for real-time monitoring of building structure deformation according to an embodiment of the present invention comprises the following steps:

[0013] S1. Install nanotechnology sensors and photonic crystal sensors at key structural locations of buildings to obtain deformation data;

[0014] S2, using quantum sensing technology to detect nano-level deformation data through interference fringes;

[0015] S3, preliminarily processes and analyzes the deformation data collected by the sensor through quantum walk technology and variational autoencoder;

[0016] S4, using quantum communication technology to transmit the initially processed deformation data to a central processing unit;

[0017] S5. In the central processing unit, a multi-sensor data fusion algorithm and a dynamic environment compensation algorithm are combined to perform real-time analysis on the received deformation data, identify and detect abnormal deformation conditions;

[0018] S6. Set up an intelligent adaptive early warning mechanism and use machine learning algorithms to dynamically adjust the early warning threshold. When the monitored deformation data exceeds the preset safety limit, the system automatically issues an alarm and triggers emergency response measures.

[0019] S7, generate a deformation monitoring report, including deformation degree, location, time and cause analysis, and store the report using blockchain technology;

[0020] S8. Establish a mixed reality-based visualization platform to overlay monitoring data and 3D models in real time, and combine deformation monitoring reports to obtain deformation visualization and analysis;

[0021] S9. Based on the generated deformation monitoring report, multi-dimensional data analysis technology is used to predict possible future deformation situations through machine learning and big data analysis, and maintenance recommendations are provided.

[0022] Optionally, the S3 specifically includes:

[0023] S31, deploy edge computing units at each sensor node to perform real-time data processing and analysis;

[0024] S32, transmitting the deformation data collected by the sensor to the edge computing unit through an efficient data interface;

[0025] S33, preprocessing the received raw data using improved singular spectrum analysis, decomposing and reconstructing the signal;

[0026] S34, inputting the data preprocessed by singular spectrum analysis into a convolutional neural network for data compression and feature extraction;

[0027] S35. Using the features extracted from the convolutional neural network, the complexity of the deformation is calculated based on high-dimensional multivariate entropy:

[0028] H(X)=-∑ip(x i )logp(x i );

[0029] Among them, H(X) is the high-dimensional multivariate entropy, p(x i ) is the state x i The probability distribution of

[0030] S36. Input the result obtained by high-dimensional multivariate entropy calculation into the variational autoencoder for nonlinear feature extraction and dimensionality reduction:

[0031]

[0032] in, is the loss function, θ and are the parameters of the generator and the inference machine respectively, z is the latent variable, D KL is the Kullback-Leibler divergence;

[0033] S37, using quantum walk technology to efficiently search and classify low-dimensional features extracted by variational autoencoders;

[0034] S38. Use topological entropy to analyze the topological structure and complexity of data after quantum walk classification;

[0035] S39. Based on the topological features obtained by topological entropy analysis, a graph embedding method is used to perform nonlinear dimensionality reduction and feature extraction of data;

[0036] S310, storing the pre-processed and feature-extracted data in a local cache, waiting to be transmitted to a central processing unit.

[0037] Optionally, the S34 specifically includes:

[0038] S341, the data preprocessed by singular spectrum analysis is used as input data x and input into the nonlinear phase space reconstruction module:

[0039] x(t i )=[x(t),x(t+τ),x(t+2τ),…,x(t+(m-1)τ)];

[0040] Among them, x(t i ) is the reconstructed phase space vector, x(t) is the time series data, τ is the time delay, and m is the embedding dimension;

[0041] S342, reconstruct the phase space vector x(t i) is input into the random walk entropy calculation module to analyze the complexity of the reconstructed data:

[0042]

[0043] Where N is the number of states, p i is the probability distribution of state i, which is calculated by random walk entropy to quantify the complexity of reconstructing data;

[0044] S343, using the calculated random walk entropy RWE i and the reconstructed phase space vector x(t i ), which is input into the fractional Brownian motion calculation module to describe the long-range dependence of the system:

[0045]

[0046] Among them, B H (t) is fractional Brownian motion, H is the Hurst index, Γ is the Gamma function, and B(s) is the standard Brownian motion;

[0047] S344, the obtained fractional Brownian motion value B H (t i ), random walk entropy RWE i and the reconstructed phase space vector x(t i ) to form a comprehensive feature representation X fusion :

[0048]

[0049] S345, the comprehensive feature representation X fusion Input into the convolutional neural network for data compression and feature extraction.

[0050] Optionally, the S5 specifically includes:

[0051] S51, receiving and preprocessing the data transmitted to the central processing unit;

[0052] S52, using a multi-sensor data fusion algorithm to perform fusion processing on the received deformation data;

[0053] S53. Use the improved Markov chain Monte Carlo method for dynamic environment compensation. The fused data is used for the Markov chain Monte Carlo method:

[0054]

[0055] Among them, x k+1 is the next state, K is the transition core, is the weight of the i-th sample, is the observation probability, is the state transition probability, For the proposed distribution;

[0056] S54, perform real-time analysis on the fused and compensated data, identify and detect abnormal deformation, and use phase space reconstruction and embedded entropy for abnormal detection:

[0057] x(t)=[x(t),x(t+τ),x(t+2τ),…,x(t+(m-1)τ)];

[0058]

[0059] Where x(t) is the reconstructed phase space vector, τ is the time delay, m is the embedding dimension, EE is the embedding entropy, and p i is the probability distribution of state i;

[0060] S55, generate a detailed deformation analysis report, including the degree, location and time of deformation, and analyze the possible causes;

[0061] S56. Combine the deformation analysis report with the real-time monitoring data and use topological data analysis to perform further pattern recognition and trend prediction:

[0062] PersistenceDiagram(PD)={(bi,d i )|i=1,…,n};

[0063] Betti k =rank(H k (X));

[0064] Where PD is the persistent graph of persistent homology, b i and d i are the generation and extinction time of the ith homology class, Betti k is the k-th Betti number, representing the rank of the k-dimensional homology group.

[0065] Optionally, the S6 specifically includes:

[0066] S61, receiving the fused and compensated deformation data from the central processing unit as input of the intelligent adaptive early warning system;

[0067] S62, using a deformation data prediction model based on quantum state superposition to train the received deformation data, establish a deformation prediction model M, and convert the received deformation data Z into a quantum state |ψ through quantum state superposition;

[0068] S63, predicting the real-time monitoring data according to the trained deformation prediction model M to obtain a prediction result;

[0069] S64, calculating the prediction error by calculating the difference between the quantum states;

[0070] S65, dynamically adjust the warning threshold T using a fractional-order calculus adaptive control algorithm;

[0071] S66, comparing the real-time monitoring data with the warning threshold T after dynamic adjustment, when the monitored deformation data x(t) exceeds the warning threshold T(t), the system automatically issues an alarm;

[0072] S67, triggering emergency response measures, recording alarm information, including time, location and degree of deformation, and storing the information in a database of a central processing unit. After the alarm is triggered, the system records relevant information for subsequent analysis and processing;

[0073] S68. Use historical alarm data and monitoring data to perform pattern analysis and trend prediction through multi-scale singular spectrum entropy:

[0074]

[0075] Where N is the number of singular values ​​after singular value decomposition, λ i is the i-th singular value, and the multi-scale singular spectral entropy is used to perform pattern analysis and trend prediction by analyzing historical alarm data and monitoring data;

[0076] S69. Dynamically update early warning strategies and emergency response plans based on pattern analysis and trend forecasting results, and use trend forecasting results to adjust early warning strategies and emergency response plans.

[0077] Optionally, the S8 includes the following steps:

[0078] S81, storing the monitored deformation data in the blockchain network;

[0079] S82, using a quantum hash function to perform hash processing on the deformed data to generate a unique identifier for the data;

[0080] S83, packaging the generated quantum hash value together with the deformation data into a block, and adding a timestamp and node identity authentication information to generate a new block;

[0081] S84. Add the newly generated block to the blockchain through the quantum Byzantine fault tolerance algorithm QBFT to synchronize the data;

[0082] S85. Establish a mixed reality-based visualization platform to provide intuitive deformation visualization and analysis by superimposing real-time monitoring data and 3D models;

[0083] S86. Extract the deformation data stored in the blockchain to the visualization platform and perform quantum computing optimized format conversion;

[0084] S87. Use mixed reality devices to overlay deformation data onto the 3D model of the building to generate real-time deformation visualizations, and apply quantum image processing technology to enhance visual effects and data analysis capabilities.

[0085] Optionally, the S9 specifically includes:

[0086] S91, using quantum state geometric transformation to perform dimension reduction and feature extraction on the received raw data;

[0087] S92, reconstruct the reduced-dimensional data through multi-fractal space-time reconstruction to capture its complex dynamic characteristics;

[0088] S93, based on the quantum chain Monte Carlo optimization algorithm, efficient search and classification of reconstructed data:

[0089]

[0090] Where P(x) is the probability distribution of the quantum chain Monte Carlo, w k is the weight, μ k and σ k are the mean and standard deviation of the Gaussian distribution respectively;

[0091] S94, using multi-scale topological entropy difference MTED to calculate the complexity of deformation data;

[0092] S95. Use high-dimensional sparse tensor decomposition (HDSTD) to sparsely represent and analyze the complexity of data;

[0093] S96. Analyze the topological characteristics of data through the quantum embedded persistent coherence QEPH method;

[0094] S97, through quantum multidimensional Fourier transform, QMFT, the frequency domain analysis of the data after topological feature analysis:

[0095]

[0096] Among them, |ψ> is the input quantum state, |k> is the frequency domain quantum state, N is the number of data points, and the data after frequency domain analysis is used for deep fusion;

[0097] S98. The data obtained through quantum multi-dimensional Fourier transform is integrated through quantum view deep learning QVDL technology:

[0098]

[0099] Among them, W1, W2 are weight matrices of different views, f i is the fused function representation, x i is the input data, y i To output data, the fused data is used to provide deformation trend prediction and maintenance recommendations.

[0100] Optionally, the system specifically includes:

[0101] Sensor module: Nanotechnology sensors and photonic crystal sensors are installed at key structural locations of the building to obtain deformation data;

[0102] Distributed edge computing nodes: perform preliminary processing and analysis on the data collected by sensors;

[0103] Data transmission module: uses quantum communication technology to transmit the initially processed data to the central processing unit;

[0104] Central processing unit: Combines multi-sensor data fusion algorithm and dynamic environment compensation algorithm to analyze the received deformation data in real time, identify and detect abnormal deformation;

[0105] Quantum sensing technology module: detects tiny deformations at the nanometer level through interference fringes;

[0106] Intelligent adaptive early warning mechanism: Using machine learning algorithms to dynamically adjust the early warning threshold, when the monitored deformation data exceeds the preset safety limit, the system automatically issues an alarm and triggers emergency response measures;

[0107] Report generation module: Generates deformation monitoring reports, including deformation degree, location, time and cause analysis, and stores reports using blockchain technology;

[0108] Visualization platform: Establish a visualization platform based on mixed reality (MR), overlay monitoring data and 3D models in real time, and provide intuitive deformation visualization and analysis;

[0109] Multidimensional data analysis module: Utilizes multidimensional data analysis technology, through machine learning and big data analysis, to predict possible future deformation and provide maintenance recommendations.

[0110] Beneficial Effects

[0111] 1. Improve monitoring accuracy: By adopting nanotechnology sensors and photonic crystal sensors, nano-level deformation monitoring is achieved, which greatly improves the monitoring accuracy and can detect early minor deformation problems in time.

[0112] 2. Reduce data transmission delay: Use distributed edge computing nodes to perform preliminary processing and analysis of data, effectively reduce data transmission delay, and improve the system's real-time response capability.

[0113] 3. Enhanced data processing capabilities: Combined with multi-sensor data fusion algorithm and dynamic environment compensation algorithm, deformation data can be efficiently processed and analyzed to ensure that the system can quickly identify and detect abnormal deformation.

[0114] 4. Realize intelligent early warning: Set up an intelligent adaptive early warning mechanism and use machine learning algorithms to dynamically adjust the early warning threshold to ensure that the system can automatically issue an alarm when the deformation data exceeds the safety limit and trigger emergency response measures, thereby improving the intelligence level of the monitoring system.

[0115] 5. Ensure data security: By generating deformation monitoring reports and storing them using blockchain technology, the data is ensured to be tamper-proof and highly secure, providing a reliable data storage solution for deformation monitoring.

[0116] 6. Provide intuitive visual analysis: Establish a mixed reality-based visualization platform to overlay monitoring data and 3D models in real time, provide intuitive deformation visualization and analysis, and significantly improve engineers’ diagnostic efficiency.

[0117] 7. Enhanced prediction capabilities: Utilize multi-dimensional data analysis technology, through machine learning and big data analysis, predict possible future deformation situations and provide maintenance suggestions, thus enhancing the system's predictability and prevention capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0118] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0119] Figure 1 A summary diagram of a method and system for real-time monitoring of building structure deformation proposed by the present invention;

[0120] Figure 2 The flowchart of claim 3 of a real-time monitoring method and system for building structure deformation proposed by the present invention;

[0121] Figure 3 The flowchart of claim 4 of a real-time monitoring method and system for building structure deformation proposed by the present invention;

[0122] Figure 4 This is the flow chart of claim 8 of the real-time monitoring method and system for building structure deformation proposed by the present invention. DETAILED DESCRIPTION

[0123] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0124] refer to Figure 1-3 , a real-time monitoring method and system for building structure deformation, comprising the following steps:

[0125] S1. Install nanotechnology sensors and photonic crystal sensors at key structural locations of buildings to obtain deformation data;

[0126] S2, using quantum sensing technology to detect nano-level deformation data through interference fringes;

[0127] S3, preliminarily processes and analyzes the deformation data collected by the sensor through quantum walk technology and variational autoencoder;

[0128] S4, using quantum communication technology to transmit the initially processed deformation data to a central processing unit;

[0129] S5. In the central processing unit, a multi-sensor data fusion algorithm and a dynamic environment compensation algorithm are combined to perform real-time analysis on the received deformation data, identify and detect abnormal deformation conditions;

[0130] S6. Set up an intelligent adaptive early warning mechanism and use machine learning algorithms to dynamically adjust the early warning threshold. When the monitored deformation data exceeds the preset safety limit, the system automatically issues an alarm and triggers emergency response measures.

[0131] S7, generate a deformation monitoring report, including deformation degree, location, time and cause analysis, and store the report using blockchain technology;

[0132] S8. Establish a mixed reality-based visualization platform to overlay monitoring data and 3D models in real time, and combine deformation monitoring reports to obtain deformation visualization and analysis;

[0133] S9. Based on the generated deformation monitoring report, multi-dimensional data analysis technology is used to predict possible future deformation situations through machine learning and big data analysis, and maintenance recommendations are provided.

[0134] In this implementation, S3 specifically includes:

[0135] S31, deploy edge computing units at each sensor node to perform real-time data processing and analysis;

[0136] S32, transmitting the deformation data collected by the sensor to the edge computing unit through an efficient data interface;

[0137] S33, preprocessing the received raw data using improved singular spectrum analysis, decomposing and reconstructing the signal;

[0138] S34, inputting the data preprocessed by singular spectrum analysis into a convolutional neural network for data compression and feature extraction;

[0139] S35. Using the features extracted from the convolutional neural network, the complexity of the deformation is calculated based on high-dimensional multivariate entropy:

[0140] H(X)=-∑ i p(x i )logp(x i );

[0141] Among them, H(X) is the high-dimensional multivariate entropy, p(x i ) is the state x i The probability distribution of

[0142] S36. Input the result obtained by high-dimensional multivariate entropy calculation into the variational autoencoder for nonlinear feature extraction and dimensionality reduction:

[0143]

[0144] in, is the loss function, θ and are the parameters of the generator and the inference machine respectively, z is the latent variable, D KL is the Kullback-Leibler divergence;

[0145] S37, using quantum walk technology to efficiently search and classify low-dimensional features extracted by variational autoencoders;

[0146] S38. Use topological entropy to analyze the topological structure and complexity of data after quantum walk classification;

[0147] S39. Based on the topological features obtained by topological entropy analysis, a graph embedding method is used to perform nonlinear dimensionality reduction and feature extraction of data;

[0148] S310, storing the pre-processed and feature-extracted data in a local cache, waiting to be transmitted to a central processing unit.

[0149] In this implementation manner, the S34 specifically includes:

[0150] S341, the data preprocessed by singular spectrum analysis is used as input data x and input into the nonlinear phase space reconstruction module:

[0151] x(t i )=[x(t),x(t+τ),x(t+2τ),…,x(t+(m-1)τ)];

[0152] Among them, x(t i ) is the reconstructed phase space vector, x(t) is the time series data, τ is the time delay, and m is the embedding dimension;

[0153] S342, reconstruct the phase space vector x(t i ) is input into the random walk entropy calculation module to analyze the complexity of the reconstructed data:

[0154]

[0155] Where N is the number of states, p i is the probability distribution of state i, which is calculated by random walk entropy to quantify the complexity of reconstructing data;

[0156] S343, using the calculated random walk entropy RWE i and the reconstructed phase space vector x(t i ), which is input into the fractional Brownian motion calculation module to describe the long-range dependence of the system:

[0157]

[0158] Among them, B H (t) is fractional Brownian motion, H is the Hurst index, Γ is the Gamma function, and B(s) is the standard Brownian motion;

[0159] S344, the obtained fractional Brownian motion value B H (t i ), random walk entropy RWE i and the reconstructed phase space vector x(t i ) to form a comprehensive feature representation X fusion :

[0160]

[0161] S345, the comprehensive feature representation X fusion Input into the convolutional neural network for data compression and feature extraction.

[0162] In this implementation manner, S5 specifically includes:

[0163] S51, receiving and preprocessing the data transmitted to the central processing unit;

[0164] S52, using a multi-sensor data fusion algorithm to perform fusion processing on the received deformation data;

[0165] S53. Use the improved Markov chain Monte Carlo method for dynamic environment compensation. The fused data is used for the Markov chain Monte Carlo method:

[0166]

[0167] Among them, x k+1 is the next state, K is the transition core, is the weight of the i-th sample, is the observation probability, is the state transition probability, For the proposed distribution;

[0168] S54, perform real-time analysis on the fused and compensated data, identify and detect abnormal deformation, and use phase space reconstruction and embedded entropy for abnormal detection:

[0169] x(t)=[x(t),x(t+τ),x(t+2τ),…,x(t+(m-1)τ)];

[0170]

[0171] Where x(t) is the reconstructed phase space vector, τ is the time delay, m is the embedding dimension, EE is the embedding entropy, and p i is the probability distribution of state i;

[0172] S55, generate a detailed deformation analysis report, including the degree, location and time of deformation, and analyze the possible causes;

[0173] S56. Combine the deformation analysis report with the real-time monitoring data and use topological data analysis to perform further pattern recognition and trend prediction:

[0174] PersistenceDiagram(PD)={(b i ,d i )|i=1,…,n};

[0175] Betti k =rank(H k (X));

[0176] Where PD is the persistent graph of persistent homology, b i and d i are the generation and extinction time of the ith homology class, Betti k is the k-th Betti number, representing the rank of the k-dimensional homology group.

[0177] In this implementation manner, S6 specifically includes:

[0178] S61, receiving the fused and compensated deformation data from the central processing unit as input of the intelligent adaptive early warning system;

[0179] S62, using a deformation data prediction model based on quantum state superposition to train the received deformation data, establish a deformation prediction model M, and convert the received deformation data Z into a quantum state |ψ through quantum state superposition;

[0180] S63, predicting the real-time monitoring data according to the trained deformation prediction model M to obtain a prediction result;

[0181] S64, calculating the prediction error by calculating the difference between the quantum states;

[0182] S65, dynamically adjust the warning threshold T using a fractional-order calculus adaptive control algorithm;

[0183] S66, comparing the real-time monitoring data with the warning threshold T after dynamic adjustment, when the monitored deformation data x(t) exceeds the warning threshold T(t), the system automatically issues an alarm;

[0184] S67, triggering emergency response measures, recording alarm information, including time, location and degree of deformation, and storing the information in a database of a central processing unit. After the alarm is triggered, the system records relevant information for subsequent analysis and processing;

[0185] S68. Use historical alarm data and monitoring data to perform pattern analysis and trend prediction through multi-scale singular spectrum entropy:

[0186]

[0187] Where N is the number of singular values ​​after singular value decomposition, λ i is the i-th singular value, and the multi-scale singular spectral entropy is used to perform pattern analysis and trend prediction by analyzing historical alarm data and monitoring data;

[0188] S69. Dynamically update early warning strategies and emergency response plans based on pattern analysis and trend forecasting results, and use trend forecasting results to adjust early warning strategies and emergency response plans.

[0189] In this implementation manner, the S8 includes the following steps:

[0190] S81, storing the monitored deformation data in the blockchain network;

[0191] S82, using a quantum hash function to perform hash processing on the deformed data to generate a unique identifier for the data;

[0192] S83, packaging the generated quantum hash value together with the deformation data into a block, and adding a timestamp and node identity authentication information to generate a new block;

[0193] S84. Add the newly generated block to the blockchain through the quantum Byzantine fault tolerance algorithm QBFT to synchronize the data;

[0194] S85. Establish a mixed reality-based visualization platform to provide intuitive deformation visualization and analysis by superimposing real-time monitoring data and 3D models;

[0195] S86. Extract the deformation data stored in the blockchain to the visualization platform and perform quantum computing optimized format conversion;

[0196] S87. Use mixed reality devices to overlay deformation data onto the 3D model of the building to generate real-time deformation visualizations, and apply quantum image processing technology to enhance visual effects and data analysis capabilities.

[0197] In this implementation manner, the S9 specifically includes:

[0198] S91, using quantum state geometric transformation to perform dimension reduction and feature extraction on the received raw data;

[0199] S92, reconstruct the reduced-dimensional data through multi-fractal space-time reconstruction to capture its complex dynamic characteristics;

[0200] S93, based on the quantum chain Monte Carlo optimization algorithm, efficient search and classification of reconstructed data:

[0201]

[0202] Where P(x) is the probability distribution of the quantum chain Monte Carlo, w k is the weight, μ k and σ k are the mean and standard deviation of the Gaussian distribution respectively;

[0203] S94, using multi-scale topological entropy difference MTED to calculate the complexity of deformation data;

[0204] S95. Use high-dimensional sparse tensor decomposition (HDSTD) to sparsely represent and analyze the complexity of data;

[0205] S96. Analyze the topological characteristics of data through the quantum embedded persistent coherence QEPH method;

[0206] S97, through quantum multidimensional Fourier transform, QMFT, the frequency domain analysis of the data after topological feature analysis:

[0207]

[0208] Among them, |ψ> is the input quantum state, |k> is the frequency domain quantum state, N is the number of data points, and the data after frequency domain analysis is used for deep fusion;

[0209] S98. The data obtained through quantum multi-dimensional Fourier transform is integrated through quantum view deep learning QVDL technology:

[0210]

[0211] Among them, W1, W2 are weight matrices of different views, f i is the fused function representation, x i is the input data, y i To output data, the fused data is used to provide deformation trend prediction and maintenance recommendations.

[0212] In this implementation, the system specifically includes:

[0213] Sensor module: Nanotechnology sensors and photonic crystal sensors are installed at key structural locations of the building to obtain deformation data;

[0214] Distributed edge computing nodes: perform preliminary processing and analysis on the data collected by sensors;

[0215] Data transmission module: uses quantum communication technology to transmit the initially processed data to the central processing unit;

[0216] Central processing unit: Combines multi-sensor data fusion algorithm and dynamic environment compensation algorithm to analyze the received deformation data in real time, identify and detect abnormal deformation;

[0217] Quantum sensing technology module: detects tiny deformations at the nanometer level through interference fringes;

[0218] Intelligent adaptive early warning mechanism: Using machine learning algorithms to dynamically adjust the early warning threshold, when the monitored deformation data exceeds the preset safety limit, the system automatically issues an alarm and triggers emergency response measures;

[0219] Report generation module: Generates deformation monitoring reports, including deformation degree, location, time and cause analysis, and stores reports using blockchain technology;

[0220] Visualization platform: Establish a visualization platform based on mixed reality (MR), overlay monitoring data and 3D models in real time, and provide intuitive deformation visualization and analysis;

[0221] Multidimensional data analysis module: Utilizes multidimensional data analysis technology, through machine learning and big data analysis, to predict possible future deformation and provide maintenance recommendations.

[0222] Example 1

[0223] In order to verify the feasibility of the present invention in implementation, the present invention was applied to a 50-story commercial complex in the center of Shenzhen, the South China International Building. Due to its location in an area with complex geological conditions and the long-term impact of subway construction and surrounding building construction, it has shown signs of slight structural deformation in recent years. To ensure the safety and stability of the building, the property management company decided to introduce an advanced real-time monitoring system for building structural deformation to continuously monitor the structural deformation of the building and issue a timely warning when abnormal deformation is found.

[0224] The property management company of South China International Building selected the real-time monitoring system for building structure deformation of the present invention, which includes nanotechnology sensors, photonic crystal sensors, distributed edge computing nodes, quantum communication technology, central processing units, quantum sensing technology, intelligent adaptive early warning mechanisms, blockchain technology and a visualization platform based on mixed reality.

[0225] Nanotechnology sensors and photonic crystal sensors are installed at the key structural locations of the building, such as the core tube, beam-column joints and foundation. These sensors can obtain deformation data at the nanometer level with high precision. 200 sensors are evenly distributed on each floor of the core tube to ensure full coverage and monitoring of the building's structural status.

[0226] The data collected by the sensors are transmitted to the distributed edge computing nodes deployed on each floor of the building through efficient data interfaces. These nodes perform preliminary processing and analysis on the data, effectively reducing data transmission delays. The edge computing nodes use an improved singular spectrum analysis method to decompose and reconstruct the data and extract deformation features in real time.

[0227] The processed data is transmitted to the central processing unit through quantum communication technology. Quantum communication technology ensures the efficiency and security of data transmission, avoiding the delay and security issues in traditional data transmission methods.

[0228] In the central processing unit, the received deformation data is analyzed in real time by combining the multi-sensor data fusion algorithm and the dynamic environmental compensation algorithm to identify and detect abnormal deformation. Through the multi-sensor data fusion algorithm, the data of each sensor is comprehensively processed to obtain the overall deformation of the building. At the same time, the dynamic environmental compensation algorithm is used to correct the errors caused by changes in temperature and humidity in the external environment.

[0229] Quantum sensing technology is used to detect tiny deformations at the nanometer level through interference fringes. The introduction of quantum sensing technology enables the system to detect extremely small structural deformations, improving the accuracy of monitoring. During the monitoring process of the South China International Building, subtle displacements of 0.1 nanometers were detected at some beam-column nodes.

[0230] The system has set up an intelligent adaptive early warning mechanism, using machine learning algorithms to dynamically adjust the early warning threshold. When the monitored deformation data exceeds the preset safety limit, the system will automatically issue an alarm and trigger emergency response measures. When the deformation of the core tube of a certain floor exceeds the preset 0.5 mm safety threshold at a certain moment, the system immediately issues an early warning signal and notifies the property management staff to conduct on-site inspection and maintenance.

[0231] The system generates detailed deformation monitoring reports, including deformation degree, location, time and cause analysis, and uses blockchain technology to store the reports to ensure the data is tamper-proof and highly secure. During the one-month monitoring period, the system generated more than 200 deformation monitoring reports, which recorded the deformation of each floor and key nodes in detail.

[0232] A mixed reality-based visualization platform is established to provide intuitive deformation visualization and analysis by superimposing monitoring data and 3D models in real time through MR devices. Property management personnel can directly view the real-time deformation of the building in a virtual reality environment by wearing MR helmets, making more intuitive judgments and decisions.

[0233] Based on the generated deformation monitoring report, the system uses multi-dimensional data analysis technology, machine learning and big data analysis to predict possible deformation in the future and provide maintenance suggestions. By analyzing the monitoring data of the past year, the system predicts that some floors may experience large deformation in the next six months and recommends reinforcement in advance.

[0234] Table 1: Monitoring accuracy data

[0235]

[0236] Table 2: Data transmission delay table

[0237]

[0238] Table 3: Early warning response data table

[0239]

[0240]

[0241] Table 4: Blockchain data storage table

[0242]

[0243]

[0244] Table 5: Multidimensional data analysis and prediction table

[0245]

[0246] From the above figure, it can be concluded that the minimum deformation detected by the sensor is 0.1 nanometers, which is significantly higher than the monitoring accuracy of traditional sensors. Through quantum communication technology, the data transmission delay is reduced to 0.01 seconds, ensuring the real-time nature of the data. The intelligent adaptive early warning mechanism successfully issued 5 early warning signals, one of which timely prevented potential safety hazards caused by structural deformation. All monitoring reports are stored through blockchain technology to ensure the data is tamper-proof and highly secure. The mixed reality-based visualization platform enables engineers to intuitively view deformation conditions, greatly improving diagnostic efficiency and accuracy. Multidimensional data analysis technology predicts possible deformations in the next six months and provides detailed maintenance recommendations, significantly improving the system's predictability and prevention capabilities.

[0247] In summary, the real-time monitoring system for building structure deformation of the present invention effectively solves the defects in the prior art through a high-precision, real-time, and intelligent monitoring and early warning mechanism, ensures the safety and stability of buildings, and provides strong technical support for urban construction and management.

[0248] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A real-time monitoring method for building structure deformation, characterized in that: The steps include: S1. Install nanotechnology sensors and photonic crystal sensors at key structural locations of buildings to obtain deformation data; S2, using quantum sensing technology to detect nano-level deformation data through interference fringes; S3, preliminarily process and analyze the collected deformation data through quantum walk technology and variational autoencoder; S4, using quantum communication technology to transmit the initially processed deformation data to a central processing unit; S5. In the central processing unit, a multi-sensor data fusion algorithm and a dynamic environment compensation algorithm are combined to perform real-time analysis on the received deformation data, identify and detect abnormal deformation conditions; S6. Set up an intelligent adaptive early warning mechanism and use machine learning algorithms to dynamically adjust the early warning threshold. When the monitored deformation data exceeds the preset safety limit, the system automatically issues an alarm and triggers emergency response measures. S7, generate a deformation monitoring report, including deformation degree, location, time and cause analysis, and store the report using blockchain technology; S8. Establish a mixed reality-based visualization platform to overlay monitoring data and 3D models in real time, and combine deformation monitoring reports to obtain deformation visualization and analysis; S9. Based on the generated deformation monitoring report, multi-dimensional data analysis technology is used to predict possible future deformation situations through machine learning and big data analysis, and maintenance recommendations are provided.

2. A real-time monitoring method for building structure deformation according to claim 1, characterized in that: The S3 specifically includes: S31, deploy edge computing units at each sensor node to perform real-time data processing and analysis; S32, transmitting the deformation data collected by the sensor to the edge computing unit through an efficient data interface; S33, preprocessing the received raw data using improved singular spectrum analysis, decomposing and reconstructing the signal; S34, inputting the data preprocessed by singular spectrum analysis into a convolutional neural network for data compression and feature extraction; S35. Using the features extracted from the convolutional neural network, the complexity of the deformation is calculated based on high-dimensional multivariate entropy: H(X)=-∑ i p(x i )logp(x i ); Among them, H(X) is the high-dimensional multivariate entropy, p(x i ) is the state x i The probability distribution of S36. Input the result obtained by high-dimensional multivariate entropy calculation into the variational autoencoder for nonlinear feature extraction and dimensionality reduction: in, is the loss function, θ and are the parameters of the generator and the inference machine respectively, z is the latent variable, D KL is the Kullback-Leibler divergence; S37, using quantum walk technology to efficiently search and classify low-dimensional features extracted by variational autoencoders; S38. Use topological entropy to analyze the topological structure and complexity of data after quantum walk classification; S39. Based on the topological features obtained by topological entropy analysis, a graph embedding method is used to perform nonlinear dimensionality reduction and feature extraction of data; S310, storing the pre-processed and feature-extracted data in a local cache, waiting to be transmitted to a central processing unit.

3. A real-time monitoring method for building structure deformation according to claim 1, characterized in that: The S34 specifically includes: S341, the data preprocessed by singular spectrum analysis is used as input data x and input into the nonlinear phase space reconstruction module: x(t i )=[x(t),x(t+τ),x(t+2τ),...,x(t+(m-1)τ)]; Among them, x(t i ) is the reconstructed phase space vector, x(t) is the time series data, τ is the time delay, and m is the embedding dimension; S342, reconstruct the phase space vector x(t i ) is input into the random walk entropy calculation module to analyze the complexity of the reconstructed data: Where N is the number of states, p i is the probability distribution of state i, which is calculated by random walk entropy to quantify the complexity of reconstructing data; S343, using the calculated random walk entropy RWE i and the reconstructed phase space vector x(t i ), which is input into the fractional Brownian motion calculation module to describe the long-range dependence of the system: Among them, B H (t) is fractional Brownian motion, H is the Hurst index, Γ is the Gamma function, and B(s) is the standard Brownian motion; S344, the obtained fractional Brownian motion value B H (t i ), random walk entropy RWE i and the reconstructed phase space vector x(t i ) to form a comprehensive feature representation X fusion : S345, the comprehensive feature representation X fusion Input into the convolutional neural network for data compression and feature extraction.

4. A real-time monitoring method for building structure deformation according to claim 1, characterized in that: The S5 specifically includes: S51, receiving and preprocessing the data transmitted to the central processing unit; S52, using a multi-sensor data fusion algorithm to perform fusion processing on the received deformation data; S53. Use the improved Markov chain Monte Carlo method for dynamic environment compensation. The fused data is used for the Markov chain Monte Carlo method: Among them, x k+1 is the next state, K is the transition core, is the weight of the i-th sample, is the observation probability, is the state transition probability, For the proposed distribution; S54, perform real-time analysis on the fused and compensated data, identify and detect abnormal deformation, and use phase space reconstruction and embedded entropy for abnormal detection: x(t)=[x(t), x(t+τ), x(t-2τ),..., x(t+(m-1)τ)]; Where x(t) is the reconstructed phase space vector, τ is the time delay, m is the embedding dimension, EE is the embedding entropy, and pi is the probability distribution of state i; S55, generate a detailed deformation analysis report, including the degree, location and time of deformation, and analyze the possible causes; S56. Combine the deformation analysis report with the real-time monitoring data and use topological data analysis to perform further pattern recognition and trend prediction: PersistenceDiagram(PD)={(b i ,di)|i=1,...,n}; Bettii k =rank(H k (X)); Where PD is the persistent graph of persistent homology, b i and d i are the generation and extinction time of the ith homology class, Betti k is the k-th Betti number, representing the rank of the k-dimensional homology group.

5. A real-time monitoring method for building structure deformation according to claim 1, characterized in that: The S6 specifically includes: S61, receiving the fused and compensated deformation data from the central processing unit as input of the intelligent adaptive early warning system; S62, using a deformation data prediction model based on quantum state superposition to train the received deformation data, establish a deformation prediction model M, and convert the received deformation data Z into a quantum state |ψ through quantum state superposition; S63, predicting the real-time monitoring data according to the trained deformation prediction model M to obtain a prediction result; S64, calculating the prediction error by calculating the difference between the quantum states; S65, dynamically adjust the warning threshold T using a fractional-order calculus adaptive control algorithm; S66, comparing the real-time monitoring data with the warning threshold T after dynamic adjustment, when the monitored deformation data x(t) exceeds the warning threshold T, the system automatically issues an alarm; S67, triggering emergency response measures, recording alarm information, including time, location and degree of deformation, and storing the information in a database of a central processing unit. After the alarm is triggered, the system records relevant information; S68. Use historical alarm data and monitoring data to perform pattern analysis and trend prediction through multi-scale singular spectrum entropy: Where N is the number of singular values ​​after singular value decomposition, λ i is the i-th singular value, and the multi-scale singular spectral entropy is used to perform pattern analysis and trend prediction by analyzing historical alarm data and monitoring data; S69. Dynamically update early warning strategies and emergency response plans based on pattern analysis and trend forecasting results, and use trend forecasting results to adjust early warning strategies and emergency response plans.

6. A real-time monitoring method for building structure deformation according to claim 1, characterized in that: The S8 comprises the following steps: S81, storing the monitored deformation data in the blockchain network; S82, using a quantum hash function to perform hash processing on the deformed data to generate a unique identifier for the data; S83, packaging the generated quantum hash value together with the deformation data into a block, and adding a timestamp and node identity authentication information to generate a new block; S84. Add the newly generated block to the blockchain through the quantum Byzantine fault tolerance algorithm QBFT to synchronize the data; S85. Establish a mixed reality-based visualization platform to provide intuitive deformation visualization and analysis by superimposing real-time monitoring data and 3D models; S86. Extract the deformation data stored in the blockchain to the visualization platform and perform quantum computing optimized format conversion; S87. Use mixed reality devices to overlay deformation data onto the 3D model of the building to generate real-time deformation visualizations, and apply quantum image processing technology to enhance visual effects and data analysis capabilities.

7. A real-time monitoring system for building structure deformation according to claim 1, characterized in that: The S9 specifically includes: S91, using quantum state geometric transformation to perform dimension reduction and feature extraction on the received raw data; S92, reconstruct the reduced-dimensional data through multi-fractal space-time reconstruction to capture its complex dynamic characteristics; S93, based on the quantum chain Monte Carlo optimization algorithm, efficient search and classification of reconstructed data: Where P(x) is the probability distribution of the quantum chain Monte Carlo, w k is the weight, μ k and σ k are the mean and standard deviation of the Gaussian distribution respectively; S94, using multi-scale topological entropy difference MTED to calculate the complexity of deformation data; S95. Use high-dimensional sparse tensor decomposition (HDSTD) to sparsely represent and analyze the complexity of data; S96. Analyze the topological characteristics of data through the quantum embedded persistent coherence QEPH method; S97, through quantum multidimensional Fourier transform, QMFT, the frequency domain analysis of the data after topological feature analysis: Among them, |ψ> is the input quantum state, |k> is the frequency domain quantum state, N is the number of data points, and the data after frequency domain analysis is used for deep fusion; S98. The data obtained through quantum multi-dimensional Fourier transform is integrated through quantum view deep learning QVDL technology: Among them, W1, W2 are weight matrices of different views, f i is the fused function representation, x i is the input data, y i To output data, the fused data is analyzed and predicted.

8. A real-time monitoring system for building structure deformation according to claim 1, characterized in that: The system specifically comprises: Sensor module: Nanotechnology sensors and photonic crystal sensors are installed at key structural locations of the building to obtain deformation data; Distributed edge computing nodes: perform preliminary processing and analysis on the data collected by sensors; Data transmission module: uses quantum communication technology to transmit the initially processed data to the central processing unit; Central processing unit: Combines multi-sensor data fusion algorithm and dynamic environment compensation algorithm to perform real-time analysis on the received deformation data and identify and detect abnormal deformation; Quantum sensing technology module: detects tiny deformations at the nanometer level through interference fringes; Intelligent adaptive early warning mechanism: Using machine learning algorithms to dynamically adjust the early warning threshold, when the monitored deformation data exceeds the preset safety limit, the system automatically issues an alarm and triggers emergency response measures; Report generation module: Generates deformation monitoring reports, including deformation degree, location, time and cause analysis, and stores reports using blockchain technology; Visualization platform: Establish a mixed reality-based visualization platform to overlay monitoring data and 3D models in real time; Multidimensional data analysis module: Utilize multidimensional data analysis technology to analyze possible future deformation situations through machine learning and big data analysis.

Citation Information

Cited By

  • Building material quality detection method and system

    CN119395237A

  • High-speed rail surface deformation LSTM prediction method and device based on PS point metadata feature clustering

    CN120217853A

  • Concrete beam stress intelligent monitoring method, device and equipment and storage medium

    CN120805084A

  • Cross-platform document data management method and device

    CN121070888A

  • Advanced early warning method for settlement trend of bridge abutment construction based on convolutional mixed density network

    CN121188707A