Method for monitoring and early warning of grouting under plate

Abstract

The application discloses a method for monitoring and early warning of plate grouting, which comprises the following steps: S1: collecting grouting data, wherein the grouting data comprises grouting time data, grouting material consumption data and grouting pressure data; S2: preprocessing the grouting data, performing outlier analysis on the preprocessed grouting data, obtaining grouting data outliers, and performing grouting alarm; S3: performing correlation analysis on the preprocessed grouting data and grouting parameters, and obtaining correlation analysis results; wherein the grouting parameters comprise grouting flow rate and pipe wall vibration condition; and S4: adjusting the grouting parameters based on the correlation analysis results, and obtaining grouting prediction results. Through comprehensive recording of the change trend characteristics of the grouting time, the grouting material consumption and the grouting pressure, the method realizes monitoring of the grouting and early warning of abnormal conditions, improves the grouting efficiency, and saves the grouting cost.

Description

Technical Field

[0001] This invention belongs to the field of grouting monitoring technology under slabs, and specifically relates to a method for monitoring and early warning of grouting under slabs. Background Technology

[0002] Current grouting monitoring methods lack a comprehensive approach to recording grouting time, material usage, and pressure variation trends. Traditional grouting typically uses mechanical pressure and flow meters, which only monitor parameters at a specific point in time. When grouting pressure rises rapidly and remains high, negligence in instrument checks by grouting personnel can easily lead to damage to grouting pipelines. Furthermore, real-time data on pressure and flow during grouting provides crucial feedback on the geological conditions of the grouting formation, serving as a reliable reference for dynamic adjustments. The timely and accurate provision of this data significantly impacts the safety and quality of grouting. Therefore, a method for monitoring and early warning of under-slab grouting is urgently needed, aiming to achieve better grouting results through parameter adjustments. Summary of the Invention

[0003] This invention aims to address the shortcomings of existing technologies by proposing a method for monitoring and early warning of grouting under slabs. By comprehensively recording the grouting time, grouting material dosage, and grouting pressure change trends, the method enables monitoring of grouting and early warning of abnormal situations, thereby improving grouting efficiency and saving grouting costs.

[0004] To achieve the above objectives, the present invention provides the following solution:

[0005] The method for monitoring and early warning of grouting under slabs includes the following steps:

[0006] S1: Collect grouting data, wherein the grouting data includes grouting time data, grouting material usage data, and grouting pressure data;

[0007] S2: Preprocess the grouting data, perform outlier analysis on the preprocessed grouting data, obtain outlier values ​​in the grouting data, and trigger a grouting alarm;

[0008] S3: Perform correlation analysis on the preprocessed grouting data and grouting parameters to obtain the correlation analysis results; wherein, the grouting parameters include grouting flow rate and pipe wall vibration.

[0009] S4: Based on the correlation analysis results, adjust the grouting parameters to obtain grouting prediction results.

[0010] Preferably, in step S1, the method for collecting the grouting data is as follows:

[0011] Based on the flow controller, the grouting flow rate in the grouting pipe is controlled. When fluid passes through the grouting pipe, timing starts. When the grouting flow rate is less than a preset flow rate threshold, grouting and timing stop, and the grouting time data is obtained.

[0012] Based on the flow meter, the grouting volume is obtained; based on the grouting volume, the amount of grouting material used is obtained.

[0013] Based on the grouting time data and the grouting volume, the void volume under the slab is obtained, and based on the void volume under the slab, the grouting pressure data is obtained.

[0014] Preferably, in step S2, the method for obtaining the abnormal values ​​of the grouting data is as follows:

[0015] Based on the grouting time data and the grouting volume, dissimilarity matrices based on Euclidean distance are established respectively.

[0016] Based on the dissimilarity matrix, calculate the correlation matrix;

[0017] Based on the correlation degree matrix, calculate the correlation probability matrix;

[0018] Based on the aforementioned correlation probability matrix, an anomaly probability vector is obtained;

[0019] Based on the aforementioned anomaly probability vector, abnormal values ​​of grouting time data and abnormal values ​​of grouting volume are obtained respectively.

[0020] Based on the abnormal values ​​of the grouting time data and the abnormal values ​​of the grouting volume data, abnormal values ​​of the grouting material usage data and the abnormal values ​​of the grouting pressure data are obtained.

[0021] Preferably, in step S3, the method for obtaining the correlation analysis results is as follows:

[0022] The grouting time, grouting material usage, and grouting pressure are taken as dependent variables, and the grouting parameters are taken as independent variables. A functional relationship between the dependent variables and the independent variables is established.

[0023] Based on the functional relationship, the main factors and interaction factors affecting the dependent variable are obtained;

[0024] The main factors and the interaction factors are sorted to obtain the correlation analysis results between the grouting data and the grouting parameters.

[0025] Preferably, in step S4, the method for obtaining the grouting prediction result is as follows:

[0026] Based on the correlation analysis results, the grouting parameters are adjusted by preset adjustment units.

[0027] Based on the adjustment of the grouting parameters and the corresponding void volume under the slab, the predicted values ​​of grouting time, grouting material consumption, and grouting pressure are obtained, thus completing the monitoring and prediction of the grouting situation under the slab.

[0028] Preferably, a BP neural network is used to predict the grouting situation. The specific method is as follows:

[0029] A dataset is established based on the adjusted grouting parameters and the corresponding void volume under the slab;

[0030] The dataset was trained using a BP neural network with initial weights and initial thresholds to obtain training results; the training results are preliminary predicted values ​​for grouting time, grouting material usage, and grouting pressure.

[0031] The expected values ​​for grouting time, grouting material usage, and grouting pressure are taken as the expected results.

[0032] The training result is compared with the expected result. Based on the comparison result, it is determined whether the convergence condition has been met. If yes, the training ends. If no, the initial weights and the initial threshold are optimized, and training continues.

[0033] Preferably, the method for optimizing the initial weights and the initial threshold using the eagle flock algorithm is as follows:

[0034] The weights and thresholds are used as independent variables, and the first fitness value corresponding to the independent variables is calculated.

[0035] Global optimization is performed on the independent variable factors to obtain the second fitness value;

[0036] The independent variable factors obtained after global optimization are locally optimized to obtain the third fitness value;

[0037] Based on the first fitness value, the second fitness value, and the third fitness value, the initial weight and the initial threshold are optimized.

[0038] Preferably, the method further includes establishing a grouting pressure diagram with grouting time data as the vertical axis and grouting pressure data as the horizontal axis; visualizing the grouting pressure diagram to monitor the grouting pressure under the slab.

[0039] Compared with existing technologies, the advantages of this invention are as follows: This invention comprehensively collects and records grouting time, grouting material dosage, and grouting pressure, realizing intelligent monitoring and prediction of grouting. Based on outlier alarms and pressure map visualization, it reduces unnecessary grouting cost consumption and improves grouting efficiency and safety. Attached Figure Description

[0040] To more clearly illustrate the technical solution of the present invention, the drawings used in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 This is a flowchart of the method for monitoring and early warning of grouting under slabs according to an embodiment of the present invention. Detailed Implementation

[0042] 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.

[0043] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0044] Example 1

[0045] like Figure 1 As shown, the method for monitoring and early warning of grouting under slabs includes the following steps:

[0046] S1: Collect grouting data, including grouting time data, grouting material usage data, and grouting pressure data;

[0047] A further implementation method is that, in step S1, the method for collecting grouting data is as follows:

[0048] Based on a flow controller, the grouting flow rate in the grouting pipe is controlled. Timing starts when fluid passes through the grouting pipe, and stops when the grouting flow rate is less than a preset flow rate threshold, thus obtaining grouting time data. In practice, it has been shown that the grouting time in adjacent slab areas is highly correlated. Areas with longer grouting times tend to have longer grouting times due to more severe voids under the slab. This can be addressed by adding a flow controller to the grouting pipe close to the grouting head. Timing starts when fluid is detected passing through the grouting pipe, and stops when the flow rate is less than a certain threshold. The grouting time is then announced via voice.

[0049] Based on the flow meter, the grouting volume is obtained; based on the grouting volume, the amount of grouting material used is obtained. Because the voids under the slab vary, the consumption of grouting material also differs significantly. Furthermore, grout leakage can occur, and the owner cannot observe the grouting volume, which can lead to a series of unnecessary problems. Therefore, monitoring the grouting volume is essential. This method involves adding a flow meter to the grouting pipe. After each hole is grouted, the flow rate used in that hole is displayed and recorded. This data can be used to guide the grouting time, volume, and quantity for the next hole. When the grouting volume in a hole exceeds the preset grouting volume, an alarm will sound, prompting the owner to stop grouting.

[0050] Based on the grouting time and grouting volume, the volume of voids under the slab is obtained, and based on the volume of voids under the slab, the grouting pressure is obtained.

[0051] S2: Preprocess the grouting data and perform outlier analysis on the preprocessed grouting data to obtain outlier values ​​and trigger a grouting alarm;

[0052] A further implementation method is that, in step S2, the method for obtaining abnormal values ​​in the grouting data is as follows:

[0053] Based on grouting time data and grouting volume, dissimilarity matrices based on Euclidean distance are established respectively; where the dissimilarity matrix is ​​a data feature matrix, and by collecting a large amount of actual grouting time data and grouting volume, the feature distribution of grouting time data and the feature distribution of grouting volume are obtained.

[0054] Calculate the correlation matrix based on the dissimilarity matrix;

[0055] Based on the correlation degree matrix, the correlation probability matrix is ​​calculated; specifically, the correlation degree matrix is ​​normalized to obtain the correlation probability matrix.

[0056] Based on the correlation probability matrix, the anomaly probability vector is obtained;

[0057] Based on the anomaly probability vector, the abnormal values ​​of grouting time data and grouting volume data are obtained respectively. Specifically, each anomaly probability vector corresponds to a data point. When a data point is very small compared to all other data points, this data point is an anomaly point, that is, the abnormal value of grouting time data or the abnormal value of grouting volume data is obtained.

[0058] Based on the outliers in grouting time and grouting volume data, outliers in grouting material usage and grouting pressure data were obtained.

[0059] S3: Perform correlation analysis on the pre-processed grouting data and grouting parameters to obtain the correlation analysis results; among which, the grouting parameters include grouting flow rate and pipe wall vibration.

[0060] Factors causing pipe wall vibration include: 1. Loose or unstable grouting pipes: Loose or unstable grouting pipes can cause vibration during operation, leading to reduced grouting effect and work efficiency. 2. Excessive pump body vibration: Excessive vibration of the grouting machine pump body can be transmitted to the grouting pipes, causing pipe vibration and affecting the grouting effect. 3. Poor fluidity of the grouting material: Poor fluidity of the grouting material can lead to insufficient pressure in the grouting pump, which in turn can cause pipe vibration.

[0061] Therefore, different pipe wall vibration conditions will result in different grouting conditions. In this embodiment, the pipe wall vibration condition is described using the position data of the grouting pipe and the position data of the grouting pump body.

[0062] A further implementation method is that, in step S3, the method for obtaining the correlation analysis results is as follows:

[0063] Using grouting time, grouting material usage, and grouting pressure as dependent variables and grouting parameters as independent variables, a functional relationship between the dependent and independent variables is established. Regarding the functional relationship, two-dimensional coordinate graphs of grouting time, grouting material usage, grouting pressure, and grouting parameters are established. The relationship coefficients between grouting data and grouting parameters are obtained from the two-dimensional coordinate graphs, and the functional relationship is obtained based on the relationship coefficients.

[0064] Based on the functional relationship, we obtain the main factors and interaction factors that affect the dependent variable. The main factor, or main effect, is the difference between different levels of a factor. The interaction factor, or interaction effect, is the phenomenon that the difference between different levels of a factor changes with the different levels of other factors.

[0065] The main factors and interaction factors were ranked to obtain the correlation analysis results between grouting data and grouting parameters.

[0066] S4: Based on the correlation analysis results, adjust the grouting parameters to obtain the grouting prediction results.

[0067] A further implementation method is that, in step S4, the method for obtaining the grouting prediction result is as follows:

[0068] Based on the correlation analysis results, the adjustment unit is preset, and the grouting parameters are adjusted.

[0069] Based on the adjustment of grouting parameters and the corresponding void volume under the slab, the predicted values ​​of grouting time, grouting material consumption, and grouting pressure are obtained, thus completing the monitoring and prediction of the grouting situation under the slab.

[0070] A further implementation method involves using a BP neural network to predict grouting conditions. The specific method is as follows:

[0071] A dataset was created based on the adjusted grouting parameters and the corresponding void volume under the slab.

[0072] A BP neural network with initial weights and initial thresholds was used to train the dataset to obtain training results; the training results are preliminary predicted values ​​for grouting time, grouting material usage, and grouting pressure.

[0073] The expected values ​​for grouting time, grouting material usage, and grouting pressure are taken as the expected results.

[0074] The training results are compared with the expected results. Based on the comparison results, it is determined whether the convergence condition has been met. If yes, the training ends; if no, the initial weights and initial thresholds are optimized, and training continues.

[0075] A further implementation method involves using the eagle flock algorithm to optimize the initial weights and initial thresholds as follows:

[0076] Use weights and thresholds as independent variables, and calculate the first fitness value corresponding to the independent variable factors;

[0077] Global optimization is performed on the independent variable factors to obtain the second fitness value;

[0078] Local optimization is performed on the independent variable factors after global optimization to obtain the third fitness value;

[0079] Based on the first fitness value, the second fitness value, and the third fitness value, the initial weights and the initial threshold are optimized.

[0080] Specifically, the obtained first fitness value, second fitness value and third fitness value are compared with the preset minimum fitness value, the fitness value of the objective function is updated, and the independent variable factor corresponding to the updated minimum fitness value of the objective function is recorded.

[0081] The updated fitness value is compared again with the preset minimum fitness value until the comparison result reaches the preset range, at which point the update stops and the optimization is complete.

[0082] A further implementation includes establishing a grouting pressure graph with grouting time data as the vertical axis and grouting pressure data as the horizontal axis; visualizing the grouting pressure graph to monitor the grouting pressure under the slab. Users can observe the grouting situation in real time based on changes in the grouting pressure graph.

[0083] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Various modifications and improvements made to the technical solutions of the present invention by those skilled in the art without departing from the spirit of the present invention should fall within the protection scope defined by the claims of the present invention.

Claims

1. A method for monitoring and early warning of grouting under slabs, characterized in that, Includes the following steps: S1: Collect grouting data, wherein the grouting data includes grouting time data, grouting material usage data, and grouting pressure data; S2: Preprocess the grouting data, perform outlier analysis on the preprocessed grouting data, obtain outlier values ​​in the grouting data, and trigger a grouting alarm; S3: Perform correlation analysis on the preprocessed grouting data and grouting parameters to obtain the correlation analysis results; wherein, the grouting parameters include grouting flow rate and pipe wall vibration. S4: Based on the correlation analysis results, adjust the grouting parameters to obtain the grouting prediction results; In step S3, the method for obtaining the correlation analysis results is as follows: The grouting time, grouting material usage, and grouting pressure are taken as dependent variables, and the grouting parameters are taken as independent variables. A functional relationship between the dependent variables and the independent variables is established. Based on the functional relationship, the main factors and interaction factors affecting the dependent variable are obtained; The main factors and the interaction factors are sorted to obtain the correlation analysis results between the grouting data and the grouting parameters.

2. The method for monitoring and early warning of grouting under slabs according to claim 1, characterized in that, In step S1, the method for collecting the grouting data is as follows: Based on the flow controller, the grouting flow rate in the grouting pipe is controlled. When fluid passes through the grouting pipe, timing starts. When the grouting flow rate is less than a preset flow rate threshold, grouting and timing stop, and the grouting time data is obtained. The grouting volume is obtained based on the flow meter. Based on the grouting volume, the amount of grouting material used is obtained; Based on the grouting time data and the grouting volume, the void volume under the slab is obtained, and based on the void volume under the slab, the grouting pressure data is obtained.

3. The method for monitoring and early warning of grouting under slabs according to claim 2, characterized in that, In step S2, the method for obtaining the abnormal values ​​of the grouting data is as follows: Based on the grouting time data and the grouting volume, dissimilarity matrices based on Euclidean distance are established respectively. Based on the dissimilarity matrix, calculate the correlation matrix; Based on the correlation degree matrix, calculate the correlation probability matrix; Based on the aforementioned correlation probability matrix, an anomaly probability vector is obtained; Based on the aforementioned anomaly probability vector, abnormal values ​​of grouting time data and abnormal values ​​of grouting volume are obtained respectively. Based on the abnormal values ​​of the grouting time data and the abnormal values ​​of the grouting volume data, abnormal values ​​of the grouting material usage data and the abnormal values ​​of the grouting pressure data are obtained.

4. The method for monitoring and early warning of grouting under slabs according to claim 1, characterized in that, In step S4, the method for obtaining the grouting prediction result is as follows: Based on the correlation analysis results, the grouting parameters are adjusted by preset adjustment units. Based on the adjustment of the grouting parameters and the corresponding void volume under the slab, the predicted values ​​of grouting time, grouting material consumption, and grouting pressure are obtained, thus completing the monitoring and prediction of the grouting situation under the slab.

5. The method for monitoring and early warning of grouting under slabs according to claim 4, characterized in that, A backpropagation (BP) neural network is used to predict grouting conditions. The specific method is as follows: A dataset is established based on the adjusted grouting parameters and the corresponding void volume under the slab; The dataset was trained using a backpropagation (BP) neural network with initial weights and initial thresholds to obtain training results. The training results are preliminary predictions of grouting time, grouting material usage, and grouting pressure. The expected values ​​for grouting time, grouting material usage, and grouting pressure are taken as the expected results. The training results are compared with the expected results, and based on the comparison results, it is determined whether the convergence condition has been met. If yes, then end the training; if no, optimize the initial weights and the initial threshold, and continue training.

6. The method for monitoring and early warning of grouting under slabs according to claim 5, characterized in that, The method for optimizing the initial weights and the initial threshold using the eagle flock algorithm is as follows: The weights and thresholds are used as independent variables, and the first fitness value corresponding to the independent variables is calculated. Global optimization is performed on the independent variable factors to obtain the second fitness value; The independent variable factors obtained after global optimization are locally optimized to obtain the third fitness value; Based on the first fitness value, the second fitness value, and the third fitness value, the initial weight and the initial threshold are optimized.

7. The method for monitoring and early warning of grouting under slabs according to claim 1, characterized in that, It also includes establishing a grouting pressure diagram with grouting time data as the vertical axis and grouting pressure data as the horizontal axis; visualizing the grouting pressure diagram to monitor the grouting pressure under the slab.

Images