CN116663962A - Be used for hydraulic engineering dyke material quality detection analysis system - Google Patents

Abstract

The invention discloses a dam material quality detection and analysis system for hydraulic engineering, which belongs to the technical field of dam material detection and comprises a data acquisition module, a data processing module, an analysis and prediction module, a report output module, a database management module and a system safety module, wherein the data acquisition module is connected with the data processing module; the invention can discover the trend and rule of the change of the dam material quality in advance, forecast the possible risk and danger, and early warn and take corresponding measures and countermeasures in time.

Description

Be used for hydraulic engineering dyke material quality detection analysis system

Technical Field

The invention relates to the technical field of dam material detection, in particular to a dam material quality detection and analysis system for hydraulic engineering.

Background

The dam for hydraulic engineering is generally used for water blocking and flood control at the edges of rivers and lakes, the material selection of the dam is very important, if the material selection is improper, flood is allowed to flood, the dam for hydraulic engineering is an important hydraulic building, and the safety and stability of the material quality of the dam directly influence the reliability and service life of engineering;

the data analysis method in the prior art is single, and comprehensive effects of various factors and influence factors are difficult to comprehensively consider, so that prediction accuracy and precision are not high, certain hysteresis can exist in the existing data acquisition and analysis means, the change trend and rule of dam material quality are difficult to reflect in real time, and early warning and processing cannot be performed in time.

Disclosure of Invention

The invention aims to provide a system for detecting and analyzing the quality of a hydraulic engineering dam material, which is used for solving the problems in the background art:

the data analysis method in the prior art is single, and comprehensive effects of various factors and influence factors are difficult to comprehensively consider, so that prediction accuracy and precision are not high, certain hysteresis can exist in the existing data acquisition and analysis means, the change trend and rule of dam material quality are difficult to reflect in real time, and early warning and processing cannot be performed in time.

A system for quality detection and analysis of hydraulic engineering dam material, comprising:

the data acquisition module is used for acquiring physical, chemical and mechanical property data of the dam material, including density, strength, toughness, water absorption and permeability of the material;

the data processing module is used for processing the acquired data and comprises data cleaning, data analysis and data mining, and effective information is extracted;

the analysis and prediction module is used for analyzing and predicting by adopting a machine learning technology according to the data processing result, identifying the quality problem of the material and predicting possible faults and damage conditions;

the report output module outputs the analysis and prediction result as a report and provides the report with reference to engineers and related personnel so as to facilitate the establishment of corresponding repair and maintenance plans;

the database management module is used for managing data in the system, including storage, backup and recovery of the data;

the system security module guarantees the security of the system and comprises user identity verification, access right control and data encryption.

The system comprises a data acquisition module, a data processing module, an analysis prediction module, a report output module, a database management module, a data acquisition module, a data processing module, an analysis prediction module and a report output module.

The data processing module comprises:

the data cleaning and denoising processing module is used for removing noise and abnormal values and cleaning missing data, so that a data set can be used for subsequent analysis and prediction;

the data integration and conversion module integrates the data of different data sources into a data set and converts the data into a format which can be used for analysis;

the data normalization and standardization module converts data with different dimensions into data with the same dimensions, so that data analysis and processing are facilitated;

and the data visualization module is used for visualizing and presenting the data, including drawing charts and maps, so that the data is convenient for people to understand and analyze.

The data cleaning and denoising processing module comprises:

the data deduplication module is used for checking whether repeated data exist in the data set and rejecting the repeated data;

the abnormal value processing module is used for checking whether abnormal values exist in the data set and processing the abnormal values;

a data format conversion module: and converting the data with different formats so as to perform subsequent data analysis and processing.

And a data normalization module: the data normalization module converts data with different dimensions into data with the same dimension by adopting a normalization processing method so as to compare and analyze the data;

and the data integration module integrates data from different data sources together so as to perform unified analysis and processing.

The analysis and prediction module comprises:

the feature selection and dimension reduction module selects features influencing the prediction result from the data set, reduces the number of features through dimension reduction, and improves the training efficiency of the model;

and the model selection and training module is used for selecting a proper model according to the property of the prediction task, wherein the proper model comprises linear regression, a decision tree and a neural network, and the proper model is obtained through training.

And the model evaluation and optimization module evaluates the performance and effect of the model and optimizes the prediction capability and generalization capability of the model by adjusting the parameters of the model.

And the prediction result visualization module is used for visualizing and presenting the prediction result, so that the prediction result is convenient for people to understand and analyze.

The report output module includes:

and the detection result overview module displays the generalized information of the detection result in the form of characters, tables and charts, wherein the generalized information comprises basic statistical information of data, the number of abnormal points and the positions of the abnormal points.

The analysis and prediction result module is used for presenting data analysis and prediction results to a user in a data visualization mode, helping the user to know the trend, change and rule of the material quality and providing a conclusion and suggestion based on model prediction;

the report generation and export module stores the generated report in an electronic document format, is convenient for users to view and share, and provides a function of exporting data so as to be used by the users in other analysis tools;

the user interaction and feedback module provides an interface for user feedback, receives comments and suggestions of a user, and continuously improves the performance and functions of the system according to the feedback of the user;

and the security and privacy protection module ensures that report data generated by the system is safe and reliable, does not reveal user privacy information and accords with related data protection rules and regulations.

The system security module includes:

the user identity verification module system needs to carry out identity verification on the user so as to ensure that only legal users can access the system;

access right control module: the access right control module system needs to control the access right of the user so as to ensure that the user can only access the data and functions with the right.

And a data encryption module: the data encryption module system encrypts sensitive data to ensure the security of the data in the transmission and storage processes;

a firewall, which protects the system from network attacks, filters illegal accesses and attacks, and prevents access from untrusted networks and intrusion of malicious code;

audit log module: the audit log module is convenient for finding and solving potential safety problems, and the audit log records the login, operation, modification and deletion operation behaviors of a user and records the time stamp and the user information.

Compared with the prior art, the invention has the advantages that:

1) And the detection precision is improved: by adopting various detection means and algorithms and combining a big data analysis and prediction model, the detection precision and accuracy of the dam material quality can be improved, hidden dangers and defects can be found, and accidents and losses can be reduced.

2) Enhancing the early warning capability: through real-time monitoring and analysis, the trend and rule of the change of the dam material quality can be found in advance, the possible risk and danger are predicted, and corresponding measures and countermeasures are early-warned and taken in time.

3) Optimizing the management flow: the consumption of manpower and material resources can be greatly reduced, the management efficiency and benefit are improved, and the management cost and workload are reduced by a digital and automatic management mode.

4) The working safety is improved: by comprehensively monitoring and analyzing the quality of the dam material, the safety guarantee level of workers can be improved, the working risk and the working pressure are reduced, and the working satisfaction and quality are improved.

5) Enhancing information sharing: through establishing a unified data platform and a unified database, sharing and exchange of data can be realized, intercommunication and circulation of information are promoted, technological progress and knowledge innovation are promoted, and the whole level and competitiveness of the industry are improved.

Drawings

FIG. 1 is a block diagram of a system for detecting and analyzing the quality of dam materials of hydraulic engineering.

Detailed Description

The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

A system for quality detection and analysis of hydraulic engineering dam material, comprising:

the data acquisition module is used for acquiring physical, chemical and mechanical property data of the dam material, including density, strength, toughness, water absorption and permeability of the material;

the data processing module processes the acquired data and comprises data cleaning, data analysis and data mining, and effective information is extracted;

the analysis and prediction module is used for analyzing and predicting by adopting a machine learning technology according to the data processing result, identifying the quality problem of the material and predicting possible faults and damage conditions;

the report output module outputs the analysis and prediction result as a report and provides the report to engineers and related personnel for reference so as to facilitate the establishment of corresponding repair and maintenance plans;

the database management module is used for managing data in the system, including storage, backup and recovery of the data;

the system security module guarantees the security of the system and comprises user authentication, access right control and data encryption.

The data acquisition module is connected with the data processing module, the data processing module is connected with the analysis and prediction module, the analysis and prediction module is connected with the report output module, the database management module is connected with the data acquisition module, the data processing module, the analysis and prediction module and the report output module, and the system safety module is connected with the data acquisition module, the data processing module, the analysis and prediction module and the report output module.

The data processing module comprises:

the data cleaning and denoising processing module eliminates noise and abnormal values and cleans missing data, so that a data set can be used for subsequent analysis and prediction;

data cleaning:

data cleaning refers to correcting or deleting errors, incompleteness or inconsistent parts in data so as to ensure the quality and accuracy of the data. Common data cleansing operations include deduplication, padding missing values, correcting error values, and the like.

Denoising:

denoising refers to processing noise present in data to eliminate the effect of the noise. Common denoising processing methods include smoothing processing, filtering processing, and the like.

The mean filter formula is:

y_i＝\frac{1}{n}\sum_{j＝i-k}^{i+k}x_j

where x is the original data, y is the processed data, n is the window size, and k is the window radius.

The median filter formula is:

y_i＝median(x_{i-k},x_{i-k+1},...,x_{i+k})

where x is the original data, y is the processed data, and k is the window radius.

The linear interpolation is formulated as:

y_i＝y_{i-1}+\frac{x_{i}-x_{i-1}}{x_{i+1}-x_{i-1}}(y_{i+1}-y_{i-1})

where x is the position of the known data, y is the value of the known data, and y_i is the value of the data to be filled

The data integration and conversion module integrates the data of different data sources into a data set and converts the data into a format which can be used for analysis;

the data normalization and standardization module converts data with different dimensions into data with the same dimensions, so that data analysis and processing are facilitated;

maximum and minimum normalization is adopted:

the maximum and minimum normalization is to linearly map the original data into the [0,1] interval, and the formula is as follows:

x_{new}＝\frac{x-x_{min}}{x_{max}-x_{min}}

where x is the original data, and x_ { min } and x_ { max } are the minimum and maximum values in the original data, respectively.

And the data visualization module is used for visualizing and presenting the data, including drawing a chart and a map, so that the data is convenient for people to understand and analyze.

The data cleaning and denoising processing module comprises:

the data deduplication module is used for checking whether repeated data exist in the data set and rejecting the repeated data;

the abnormal value processing module is used for checking whether the abnormal value exists in the data set and processing the abnormal value;

a data format conversion module: and converting the data with different formats so as to perform subsequent data analysis and processing.

And a data normalization module: the data normalization module converts the data with different dimensions into the data with the same dimension by adopting a normalization processing method so as to compare and analyze the data;

and the data integration module integrates data from different data sources together so as to perform unified analysis and processing.

The analysis and prediction module comprises:

the feature selection and dimension reduction module selects features influencing the prediction result from the data set, reduces the number of features through dimension reduction, and improves the training efficiency of the model;

feature selection and dimension reduction are commonly used operations in data analysis, and are used for selecting features influencing a prediction result from a data set, reducing the number of features through dimension reduction, and improving training efficiency and prediction performance of a model. Common feature selection and dimension reduction methods include Principal Component Analysis (PCA), linear Discriminant Analysis (LDA), correlation coefficient method, chi-square test and the like.

Taking principal component analysis as an example, the specific operation is as follows:

and (3) carrying out centering treatment on the original data, namely subtracting the average value of each feature from the average value of the feature in the original data to obtain a zero-average data set.

And calculating a covariance matrix of the data, and decomposing the characteristic value to obtain a characteristic value and a characteristic vector.

And selecting the first k eigenvectors to reduce the dimension of the data, wherein k is the reserved eigenvalue.

The dimension reduced data is used for subsequent modeling and prediction.

And (3) carrying out centering treatment on the original data, namely subtracting the average value of each feature from the average value of the feature in the original data to obtain a zero-average data set.

And calculating a covariance matrix of the data, and decomposing the characteristic value to obtain a characteristic value and a characteristic vector.

And selecting the first k eigenvectors to reduce the dimension of the data, wherein k is the reserved eigenvalue.

The dimension reduced data is used for subsequent modeling and prediction.

The mathematical formula of principal component analysis is as follows:

and n samples are provided, each sample has m characteristics, the original data matrix is X (n multiplied by m), and the calculation process of the principal component analysis is as follows:

the data is subjected to centering treatment to obtain a zero-mean data matrix Z (n multiplied by m):

Z＝X-1/n*∑(X)

where 1/n is the normalization factor and sigma (X) is the mean vector for each column of the data matrix.

Calculating covariance matrix C (m×m) of data:

C＝1/n*Z^T*Z

wherein Z≡T represents the transposed matrix of Z.

And carrying out eigenvalue decomposition on the covariance matrix C to obtain eigenvalues lambda 1, lambda 2, lambda m and eigenvectors v1, v2, lambda m, wherein the eigenvectors are arranged from large to small according to the corresponding eigenvalues.

Selecting the first k eigenvectors, and performing dimension reduction on the data matrix Z to obtain a dimension-reduced data matrix Y (n multiplied by k):

Y＝Z*V_k

where v_k is a matrix containing the first k eigenvectors.

The model selection and training module selects a proper model according to the property of a prediction task, wherein the proper model comprises linear regression, a decision tree and a neural network, and the proper model is obtained through training, and the model selection and training module specifically comprises the following steps:

model selection:

in selecting a model, consideration is required to be given to the performance and applicability of the model, as well as the characteristics and number of data. Common models include linear regression, decision trees, support vector machines, neural networks, and the like.

Data preprocessing:

prior to training the model, the data needs to be preprocessed to ensure quality and accuracy of the data. The data preprocessing operation comprises data cleaning, data normalization, feature selection and the like.

Training by adopting a least square method model:

the purpose of model training is to determine parameters of the model by training the data to predict unknown data. In training a model, data needs to be divided into a training set and a testing set.

The least squares method is a commonly used linear regression model training algorithm. The formula is as follows:

argmin_{w}||Xw-y||^2_2

wherein w is a model parameter, X is a feature matrix, and y is a target value.

Evaluation was performed using an R square model:

the purpose of model evaluation is to evaluate the performance and accuracy of the model in order to adjust model parameters and select a more appropriate model.

R square value:

the R square is an index for evaluating the performance of the model, and the formula is:

R^2＝1-\frac{\sum_{i＝1}^{n}(y_i-\hat{y_i})^2}{\sum_{i＝1}^{n}(y_i-\bar{y})^2}

where y is the true value, \hat { y } is the predicted value, \bar { y } is the average value.

And the model evaluation and optimization module evaluates the performance and effect of the model and optimizes the prediction capability and generalization capability of the model by adjusting the parameters of the model.

And the prediction result visualization module is used for visualizing and presenting the prediction result, so that the prediction result is convenient for people to understand and analyze.

The report output module includes:

the detection result overview module displays the generalized information of the detection result in the form of characters, tables and charts, wherein the generalized information comprises basic statistical information of data, the number of abnormal points and the positions of the abnormal points.

The analysis and prediction result module is used for presenting data analysis and prediction results to a user in a data visualization mode, helping the user to know the trend, change and rule of the material quality and providing a conclusion and suggestion based on model prediction;

the report generation and export module stores the generated report in an electronic document format, is convenient for users to view and share, and provides a function of exporting data so as to be used by the users in other analysis tools;

the user interaction and feedback module provides an interface for user feedback, receives comments and suggestions of a user, and continuously improves the performance and functions of the system according to the feedback of the user;

the security and privacy protection module ensures that report data generated by the system is safe and reliable, does not reveal user privacy information, and accords with related data protection rules and regulations.

The system security module includes:

the user identity verification module is used for verifying the identity of the user by the user identity verification module system so as to ensure that only legal users can access the system;

access right control module: the access right control module system needs to control the access right of the user so as to ensure that the user can only access the data and functions with the right.

And a data encryption module: the data encryption module system encrypts sensitive data to ensure the security of the data in the transmission and storage processes;

a firewall, which protects the system from network attacks, filters illegal accesses and attacks, and prevents access from untrusted networks and intrusion of malicious codes;

audit log module: the audit log module is convenient for finding and solving potential safety problems, and the audit log records the login, operation, modification and deletion operation behaviors of a user and records the time stamp and the user information.

The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and their equivalents.

Claims (6)

1. A system for detecting and analyzing the quality of dam materials of hydraulic engineering, comprising:

the data acquisition module is used for acquiring physical, chemical and mechanical property data of the dam material, including density, strength, toughness, water absorption and permeability of the material;

the data processing module is used for processing the acquired data and comprises data cleaning, data analysis and data mining, and effective information is extracted;

the analysis and prediction module is used for analyzing and predicting by adopting a machine learning technology according to the data processing result, identifying the quality problem of the material and predicting possible faults and damage conditions;

the report output module outputs the analysis and prediction result as a report and provides the report with reference to engineers and related personnel so as to facilitate the establishment of corresponding repair and maintenance plans;

the database management module is used for managing data in the system, including storage, backup and recovery of the data;

the system security module guarantees the security of the system and comprises user identity verification, access right control and data encryption.

The system comprises a data acquisition module, a data processing module, an analysis prediction module, a report output module, a database management module, a data acquisition module, a data processing module, an analysis prediction module and a report output module.

2. The system for detecting and analyzing the quality of a dam material for hydraulic engineering according to claim 1, wherein the data processing module comprises:

the data cleaning and denoising processing module is used for removing noise and abnormal values and cleaning missing data, so that a data set can be used for subsequent analysis and prediction;

the data integration and conversion module integrates the data of different data sources into a data set and converts the data into a format which can be used for analysis;

the data normalization and standardization module converts data with different dimensions into data with the same dimensions, so that data analysis and processing are facilitated;

and the data visualization module is used for visualizing and presenting the data, including drawing charts and maps, so that the data is convenient for people to understand and analyze.

3. The system for detecting and analyzing the quality of a dam material for hydraulic engineering according to claim 2, wherein the data cleaning and denoising process module comprises:

the data deduplication module is used for checking whether repeated data exist in the data set and rejecting the repeated data;

the abnormal value processing module is used for checking whether abnormal values exist in the data set and processing the abnormal values;

a data format conversion module: and converting the data with different formats so as to perform subsequent data analysis and processing.

And a data normalization module: the data normalization module converts data with different dimensions into data with the same dimension by adopting a normalization processing method so as to compare and analyze the data;

and the data integration module integrates data from different data sources together so as to perform unified analysis and processing.

4. The system for detecting and analyzing the quality of a dam material for hydraulic engineering according to claim 1, wherein the analysis prediction module comprises:

the feature selection and dimension reduction module selects features influencing the prediction result from the data set, reduces the number of features through dimension reduction, and improves the training efficiency of the model;

and the model selection and training module is used for selecting a proper model according to the property of the prediction task, wherein the proper model comprises linear regression, a decision tree and a neural network, and the proper model is obtained through training.

And the model evaluation and optimization module evaluates the performance and effect of the model and optimizes the prediction capability and generalization capability of the model by adjusting the parameters of the model.

And the prediction result visualization module is used for visualizing and presenting the prediction result, so that the prediction result is convenient for people to understand and analyze.

5. The system for detecting and analyzing the quality of a dam material for hydraulic engineering according to claim 1, wherein the report output module comprises:

and the detection result overview module displays the generalized information of the detection result in the form of characters, tables and charts, wherein the generalized information comprises basic statistical information of data, the number of abnormal points and the positions of the abnormal points.

The analysis and prediction result module is used for presenting data analysis and prediction results to a user in a data visualization mode, helping the user to know the trend, change and rule of the material quality and providing a conclusion and suggestion based on model prediction;

the report generation and export module stores the generated report in an electronic document format, is convenient for users to view and share, and provides a function of exporting data so as to be used by the users in other analysis tools;

the user interaction and feedback module provides an interface for user feedback, receives comments and suggestions of a user, and continuously improves the performance and functions of the system according to the feedback of the user;

and the security and privacy protection module ensures that report data generated by the system is safe and reliable, does not reveal user privacy information and accords with related data protection rules and regulations.

6. A system for detecting and analyzing the quality of a dam material for hydraulic engineering according to claim 1, wherein the system safety module comprises:

the user identity verification module system needs to carry out identity verification on the user so as to ensure that only legal users can access the system;

access right control module: the access right control module system needs to control the access right of the user so as to ensure that the user can only access the data and functions with the right.

And a data encryption module: the data encryption module system encrypts sensitive data to ensure the security of the data in the transmission and storage processes;

a firewall, which protects the system from network attacks, filters illegal accesses and attacks, and prevents access from untrusted networks and intrusion of malicious code;

audit log module: the audit log module is convenient for finding and solving potential safety problems, and the audit log records the login, operation, modification and deletion operation behaviors of a user and records the time stamp and the user information.