Concrete quality rating method and system based on multilayer neural convolutional network

Abstract

The invention relates to the technical field of concrete detection, and discloses a concrete quality rating method and system based on a multilayer neural convolutional network, and the method comprises the steps: building a standardized performance index data set, training the standardized performance index data set through employing a support vector machine algorithm, and building a concrete material resistance evaluation model; environment parameters of a construction site are collected in real time through a wireless sensor network, and the influence of the current construction environment on concrete is judged; and inputting the construction environment parameters into the concrete material performance evaluation model to obtain an optimal concrete material ratio suggestion, uploading the concrete material performance parameters to a cloud server in the concrete use process, and uploading a concrete quality evaluation report to a concrete quality monitoring platform after concrete construction is completed. According to the invention, intelligent evaluation and optimization of the concrete material performance are realized, and the concrete quality and efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete detection, and in particular to a concrete quality rating method and system based on a multi-layer neural convolutional network. Background Art

[0002] During concrete construction, the performance of concrete materials is crucial. Traditional concrete quality assessment methods are unable to fully consider the impact of the environment, making it difficult to ensure concrete quality. The core of this mechanism is to build a multi-layer neural convolutional network model to evaluate the performance of concrete materials. First, it is necessary to collect performance data of concrete materials with different proportions in various environments, including strength, shrinkage, crack resistance and other indicators, to form a performance database. Then, use this data to train the neural network model so that it can accurately predict the performance of concrete materials in different environmental conditions.

[0003] In the actual concrete construction process, it is necessary to monitor the environmental parameters of the site in real time and use them as input parameters to call the trained neural network model to evaluate the performance of concrete materials and give a quantitative score of the material performance. Based on the scoring results, it can be determined whether the material is suitable for the current environment and the material ratio can be optimized and adjusted.

[0004] In order to further improve the reliability of concrete quality, it is also necessary to monitor the performance of concrete materials in real time during the construction process. Once abnormal fluctuations in material performance are found, it is necessary to analyze the causes in a timely manner and adjust the material ratio or construction process if necessary to ensure that the concrete quality is always under control.

[0005] By constructing a multi-layer neural convolutional network model and combining it with real-time monitoring and dynamic adjustment, an effective concrete quality rating mechanism can be established to provide strong support for engineering construction. Summary of the invention

[0006] The purpose of the present invention is to overcome one or more of the above-mentioned existing technical problems and provide a concrete quality rating method based on a multi-layer neural convolutional network.

[0007] To achieve the above object, the present invention provides a concrete quality rating method based on a multi-layer neural convolutional network, comprising: Acquire performance index data of concrete materials with different mix ratios from a pre-established concrete material performance database under different environments, and pre-process the performance index data to obtain a standardized performance index data set; The support vector machine algorithm is used to train the standardized performance index data set and establish a concrete material resistance performance evaluation model; The environmental parameters of the construction site are collected in real time through the wireless sensor network, and the environmental parameters are transmitted to the cloud server to determine the impact of the current construction environment on concrete; Input the construction environment parameters into the concrete material performance evaluation model, and evaluate and predict the applicability of concrete materials with different proportions in the current environment based on the pre-trained model parameters to obtain the optimal concrete material proportion recommendation; During the use of concrete, the fiber optic sensor buried inside the connected object monitors the performance parameters of the concrete material in real time and uploads the performance parameters of the concrete material to the cloud server; After the concrete construction is completed, the fuzzy comprehensive evaluation method is used to rate the concrete quality, generate a concrete quality assessment report, and upload the concrete quality assessment report to the concrete quality monitoring platform.

[0008] According to one aspect of the present invention, based on the data structure and storage format of a pre-established database of concrete material performance under different environments, a database query statement is used to obtain original data of performance indicators of concrete materials with different mix ratios; Clean the acquired raw data of performance indicators to remove missing values ​​and outlier data; According to the concrete material performance evaluation standard, the cleaned performance index data is normalized and the index data of different dimensions are converted into dimensionless values; The maximum and minimum value normalization method is used to map the normalized performance indicator data into a preset interval to obtain standardized performance indicator data; According to the mix ratio information of concrete materials, the normalized performance index data are grouped to construct performance index data subsets of concrete materials with different mix ratios; Perform statistical analysis on each performance index data subset, calculate the mean, variance and standard deviation of each index, and evaluate the performance differences of concrete materials with different mix ratios; The normalized performance indicator data and statistical analysis results are combined to construct a normalized performance indicator data set.

[0009] According to one aspect of the present invention, the kernel function type, penalty factor and kernel function parameters of the support vector machine algorithm are determined according to the business requirements of concrete material performance evaluation; The K-fold cross-validation method is used to optimize the hyperparameters of the support vector machine model, the optimal model hyperparameter combination is determined through grid search, and the support vector machine model is constructed using the optimal hyperparameter combination; The normalized performance index data set is divided into a training set and a test set, and the constructed support vector machine model is trained using the training set data to obtain a trained concrete material performance evaluation model; Input the test set data into the trained evaluation model, obtain the prediction results output by the evaluation model, compare the prediction results with the true labels of the test set, and calculate the performance evaluation index of the evaluation model; If the performance evaluation index of the evaluation model meets the preset threshold, the trained evaluation model is deployed to the production environment, the new concrete material performance index data is evaluated, and the evaluation results are output.

[0010] According to one aspect of the present invention, a wireless sensor network is formed by deploying multiple wireless sensor nodes at a construction site to collect the ambient temperature, ambient humidity and ambient wind speed of the construction site in real time; The relevant parameters collected by the wireless sensor nodes are transmitted to the cloud server through the wireless communication module; On the cloud server, the support vector machine algorithm is used to analyze the received drought-related parameters to obtain multiple drought characteristic parameters; On the cloud server, a decision tree algorithm is used to comprehensively judge multiple drought characteristic parameters to obtain the environmental severity of the current construction site environment. According to the environmental severity, early warning information is sent to the management personnel of the construction site through the cloud server to prompt them to take corresponding construction measures. On the cloud server, based on historical environmental parameters and current environmental characteristic parameters, the construction site environmental trend in the future is predicted; Based on the predicted environmental trends, construction measures suggestions for a period of time in the future are generated on the cloud server and sent to the managers at the construction site for their reference and execution.

[0011] According to one aspect of the present invention, environmental degree parameters under the current environment are obtained as input data of a concrete material drought resistance performance evaluation model; According to the pre-trained evaluation model parameters, a concrete material resistance performance evaluation model is constructed to evaluate the applicability of concrete materials with different proportions; For concrete materials with different proportions, an evaluation model is used to quickly evaluate and predict their performance in the current environment; By comparing the evaluation and prediction results of concrete materials with different mix ratios, the concrete material mix with the best performance under the current environment is determined; If the current environment changes, the updated environmental degree parameters are re-obtained and input into the evaluation model for re-evaluation and prediction; Based on the updated evaluation and prediction results, the optimal concrete material mix recommendation is dynamically adjusted to ensure that it is suitable for the current environment.

[0012] According to one aspect of the present invention, a plurality of optical fiber sensors are pre-buried inside the connected object according to the requirements of concrete construction, and the positions and numbers of the sensors are reasonably arranged according to the size and shape of the concrete body; During the concrete process, the optical fiber sensor collects the performance index data of the concrete material, such as temperature, pressure and flow rate, in real time, and uploads the collected data to the cloud server through the wireless communication module; After receiving the monitoring data, the cloud server uses data preprocessing technology to clean and standardize the data, remove outliers and invalid data, and obtain a standardized data set; According to the requirements of concrete material performance evaluation, characteristic parameters closely related to material performance are extracted from the standardized data set to build a material performance evaluation model; The support vector machine algorithm is used to train the material performance evaluation model to obtain the optimized model parameters; During the concrete construction process, the real-time monitoring data is input into the trained material performance evaluation model to obtain the predicted value of the material performance and compare it with the set performance threshold; If the predicted material performance index is lower than the set threshold, an early warning message will be sent to the construction site to prompt the construction personnel to adjust the concrete process parameters.

[0013] According to one aspect of the present invention, based on various parameter data collected during the concrete construction process, a comprehensive evaluation value of concrete quality is calculated through a preset fuzzy comprehensive evaluation model, the quality grade to which the evaluation value belongs is determined, and a concrete quality evaluation report is generated; Convert the generated concrete quality assessment report into a digital file that meets the data format requirements of the concrete quality monitoring platform, connect with the data interface of the concrete quality monitoring platform, and upload the digital assessment report to the data storage location specified by the concrete quality monitoring platform; After receiving the uploaded concrete quality assessment report, the concrete quality monitoring platform automatically adds it to the ledger of concrete quality assessment reports, performs a hash operation on the report data, and generates a unique identifier; Establish a query index for the assessment report to provide convenient data query and access services for relevant parties.

[0014] To achieve the above object, the present invention provides a concrete quality rating system based on a multi-layer neural convolutional network, comprising: Data processing module: obtains the performance index data of concrete materials with different proportions in the pre-established concrete material performance database under different environments, and pre-processes the performance index data to obtain a standardized performance index data set; Evaluation model building module: Use support vector machine algorithm to train the standardized performance index data set to establish a concrete material resistance performance evaluation model; Construction data acquisition module: collects environmental parameters of the construction site in real time through the wireless sensor network, transmits the environmental parameters to the cloud server, and determines the impact of the current construction environment on concrete; Concrete mix ratio module: inputs construction environment parameters into the concrete material performance evaluation model, evaluates and predicts the applicability of concrete materials with different mix ratios in the current environment based on pre-trained model parameters, and obtains the optimal concrete material mix ratio recommendation; Data transmission module: During the use of concrete, the optical fiber sensor buried inside the connected object monitors the performance parameters of the concrete material in real time and uploads the performance parameters of the concrete material to the cloud server; Platform monitoring module: After the concrete construction is completed, the fuzzy comprehensive evaluation method is used to rate the concrete quality, generate a concrete quality assessment report, and upload the concrete quality assessment report to the concrete quality monitoring platform.

[0015] To achieve the above-mentioned purpose, the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the above-mentioned method for grading concrete quality based on a multi-layer neural convolutional network is implemented.

[0016] To achieve the above-mentioned purpose, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned concrete quality rating method based on a multi-layer neural convolutional network is implemented.

[0017] Based on this, the beneficial effects of the present invention are as follows: the method first establishes a concrete material performance database and uses a support vector machine algorithm to train a performance evaluation model. At the construction site, environmental parameters are collected in real time through a wireless sensor network to judge the environmental degree, and the evaluation model is input to predict the optimal concrete material ratio. During the concrete process, optical fiber sensors are used to monitor material performance and upload it to the cloud. After the construction is completed, fuzzy comprehensive evaluation is used to rate the concrete quality, generate a report and upload it to the concrete quality monitoring platform. The present invention realizes the intelligent evaluation and optimization of concrete material performance under specific environments, improves the quality and efficiency of concrete, and provides effective technical support for engineering construction in specific areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of a concrete quality rating method based on a multi-layer neural convolutional network according to an exemplary embodiment; Figure 2The present invention is a flowchart of a concrete quality rating system based on a multi-layer neural convolutional network according to an exemplary embodiment. DETAILED DESCRIPTION

[0019] The present invention will now be discussed with reference to exemplary embodiments. It should be understood that the embodiments discussed are only for enabling those skilled in the art to better understand and thereby implement the present invention, rather than implying any limitation on the scope of the present invention.

[0020] As used herein, the term “including” and variations thereof are to be interpreted as open-ended terms meaning “including but not limited to.” The term “based on” is to be interpreted as “based, at least in part, on,” and the terms “one embodiment” and “an embodiment” are to be interpreted as “at least one embodiment.”

[0021] According to one embodiment of the present invention, Figure 1 is a flow chart of a concrete quality rating method based on a multi-layer neural convolutional network according to an exemplary embodiment. Figure 1 As shown, to achieve the above purpose, the present invention provides a concrete quality rating method based on a multi-layer neural convolutional network, comprising: Acquire performance index data of concrete materials with different mix ratios from a pre-established concrete material performance database under different environments, and pre-process the performance index data to obtain a standardized performance index data set; The support vector machine algorithm is used to train the standardized performance index data set and establish a concrete material resistance performance evaluation model; The environmental parameters of the construction site are collected in real time through the wireless sensor network, and the environmental parameters are transmitted to the cloud server to determine the impact of the current construction environment on concrete; Input the construction environment parameters into the concrete material performance evaluation model, and evaluate and predict the applicability of concrete materials with different proportions in the current environment based on the pre-trained model parameters to obtain the optimal concrete material proportion recommendation; During the use of concrete, the fiber optic sensor buried inside the connected object monitors the performance parameters of the concrete material in real time and uploads the performance parameters of the concrete material to the cloud server; After the concrete construction is completed, the fuzzy comprehensive evaluation method is used to rate the concrete quality, generate a concrete quality assessment report, and upload the concrete quality assessment report to the concrete quality monitoring platform.

[0022] According to one embodiment of the present invention, based on the data structure and storage format of a pre-established database of concrete material performance under different environments, a database query statement is used to obtain original data of performance indicators of concrete materials with different mix ratios; Clean the acquired raw data of performance indicators to remove missing values ​​and outlier data; According to the concrete material performance evaluation standard, the cleaned performance index data is normalized and the index data of different dimensions are converted into dimensionless values; The maximum and minimum value normalization method is used to map the normalized performance indicator data into a preset interval to obtain standardized performance indicator data; According to the mix ratio information of concrete materials, the normalized performance index data are grouped to construct performance index data subsets of concrete materials with different mix ratios; Perform statistical analysis on each performance index data subset, calculate the mean, variance and standard deviation of each index, and evaluate the performance differences of concrete materials with different mix ratios; The normalized performance indicator data and statistical analysis results are combined to construct a normalized performance indicator data set.

[0023] According to one embodiment of the present invention, the kernel function type, penalty factor and kernel function parameters of the support vector machine algorithm are determined according to the business requirements of concrete material performance evaluation; The K-fold cross-validation method is used to optimize the hyperparameters of the support vector machine model, the optimal model hyperparameter combination is determined through grid search, and the support vector machine model is constructed using the optimal hyperparameter combination; The normalized performance index data set is divided into a training set and a test set, and the constructed support vector machine model is trained using the training set data to obtain a trained concrete material performance evaluation model; Input the test set data into the trained evaluation model, obtain the prediction results output by the evaluation model, compare the prediction results with the true labels of the test set, and calculate the performance evaluation index of the evaluation model; If the performance evaluation index of the evaluation model meets the preset threshold, the trained evaluation model is deployed to the production environment, the new concrete material performance index data is evaluated, and the evaluation results are output.

[0024] According to one embodiment of the present invention, a wireless sensor network is formed by deploying multiple wireless sensor nodes at the construction site to collect the ambient temperature, ambient humidity and ambient wind speed of the construction site in real time; The relevant parameters collected by the wireless sensor nodes are transmitted to the cloud server through the wireless communication module; On the cloud server, the support vector machine algorithm is used to analyze the received drought-related parameters to obtain multiple drought characteristic parameters; On the cloud server, a decision tree algorithm is used to comprehensively judge multiple drought characteristic parameters to obtain the environmental severity of the current construction site environment. According to the environmental severity, early warning information is sent to the management personnel of the construction site through the cloud server to prompt them to take corresponding construction measures. On the cloud server, based on historical environmental parameters and current environmental characteristic parameters, the construction site environmental trend in the future is predicted; Based on the predicted environmental trends, construction measures suggestions for a period of time in the future are generated on the cloud server and sent to the managers at the construction site for their reference and execution.

[0025] According to one embodiment of the present invention, an environmental degree parameter under the current environment is obtained as input data of a concrete material drought resistance performance evaluation model; According to the pre-trained evaluation model parameters, a concrete material resistance performance evaluation model is constructed to evaluate the applicability of concrete materials with different proportions; For concrete materials with different proportions, an evaluation model is used to quickly evaluate and predict their performance in the current environment; By comparing the evaluation and prediction results of concrete materials with different mix ratios, the concrete material mix with the best performance under the current environment is determined; If the current environment changes, the updated environmental degree parameters are re-obtained and input into the evaluation model for re-evaluation and prediction; Based on the updated evaluation and prediction results, the optimal concrete material mix recommendation is dynamically adjusted to ensure that it is suitable for the current environment.

[0026] According to one embodiment of the present invention, a plurality of optical fiber sensors are pre-buried inside the connected object according to the requirements of concrete construction, and the positions and number of the sensors are reasonably arranged according to the size and shape of the concrete body; During the concrete process, the optical fiber sensor collects the performance index data of the concrete material, such as temperature, pressure and flow rate, in real time, and uploads the collected data to the cloud server through the wireless communication module; After receiving the monitoring data, the cloud server uses data preprocessing technology to clean and standardize the data, remove outliers and invalid data, and obtain a standardized data set; According to the requirements of concrete material performance evaluation, characteristic parameters closely related to material performance are extracted from the standardized data set to build a material performance evaluation model; The support vector machine algorithm is used to train the material performance evaluation model to obtain the optimized model parameters; During the concrete construction process, the real-time monitoring data is input into the trained material performance evaluation model to obtain the predicted value of the material performance and compare it with the set performance threshold; If the predicted material performance index is lower than the set threshold, an early warning message will be sent to the construction site to prompt the construction personnel to adjust the concrete process parameters.

[0027] According to one embodiment of the present invention, based on various parameter data collected during the concrete construction process, a preset fuzzy comprehensive evaluation model is used to calculate a comprehensive evaluation value of concrete quality, determine the quality grade to which the evaluation value belongs, and generate a concrete quality evaluation report; Convert the generated concrete quality assessment report into a digital file that meets the data format requirements of the concrete quality monitoring platform, connect with the data interface of the concrete quality monitoring platform, and upload the digital assessment report to the data storage location specified by the concrete quality monitoring platform; After receiving the uploaded concrete quality assessment report, the concrete quality monitoring platform automatically adds it to the ledger of concrete quality assessment reports, performs a hash operation on the report data, and generates a unique identifier; Establish a query index for the assessment report to provide convenient data query and access services for relevant parties.

[0028] According to one embodiment of the present invention, the original data set of performance indicators of concrete materials is first obtained, and the data set contains 10 performance indicator data of 1000 concrete material samples. Data preprocessing is performed on the original data set, and the missing values ​​are processed by the mean filling method. The outliers are identified and eliminated by using the box plot. After data cleaning, a performance indicator data set of 950 valid samples is obtained. Then, the preprocessed performance indicator data set is normalized to the maximum and minimum values, and each indicator data is mapped to the interval [0,1] to eliminate the influence of the indicator dimension difference. According to the requirements of concrete material performance evaluation, the Gaussian kernel function is selected as the kernel function of the support vector machine. The optimal hyperparameter combination of the penalty factor C of 10 and the kernel function parameter γ of 1 is determined by 5-fold cross validation and grid search, and a support vector machine model is constructed. The normalized data set is divided into a training set and a test set in a ratio of 8:2. The support vector machine model is trained using 760 samples of the training set to obtain a concrete material resistance performance evaluation model. The 190 samples of the test set were input into the evaluation model to obtain the performance level predicted by the model and compared with the real labels of the test set. The precision of the evaluation model was calculated to be 92, the recall rate was 89, and the F1 value was 91, all exceeding the preset threshold of 85 and meeting the performance requirements. Finally, the trained evaluation model was deployed to the production environment to evaluate the performance of the new concrete material performance index data, providing decision support for the formulation optimization and performance improvement of concrete materials.

[0029] According to one embodiment of the present invention, 10 wireless sensor nodes are deployed at the construction site, each node is equipped with an SHT31 temperature and humidity sensor and an FX-WS wind speed sensor, and the ambient temperature, humidity and wind speed data are collected at intervals of 5 minutes. The node uploads the data to the cloud server through the Zigbee wireless communication module. The server is based on the support vector machine algorithm, uses the radial basis kernel function, sets the penalty factor C=10, and the number of training samples is 1000, and extracts four drought characteristic parameters of average temperature, average humidity, average wind speed and duration. Then, the CART decision tree algorithm is used to select the optimal partition attribute based on the information gain ratio, recursively construct a decision tree with a depth of 5, and make a comprehensive judgment on the characteristic parameters. When the average temperature is ≥35°C, the average humidity is ≤30% and the duration exceeds 72 hours, it is determined to be a drought state, and an early warning text message is sent to the management personnel. At the same time, a long short-term memory neural network is used, the number of hidden layer neurons is set to 128, and the learning rate is 01, and the data of the past 30 days are used to predict the drought trend in the next 7 days. If the probability of drought in the next three days exceeds 60%, measures will be recommended and sent to management personnel to assist them in developing response plans to minimize the impact of drought and ensure construction progress and quality.

[0030] According to one embodiment of the present invention, firstly, the soil moisture content and other parameters under the current environment are obtained through sensors as the input of the evaluation model. The evaluation model is based on the support vector machine algorithm, and the optimal model parameters are obtained through a large amount of historical data training. For concrete materials with different raw material ratios, the evaluation model is substituted for prediction and analysis to obtain the performance scores of each ratio scheme, such as 85 for scheme A, 92 for scheme B, and 78 for scheme C. The scoring results are sorted and compared, and the highest-scoring scheme B is determined to be the optimal ratio, and a ratio recommendation report is generated and submitted to the relevant departments. If the current environmental level changes, such as the water content drops from 8% to 5%, the evaluation model is triggered to automatically update the prediction, the score of scheme B drops to 87, and the score of scheme C rises to 89 to become the new optimal ratio, and the ratio recommendation is dynamically adjusted to adapt to the new drought environment. The entire evaluation and prediction process is automatically completed by a computer program without manual intervention, which improves the intelligent level of concrete material ratio optimization and the real-time response to environmental changes.

[0031] According to one embodiment of the present invention, when pre-embedded optical fiber sensors are set in the body of the connected object, the position and number of sensors are reasonably arranged according to the size and shape of the connected object. For example, in a cylindrical connected object with a diameter of 2 meters and a height of 10 meters, a sensor can be arranged every 1 meter in the vertical direction and a sensor can be arranged every 90 degrees in the horizontal direction, with a total of 40 sensors arranged. During the construction process, the optical fiber sensor collects the temperature, pressure, flow rate and other performance index data of the concrete material in real time at a frequency of 100Hz, and uploads the data to the cloud server through the wireless communication module. The cloud server uses data preprocessing technology to clean and standardize the received massive monitoring data, removes abnormal value data exceeding 20% ​​of the normal range and invalid data with missing fields exceeding 10%, and normalizes the data to the [0,1] interval through the minimum-maximum normalization method to obtain a normalized data set. According to the requirements of concrete material performance evaluation, a correlation analysis method is used to extract 10 characteristic parameters closely related to material density, strength, viscosity and other properties from the normalized data set, such as temperature mean, pressure standard deviation, flow rate peak, etc., to build a material performance evaluation model. The support vector machine algorithm is used, with the Gaussian kernel function as the kernel function, the penalty factor C=10, the training set sample size of 10000, and the number of iterations of 1000 times, to train the material performance evaluation model and obtain the optimal parameters of the model. The real-time monitoring data is input into the trained support vector machine model to predict the density, strength and other performance index values ​​of the material, and the predicted value is compared with the set performance threshold. If the density prediction value is lower than the set 5g / cm³ or the strength prediction value is lower than the set 20MPa, an early warning message is issued to the construction site to prompt the construction personnel to adjust the process parameters in time, or take countermeasures such as reinforcement and secondary concrete to ensure that the performance of the concrete material meets the design requirements and ensure the quality of concrete construction.

[0032] According to one embodiment of the present invention, during the concrete construction process, the concrete pressure, flow rate, slurry density and other parameter data are collected in real time through sensors deployed at the construction site, and the data is transmitted to the concrete quality assessment system. Based on the preset fuzzy comprehensive evaluation model, the system normalizes the collected data, calculates the membership function value of each parameter, and obtains a comprehensive assessment value of concrete quality of 85 by weighted average. According to the preset quality grade classification standard, the concrete quality is judged to be "good". The system automatically generates a concrete quality assessment report, converts the report into a digital file in JSON format, and uploads it to the data storage node of the concrete quality monitoring platform through the API interface. After receiving the assessment report, the concrete quality monitoring platform performs a SHA256 hash operation on the report data to generate a hash value. The concrete quality monitoring platform establishes a query index for the report based on the hash value of the assessment report, and provides a report query service based on block hash to the relevant parties through the Web service. When the uploaded assessment report needs to be modified, the system will regenerate the report and upload it to the concrete quality monitoring platform, and realize the version management of the report by associating the hash value of the original report. The concrete quality monitoring platform regularly performs cloud backup and off-site disaster recovery storage of assessment report data to ensure the long-term security and recoverability of data.

[0033] In addition, in order to achieve the above-mentioned purpose, the present invention also provides a concrete quality rating system based on a multi-layer neural convolutional network. Figure 2 is a flowchart of a concrete quality rating system based on a multi-layer neural convolutional network according to an exemplary embodiment. Figure 2 As shown, a concrete quality rating system based on a multi-layer neural convolutional network in the present invention includes: Data processing module: obtains the performance index data of concrete materials with different proportions in the pre-established concrete material performance database under different environments, and pre-processes the performance index data to obtain a standardized performance index data set; Evaluation model building module: Use support vector machine algorithm to train the standardized performance index data set to establish a concrete material resistance performance evaluation model; Construction data acquisition module: collects environmental parameters of the construction site in real time through the wireless sensor network, transmits the environmental parameters to the cloud server, and determines the impact of the current construction environment on concrete; Concrete mix ratio module: inputs construction environment parameters into the concrete material performance evaluation model, evaluates and predicts the applicability of concrete materials with different mix ratios in the current environment based on pre-trained model parameters, and obtains the optimal concrete material mix ratio recommendation; Data transmission module: During the use of concrete, the performance parameters of concrete materials are monitored in real time through the optical fiber sensors buried inside the connected objects, and the performance parameters of concrete materials are uploaded to the cloud server; Platform monitoring module: After the concrete construction is completed, the fuzzy comprehensive evaluation method is used to rate the concrete quality, generate a concrete quality assessment report, and upload the concrete quality assessment report to the concrete quality monitoring platform.

[0034] Based on this, the beneficial effect of the present invention is that the method first establishes a concrete material performance database and uses a support vector machine algorithm to train a performance evaluation model. At the construction site, environmental parameters are collected in real time through a wireless sensor network to judge the environmental degree, and the evaluation model is input to predict the optimal concrete material ratio. During the concrete process, optical fiber sensors are used to monitor material performance and upload it to the cloud. After the construction is completed, fuzzy comprehensive evaluation is used to rate the concrete quality, generate a report and upload it to the concrete quality monitoring platform. The present invention realizes the intelligent evaluation and optimization of concrete material performance under specific environments, improves the quality and efficiency of concrete, and provides effective technical support for engineering construction in specific areas.

[0035] Those of ordinary skill in the art will appreciate that the modules and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0036] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and equipment can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0037] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0038] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the embodiments of the present invention.

[0039] In addition, each functional module in the embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0040] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the energy-saving signal sending / receiving method of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

[0041] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the present application.

[0042] It should be understood that the size of the serial numbers of each step in the content of the invention and the embodiments of the present invention does not absolutely mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Claims

1. A concrete quality rating method based on a multi-layer neural convolutional network, characterized in that: include: Acquire performance index data of concrete materials with different mix ratios from a pre-established concrete material performance database under different environments, and pre-process the performance index data to obtain a standardized performance index data set; The support vector machine algorithm is used to train the standardized performance index data set and establish a concrete material resistance performance evaluation model; The environmental parameters of the construction site are collected in real time through the wireless sensor network, and the environmental parameters are transmitted to the cloud server to determine the impact of the current construction environment on concrete; Input the construction environment parameters into the concrete material performance evaluation model, and evaluate and predict the applicability of concrete materials with different proportions in the current environment based on the pre-trained model parameters to obtain the optimal concrete material proportion recommendation; During the use of concrete, the fiber optic sensor buried inside the connected object monitors the performance parameters of the concrete material in real time and uploads the performance parameters of the concrete material to the cloud server; After the concrete construction is completed, the fuzzy comprehensive evaluation method is used to rate the concrete quality, generate a concrete quality assessment report, and upload the concrete quality assessment report to the concrete quality monitoring platform.

2. A method for grading concrete quality based on a multi-layer neural convolutional network as claimed in claim 1, characterized in that: According to the data structure and storage format of the concrete material performance database under different environments established in advance, the original data of performance indicators of concrete materials with different proportions are obtained by using database query statements; Clean the acquired raw data of performance indicators to remove missing values ​​and outlier data; According to the concrete material performance evaluation standard, the cleaned performance index data is normalized and the index data of different dimensions are converted into dimensionless values; The maximum and minimum value normalization method is used to map the normalized performance indicator data into a preset interval to obtain standardized performance indicator data; According to the mix ratio information of concrete materials, the normalized performance index data are grouped to construct performance index data subsets of concrete materials with different mix ratios; Perform statistical analysis on each performance index data subset, calculate the mean, variance and standard deviation of each index, and evaluate the performance differences of concrete materials with different mix ratios; The normalized performance indicator data and statistical analysis results are combined to construct a normalized performance indicator data set.

3. A method for grading concrete quality based on a multi-layer neural convolutional network as claimed in claim 2, characterized in that: According to the business needs of concrete material performance evaluation, determine the kernel function type, penalty factor and kernel function parameters of the support vector machine algorithm; The K-fold cross-validation method is used to optimize the hyperparameters of the support vector machine model, the optimal model hyperparameter combination is determined through grid search, and the support vector machine model is constructed using the optimal hyperparameter combination; The normalized performance index data set is divided into a training set and a test set, and the constructed support vector machine model is trained using the training set data to obtain a trained concrete material performance evaluation model; Input the test set data into the trained evaluation model, obtain the prediction results output by the evaluation model, compare the prediction results with the true labels of the test set, and calculate the performance evaluation index of the evaluation model; If the performance evaluation index of the evaluation model meets the preset threshold, the trained evaluation model is deployed to the production environment, the new concrete material performance index data is evaluated, and the evaluation results are output.

4. A method for grading concrete quality based on a multi-layer neural convolutional network as claimed in claim 3, characterized in that: By deploying multiple wireless sensor nodes at the construction site, a wireless sensor network is formed to collect the ambient temperature, humidity and wind speed of the construction site in real time; The relevant parameters collected by the wireless sensor nodes are transmitted to the cloud server through the wireless communication module; On the cloud server, the support vector machine algorithm is used to analyze the received drought-related parameters to obtain multiple drought characteristic parameters; On the cloud server, a decision tree algorithm is used to comprehensively judge multiple drought characteristic parameters to obtain the environmental severity of the current construction site environment. According to the environmental severity, early warning information is sent to the management personnel of the construction site through the cloud server to prompt them to take corresponding construction measures. On the cloud server, based on historical environmental parameters and current environmental characteristic parameters, the construction site environmental trend in the future is predicted; Based on the predicted environmental trends, construction measures suggestions for a period of time in the future are generated on the cloud server and sent to the managers at the construction site for their reference and execution.

5. A method for grading concrete quality based on a multi-layer neural convolutional network as claimed in claim 4, characterized in that: Obtain environmental degree parameters under the current environment as input data for the evaluation model of drought resistance of concrete materials; According to the pre-trained evaluation model parameters, a concrete material resistance performance evaluation model is constructed to evaluate the applicability of concrete materials with different proportions; For concrete materials with different proportions, an evaluation model is used to quickly evaluate and predict their performance in the current environment; By comparing the evaluation and prediction results of concrete materials with different mix ratios, the concrete material mix with the best performance under the current environment is determined; If the current environment changes, the updated environmental degree parameters are re-obtained and input into the evaluation model for re-evaluation and prediction; Based on the updated evaluation and prediction results, the optimal concrete material mix recommendation is dynamically adjusted to ensure that it is suitable for the current environment.

6. A method for grading concrete quality based on a multi-layer neural convolutional network as claimed in claim 5, characterized in that: According to the requirements of concrete construction, multiple optical fiber sensors are pre-buried inside the connected object, and the location and number of sensors are reasonably arranged according to the size and shape of the concrete body; During the concrete process, the optical fiber sensor collects the performance index data of the concrete material, such as temperature, pressure and flow rate, in real time, and uploads the collected data to the cloud server through the wireless communication module; After receiving the monitoring data, the cloud server uses data preprocessing technology to clean and standardize the data, remove outliers and invalid data, and obtain a standardized data set; According to the requirements of concrete material performance evaluation, characteristic parameters closely related to material performance are extracted from the standardized data set to build a material performance evaluation model; The support vector machine algorithm is used to train the material performance evaluation model to obtain the optimized model parameters; During the concrete construction process, the real-time monitoring data is input into the trained material performance evaluation model to obtain the predicted value of the material performance and compare it with the set performance threshold; If the predicted material performance index is lower than the set threshold, an early warning message will be sent to the construction site to prompt the construction personnel to adjust the concrete process parameters.

7. A method for grading concrete quality based on a multi-layer neural convolutional network as claimed in claim 6, characterized in that: According to the various parameter data collected during the concrete construction process, the comprehensive evaluation value of the concrete quality is calculated through the preset fuzzy comprehensive evaluation model, the quality grade to which the evaluation value belongs is determined, and a concrete quality evaluation report is generated; Convert the generated concrete quality assessment report into a digital file that meets the data format requirements of the concrete quality monitoring platform, connect with the data interface of the concrete quality monitoring platform, and upload the digital assessment report to the data storage location specified by the concrete quality monitoring platform; After receiving the uploaded concrete quality assessment report, the concrete quality monitoring platform automatically adds it to the ledger of concrete quality assessment reports, performs a hash operation on the report data, and generates a unique identifier; Establish a query index for the assessment report to provide convenient data query and access services for relevant parties.

8. A concrete quality rating system based on a multi-layer neural convolutional network, characterized in that: include: Data processing module: obtains the performance index data of concrete materials with different proportions in the pre-established concrete material performance database under different environments, and pre-processes the performance index data to obtain a standardized performance index data set; Evaluation model building module: Use support vector machine algorithm to train the standardized performance index data set to establish a concrete material resistance performance evaluation model; Construction data acquisition module: collects environmental parameters of the construction site in real time through the wireless sensor network, transmits the environmental parameters to the cloud server, and determines the impact of the current construction environment on concrete; Concrete mix ratio module: inputs construction environment parameters into the concrete material performance evaluation model, evaluates and predicts the applicability of concrete materials with different mix ratios in the current environment based on pre-trained model parameters, and obtains the optimal concrete material mix ratio recommendation; Data transmission module: During the use of concrete, the performance parameters of concrete materials are monitored in real time through the optical fiber sensors buried inside the connected objects, and the performance parameters of concrete materials are uploaded to the cloud server; Platform monitoring module: After the concrete construction is completed, the fuzzy comprehensive evaluation method is used to rate the concrete quality, generate a concrete quality assessment report, and upload the concrete quality assessment report to the concrete quality monitoring platform.

9. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and executable on the processor, wherein when the computer program is executed by the processor, a concrete quality rating method based on a multi-layer neural convolutional network as claimed in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for grading concrete quality based on a multi-layer neural convolutional network as described in any one of claims 1 to 7 is implemented.

Images