A water conservancy project concrete quality detection and analysis system

Through the concrete quality inspection and analysis system of water conservancy engineering, the data collection, preprocessing and analysis modules are used to solve the diversity of concrete inspection data, improve the accuracy and efficiency of inspection, and provide targeted maintenance solutions to ensure the safety of the reservoir Sex and service life.

CN118552091BInactive Publication Date: 2024-11-12WATER RESOURCES RES INST OF SHANDONG PROVINCE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411017183.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

In the prior art, there are various types of concrete inspection data for water conservancy projects and the lack of unified measurement standards, which leads to difficulties in data integration and analysis, which affects the accuracy and efficiency of inspection.

Method used

A concrete quality inspection and analysis system for water conservancy engineering is designed, including data collection, preprocessing and analysis modules. The quality evaluation score and restoration and maintenance plan of concrete are obtained through the trained quality evaluation prediction model. The system includes data cleaning, regulations, and model training. and maintenance scheme generate sub-models.

Benefits of technology

It improves the accuracy and efficiency of concrete quality inspection, provides targeted restoration and maintenance solutions, and ensures the safety and service life of the reservoir.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118552091B_ABST
    Figure CN118552091B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of water conservancy engineering concrete detection, and in particular to a water conservancy engineering concrete quality detection and analysis system, which is used in the construction and maintenance process of large reservoirs and includes: a data collection module, which is used to collect quality detection data of concrete to be tested; the quality detection data includes: compressive strength detection data, concrete density detection data, and frost resistance detection data; a data preprocessing module, which is used to preprocess the quality detection data of concrete to be tested and obtain the preprocessed data; a data analysis module, which is used to input the preprocessed data into a trained quality assessment prediction model to obtain a quality assessment report of the concrete to be tested; the quality assessment prediction model includes: a concrete quality scoring sub-model and a concrete maintenance plan generation sub-model. The present invention improves the accuracy and efficiency of concrete quality detection in large reservoirs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of water conservancy engineering concrete detection, and in particular to a water conservancy engineering concrete quality detection and analysis system. Background Art

[0002] Concrete, referred to as "concrete", refers to an artificial stone made of cementitious materials (such as cement), aggregates (such as sand, stone), water, and admixtures and additives added when necessary in a certain proportion, which is evenly stirred, compacted into shape, and cured and hardened. It is widely used in water conservancy projects.

[0003] In water conservancy projects, especially in large reservoirs, the quality of concrete structures is crucial to the safety and durability of the entire project; the inspection and analysis of concrete quality ensures the overall quality of the project by ensuring the compliance of concrete materials and construction processes.

[0004] At present, concrete quality inspection mainly relies on various non-destructive testing technologies and laboratory testing methods. However, the data types and formats generated by various testing methods are diverse, and there is a lack of unified measurement standards, which makes it difficult to integrate and analyze data, affecting the accuracy and efficiency of comprehensive evaluation.

[0005] Therefore, there is an urgent need for a water conservancy project concrete quality detection and analysis system. Summary of the invention

[0006] 1. Technical issues to be resolved

[0007] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a water conservancy project concrete quality detection and analysis system, which solves the technical problems that the data types obtained during concrete detection in large reservoirs are diverse and lack a unified measurement standard, making it difficult to integrate and analyze the data.

[0008] (II) Technical solution

[0009] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0010] The embodiment of the present invention provides a water conservancy project concrete quality detection and analysis system, which is used in the construction and maintenance of large reservoirs, and includes:

[0011] A data collection module is used to collect quality inspection data of the concrete to be tested;

[0012] The quality inspection data include: compressive strength inspection data, concrete density inspection data, and frost resistance inspection data;

[0013] A data preprocessing module, used for preprocessing the quality detection data of the concrete to be tested to obtain preprocessed data;

[0014] A data analysis module, used for inputting the preprocessed data into a trained quality assessment prediction model to obtain a quality assessment report of the concrete to be tested;

[0015] The quality assessment prediction model includes: a concrete quality scoring sub-model and a concrete maintenance plan generation sub-model;

[0016] The quality assessment report includes: a quality assessment score of the concrete to be tested and a repair and maintenance plan.

[0017] Optionally, the data preprocessing module includes: a data cleaning unit and a data reduction unit;

[0018] The data cleaning unit is used to identify and correct the erroneous, inconsistent and missing data in the quality inspection data of the concrete to be tested, and obtain the data after data cleaning;

[0019] The data reduction unit is used to simplify the cleaned data according to a dimension reduction algorithm to obtain preprocessed data.

[0020] Optionally, the system further comprises:

[0021] A model training module is used to train the quality assessment prediction model using a training data set to obtain a trained quality assessment prediction model;

[0022] The training data set is the historical quality inspection data of the pre-processed concrete samples and the corresponding quality assessment scores and repair and maintenance plan records.

[0023] Optionally, the adopting a training data set to train the quality assessment prediction model to obtain a trained quality assessment prediction model comprises:

[0024] Each data in the training data set is input into the quality assessment prediction model for training until the preset regression loss function and classification loss function corresponding to the quality assessment prediction model converge, thereby obtaining a trained quality assessment prediction model.

[0025] Optionally, the preprocessed data is input into a trained quality assessment prediction model to obtain a quality assessment report of the concrete to be tested, including:

[0026] The preprocessed data is input into the concrete quality scoring sub-model to obtain the quality assessment score of the concrete to be tested; the concrete quality assessment score is input into the concrete maintenance plan generation sub-model to obtain the repair and maintenance plan of the concrete to be tested.

[0027] Optionally, inputting the preprocessed data into a concrete quality scoring sub-model to obtain a quality assessment score of the concrete to be tested comprises:

[0028] The concrete quality scoring sub-model is: ,

[0029] in, S is the quality assessment score, b is the bias term, a constant; The weight corresponding to each indicator is N is the number of samples for each indicator, For the i The first indicator j samples, For each indicator, the minimum value in the preset range, The maximum value of each indicator within the preset range.

[0030] Optionally, the weight corresponding to each indicator is: ,

[0031] in, For each indicator Overall quality of concrete Q The correlation coefficient between is the adjustment factor for each indicator, is the decay rate of each indicator, For time, is an exponential decay function for each indicator.

[0032] Optionally, the preset range of compressive strength is 20-50 MPa, the preset range of concrete density is 2.2-2.6 g / cm3, and the preset range of frost resistance is 25-100 freeze-thaw cycles.

[0033] Optionally, the concrete quality assessment score is input into a concrete maintenance solution generation sub-model to obtain a repair and maintenance solution for the concrete to be tested, and the concrete maintenance solution generation sub-model includes:

[0034] Hidden layer feature extraction unit, decision logic determination unit;

[0035] The hidden layer feature extraction unit is used to extract the hidden layer features of the concrete quality assessment score input into the concrete maintenance plan generation sub-model;

[0036] The decision logic determination unit is used to determine the final concrete repair and maintenance plan based on a preset decision tree algorithm.

[0037] Optionally, the hidden layer feature extraction unit comprises an autoencoder for extracting hidden layer features of the concrete quality assessment score input to the concrete maintenance plan generation sub-model;

[0038] The automatic encoder comprises an encoder and a decoder, wherein the encoder and the decoder each comprise l a The convolution kernel size is 1×1. l a is a preset value.

[0039] (III) Beneficial effects

[0040] The beneficial effects of the present invention are as follows: a water conservancy project concrete quality detection and analysis system of the present invention, because it inputs the quality detection data of concrete into a trained quality assessment prediction model to obtain the quality assessment score of concrete and the repair and maintenance plan, compared with the existing technology, it improves the accuracy and efficiency of concrete quality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The present invention is a schematic diagram of a water conservancy project concrete quality detection and analysis system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0043] A water conservancy project concrete quality detection and analysis system proposed in an embodiment of the present invention improves the accuracy and efficiency of concrete quality detection by inputting concrete quality detection data into a trained quality assessment prediction model to obtain a concrete quality assessment score and a repair and maintenance plan.

[0044] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0045] Specific embodiment description part

[0046] Example 1

[0047] See also Figure 1 A water conservancy project concrete quality detection and analysis system according to an embodiment of the present invention is used in the construction and maintenance of large reservoirs, and includes:

[0048] A data collection module is used to collect quality inspection data of the concrete to be tested;

[0049] The quality inspection data include: compressive strength inspection data, concrete density inspection data, and frost resistance inspection data;

[0050] A data preprocessing module, used for preprocessing the quality detection data of the concrete to be tested to obtain preprocessed data;

[0051] A data analysis module, used for inputting the preprocessed data into a trained quality assessment prediction model to obtain a quality assessment report of the concrete to be tested;

[0052] The quality assessment prediction model includes: a concrete quality scoring sub-model and a concrete maintenance plan generation sub-model;

[0053] The quality assessment report includes: a quality assessment score of the concrete to be tested and a repair and maintenance plan.

[0054] In the specific implementation process, at different stages of reservoir construction, such as the initial pouring period, the maintenance period and the operation period, various sensors and detection equipment are used to perform measurements to obtain the compressive strength test data, concrete density test data and frost resistance test data of the concrete to be tested. For example, the concrete test data is obtained by a concrete compressive strength testing machine; the concrete density test data is obtained by an ultrasonic detector; and the frost resistance test data is obtained by using a freeze-thaw testing machine to conduct a freeze-thaw cycle test.

[0055] In this embodiment, for example, during the construction of a large reservoir, the quality of concrete in key parts of the large reservoir is regularly inspected to obtain the quality inspection data of the concrete. The system first preprocesses the quality inspection data and then inputs it into the trained quality assessment prediction model. After model analysis, the quality score of the concrete is 70 points, indicating that there are certain quality problems. Then, the concrete maintenance plan generation sub-model generates a repair plan and recommends the following measures: adjust the concrete mix ratio to increase the compressive strength, and maintain the lake maintenance conditions to improve the internal structure of the concrete; finally, guide the engineering team to specify a targeted maintenance plan based on the generated quality assessment score and repair and maintenance plan, so as to effectively ensure the safety and service life of the reservoir.

[0056] A water conservancy project concrete quality detection and analysis system in this embodiment is used for quality detection of large reservoirs. By inputting the quality detection data of concrete into a trained quality assessment prediction model, the quality assessment score of concrete and the repair and maintenance plan are obtained, thereby improving the accuracy and efficiency of concrete quality detection. At the same time, the engineering team is guided to repair and maintain large reservoirs according to the obtained repair and maintenance plan, which can effectively protect the safety and service life of the reservoir and ensure long-term stable operation.

[0057] Example 2

[0058] A water conservancy project concrete quality detection and analysis system according to an embodiment of the present invention is used in the construction and maintenance of large reservoirs, and includes:

[0059] A data collection module is used to collect quality inspection data of the concrete to be tested;

[0060] Quality inspection data include: compressive strength inspection data, concrete density inspection data, and frost resistance inspection data;

[0061] A data preprocessing module is used to preprocess the quality inspection data of the concrete to be tested and obtain the preprocessed data;

[0062] A data analysis module is used to input the preprocessed data into the trained quality assessment prediction model to obtain a quality assessment report of the concrete to be tested;

[0063] The quality assessment prediction model includes: concrete quality scoring sub-model and concrete maintenance plan generation sub-model;

[0064] The quality assessment report includes: the quality assessment score of the tested concrete and the repair and maintenance plan.

[0065] In this embodiment, the data preprocessing module includes: a data cleaning unit and a data reduction unit;

[0066] The data cleaning unit is used to identify and correct the erroneous, inconsistent and missing data in the quality inspection data of the concrete to be tested, and obtain the data after data cleaning.

[0067] In the specific implementation process, through the built-in algorithm and rule library, the data cleaning unit identifies abnormal values ​​and error values ​​in the quality test data of the concrete to be tested. For example, if a certain compressive strength test data exceeds a reasonable range, the system will mark the data as error data and correct the error data based on the data trend of the remaining compressive strength test data.

[0068] The data reduction unit is used to simplify the cleaned data according to the dimension reduction algorithm to obtain the preprocessed data.

[0069] The data reduction unit in this embodiment uses a principal component analysis (PLA) algorithm to perform dimensionality reduction.

[0070] In the specific implementation process, for example, the concrete density test data includes the concrete surface density test data and the concrete internal density test data, etc., which constitute a multidimensional data set; the PLA algorithm obtains the key feature that best represents the entire data set based on the correlation between the various indicators in the multidimensional data set, which is the concrete internal density test data, and deletes the concrete surface density test data in the multidimensional data set, thereby achieving the purpose of streamlining data and making the subsequent quality assessment prediction model more efficient and accurate.

[0071] Specifically, the system also includes:

[0072] A model training module is used to train the quality assessment prediction model using a training data set to obtain a trained quality assessment prediction model;

[0073] The training dataset consists of the historical quality inspection data of pre-processed concrete samples and the corresponding quality assessment scores and repair and maintenance plan records.

[0074] The quality assessment prediction model is trained using a training data set, and obtaining the trained quality assessment prediction model includes:

[0075] Each data in the training data set is input into the quality assessment prediction model for training until the preset regression loss function and classification loss function corresponding to the quality assessment prediction model converge, thereby obtaining a trained quality assessment prediction model.

[0076] In this embodiment, when the model is trained, the model parameters are randomly initialized, and the model parameters are the adjustment factor, the bias term and the decision tree parameters of each indicator.

[0077] In the specific implementation process, each set of data in the training data set is input into the quality assessment prediction model in turn, and the quality assessment score and repair and maintenance plan of the concrete sample are obtained based on the current parameters; the difference between the predicted result and the actual known result is calculated, and the regression loss function is used to evaluate the accuracy of the quality assessment score. The classification loss function is used to measure the matching degree of the repair and maintenance plan. According to the result of the loss function, the model parameters are updated through the back propagation algorithm to gradually reduce the loss function until convergence. The quality assessment prediction model at this time is the trained quality assessment prediction model.

[0078] Specifically, the preprocessed data is input into the trained quality assessment prediction model to obtain the quality assessment report of the concrete to be tested, including:

[0079] The preprocessed data is input into the concrete quality scoring sub-model to obtain the quality assessment score of the concrete to be tested; the concrete quality assessment score is input into the concrete maintenance plan generation sub-model to obtain the repair and maintenance plan of the concrete to be tested.

[0080] In the specific implementation process, the preprocessed data is input into the concrete quality scoring sub-model to obtain the quality assessment score of the concrete to be tested, including:

[0081] The concrete quality scoring sub-model is: ,

[0082] in, S is the quality assessment score, b is the bias term, a constant; The weight corresponding to each indicator is N is the number of samples for each indicator, For the i The first indicator j samples, For each indicator, the minimum value in the preset range, The maximum value of each indicator within the preset range.

[0083] Optionally, the weight corresponding to each indicator is: ,

[0084] in, For each indicator Overall quality of concrete Q The correlation coefficient between is the adjustment factor for each indicator, is the decay rate of each indicator, For time, is an exponential decay function for each indicator.

[0085] In this embodiment, the preset range of compressive strength is 20-50 MPa, the preset range of concrete density is 2.2-2.6 g / cm3, and the preset range of frost resistance is 25-100 freeze-thaw cycles.

[0086] For example, assuming that the average value of the compressive strength test data of the concrete to be tested is 35 MPa, the average value of the concrete density test data is 2.4 g / cm3, the average number of freeze-thaw cycles in the frost resistance test data is 60 times, and the bias item is 20, the weights corresponding to the three indicators are 0.5, 0.3, and 0.2 respectively. At this time, the quality assessment score of the concrete to be tested can be obtained as 68.67 points based on the concrete quality scoring sub-model.

[0087] Specifically, the concrete quality assessment score is input into the concrete maintenance plan generation sub-model to obtain the repair and maintenance plan of the concrete to be tested. The concrete maintenance plan generation sub-model includes:

[0088] Hidden layer feature extraction unit, decision logic determination unit;

[0089] The hidden layer feature extraction unit is used to extract the hidden layer features of the concrete quality assessment score input into the concrete maintenance plan generation sub-model;

[0090] The decision logic determination unit is used to determine the final concrete repair and maintenance plan based on a preset decision tree algorithm.

[0091] Specifically, the latent feature extraction unit includes an autoencoder for extracting latent features of a concrete quality assessment score input to a concrete maintenance program generation sub-model;

[0092] The automatic encoder includes an encoder and a decoder, wherein the encoder and the decoder each include l a The convolution kernel size is 1×1. l a is a preset value.

[0093] The decision tree algorithm is a supervised learning method used for classification and regression tasks. In this embodiment, it is used to generate a specific repair and maintenance plan based on the features extracted from the autoencoder. The decision tree moves down the tree structure through a series of feature tests until it reaches a leaf node, which provides the final output.

[0094] In the specific implementation process, the concrete repair and maintenance methods include: applying waterproof coatings or sealants to protect the concrete surface from water erosion and chemical damage; using carbon fiber cloth (CFRP), glass fiber cloth (GFRP) or steel plates for external reinforcement; completely removing the concrete and replacing it with new concrete; using penetrating hardeners to penetrate into the interior of the concrete to increase the hardness and density of the concrete, etc.

[0095] In this embodiment, by inputting the quality inspection data of concrete into the trained quality assessment prediction model, the quality assessment score of concrete and the repair and maintenance plan are obtained, the accuracy and efficiency of concrete quality inspection are improved, and a specific repair plan is given, thereby improving the safety and durability of large reservoirs through repair and avoiding potential risks.

[0096] In the description of the present invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0097] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0098] In the present invention, unless otherwise clearly specified and limited, when a first feature is “on” or “below” a second feature, it may be that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Moreover, when a first feature is “above”, “above” or “above” a second feature, it may be that the first feature is directly above or obliquely above the second feature, or it may simply mean that the first feature is higher in level than the second feature. When a first feature is “below”, “below” or “below” a second feature, it may be that the first feature is directly below or obliquely below the second feature, or it may simply mean that the first feature is lower in level than the second feature.

[0099] In the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0100] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may alter, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A water conservancy project concrete quality detection and analysis system, It is characterized in that Used in the construction and maintenance of large reservoirs, including: A data collection module is used to collect quality inspection data of the concrete to be tested; The quality inspection data include: compressive strength inspection data, concrete density inspection data, and frost resistance inspection data; A data preprocessing module, used for preprocessing the quality detection data of the concrete to be tested to obtain preprocessed data; A data analysis module, used for inputting the preprocessed data into a trained quality assessment prediction model to obtain a quality assessment report of the concrete to be tested; The quality assessment prediction model includes: a concrete quality scoring sub-model and a concrete maintenance plan generation sub-model; The quality assessment report includes: the quality assessment score of the concrete to be tested and the repair and maintenance plan; Input the preprocessed data into the trained quality assessment prediction model to obtain the quality assessment report of the concrete to be tested, including: Input the preprocessed data into the concrete quality scoring sub-model to obtain the quality assessment score of the concrete to be tested; input the concrete quality assessment score into the concrete maintenance plan generation sub-model to obtain the repair and maintenance plan of the concrete to be tested; Inputting the preprocessed data into the concrete quality scoring sub-model to obtain the quality assessment score of the concrete to be tested includes: , in, S is the quality assessment score, b is the bias term, a constant; The weight corresponding to each indicator is N is the number of samples for each indicator, For the i The first indicator j samples, For each indicator, the minimum value in the preset range, The maximum value of each indicator within the preset range; The concrete quality assessment score is input into the concrete maintenance plan generation sub-model to obtain the repair and maintenance plan of the concrete to be tested. The concrete maintenance plan generation sub-model includes: Hidden layer feature extraction unit, decision logic determination unit; The hidden layer feature extraction unit is used to extract the hidden layer features of the concrete quality assessment score input into the concrete maintenance plan generation sub-model; The decision logic determination unit is used to determine the final concrete repair and maintenance plan based on a preset decision tree algorithm; The hidden layer feature extraction unit includes an autoencoder for extracting hidden layer features of a concrete quality assessment score input to a concrete maintenance program generation sub-model; The automatic encoder comprises an encoder and a decoder, wherein the encoder and the decoder each comprise l a The convolution kernel size is 1×1. l a is a preset value.

2. The water conservancy project concrete quality detection and analysis system according to claim 1, It is characterized in that The data preprocessing module includes: a data cleaning unit and a data reduction unit; The data cleaning unit is used to identify and correct the erroneous, inconsistent and missing data in the quality inspection data of the concrete to be tested, and obtain the data after data cleaning; The data reduction unit is used to simplify the cleaned data according to a dimension reduction algorithm to obtain preprocessed data.

3. The water conservancy project concrete quality detection and analysis system according to claim 1, It is characterized in that The system further comprises: A model training module is used to train the quality assessment prediction model using a training data set to obtain a trained quality assessment prediction model; The training data set is the historical quality inspection data of the pre-processed concrete samples and the corresponding quality assessment scores and repair and maintenance plan records.

4. The water conservancy project concrete quality detection and analysis system according to claim 3, It is characterized in that The adopting the training data set to train the quality assessment prediction model to obtain the trained quality assessment prediction model comprises: Each data in the training data set is input into the quality assessment prediction model for training until the preset regression loss function and classification loss function corresponding to the quality assessment prediction model converge, thereby obtaining a trained quality assessment prediction model.

5. The water conservancy project concrete quality detection and analysis system according to claim 1, It is characterized in that The weight corresponding to each indicator is: , in, For each indicator Overall quality of concrete Q The correlation coefficient between is the adjustment factor for each indicator, is the decay rate of each indicator, For time, is an exponential decay function for each indicator.

6. The water conservancy project concrete quality detection and analysis system according to claim 1, It is characterized in that The preset range of compressive strength is 20-50MPa, the preset range of concrete density is 2.2-2.6 g / cm3, and the preset range of frost resistance is 25-100 freeze-thaw cycles.