Structure monitoring and evaluating system integrating data trend prediction

Abstract

The invention discloses a structure monitoring and evaluating system integrated with data trend prediction, which is based on a Flask lightweight Web application framework and a long short-term memory neural network algorithm, builds an algorithm system integrating user management, a website homepage and a functional module, and realizes the real-time monitoring and evaluating of the structure by means of the intuition of Web end operation. The whole process of model construction, training and prediction is presented in a what you see is what you get mode, and the convenience of monitoring index trend prediction achieved by engineers through a machine learning algorithm is effectively improved.

Description

Technical Field

[0001] The invention relates to the technical field of building structure monitoring and evaluation, and in particular to a structure monitoring and evaluation system integrating data trend prediction. Background Art

[0002] Based on the existing structural performance indicators, including strain, deflection, settlement, acceleration and other time series data, we can deeply deduce its possible future development trends and change laws, aiming to warn potential dangerous areas in advance, so as to accurately diagnose the overall safety status of the building structure. This is a core issue in the field of intelligent monitoring and evaluation of building structures.

[0003] To address this problem, domestic and foreign scholars have widely used a predictive assessment method based on measured response data. This method simulates and deduces the future time-varying characteristics of various types of monitoring indicators through nonlinear fitting or machine learning algorithms, and then judges the structural risk. However, its promotion and application in actual engineering is still hindered for the following reasons: (1) The prediction model parameter setting is not flexible. The prediction algorithm model based on deep learning has been widely studied in the monitoring field, but the model parameters are of many types and have great influence. How to customize various types of parameters to adapt to the optimal prediction model has become an important issue in its promotion and application.

[0004] (2) The algorithm model calculation and analysis is not intuitive. Although the deep learning model can simulate the law of data change more accurately, its calculation principle is still a "black box" and the intermediate process is often difficult to understand. Therefore, the visualization of the deep learning model analysis process is also the key to its engineering promotion.

[0005] (3) Existing prediction methods are not convenient to operate. Existing prediction and analysis methods based on measured data require certain big data analysis and processing capabilities, familiarity with the algorithm core of the prediction model, and corresponding computing power foundation. They have higher professional requirements for traditional civil engineers, and the inconvenience of operation methods has limited their actual promotion and application. Summary of the invention

[0006] The present application provides a structural monitoring and evaluation system integrating data trend prediction to solve the problems existing in the prior art such as inflexible prediction model parameter setting, non-intuitive algorithm model calculation and analysis, and inconvenient operation of existing prediction methods.

[0007] According to the first aspect, an embodiment provides a structural monitoring and evaluation system with integrated data trend prediction, which is implemented based on the Flask lightweight Web framework, and the system includes: The data reading module is used to select the data type of the structural performance indicator and the data file to be analyzed in the data reading column, import the data file and draw a data time series diagram; The outlier elimination module is used to set the filter window value and outlier detection threshold in the outlier elimination column, complete the elimination of abnormal data and draw the filtered data time series diagram; The model building module is used to set the sliding window value, the number of model training times and the number of single training samples in the model building column, complete the prediction model building, and draw the model error graph; The trend forecast module is used to set the forecast days in the trend forecast column, complete the forecast of future trends of the data, and draw a trend forecast chart.

[0008] Furthermore, the data reading module is specifically used for: Read data files; If the file does not exist, a warning pops up; If the file exists, a confirmation upload option will pop up; If the upload is confirmed, an execution variable is added to the read information and the execution variable is assigned to True. Then, the execution variable is passed to the import data view function in the Flask program. After completion, a prompt indicating that the upload is successful is popped up; If you do not confirm the upload, a prompt to cancel the upload will pop up.

[0009] Furthermore, the data reading module is specifically used for: Confirm whether to draw the data timing diagram; If the drawing is confirmed, the file information is read, and the execution variable is added, the execution variable is assigned to True, and the execution variable is transmitted to the drawing graph view function in the Flask program. After the program is executed, the newly generated image name and storage location are sent to the HTML front end, and the original data time series diagram is updated; If you do not confirm the drawing, a prompt to cancel the drawing will pop up.

[0010] Furthermore, the function of drawing a graphics view is specifically used to: Get the execution parameters in the script for drawing data graphs on the HTML page. If the execution parameter value is True, get the user ID and data type, build the image storage address, return the image storage address to the HTML web page front end, and prompt that the image is drawn successfully. If the execution parameter value is not True, return an error prompt.

[0011] Furthermore, the outlier removal module is specifically used to: Confirm whether to draw a data time series diagram excluding outliers; If the drawing is confirmed, the file information is read, and the execution variable is added, the execution variable is assigned to True, and the execution variable is transmitted to the abnormal data check view function in the Flask program. After the program is executed, the newly generated image name and storage location are sent to the HTML front end, and the original data time series diagram is updated; If you do not confirm the drawing, a prompt to cancel the drawing will pop up.

[0012] Furthermore, the abnormal data checking view function is specifically used to: Get the execution parameters in the script for removing abnormal data from the HTML page. If the execution parameter value is True, get the user ID, data type, filter window size, and abnormal value detection threshold. Read the training or test data in the selected Excel file, and then use the Hampel algorithm to remove outliers in the time series data that exceed the specified threshold, and replace the outliers with the median of the data under the same sliding window, finally forming the filtered training and test data; Save the filtered data to the specified directory, draw an outlier elimination graph, add the user ID to the graph name, and save it to the specified directory; The storage address of the outlier elimination graph is returned to the HTML web page front end.

[0013] Furthermore, the model building module is specifically used for: Confirm whether to establish a prediction model; If the establishment is confirmed, the file information is read, and the execution variable is added, and the execution variable is assigned to True, and the progress bar parameter is read and assigned to 0; Create a progress bar update sub-function, which first accesses the progress bar view function in the Flask program. The progress bar view function returns the completion rate to the HTML front end, and then updates the value, width and value position of the progress bar, and refreshes the page every preset time; Access the model view function established in the Flask program. If there is no response, return the network error information; if there is a response, combine the image location information with the current time to form a new image name, and update the model error graph in the current page; If you do not confirm the creation, a prompt to cancel the modeling will pop up.

[0014] Furthermore, the model view function is established to: Get the execution variable in the script of the prediction model establishment on the HTML page. If the execution variable is True, get the user ID, data type, sliding window size, number of model training times and number of single training samples. Read the data after removing outliers and use the preprocessing function to normalize the training or test data; Loop through the data set, extract the input features and target values ​​of the normalized data under the specified window, and adjust the dimension order of the array; Build a long short-term memory neural network model, set the loss function and optimizer; Define the global variables training completion rate and current iteration number, perform loop iteration, if the current iteration number is less than the total iteration number, complete one model training, save the model loss rate, and update the training completion rate; Calculate the model prediction value to obtain the loss evaluation index parameters of the prediction result, wherein the loss evaluation index parameters include mean square error, root mean square error, mean absolute error and goodness of fit; Draw the model loss rate curve and loss evaluation index bar chart, add the user ID in the chart name, and save it to the specified folder; The storage address of the loss rate curve chart and the loss evaluation index bar chart is returned to the HTML front end.

[0015] Furthermore, the trend prediction module is specifically used for: Confirm whether to conduct data trend prediction; If the prediction is confirmed, the file information is read, and the execution variable is added, and the execution variable is assigned to True, and the progress bar parameter is read and assigned to 0; Create a progress bar update sub-function, which first accesses the progress bar view function in the Flask program. The progress bar view function returns the completion rate to the HTML front end, and then updates the value, width and value position of the progress bar, and refreshes the page every preset time; Access the trend forecast view function in the Flask program. If there is no response, return a network error message; if there is a response, combine the image location information with the current time to form a new image name, and update the trend forecast chart in the current page; If you do not confirm the prediction, a prompt to cancel the prediction will pop up.

[0016] Furthermore, the trend prediction view function is specifically used to: Get the execution parameters in the script for predicting future trends on the HTML page. If the execution parameter value is True, get the user ID, data type, and forecast days. Define the global variable prediction completion rate and the current number of iterations, call the trained long short-term memory neural network model cyclically, predict future data changes day by day, store the prediction results, and update the prediction completion rate; Draw the predicted image, including the comparison between the predicted value and the measured value, add the user ID to the image name, and save it to the specified folder; Return the storage address of the prediction graph to the HTML front end.

[0017] The present application provides a structural monitoring and evaluation system integrating data trend prediction, which has the following beneficial effects: (1) Based on the Flask lightweight Web framework, the present invention constructs a structural monitoring and evaluation system with an integrated data trend prediction module, which realizes the parameterization and interactive operation of the entire process of neural network model from construction, training and prediction, significantly improves the convenience of model parameter setting and analysis, and intuitively reflects the impact of different parameter changes on the model prediction accuracy and efficiency.

[0018] (2) The interactive web-based algorithm system constructed by the present invention provides a graphical result display window and an analysis progress display bar, which presents the entire process of data selection, data noise reduction, model construction and trend prediction in a WYSIWYG manner, clearly reflects the construction process and analysis results of the neural network model, and improves the feasibility of promoting complex algorithms in engineering.

[0019] (3) The monitoring and evaluation system proposed in the present invention realizes the lightweight integration of the data trend module on the algorithm platform with a simple operation interface and clear display method, which reduces the learning and operation costs of engineering personnel for complex neural network models. At the same time, it has flexible scalability and can meet the secondary development needs of other functional modules in the later stage, which is convenient for engineering promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the logical structure of a structural monitoring and evaluation system integrating data trend prediction provided by one embodiment of the present invention; Figure 2 An overall implementation flow chart of data trend prediction of a structural monitoring and evaluation system with integrated data trend prediction provided by one embodiment of the present invention; Figure 3 A schematic diagram of user information management and login verification in a structural monitoring and evaluation system with integrated data trend prediction provided by one embodiment of the present invention; Figure 4 A login interface of a structural monitoring and evaluation system with integrated data trend prediction provided by an embodiment of the present invention; Figure 5 A schematic diagram of a data trend prediction module of a structural monitoring and evaluation system integrating data trend prediction is provided for an embodiment of the present invention; in the figure, (a) is a data reading column, (b) is an outlier removal column, (c) is a model building column, and (d) is a trend prediction column. DETAILED DESCRIPTION

[0021] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0022] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0023] The first embodiment of the present invention provides a structural monitoring and evaluation system with integrated data trend prediction, which is implemented based on the Flask lightweight Web framework. Figure 1 As shown, it specifically includes: The data reading module 210 is used to select the data type of the structural performance indicator and the data file to be analyzed in the data reading column, import the data file and draw a data time series diagram; An outlier elimination module 220 is used to set a filter window value and an outlier detection threshold in an outlier elimination column, eliminate abnormal data, and draw a filtered data timing diagram; The model building module 230 is used to set the sliding window value, the number of model training times and the number of single training samples in the model building column, complete the prediction model building, and draw the model error graph; The trend prediction module 240 is used to set the prediction days in the trend prediction column, complete the prediction of the future trend of the data, and draw a trend prediction graph.

[0024] Combine the following Figure 2 Describe the specific functional content of each module of the system.

[0025] In this embodiment, the system first includes a user login module 100, which is used to obtain the user's login information and perform verification, and enter the algorithm platform homepage after the verification is passed.

[0026] Specifically, user information management: In the backend of the login interface, user information is stored in the MySQL database, and data management is implemented using Navicat Premium; user information includes: user ID, user mobile number, login password, user name, and user role. User roles are divided into administrators and customers. Use Flask Blueprint to create a user login module 100, which obtains the user information entered in the login interface and compares it with the database information to verify the user login permission. The login interface is as follows Figure 4 shown.

[0027] The user login module 100 in this embodiment is specifically used for: (1) Use Flask request.method to determine the current HTTP request method. If it is a GET request, refresh the page directly; if it is a POST request, proceed to the next step; (2) Use Flask request.form.get to obtain the user role, user phone number and user password on the current login page; (3) Use Pymysql to connect to the user information database, create a cursor object, and establish a database connection pool to ensure real-time connection with the MySQL database. Based on the user information obtained on the login page, use the cursor object to query the user information in the database and obtain the query results row by row. After the query is completed, close the cursor and database connection (such as Figure 3 ).

[0028] (4) Determine whether the query result exists. If it does, use Flask session to manage user data and jump to the homepage of the website; if it does not exist, refresh the page and prompt that the login account is incorrect.

[0029] After the user successfully logs in and enters the algorithm platform homepage, he can enter the data trend prediction module 200 by clicking the function module button in the homepage navigation bar and selecting data trend prediction in the drop-down menu.

[0030] In this embodiment, the algorithm platform homepage includes four parts: navigation bar, platform introduction, function module, and engineering application. The navigation bar contains the page name, platform introduction button, function module button, engineering application button, and external website connection button; the platform introduction is an introduction to the main functions of the website and the patented technology it relies on; the function module column is the structural monitoring and evaluation functions that can be realized on the current website, that is, data trend prediction (Web end); the engineering application column is an introduction to the application and promotion of related engineering projects.

[0031] like Figure 5As shown, the data trend prediction module 200 in this embodiment mainly includes functional modules such as a data reading module 210, an outlier elimination module 220, a model building module 230 and a trend prediction module 240.

[0032] The data reading module 210 in this embodiment is used to import data and draw a data time series diagram after selecting the data type and the data file to be analyzed in the data reading column.

[0033] The HTML page of the data reading column contains a title, a drop-down menu button, a file selection input box, an import data button, a data timing diagram button, a data timing diagram window, and a sample data download link. The data types include: strain, deflection, settlement, displacement, deformation, and acceleration.

[0034] For the above import data button, the script steps in the HTML page are as follows: (1) Read the data file. If the file does not exist, a warning pops up; (2) If the file exists, a confirmation upload option pops up. If confirmed, an execution variable is added to the read information and the execution variable is assigned a value of True. Then, the execution variable is passed to the import data view function in the Flask program. After completion, a prompt pops up indicating that the upload is successful. If not confirmed, a prompt pops up to cancel the upload.

[0035] In this embodiment, the data view function is imported, specifically used for: (1) Use Flask request to obtain the file name in the data reading column of the HTML page; (2) Use Flask request to obtain the execution parameters in the script that imports data from the HTML page. If the parameter value is True, obtain the user ID and data type, and save the file to a temporary folder; (3) Use pandas to read the selected Excel file to obtain training and test data; (4) Use the training and test data to draw a data time series diagram, add the user ID to the diagram name, save it to a temporary folder, and store the image name in a global variable. The system will prompt that the data has been imported successfully.

[0036] For the button for drawing a data time series graph, the steps of the script in the HTML page are as follows: (1) Confirm whether to draw the data timing diagram. If yes, read the file information, add the execution variable, and assign the execution variable to True; (2) The execution variable is transferred to the graphics view drawing function in the Flask program. After the program is executed, the newly generated image name and storage location are sent to the HTML front end, and the original data time series diagram is updated.

[0037] (3) If you do not confirm, a prompt to cancel the drawing will pop up.

[0038] In this embodiment, the graphics view drawing function is specifically used to: (1) Use Flask request to obtain the execution parameters in the script for drawing data graphs on the HTML page. If the execution parameter value is True, obtain the user ID and data type and construct the image storage address; (2) Use the Flask jsonify function to return the image storage address to the HTML web page front end and prompt that the image is drawn successfully; (3) If the parameter value is not True, an error message is returned.

[0039] The outlier elimination module 220 in this embodiment is used to set the filter window value and the outlier detection threshold in the outlier elimination column, complete the elimination of abnormal data and draw the filtered data timing diagram.

[0040] Among them, the HTML page of the outlier removal column includes a title, a filter window value input box, an outlier detection threshold input box, an outlier data removal button, and an outlier removal graph window.

[0041] The steps of the script for the button to remove abnormal data in the HTML page are as follows: (1) Confirm whether to draw a data time series diagram that removes outliers. If yes, read the file information, add an execution variable, and assign the execution variable to True; (2) The execution variable is transferred to the abnormal data check view function in the Flask program. After the program is executed, the newly generated image name and storage location are sent to the HTML front end, and the original data time series diagram is updated; (3) If you do not confirm, a prompt to cancel the drawing will pop up.

[0042] In this embodiment, the abnormal data check view function is specifically used to: (1) Use Flask request to obtain the execution parameters of the script for removing abnormal data from the HTML page. If the parameter value is True, obtain the user ID, data type, filter window size, and outlier detection threshold; (2) Use pandas to read the training and test data in the selected Excel file, and then use the Hampel algorithm to remove outliers in the time series data that exceed the specified threshold and replace them with the median of the data under the same sliding window, finally forming the filtered training and test data; (3) Use pandas to save the filtered data in xlsx format to the specified directory, draw an outlier elimination chart, add the user ID to the chart name, and save it to the specified directory; (4) Use Flask jsonify to return the storage address of the outlier elimination graph to the HTML web front end.

[0043] The model building module 230 in this embodiment is used to set the sliding window value, the number of model training times and the number of single training samples in the model building column, complete the prediction model building, and draw the model error graph; Among them, the HTML page of the model building column includes a title, a sliding window value input box, a model training times input box, a single training sample number input box, a prediction model building button, a progress bar, and a model error graph window.

[0044] The steps of the script for the above-mentioned button to build a prediction model in the HTML page are as follows: (1) Confirm whether to establish a prediction model. If yes, read the file information, add an execution variable, assign the execution variable to True, and read the progress bar parameter and assign it to 0; (2) Create a progress bar update sub-function, which first accesses the progress bar view function in the Flask program. The view function returns the completion rate to the HTML front-end through the Flask jsonify function, and then updates the value, width, and value position of the progress bar, and refreshes the page every 0.5 seconds; (3) Access the model view function established in the Flask program. If there is no response, a network error message is returned; if there is a response, the image location information is combined with the current time to form a new image name, and the model error graph in the current page is updated.

[0045] (4) If you do not confirm the establishment, a prompt to cancel the modeling will pop up.

[0046] In this embodiment, a model view function is established, which is specifically used for: (1) Use Flask request to obtain the execution variable in the HTML page to establish the prediction model script. If the execution variable is True, obtain the user ID, data type, sliding window size, number of model training times, and number of single training samples; (2) Use pandas read_excel to read the data after removing outliers, and use sklearn preprocessing functions to normalize the training and test data; (3) Loop through the data set, extract the input features and target values ​​of the normalized data under the specified window, and adjust the dimension order of the array; (4) Use keras to construct a long short-term memory neural network containing 1 long short-term memory neural network layer (128 neurons), 3 fully connected layers (128 neurons), and 1 fully connected layer (1 neuron). The loss function is set to MSE and the optimizer is set to ADAM. (5) Define the global variables training completion rate and current number of iterations. Use the while loop. If the current number of iterations is less than the total number of iterations, the model training is completed once, the model loss rate is saved, and the training completion rate is updated. (6) Use keras to calculate the model prediction value and obtain the four loss evaluation index parameters of the prediction result: mean square error, root mean square error, mean absolute error, and goodness of fit; (7) Draw the model loss rate curve and loss evaluation index bar chart, add the user ID in the chart name, and save it to the specified folder; (8) Use the Flask jsonify function to return the storage address of the loss rate curve and the loss evaluation index bar chart to the HTML front end.

[0047] The trend prediction module 240 in this embodiment is used to set the prediction days in the trend prediction column, complete the prediction of the future trend of the data, and draw a trend prediction graph.

[0048] The HTML page of the trend forecast column includes a title, a forecast day input box, a button for predicting future trends, a progress bar, and a trend forecast graph window.

[0049] For the button to predict future trends, the script steps in the HTML page are as follows: (1) Confirm whether to perform data trend prediction. If yes, read the file information, add an execution variable, assign the execution variable to True, and read the progress bar parameter and assign it to 0; (2) Create a progress bar update sub-function, which first accesses the progress bar view function in the Flask program. The view function returns the completion rate to the HTML front-end through the Flask jsonify function, and then updates the value, width, and value position of the progress bar, and refreshes the page every 0.5 seconds; (3) Access the trend prediction view function in the Flask program. If there is no response, a network error message is returned. If there is a response, the image location information is combined with the current time to form a new image name, and the trend prediction chart in the current page is updated.

[0050] (4) If you do not confirm the prediction, a prompt to cancel the prediction will pop up.

[0051] In this embodiment, the trend prediction view function is specifically used to: (1) Use Flask request to obtain the execution parameters in the script of the HTML page predicting future trends. If the execution parameter value is True, obtain the user ID, data type, and predicted days; (2) Define the global variables prediction completion rate and the current number of iterations, cyclically call the trained long short-term memory neural network model, predict future data changes day by day, store the prediction results, and update the prediction completion rate; (3) Draw the predicted image, including the comparison between the predicted value and the measured value, add the user ID to the image name, and save it to the specified folder; (4) Use the Flask jsonify function to return the storage address of the prediction graph to the HTML front end.

[0052] Application examples: Applying the technology of the present invention, a corresponding algorithm system is developed, and the system login interface is as follows: Figure 4 After logging into the system as an administrator, jump to the system homepage. Select the data trend forecast module on the system homepage, click Use Now, and enter the module. Figure 5 As shown. Taking the existing measured settlement data (training set: test set = 300:50) as an example, the data import is completed, and the data outliers are eliminated with the default parameters. The number of model training times is set to 1000 times, and the neural network model is constructed and trained. The model fitting goodness is 0.9, which proves that the model training accuracy meets the requirements. Finally, the trend of data changes in the next 100 days is predicted. The technology of the present invention realizes the prediction of future evolution trends of monitoring data in a clear and concise manner, improves the user's operating experience, and realizes the application and promotion of complex machine learning algorithms in actual engineering.

[0053] The above specific examples are used to illustrate the present invention, which is only used to help understand the present invention and is not intended to limit the present invention. For those skilled in the art, according to the concept of the present invention, some simple deductions, modifications or substitutions can be made.

Claims

1. A structural monitoring and evaluation system integrating data trend prediction, characterized in that: Based on the Flask lightweight Web framework, the system includes: The data reading module is used to select the data type of the structural performance indicator and the data file to be analyzed in the data reading column, import the data file and draw a data time series diagram; The outlier elimination module is used to set the filter window value and outlier detection threshold in the outlier elimination column, complete the elimination of abnormal data and draw the filtered data time series diagram; The model building module is used to set the sliding window value, the number of model training times and the number of single training samples in the model building column, complete the prediction model building, and draw the model error graph; The trend forecast module is used to set the forecast days in the trend forecast column, complete the forecast of future trends of the data, and draw a trend forecast chart.

2. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 1, characterized in that: The data reading module is specifically used for: Read data files; If the file does not exist, a warning pops up; If the file exists, a confirmation upload option will pop up; If the upload is confirmed, an execution variable is added to the read information and the execution variable is assigned to True. Then, the execution variable is passed to the import data view function in the Flask program. After completion, a prompt indicating that the upload is successful is popped up; If you do not confirm the upload, a prompt to cancel the upload will pop up.

3. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 1, characterized in that: The data reading module is specifically used for: Confirm whether to draw the data timing diagram; If the drawing is confirmed, the file information is read, and the execution variable is added, the execution variable is assigned to True, and the execution variable is transmitted to the drawing graph view function in the Flask program. After the program is executed, the newly generated image name and storage location are sent to the HTML front end, and the original data time series diagram is updated; If you do not confirm the drawing, a prompt to cancel the drawing will pop up.

4. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 3, characterized in that: The function of drawing a graphics view is specifically used for: Get the execution parameters in the script for drawing data graphs on the HTML page. If the execution parameter value is True, get the user ID and data type, build the image storage address, return the image storage address to the HTML web page front end, and prompt that the image is drawn successfully. If the execution parameter value is not True, return an error prompt.

5. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 1, characterized in that: The outlier removal module is specifically used for: Confirm whether to draw a data time series diagram excluding outliers; If the drawing is confirmed, the file information is read, and the execution variable is added, the execution variable is assigned to True, and the execution variable is transmitted to the abnormal data check view function in the Flask program. After the program is executed, the newly generated image name and storage location are sent to the HTML front end, and the original data time series diagram is updated; If you do not confirm the drawing, a prompt to cancel the drawing will pop up.

6. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 5, characterized in that: The abnormal data checking view function is specifically used to: Get the execution parameters in the script for removing abnormal data from the HTML page. If the execution parameter value is True, get the user ID, data type, filter window size, and abnormal value detection threshold. Read the training or test data in the selected Excel file, and then use the Hampel algorithm to remove outliers in the time series data that exceed the specified threshold, and replace the outliers with the median of the data under the same sliding window, finally forming the filtered training and test data; Save the filtered data to the specified directory, draw an outlier elimination graph, add the user ID to the graph name, and save it to the specified directory; The storage address of the outlier elimination graph is returned to the HTML web page front end.

7. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 1, characterized in that: The model building module is specifically used for: Confirm whether to establish a prediction model; If the establishment is confirmed, the file information is read, and the execution variable is added, and the execution variable is assigned to True, and the progress bar parameter is read and assigned to 0; Create a progress bar update sub-function, which first accesses the progress bar view function in the Flask program. The progress bar view function returns the completion rate to the HTML front end, and then updates the value, width and value position of the progress bar, and refreshes the page every preset time; Access the model view function established in the Flask program. If there is no response, a network error message is returned; If there is a response, the image location information is combined with the current time to form a new image name, and the model error graph in the current page is updated; If you do not confirm the creation, a prompt to cancel the modeling will pop up.

8. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 7, characterized in that: The model view function is specifically used to: Get the execution variable in the script of the prediction model establishment on the HTML page. If the execution variable is True, get the user ID, data type, sliding window size, number of model training times and number of single training samples. Read the data after removing outliers and use the preprocessing function to normalize the training or test data; Loop through the data set, extract the input features and target values ​​of the normalized data under the specified window, and adjust the dimension order of the array; Build a long short-term memory neural network model, set the loss function and optimizer; Define the global variables training completion rate and current iteration number, perform loop iteration, if the current iteration number is less than the total iteration number, complete one model training, save the model loss rate, and update the training completion rate; Calculate the model prediction value to obtain the loss evaluation index parameters of the prediction result, wherein the loss evaluation index parameters include mean square error, root mean square error, mean absolute error and goodness of fit; Draw the model loss rate curve and loss evaluation index bar chart, add the user ID in the chart name, and save it to the specified folder; The storage address of the loss rate curve chart and the loss evaluation index bar chart is returned to the HTML front end.

9. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 1, characterized in that: The trend prediction module is specifically used for: Confirm whether to conduct data trend prediction; If the prediction is confirmed, the file information is read, and the execution variable is added, and the execution variable is assigned to True, and the progress bar parameter is read and assigned to 0; Create a progress bar update sub-function, which first accesses the progress bar view function in the Flask program. The progress bar view function returns the completion rate to the HTML front end, and then updates the value, width and value position of the progress bar, and refreshes the page every preset time; Access the trend forecast view function in the Flask program. If there is no response, a network error message is returned; If there is a response, the image location information is combined with the current time to form a new image name, and the trend forecast chart in the current page is updated; If you do not confirm the prediction, a prompt to cancel the prediction will pop up.

10. A structural monitoring and evaluation system integrating data trend prediction as claimed in claim 9, characterized in that: The trend forecast view function is specifically used for: Get the execution parameters in the script for predicting future trends on the HTML page. If the execution parameter value is True, get the user ID, data type, and forecast days. Define the global variable prediction completion rate and the current number of iterations, call the trained long short-term memory neural network model cyclically, predict future data changes day by day, store the prediction results, and update the prediction completion rate; Draw the predicted image, including the comparison between the predicted value and the measured value, add the user ID to the image name, and save it to the specified folder; Return the storage address of the prediction graph to the HTML front end.

Images