Integrated inclinometer monitoring system and method

Abstract

The invention discloses an integrated inclinometer monitoring system and method, and relates to the technical field of integrated inclinometer monitoring, the integrated inclinometer monitoring system comprises a multi-dimensional data acquisition module, a multi-dimensional data preprocessing module, a building monitoring module, an inclination angle deviation monitoring module and an inclination angle deviation early warning module, obtaining multi-dimensional data of the building; the building monitoring module is divided into an inclination angle unit, a displacement unit, a stress-strain unit and a vibration unit, and the inclination angle unit, the displacement unit, the stress-strain unit and the vibration unit are respectively used for acquiring monitoring deviation rates of inclination angle data, displacement data, stress-strain data and vibration data of a building; according to the method, a multi-dimensional data acquisition technology, a data preprocessing technology, a neural network algorithm technology and a modern information technology are closely combined, so that real-time and comprehensive monitoring on the inclination angle deviation of the building is achieved, and the intelligent degree in the monitoring process of the integrated inclinometer is remarkably enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated inclinometer monitoring, and particularly to an integrated inclinometer monitoring system and method. Background Art

[0002] In many engineering fields and scientific researches, the accurate monitoring of the inclination angle of an object is crucial. Traditional monitoring methods have problems such as low data acquisition efficiency, unstable transmission, and limited processing and analysis capabilities. It is necessary to manually go to the site to read data regularly, which not only consumes a large amount of manpower and material resources, but also easily leads to data omission and errors due to human negligence. When transmitting data over a long distance, the signal is easily interfered and lost or distorted, resulting in inaccurate monitoring results. With the rapid development of the Internet of Things, sensor, and communication technologies, an integrated inclinometer monitoring system and method have been widely applied in the fields of buildings, bridge piers, iron towers, high formwork, and bridges, providing a strong guarantee for improving the accuracy, timeliness, intelligent level of monitoring, and the safe and stable operation of various fields. Although the existing technologies have made great progress in the direction of integrated inclinometer monitoring, there are still some problems to be optimized. The monitoring data of the existing integrated inclinometer monitoring technology is single. In building construction, as the building height increases and the structural complexity improves, the building main body will not only tilt, but also be accompanied by other complex deformations. Single monitoring data is difficult to accurately reflect the true state of the building and cannot meet the monitoring requirements under complex working conditions. Moreover, the existing technologies cannot identify the deviation of the monitoring data and respond to the deviation of the monitoring data, resulting in poor monitoring effects. Summary of the Invention

[0003] The purpose of the present invention is to provide an integrated inclinometer monitoring system and method to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the technical solution adopted by the present invention is: In the first aspect, an integrated inclinometer monitoring system includes a multi-dimensional data acquisition module, a multi-dimensional data preprocessing module, a building monitoring module, an inclination deviation monitoring module, and an inclination deviation early warning module, wherein each module is communicatively connected; The multi-dimensional data acquisition module obtains multi-dimensional data of a building through sensors, wherein the multi-dimensional data of the building includes inclination data, displacement data, stress and strain data, and vibration data, providing basic data support for comprehensively monitoring the state of the building; The multi-dimensional data preprocessing module preprocesses the acquired multi-dimensional data of the building, improving the quality of the acquired multi-dimensional data of the building and laying a foundation for subsequent accurate monitoring and analysis; The building monitoring module is divided into an inclination unit, a displacement unit, a stress-strain unit, and a vibration unit. Among them, the inclination unit, displacement unit, stress-strain unit, and vibration unit are respectively used to obtain the monitoring deviation rates of the building inclination data, displacement data, stress-strain data, and vibration data, so as to quantitatively evaluate the monitoring of various aspects of the building data; The inclination deviation monitoring module uses a neural network algorithm to construct an inclination deviation monitoring model, providing an effective technical means for accurately analyzing and predicting the inclination deviation of the building; The inclination deviation warning module uses the inclination deviation monitoring model to evaluate the inclination deviation of the building by monitoring the multi-dimensional data of the building, and sends a signal through a signal lamp.

[0005] A further improvement of the technical solution of the present invention is that the process of the multi-dimensional data acquisition module obtaining the inclination data, displacement data, stress-strain data, and vibration data through sensors includes: The sensors include a MEMS inclination sensor, a laser displacement sensor, a resistance strain gauge stress sensor, and an acceleration sensor; the inclination data is the inclination angle of the building; the displacement data is the horizontal displacement and vertical displacement of the building; the stress-strain data is the stress data and strain data of the building; the vibration data is the vibration frequency and amplitude of the building; Fix the MEMS inclination sensor on the building, and based on MEMS technology, collect the inclination angle of the building; set up a base on the ground, install the laser displacement device on the base, and collect the horizontal displacement and vertical displacement of the building; Paste the resistance strain gauge stress sensor on the surface of the building. The resistance strain gauge stress sensor is internally provided with a resistance strain gauge. Based on the piezoresistive effect of semiconductor materials, collect the stress data and strain data of the building; Install the acceleration sensor on the top floor of the building, set the parameters of the acceleration sensor, based on Newton's second law, measure the time-domain data of the vibration acceleration of the building, and use the Fourier transform algorithm to convert the time-domain data of the vibration acceleration into a vibration acceleration frequency-domain diagram. The peak value in the vibration acceleration frequency-domain diagram is the amplitude of the building, and the frequency corresponding to the peak value in the vibration acceleration frequency-domain diagram is the vibration frequency of the building.

[0006] A further improvement of the technical solution of the present invention is that the process of the multi-dimensional data preprocessing module preprocessing the collected multi-dimensional data of the building includes: Adopt the mean filtering method to denoise the collected multi-dimensional data of the building; calibrate the collected data according to the calibration parameters to remove the error values in the collected multi-dimensional data of the building; according to the building material and structure, set thresholds for the inclination angle, horizontal displacement, vertical displacement, stress data, strain data, vibration frequency, and amplitude of the building respectively, and remove the data greater than the threshold.

[0007] A further improvement of the technical solution of the present invention lies in that: the process of the inclination angle unit obtaining the monitoring deviation rate of the building inclination angle data includes: The process of obtaining the monitoring deviation rate of the building inclination angle data by using the inclination angle threshold of the building is as follows:

[0008] Wherein, U is the monitoring deviation rate of the building inclination angle data, is the inclination angle of the building, is the inclination angle threshold of the building.

[0009] A further improvement of the technical solution of the present invention lies in that: the process of the displacement unit obtaining the monitoring deviation rate of the building displacement data includes: The monitoring deviation rate of the building displacement data is composed of the monitoring deviation rate of the building horizontal displacement and the monitoring deviation rate of the building vertical displacement. Set the monitoring weight of the building horizontal displacement and the monitoring weight of the building vertical displacement; The process of obtaining the monitoring deviation rate of the building horizontal displacement by using the horizontal displacement threshold of the building is as follows:

[0010] Wherein, K is the monitoring deviation rate of the building horizontal displacement, is the horizontal displacement of the building, and is the horizontal displacement threshold of the building; The process of obtaining the monitoring deviation rate of the building vertical displacement by using the vertical displacement threshold of the building is as follows:

[0011] Wherein, V is the monitoring deviation rate of the building vertical displacement, is the vertical displacement of the building, is the vertical displacement threshold of the building; The process of obtaining the monitoring deviation rate of the building displacement data through the monitoring weight of the building horizontal displacement and the monitoring weight of the building vertical displacement is as follows:

[0012] Wherein, KV is the monitoring deviation rate of the building displacement data, and are respectively the monitoring weight of the building horizontal displacement and the monitoring weight of the building vertical displacement, K is the monitoring deviation rate of the building horizontal displacement, and V is the monitoring deviation rate of the building vertical displacement.

[0013] A further improvement of the technical solution of the present invention lies in that: the process of the stress and strain unit obtaining the monitoring deviation rate of the building stress and strain data includes: The monitoring deviation rate of the building stress and strain data consists of the monitoring deviation rate of the building stress data and the monitoring deviation rate of the building strain data, and the monitoring weights of the building stress data and the building strain data are set; The process of obtaining the monitoring deviation rate of the building stress data by using the stress data threshold of the building is as follows: where N is the monitoring deviation rate of the building stress data, is the building stress data, is the stress data threshold of the building; The process of obtaining the monitoring deviation rate of the building strain data by using the strain data threshold of the building is as follows: where D is the monitoring deviation rate of the building strain data, is the building strain data, is the strain data threshold of the building; The process of obtaining the monitoring deviation rate of the building stress and strain data through the monitoring weights of the building stress data and the building strain data is as follows: where ND is the monitoring deviation rate of the building stress and strain data, and are the monitoring weights of the building stress data and the building strain data respectively, N is the monitoring deviation rate of the building stress data, and D is the monitoring deviation rate of the building strain data.

[0014] A further improvement of the technical solution of the present invention lies in that the process of obtaining the monitoring deviation rate of the building vibration data by the vibration unit includes: The monitoring deviation rate of the building vibration data consists of the monitoring deviation rate of the building vibration frequency and the monitoring deviation rate of the building amplitude, and the monitoring weights of the building vibration frequency and the building amplitude are set; The process of obtaining the monitoring deviation rate of the building vibration frequency by using the vibration frequency threshold of the building is as follows: where F is the monitoring deviation rate of the building vibration frequency, is the vibration frequency of the building, is the vibration frequency threshold of the building; The process of obtaining the monitoring deviation rate of the building amplitude by using the amplitude threshold of the building is as follows: where H is the monitoring deviation rate of the building amplitude, is the amplitude of the building, is the amplitude threshold of the building; The process of obtaining the monitoring deviation rate of the building vibration data through the monitoring weights of the building vibration frequency and the building amplitude is as follows: where FH is the monitoring deviation rate of the building vibration data, and They are the weight of building vibration frequency monitoring and the weight of building amplitude monitoring respectively. F is the deviation rate of building vibration frequency monitoring, and H is the deviation rate of building amplitude monitoring.

[0015] A further improvement of the technical solution of the present invention lies in that: in the inclination deviation monitoring module, the process of constructing an inclination deviation monitoring model by using a neural network algorithm includes: Construct a neural network model. Take the multi-dimensional data of the building and its monitoring deviation rate as the data set, and divide it into a training set and a test set according to a ratio of 7:3. Select MLP as the neural network structure. The input layer includes four neurons, which receive the multi-dimensional data of the building. The hidden layer uses the MSE function, and the output layer includes four neurons, which output the monitoring deviation rate corresponding to the multi-dimensional data of the building. Among them, the input data of the input layer specifically includes the inclination data, displacement data, stress and strain data, and vibration data of the building. The output data of the output layer specifically includes the monitoring deviation rate of inclination data, the monitoring deviation rate of displacement data, the monitoring deviation rate of stress and strain data, and the monitoring deviation rate of vibration data; Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and backward propagation. Among them, forward propagation is used to calculate the predicted output data, and backward propagation is used to update the weights and biases of the model. Through repeated iterative training, learn the non-linear relationship between inclination data and the monitoring deviation rate of inclination data, the non-linear relationship between displacement data and the monitoring deviation rate of displacement data, the non-linear relationship between stress and strain data and the monitoring deviation rate of stress and strain data, and the non-linear relationship between vibration data and the monitoring deviation rate of vibration data until the set number of iterative training times is reached, and obtain the trained neural network model; Input the test set data into the trained neural network model, use the MSE function to evaluate the error between the output value and the actual value of the neural network model, adjust the parameters of the neural network model according to the evaluation results, optimize the performance of the neural network model, and obtain the inclination deviation monitoring model.

[0016] A further improvement of the technical solution of the present invention lies in that: in the inclination deviation warning module, the process of using the inclination deviation monitoring model to evaluate the inclination deviation of the building's multi-dimensional data and sending a signal through a signal lamp includes: Combined with the inclination deviation monitoring model, analyze the multi-dimensional data of the building and its monitoring deviation rate, and set signal lamps. The colors of the signal lamps include green, yellow, and red. Among them, the green signal lamp indicates low deviation, yellow indicates medium deviation, and red indicates high deviation; When the monitoring deviation rate of the multi-dimensional data of the building is lower than 5%, it indicates that the multi-dimensional data of the corresponding building has a low deviation in the monitoring of the building inclination angle, and the green signal light is on; when the monitoring deviation rate of the multi-dimensional data of the building is between 5% and 20%, it indicates that the multi-dimensional data of the corresponding building has a medium deviation in the monitoring of the building inclination angle, and the yellow signal light is on; when the monitoring deviation rate of the multi-dimensional data of the building is greater than 20%, it indicates that the multi-dimensional data of the corresponding building has a high deviation in the monitoring of the building inclination angle, and the red signal light is on.

[0017] In a second aspect, an integrated inclinometer monitoring method is used to implement the above-mentioned integrated inclinometer monitoring system, and it consists of the following steps: Step 1: Use a MEMS inclinometer sensor, a laser displacement sensor, a resistive strain gauge stress sensor, and an acceleration sensor to collect the tilt angle of the building, the horizontal and vertical displacements of the building, the stress data and strain data of the building, and the vibration frequency and amplitude of the building respectively; Step 2: Preprocess the collected multi-dimensional data of the building, and calculate the monitoring deviation rates of the building inclination angle data, displacement data, stress-strain data, and vibration data respectively; Step 3: Use a neural network algorithm to construct an inclination deviation monitoring model; Step 4: Use the inclination deviation monitoring model to evaluate the inclination deviation of the building monitored by the multi-dimensional data of the building, and send a signal through the signal light.

[0018] The beneficial effects of the present invention are as follows: In the integrated inclinometer monitoring system and method of the present invention, compared with the traditional integrated inclinometer monitoring system and method, the multi-dimensional data acquisition technology, data preprocessing technology, neural network algorithm technology in the method of the present invention are closely combined with modern information technology to accurately capture the inclination angle data, displacement data, stress-strain data, and vibration data of the building, obtain the monitoring deviation rate of the multi-dimensional data of the building, and achieve real-time and comprehensive monitoring of the monitoring deviation of the building inclination angle. By constructing an inclination deviation monitoring model and sending different color signals through the signal light according to the deviation degree, the problems of single monitoring data and inability to identify the inclination data deviation in the existing integrated inclinometer monitoring technology are solved, ensuring that the method in the present invention can refine the dynamic monitoring standard for an integrated inclinometer monitoring system and method within a more accurate range, making the monitored data a more accurate index under the same conditions. The research and application of this method significantly enhance the intelligent level in the integrated inclinometer monitoring process. Description of the Drawings

[0019] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a block diagram of an integrated inclinometer monitoring system of the present invention; Figure 2 It is a flowchart of an integrated inclinometer monitoring method of the present invention. Specific embodiments

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0022] Embodiment 1, as Figure 1 shown, the present invention provides an integrated inclinometer monitoring system, including a multi-dimensional data acquisition module, a multi-dimensional data preprocessing module, a building monitoring module, an inclination deviation monitoring module, and an inclination deviation warning module. Among them, each module is communicatively connected; The multi-dimensional data acquisition module obtains multi-dimensional data of a building through sensors. Among them, the multi-dimensional data of the building includes inclination data, displacement data, stress-strain data, and vibration data, providing basic data support for comprehensively monitoring the state of the building; The multi-dimensional data preprocessing module preprocesses the acquired multi-dimensional data of the building, improving the quality of the acquired multi-dimensional data of the building and laying a foundation for subsequent precise monitoring and analysis; The building monitoring module is divided into an inclination unit, a displacement unit, a stress-strain unit, and a vibration unit. Among them, the inclination unit, displacement unit, stress-strain unit, and vibration unit are respectively used to obtain the monitoring deviation rates of the inclination data, displacement data, stress-strain data, and vibration data of the building, so as to quantitatively evaluate the monitoring of various aspects of data of the building; The inclination deviation monitoring module uses a neural network algorithm to construct an inclination deviation monitoring model, providing an effective technical means for accurately analyzing and predicting the inclination deviation of the building; The inclination deviation warning module uses the inclination deviation monitoring model to evaluate the inclination deviation of the building monitored by the multi-dimensional data of the building and sends a signal through a signal lamp.

[0023] Preferably, the process of the multi-dimensional data acquisition module obtaining inclination data, displacement data, stress-strain data, and vibration data through sensors includes: Among them, the sensors include MEMS inclination sensors, laser displacement sensors, resistive strain gauge stress sensors, and acceleration sensors; the inclination data is the inclination angle of the building; the displacement data is the horizontal and vertical displacements of the building; the stress-strain data is the stress and strain data of the building; the vibration data is the vibration frequency and amplitude of the building. Fix the MEMS inclination sensor on the building, and based on MEMS technology, collect the inclination angle of the building; set up a base on the ground, install the laser displacement device on the base, and collect the horizontal and vertical displacements of the building. Paste the resistive strain gauge stress sensor on the surface of the building. The resistive strain gauge stress sensor has an internal resistive strain gauge, and based on the piezoresistive effect of semiconductor materials, collect the stress and strain data of the building. Install the acceleration sensor on the top floor of the building, set the parameters of the acceleration sensor, based on Newton's second law, measure the time-domain data of the vibration acceleration of the building, and use the Fourier transform algorithm to convert the time-domain data of the vibration acceleration into a frequency-domain diagram of the vibration acceleration. The peak value in the frequency-domain diagram of the vibration acceleration is the amplitude of the building, and the frequency corresponding to the peak value in the frequency-domain diagram of the vibration acceleration is the vibration frequency of the building.

[0024] Preferably, the process of the multi-dimensional data preprocessing module preprocessing the multi-dimensional data of the building includes: Adopt the mean filtering method to denoise the multi-dimensional data of the building collected; calibrate the collected data according to the calibration parameters to remove the error values in the multi-dimensional data of the building collected; according to the material and structure of the building, set thresholds for the inclination angle, horizontal displacement, vertical displacement, stress data, strain data, vibration frequency, and amplitude of the building respectively, and remove the data greater than the thresholds.

[0025] Preferably, the process of the inclination unit obtaining the monitoring deviation rate of the building inclination data includes: The process of obtaining the monitoring deviation rate of the building inclination data using the inclination angle threshold of the building is: Among them, U is the monitoring deviation rate of the building inclination data, is the inclination angle of the building, is the inclination angle threshold of the building.

[0026] Preferably, the process of the displacement unit obtaining the monitoring deviation rate of the building displacement data includes: Among them, the monitoring deviation rate of the building displacement data is composed of the monitoring deviation rate of the building horizontal displacement and the monitoring deviation rate of the building vertical displacement. Set the monitoring weight of the building horizontal displacement and the monitoring weight of the building vertical displacement. The process of obtaining the monitoring deviation rate of the horizontal displacement of a building by using the horizontal displacement threshold of the building is as follows: Where K is the monitoring deviation rate of the horizontal displacement of the building, is the horizontal displacement of the building, and is the horizontal displacement threshold of the building; The process of obtaining the monitoring deviation rate of the vertical displacement of a building by using the vertical displacement threshold of the building is as follows: Where V is the monitoring deviation rate of the vertical displacement of the building, is the vertical displacement of the building, and is the vertical displacement threshold of the building; The process of obtaining the monitoring deviation rate of the displacement data of a building through the monitoring weight of the horizontal displacement of the building and the monitoring weight of the vertical displacement of the building is as follows: Where KV is the monitoring deviation rate of the displacement data of the building, and are the monitoring weight of the horizontal displacement of the building and the monitoring weight of the vertical displacement of the building respectively, K is the monitoring deviation rate of the horizontal displacement of the building, and V is the monitoring deviation rate of the vertical displacement of the building.

[0027] Preferably, for the stress-strain unit, the process of obtaining the monitoring deviation rate of the stress-strain data of the building includes: Where the monitoring deviation rate of the stress-strain data of the building is composed of the monitoring deviation rate of the stress data of the building and the monitoring deviation rate of the strain data of the building, and the monitoring weight of the stress data of the building and the monitoring weight of the strain data of the building are set; The process of obtaining the monitoring deviation rate of the stress data of a building by using the stress data threshold of the building is as follows: Where N is the monitoring deviation rate of the stress data of the building, is the stress data of the building, and is the stress data threshold of the building; The process of obtaining the monitoring deviation rate of the strain data of a building by using the strain data threshold of the building is as follows: Where D is the monitoring deviation rate of the strain data of the building, is the strain data of the building, and is the strain data threshold of the building; The process of obtaining the monitoring deviation rate of the stress-strain data of a building through the monitoring weight of the stress data of the building and the monitoring weight of the strain data of the building is as follows: Where ND is the monitoring deviation rate of the stress-strain data of the building, and are the monitoring weight of the stress data of the building and the monitoring weight of the strain data of the building respectively, N is the monitoring deviation rate of the stress data of the building, and D is the monitoring deviation rate of the strain data of the building.

[0028] Preferably, the process of the vibration unit for obtaining the monitoring deviation rate of the building vibration data includes: Among them, the monitoring deviation rate of the building vibration data is composed of the monitoring deviation rate of the building vibration frequency and the monitoring deviation rate of the building amplitude. Set the monitoring weight of the building vibration frequency and the monitoring weight of the building amplitude; The process of obtaining the monitoring deviation rate of the building vibration frequency by using the vibration frequency threshold of the building is: Among them, F is the monitoring deviation rate of the building vibration frequency, is the vibration frequency of the building, is the vibration frequency threshold of the building; The process of obtaining the monitoring deviation rate of the building amplitude by using the amplitude threshold of the building is: Among them, H is the monitoring deviation rate of the building amplitude, is the amplitude of the building, is the amplitude threshold of the building; The process of obtaining the monitoring deviation rate of the building vibration data through the monitoring weight of the building vibration frequency and the monitoring weight of the building amplitude is as follows: Among them, FH is the monitoring deviation rate of the building vibration data, and are the monitoring weight of the building vibration frequency and the monitoring weight of the building amplitude respectively, F is the monitoring deviation rate of the building vibration frequency, and H is the monitoring deviation rate of the building amplitude.

[0029] Preferably, the process of the inclination deviation monitoring module for constructing the inclination deviation monitoring model by using the neural network algorithm includes: Construct a neural network model. Take the building multi-dimensional data and its monitoring deviation rate as the data set, and divide it into a training set and a test set according to the ratio of 7:3. Select MLP as the neural network structure. The input layer includes four neurons, which receive the building multi-dimensional data. The hidden layer uses the MSE function. The output layer includes four neurons, which output the monitoring deviation rate corresponding to the building multi-dimensional data. Among them, the input data of the input layer specifically includes the inclination data, displacement data, stress and strain data, and vibration data of the building. The output data of the output layer specifically includes the monitoring deviation rate of the inclination data, the monitoring deviation rate of the displacement data, the monitoring deviation rate of the stress and strain data, and the monitoring deviation rate of the vibration data; Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and backward propagation. Among them, forward propagation is used to calculate the predicted output data, and backward propagation is used to update the weights and biases of the model. By repeating the iterative training, learn the non-linear relationships between the inclination angle data and the monitoring deviation rate of the inclination angle data, the displacement data and the monitoring deviation rate of the displacement data, the stress-strain data and the monitoring deviation rate of the stress-strain data, and the vibration data and the monitoring deviation rate of the vibration data until the set number of iterative training times is reached, and obtain the trained neural network model; Input the test set data into the trained neural network model, use the MSE function to evaluate the error between the output value and the actual value of the neural network model, adjust the parameters of the neural network model according to the evaluation results, optimize the performance of the neural network model, and obtain the inclination angle deviation monitoring model.

[0030] Preferably, the inclination angle deviation warning module uses the inclination angle deviation monitoring model to evaluate the inclination angle deviation of the building's multi-dimensional data monitoring of the building. The process of sending a signal through the signal lamp includes: Combined with the inclination angle deviation monitoring model, analyze the building's multi-dimensional data and its monitoring deviation rate, set the signal lamp, and the signal lamp colors include green, yellow, and red. Among them, the green signal lamp indicates low deviation, yellow indicates medium deviation, and red indicates high deviation; When the monitoring deviation rate of the building's multi-dimensional data is less than 5%, it indicates that the corresponding building's multi-dimensional data has a low deviation in the building's inclination angle monitoring, and the green signal lamp is on; when the monitoring deviation rate of the building's multi-dimensional data is between 5% and 20%, it indicates that the corresponding building's multi-dimensional data has a medium deviation in the building's inclination angle monitoring, and the yellow signal lamp is on; when the monitoring deviation rate of the building's multi-dimensional data is greater than 20%, it indicates that the corresponding building's multi-dimensional data has a high deviation in the building's inclination angle monitoring, and the red signal lamp is on.

[0031] Example 2, as Figure 2 shown, on the basis of Example 1, the present invention provides a technical solution: an integrated inclinometer monitoring method for implementing the above-mentioned integrated inclinometer monitoring system, which consists of the following steps: Step 1: Use MEMS inclinometers, laser displacement sensors, resistance strain gauge stress sensors, and acceleration sensors to collect the inclination angle of the building, the horizontal and vertical displacements of the building, the stress and strain data of the building, and the vibration frequency and amplitude of the building respectively; Step 2: Preprocess the collected multi-dimensional data of the building, and calculate the monitoring deviation rates of the building's inclination angle data, displacement data, stress-strain data, and vibration data respectively; Step 3: Use the neural network algorithm to construct an inclination angle deviation monitoring model; Step 4: Use the inclination deviation monitoring model to evaluate the inclination deviation of the building by monitoring the multi-dimensional data of the building, and send a signal through the signal lamp.

[0032] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed by this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

1. An integrated inclinometer monitoring system, comprising a multi-dimensional data acquisition module, a multi-dimensional data preprocessing module, a building monitoring module, an inclination deviation monitoring module, and an inclination deviation warning module, wherein, Each module is communicatively connected, and is characterized in that: The multi-dimensional data acquisition module acquires multi-dimensional data of a building through sensors, wherein the multi-dimensional data of the building includes inclination data, displacement data, stress-strain data, and vibration data; The multi-dimensional data preprocessing module preprocesses the acquired multi-dimensional data of the building; The building monitoring module is divided into an inclination unit, a displacement unit, a stress-strain unit, and a vibration unit. Among them, the inclination unit, the displacement unit, the stress-strain unit, and the vibration unit are respectively used to obtain the monitoring deviation rates of the inclination data, displacement data, stress-strain data, and vibration data of the building; The inclination deviation monitoring module constructs an inclination deviation monitoring model by using a neural network algorithm; The inclination deviation warning module uses the inclination deviation monitoring model to evaluate the inclination deviation of the building monitored by the multi-dimensional data of the building, and issues a signal through a signal lamp.

2. The integrated inclinometer monitoring system according to claim 1, wherein: The process by which the multi-dimensional data acquisition module acquires inclination data, displacement data, stress-strain data, and vibration data through sensors includes: The sensors include MEMS inclination sensors, laser displacement sensors, resistance strain gauge stress sensors, and acceleration sensors; the inclination data is the inclination angle of the building; the displacement data is the horizontal displacement and vertical displacement of the building; the stress-strain data is the stress data and strain data of the building; the vibration data is the vibration frequency and amplitude of the building; Fix the MEMS inclination sensor on the building, and based on MEMS technology, collect the inclination angle of the building; set up a base on the ground, install the laser displacement device on the base, and collect the horizontal displacement and vertical displacement of the building; Paste the resistance strain gauge stress sensor on the surface of the building. The resistance strain gauge stress sensor is internally provided with a resistance strain gauge, and based on the piezoresistive effect of semiconductor materials, collect the stress data and strain data of the building; Install the acceleration sensor on the top floor of the building, set the parameters of the acceleration sensor, and based on Newton's second law, measure the time-domain data of the vibration acceleration of the building. Use the Fourier transform algorithm to convert the time-domain data of the vibration acceleration into a frequency-domain diagram of the vibration acceleration. The peak value in the frequency-domain diagram of the vibration acceleration is the amplitude of the building, and the frequency corresponding to the peak value in the frequency-domain diagram of the vibration acceleration is the vibration frequency of the building.

3. An integrated inclinometer monitoring system according to claim 2, characterized in that: The process by which the multi-dimensional data preprocessing module preprocesses the acquired multi-dimensional data of the building includes: Adopt the mean filtering method to denoise the acquired multi-dimensional data of the building; calibrate the acquired data according to the calibration parameters to remove the error values in the acquired multi-dimensional data of the building; according to the material and structure of the building, set thresholds for the inclination angle, horizontal displacement, vertical displacement, stress data, strain data, vibration frequency, and amplitude of the building respectively, and remove the data greater than the threshold.

4. The integrated inclinometer monitoring system according to claim 3, wherein: The process by which the inclination unit obtains the monitoring deviation rate of the inclination data of the building includes: The process of obtaining the monitoring deviation rate of building inclination angle data by using the inclination angle threshold of the building is as follows: where U is the monitoring deviation rate of building inclination angle data, is the inclination angle of the building, is the inclination angle threshold of the building.

5. An integrated inclinometer monitoring system according to claim 4, characterized in that: The process by which the displacement unit obtains the monitoring deviation rate of the displacement data of the building includes: The monitoring deviation rate of the building displacement data consists of the horizontal displacement monitoring deviation rate of the building and the vertical displacement monitoring deviation rate of the building, and the horizontal displacement monitoring weight of the building and the vertical displacement monitoring weight of the building are set; The process of obtaining the monitoring deviation rate of the building's horizontal displacement using the horizontal displacement threshold of the building is as follows: where K is the monitoring deviation rate of the building's horizontal displacement, is the horizontal displacement of the building, and is the horizontal displacement threshold of the building; The process of obtaining the monitoring deviation rate of the building's vertical displacement by using the vertical displacement threshold of the building is as follows: where V is the monitoring deviation rate of the building's vertical displacement, is the vertical displacement of the building, is the vertical displacement threshold of the building; The process of obtaining the monitoring deviation rate of building displacement data through the horizontal displacement monitoring weight of the building and the vertical displacement monitoring weight of the building is as follows: , where KV is the monitoring deviation rate of building displacement data, and are the horizontal displacement monitoring weight of the building and the vertical displacement monitoring weight of the building respectively, K is the horizontal displacement monitoring deviation rate of the building, and V is the vertical displacement monitoring deviation rate of the building.

6. The integrated inclinometer monitoring system according to claim 5, wherein: For the stress-strain unit, the process of obtaining the monitoring deviation rate of the building stress-strain data includes: The monitoring deviation rate of the building stress-strain data consists of the monitoring deviation rate of the building stress data and the monitoring deviation rate of the building strain data, and the monitoring weight of the building stress data and the monitoring weight of the building strain data are set; The process of obtaining the monitoring deviation rate of building stress data by using the stress data threshold of the building is as follows: where N is the monitoring deviation rate of building stress data, is the building stress data, is the stress data threshold of the building; The process of obtaining the monitoring deviation rate of building strain data by using the strain data threshold of the building is as follows: where D is the monitoring deviation rate of building strain data, is the building strain data, is the strain data threshold of the building; The process of obtaining the monitoring deviation rate of building stress and strain data through the monitoring weight of building stress data and the monitoring weight of building strain data is as follows: where ND is the monitoring deviation rate of building stress and strain data, and are the monitoring weight of building stress data and the monitoring weight of building strain data respectively, N is the monitoring deviation rate of building stress data, and D is the monitoring deviation rate of building strain data.

7. An integrated inclinometer monitoring system according to claim 6, characterized in that: For the vibration unit, the process of obtaining the monitoring deviation rate of the building vibration data includes: The monitoring deviation rate of the building vibration data consists of the vibration frequency monitoring deviation rate of the building and the vibration amplitude monitoring deviation rate of the building, and the vibration frequency monitoring weight of the building and the vibration amplitude monitoring weight of the building are set; The process of obtaining the building vibration frequency monitoring deviation rate by using the building vibration frequency threshold is as follows: where F is the building vibration frequency monitoring deviation rate, is the building vibration frequency, is the building vibration frequency threshold; The process of obtaining the deviation rate of building amplitude monitoring by using the amplitude threshold of the building is as follows: where H is the deviation rate of building amplitude monitoring, is the amplitude of the building, is the amplitude threshold of the building; The process of obtaining the monitoring deviation rate of building vibration data through the building vibration frequency monitoring weight and the building amplitude monitoring weight is as follows: Among them, FH is the monitoring deviation rate of building vibration data, and are the building vibration frequency monitoring weight and the building amplitude monitoring weight respectively, F is the building vibration frequency monitoring deviation rate, and H is the building amplitude monitoring deviation rate.

8. An integrated inclinometer monitoring system according to claim 7, characterized in that: For the inclination deviation monitoring module, the process of constructing the inclination deviation monitoring model using the neural network algorithm includes: Construct a neural network model. Take the multi-dimensional data of the building and its monitoring deviation rate as the data set, and divide it into a training set and a test set according to a ratio of 7:

3. Select MLP as the neural network structure. The input layer includes four neurons, which receive the multi-dimensional data of the building. The hidden layer uses the MSE function, and the output layer includes four neurons, which output the monitoring deviation rate corresponding to the multi-dimensional data of the building. Among them, the input data of the input layer specifically includes the inclination data, displacement data, stress-strain data, and vibration data of the building, and the output data of the output layer specifically includes the monitoring deviation rate of the inclination data, the monitoring deviation rate of the displacement data, the monitoring deviation rate of the stress-strain data, and the monitoring deviation rate of the vibration data; Input the training set data into the neural network model, set the learning rate to 0.01, and the number of iterative training times to 1000. The training process includes forward propagation and backward propagation. Among them, forward propagation is used to calculate the predicted output data, and backward propagation is used to update the weights and biases of the model. By repeating the iterative training, learn the non-linear relationship between the inclination data and the monitoring deviation rate of the inclination data, the non-linear relationship between the displacement data and the monitoring deviation rate of the displacement data, the non-linear relationship between the stress-strain data and the monitoring deviation rate of the stress-strain data, and the non-linear relationship between the vibration data and the monitoring deviation rate of the vibration data until the set number of iterative training times is reached, and obtain the trained neural network model; Input the test set data into the trained neural network model, use the MSE function to evaluate the error between the output value and the actual value of the neural network model, adjust the parameters of the neural network model according to the evaluation results, optimize the performance of the neural network model, and obtain the inclination deviation monitoring model.

9. The integrated inclinometer monitoring system according to claim 8, characterized in that: For the inclination deviation warning module, the process of evaluating the inclination deviation of the building using the multi-dimensional data of the building by adopting the inclination deviation monitoring model and sending a signal through the signal lamp includes: Combined with the inclination deviation monitoring model, analyze the multi-dimensional data of the building and its monitoring deviation rate, and set signal lamps. The colors of the signal lamps include green, yellow, and red. Among them, the green signal lamp indicates low deviation, yellow indicates medium deviation, and red indicates high deviation; When the monitoring deviation rate of the multi-dimensional data of a building is lower than 5%, it indicates that the multi-dimensional data of the corresponding building has a low deviation in the monitoring of the building inclination angle, and the green signal light is on; when the monitoring deviation rate of the multi-dimensional data of a building is between 5% and 20%, it indicates that the multi-dimensional data of the corresponding building has a medium deviation in the monitoring of the building inclination angle, and the yellow signal light is on; when the monitoring deviation rate of the multi-dimensional data of a building is greater than 20%, it indicates that the multi-dimensional data of the corresponding building has a high deviation in the monitoring of the building inclination angle, and the red signal light is on.

10. An integrated inclinometer monitoring method, which is implemented based on the integrated inclinometer monitoring system described in any one of the above claims 1-9, and is characterized in that, It consists of the following steps: Step 1: Use a MEMS inclination sensor, a laser displacement sensor, a resistance strain gauge stress sensor, and an acceleration sensor to collect the inclination angle of the building, the horizontal and vertical displacements of the building, the stress data and strain data of the building, and the vibration frequency and amplitude of the building respectively; Step 2: Preprocess the collected multi-dimensional data of the building, and calculate the monitoring deviation rates of the building inclination angle data, displacement data, stress and strain data, and vibration data respectively; Step 3: Use a neural network algorithm to construct an inclination deviation monitoring model; Step 4: Use the inclination deviation monitoring model to evaluate the inclination deviation of the building monitored by the multi-dimensional data of the building, and send a signal through the signal light.

Images