BIM shield monitoring system based on fuzzy data query and near neighbor algorithm

Abstract

This invention discloses a BIM-based tunnel boring machine (TBM) monitoring system based on fuzzy data query and nearest neighbor algorithm. The key technical features include: a data acquisition module, a data preprocessing module, a fuzzy data query module, a nearest neighbor algorithm module, path prediction, and a BIM platform integration module. The data acquisition module is used to collect real-time tunneling data of the TBM, including tunneling speed, position, and direction. The data preprocessing module is used to preprocess the collected tunneling data, including noise reduction and outlier handling, to improve the accuracy and reliability of the data. Through modular design and the combination of advanced algorithms, this system achieves comprehensive monitoring of the TBM tunneling process. The modules work closely together, from data acquisition and preprocessing to fuzzy query, prediction, and visualization, providing accurate and efficient monitoring and decision support for TBM construction, thus improving the safety, efficiency, and intelligence level of TBM projects.

Description

Technical Field

[0001] This invention relates to the field of shield tunneling monitoring system technology, specifically to a BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm. Background Technology

[0002] With the rapid advancement of modern urbanization, the scale of underground engineering projects, especially subways and tunnels, is increasing year by year. As the core equipment in tunnel construction, the real-time monitoring and efficient management of the tunneling process of tunnel boring machines (TBMs) is particularly important. However, in practical applications, the tunneling environment of TBMs is complex, and data acquisition is often affected by noise, outliers, and measurement errors. This places high demands on the accuracy and reliability of tunneling data. Traditional monitoring systems mainly rely on simple real-time data acquisition and display functions, making it difficult to effectively handle uncertainties and ambiguities in the data, resulting in poor early warning capabilities and decision support during the tunneling process. Furthermore, under complex underground construction conditions, the tunneling path and direction may deviate from the design trajectory. If this is not detected and corrected in time, it may cause delays in construction progress or potential quality issues.

[0003] In recent years, some studies have begun to introduce fuzzy data processing methods and intelligent algorithms, such as nearest neighbor algorithms and time series analysis, to improve the intelligence level of tunnel boring machine (TBM) monitoring systems. However, there is still a lack of a systematic solution that deeply integrates fuzzy data querying, intelligent algorithms, and BIM information management platforms to achieve comprehensive, real-time monitoring and early warning of the TBM tunneling process. Therefore, this invention provides a BIM-based TBM monitoring system based on fuzzy data querying and nearest neighbor algorithms. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a BIM-based shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm, which solves the problems mentioned in the background section.

[0005] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0006] The BIM-based shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm includes: a data acquisition module, a data preprocessing module, a fuzzy data query module, a nearest neighbor algorithm module, a path prediction module, and a BIM platform integration module.

[0007] The data acquisition module is used to collect tunneling data of the tunnel boring machine in real time, including tunneling speed, position and direction;

[0008] The data preprocessing module is used to preprocess the collected tunneling data, including noise reduction and outlier handling, to improve the accuracy and reliability of the data.

[0009] The fuzzy data query module is used to perform data queries based on fuzzy data points and calculate the similarity between data points in order to handle the uncertainty and fuzziness in the data and improve the accuracy and robustness of data processing.

[0010] The nearest neighbor algorithm module is used to find the data point most similar to the current tunneling position based on the fuzzy data query results and to evaluate the accuracy of the tunneling progress and direction by comparing the nearest neighbor data with the information of the current tunneling position.

[0011] The path prediction module is used to predict the tunneling progress and direction based on the analysis results of the nearest neighbor algorithm module, and generate an early warning signal when the progress is delayed or the direction deviates from the expected direction.

[0012] The BIM platform integration module is used to display the tunneling trajectory, current location, and real-time data of the tunnel boring machine site in a three-dimensional map within the BIM information management platform, and to display early warning information on the tunneling progress and direction in a prominent manner on the three-dimensional map based on the results of the path prediction module.

[0013] Preferably, the data acquisition module includes multiple sensors for acquiring multi-dimensional data of the tunnel boring machine, including but not limited to:

[0014] Speed ​​sensors are used to monitor the tunneling speed of the tunnel boring machine;

[0015] Position sensors are used to determine the real-time position of the tunnel boring machine;

[0016] An orientation sensor is used to monitor the direction of tunnel boring machine excavation.

[0017] The data preprocessing module further includes:

[0018] The noise reduction algorithm unit is used to reduce noise in sensor data through filtering techniques.

[0019] The outlier handling unit is used to detect and correct outliers in the data to ensure the validity of the data.

[0020] Preferably, the fuzzy data query module calculates the similarity of data points through the following steps:

[0021] Define a fuzzy membership function based on the tunneling data;

[0022] The similarity weights of data points are calculated using the membership function;

[0023] Fuzzy search of data points based on similarity weights;

[0024] The evaluation process of the nearest neighbor algorithm module includes:

[0025] A multidimensional feature space is constructed based on the similarity weights output by the fuzzy data query module.

[0026] The nearest neighbor algorithm is used to find the historical data point that is closest to the current tunneling position;

[0027] Compare the current tunneling data with the nearest neighbor data to assess the deviation in tunneling progress and direction;

[0028] The path prediction module uses time series analysis methods, combined with the output of the nearest neighbor algorithm module, to generate prediction results for the tunneling path, and issues early warning signals based on the prediction results.

[0029] The BIM platform integration module includes:

[0030] The 3D visualization unit is used to display the tunneling trajectory and current location of the tunnel boring machine on a 3D map;

[0031] The early warning display unit is used to identify areas that deviate from the expected path or are behind schedule, based on the results of the path prediction module.

[0032] The data interaction unit is used by project managers to query real-time data and early warning information through the platform.

[0033] The BIM platform integration module can interface with other project management systems to achieve information sharing and collaborative management.

[0034] Preferably, the formula for the fuzzy membership function is as follows:

[0035]

[0036] In the formula, μ(x) is the membership degree of data point x; c is the center value; and σ is the fuzzy width.

[0037] The preferred formula for calculating the similarity between the computational data points is as follows:

[0038]

[0039] In the formula, S(x,y) represents the similarity between data points x and y; μ i Let be the membership degree of the i-th feature.

[0040] Preferably, the nearest neighbor distance calculation formula is as follows:

[0041]

[0042] In the formula, d(x,y) is the Euclidean distance between data points x and y; x i y i Let be the value of the i-th feature.

[0043] Preferably, the time series prediction formula of the path prediction module is as follows:

[0044]

[0045] In the formula, The predicted value for the next time step; y t α is the actual value at the current time; α is the smoothing coefficient.

[0046] Preferably, the filtering formula in the noise algorithm unit is as follows:

[0047]

[0048] In the formula, x[t] represents the raw data at time t, and w represents the window size.

[0049] Preferably, the outlier correction formula in the outlier processing unit is as follows:

[0050]

[0051] In the formula, σ is the data mean; σ is the data standard deviation; k is the correction threshold.

[0052] The shield tunneling monitoring method based on fuzzy data query and nearest neighbor algorithm includes the following steps:

[0053] S1: Collect real-time tunneling data from the tunnel boring machine;

[0054] S2: Denoise and outlier processing of the collected data;

[0055] S3: Calculate data point similarity based on fuzzy query;

[0056] S4: Use the nearest neighbor algorithm to find the data point most similar to the current tunneling location;

[0057] S5: Predict the tunneling path and direction based on the nearest neighbor results;

[0058] S6: Display the tunneling trajectory, current location, and early warning information of the tunnel boring machine in real time on the BIM platform.

[0059] In summary, the present invention has the following main beneficial effects:

[0060] This system, through a combination of modular design and advanced algorithms, achieves comprehensive monitoring of the tunnel boring machine (TBM) excavation process. The modules work closely together, from data acquisition and preprocessing to fuzzy querying, prediction, and visualization, providing accurate and efficient monitoring and decision support for TBM construction, thus improving the safety, efficiency, and intelligence of TBM projects.

[0061] The data acquisition module enables real-time acquisition of multi-dimensional data during the tunnel boring machine's excavation process, including core parameters such as excavation speed, position, and direction. It provides comprehensive data support, laying the foundation for subsequent processing and analysis, and ensuring data real-time performance and integrity. The data preprocessing module's denoising algorithm unit effectively reduces noise in the data through filtering formulas, ensuring the smoothness and stability of the input data, improving data reliability, and providing high-quality data for subsequent fuzzy queries and analysis. The outlier handling unit detects and corrects abnormal data points during the acquisition process, eliminating their interference with analysis results, ensuring data validity, and preventing system misjudgments due to outliers. The fuzzy data query module handles uncertainty and fuzziness in the data, weighting the data through fuzzy membership functions, calculating data point similarity based on fuzzy queries, improving the robustness of data analysis, reducing the impact of noise and bias on data queries, and improving the accuracy of data queries, especially ensuring the stability of the algorithm when data is noisy or partially missing.

[0062] The nearest neighbor algorithm module uses the nearest neighbor algorithm to find the closest tunneling state from historical data, providing a reference benchmark for the current tunneling progress and direction. By comparing the current tunneling position with the nearest neighbor point, it accurately assesses the deviation of tunneling progress and direction, improves the system's ability to detect anomalies during the shield tunneling process, and reduces engineering risks caused by tunneling errors.

[0063] The path prediction module combines time series prediction formulas to perform trend analysis on the tunneling path and direction, enabling early warning of the tunneling progress and direction of the tunnel boring machine. This effectively reduces the risk of deviating from the design trajectory during tunneling and promptly alerts managers through early warning signals, thereby improving the safety and efficiency of tunnel boring construction.

[0064] In the BIM platform integration module, the 3D visualization unit intuitively presents the tunneling trajectory, current location, and real-time data of the tunnel boring machine on a 3D map. By dynamically displaying the tunneling process, it facilitates managers to monitor construction progress in real time. The early warning display unit, based on the results of the path prediction module, identifies areas of tunneling path deviation or progress delays, providing prominent reminders to managers and helping the construction team quickly locate problem areas and adjust tunneling strategies in a timely manner. The data interaction unit provides real-time data query and early warning information interaction functions, enabling efficient decision support; it also supports data integration with other management systems to achieve information sharing and collaborative management. Attached Figure Description

[0065] Figure 1 This is a system flowchart of the present invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] refer to Figure 1 The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm includes: a data acquisition module, a data preprocessing module, a fuzzy data query module, a nearest neighbor algorithm module, a path prediction module, and a BIM platform integration module.

[0068] The data acquisition module is used to collect tunneling data of the tunnel boring machine in real time, including tunneling speed, position and direction;

[0069] The data preprocessing module is used to preprocess the collected tunneling data, including noise reduction and outlier handling, to improve the accuracy and reliability of the data.

[0070] The fuzzy data query module is used to perform data queries based on fuzzy data points and calculate the similarity between data points in order to handle the uncertainty and fuzziness in the data and improve the accuracy and robustness of data processing.

[0071] The nearest neighbor algorithm module is used to find the data point most similar to the current tunneling position based on the fuzzy data query results and to evaluate the accuracy of the tunneling progress and direction by comparing the nearest neighbor data with the information of the current tunneling position.

[0072] The path prediction module is used to predict the tunneling progress and direction based on the analysis results of the nearest neighbor algorithm module, and generate an early warning signal when the progress is delayed or the direction deviates from the expected direction.

[0073] The BIM platform integration module is used to display the tunneling trajectory, current location, and real-time data of the tunnel boring machine (TBM) work site on a 3D map within the BIM information management platform. Based on the path prediction module's results, it also prominently displays early warning information regarding tunneling progress and direction on the 3D map. The data acquisition module includes various sensors for collecting multi-dimensional data from the TBM, including but not limited to:

[0074] Speed ​​sensors are used to monitor the tunneling speed of the tunnel boring machine;

[0075] Position sensors are used to determine the real-time position of the tunnel boring machine;

[0076] An orientation sensor is used to monitor the direction of tunnel boring machine excavation.

[0077] The data preprocessing module further includes:

[0078] The noise reduction algorithm unit is used to reduce noise in sensor data through filtering techniques.

[0079] The outlier handling unit is used to detect and correct outliers in the data to ensure the validity of the data.

[0080] The fuzzy data query module calculates the similarity of data points through the following steps:

[0081] Define a fuzzy membership function based on the tunneling data;

[0082] The similarity weights of data points are calculated using the membership function;

[0083] Fuzzy search of data points based on similarity weights;

[0084] The evaluation process of the nearest neighbor algorithm module includes:

[0085] A multidimensional feature space is constructed based on the similarity weights output by the fuzzy data query module.

[0086] The nearest neighbor algorithm is used to find the historical data point that is closest to the current tunneling position;

[0087] Compare the current tunneling data with the nearest neighbor data to assess the deviation in tunneling progress and direction;

[0088] The path prediction module uses time series analysis methods, combined with the output of the nearest neighbor algorithm module, to generate prediction results for the tunneling path, and issues early warning signals based on the prediction results.

[0089] The BIM platform integration module includes:

[0090] The 3D visualization unit is used to display the tunneling trajectory and current location of the tunnel boring machine on a 3D map;

[0091] The early warning display unit is used to identify areas that deviate from the expected path or are behind schedule, based on the results of the path prediction module.

[0092] The data interaction unit is used by project managers to query real-time data and early warning information through the platform.

[0093] The BIM platform integration module can interface with other project management systems to achieve information sharing and collaborative management.

[0094] The formula for the fuzzy membership function is as follows:

[0095]

[0096] In the formula, μ(x) is the membership degree of data point x; c is the center value; σ is the fuzzy width;

[0097] The formula for calculating the similarity between the data points is as follows:

[0098]

[0099] In the formula, S(x,y) represents the similarity between data points x and y; μ i Let be the membership degree of the i-th feature;

[0100] The formula for calculating the nearest neighbor distance is as follows:

[0101]

[0102] In the formula, d(x,y) is the Euclidean distance between data points x and y; x i y i Let i be the value of the i-th feature;

[0103] The time series prediction formula of the path prediction module is as follows:

[0104]

[0105] In the formula, The predicted value for the next time step; y t The actual value at the current time; α is the smoothing coefficient;

[0106] The filtering formula in the noise algorithm unit is as follows:

[0107]

[0108] In the formula, x[t] represents the raw data at time t, and w represents the window size;

[0109] The outlier correction formula in the outlier processing unit is as follows:

[0110]

[0111] In the formula, σ is the data mean; σ is the data standard deviation; k is the correction threshold.

[0112] The shield tunneling monitoring method based on fuzzy data query and nearest neighbor algorithm includes the following steps:

[0113] S1: Collect real-time tunneling data from the tunnel boring machine;

[0114] S2: Denoise and outlier processing of the collected data;

[0115] S3: Calculate data point similarity based on fuzzy query;

[0116] S4: Use the nearest neighbor algorithm to find the data point most similar to the current tunneling location;

[0117] S5: Predict the tunneling path and direction based on the nearest neighbor results;

[0118] S6: Display the tunneling trajectory, current location, and early warning information of the tunnel boring machine in real time on the BIM platform.

[0119] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A BIM-based shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm, characterized in that, include: Data acquisition module, data preprocessing module, fuzzy data query module, nearest neighbor algorithm module, path prediction, and BIM platform integration module; The data acquisition module, This includes speed sensors, position sensors, and orientation sensors, used to collect tunneling data of the tunnel boring machine in real time, including tunneling speed, position, and direction; The data preprocessing module includes a noise reduction algorithm unit for reducing noise in sensor data through filtering techniques; and an outlier processing unit for detecting and correcting outliers in the data to ensure data validity. To improve the accuracy and reliability of the data; The fuzzy data query module is used to perform data queries based on fuzzy data points, calculate the similarity between data points, handle the uncertainty and fuzziness in the data, improve the accuracy and robustness of data processing, and calculate the similarity of data points through the following steps: Define a fuzzy membership function based on the tunneling data; The similarity weights of data points are calculated using the membership function; Fuzzy search of data points based on similarity weights; The nearest neighbor algorithm module is used to find the data point most similar to the current tunneling position based on the fuzzy data query results. By comparing the nearest neighbor data with the information of the current tunneling position, the accuracy of the tunneling progress and direction is evaluated. The evaluation process of the nearest neighbor algorithm module includes: A multidimensional feature space is constructed based on the similarity weights output by the fuzzy data query module. The nearest neighbor algorithm is used to find the historical data point that is closest to the current tunneling position; Compare the current tunneling data with the nearest neighbor data to assess the deviation in tunneling progress and direction; The path prediction is used to predict the tunneling progress and direction based on the analysis results of the nearest neighbor algorithm module, and to generate an early warning signal when the progress is lagging or the direction deviates from the expected direction. The path prediction uses time series analysis method, combined with the output of the nearest neighbor algorithm module, to generate the predicted tunneling path, and issues an early warning signal based on the predicted results. The BIM platform integration module is used to display the tunneling trajectory, current location, and real-time data of the tunnel boring machine (TBM) site on a 3D map within the BIM information management platform, and to prominently display early warning information on the tunneling progress and direction based on path prediction results on the 3D map. The BIM platform integration module includes: The 3D visualization unit is used to display the tunneling trajectory and current location of the tunnel boring machine on a 3D map; The early warning display unit is used to identify areas that deviate from the expected path or are behind schedule, based on the results of path prediction. The data interaction unit is used by project managers to query real-time data and early warning information through the platform. The BIM platform integration module can interface with other project management systems to achieve information sharing and collaborative management.

2. The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm according to claim 1, characterized in that, The formula for the fuzzy membership function is as follows: In the formula For data points Membership degree; The center value; The width is blurred.

3. The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm according to claim 2, characterized in that, The formula for calculating the similarity between the data points is as follows: In the formula, For data points and Similarity; For the first Membership degree of each feature.

4. The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm according to claim 3, characterized in that, The formula for calculating the nearest neighbor distance is as follows: In the formula, For data points and The Euclidean distance; For the first The values ​​of each feature.

5. The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm according to claim 4, characterized in that, The time series prediction formula for the path prediction is as follows: In the formula, This is the predicted value for the next time step; This is the actual value at the current time; This is the smoothing coefficient.

6. The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm according to claim 5, characterized in that, The filtering formula in the noise algorithm unit is as follows: In the formula, For time raw data This refers to the window size.

7. The BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm according to claim 6, characterized in that, The outlier correction formula in the outlier processing unit is as follows: In the formula, This represents the data mean. The standard deviation of the data; To correct the threshold.

8. A shield tunneling monitoring method based on fuzzy data query and nearest neighbor algorithm, wherein the BIM shield tunneling monitoring system based on fuzzy data query and nearest neighbor algorithm as described in any one of claims 1-7 is characterized in that, Includes the following steps: S1: Collect real-time tunneling data from the tunnel boring machine; S2: Denoise and outlier processing of the collected data; S3: Calculate data point similarity based on fuzzy query; S4: Use the nearest neighbor algorithm to find the data point most similar to the current tunneling location; S5: Predict the tunneling path and direction based on the nearest neighbor results; S6: Display the tunneling trajectory, current location, and early warning information of the tunnel boring machine in real time on the BIM platform.

Images