A Concrete Intelligent Material System

Abstract

The present invention discloses a concrete intelligent material system, including a raw material detection module, which obtains aggregate data of sand and gravel aggregates in the raw materials of concrete; a concrete batching module, which is connected to the raw material detection module, obtains aggregate data of sand and gravel aggregates, and adopts a net slurry rheological threshold algorithm to obtain mixing image information; a ratio adjustment module, which is connected to the concrete batching module, obtains mixing image information, and adjusts the ratio of concrete to obtain ratio adjustment information; a feedback module, which is connected to the concrete batching module, and feeds back the ratio adjustment information to the concrete batching module. Through the above scheme, the present invention has the advantages of simple logic, accuracy and reliability, and has high practical value and promotion value in the field of concrete material management technology.

Description

Technical Field

[0001] The invention relates to the technical field of concrete material management, and in particular to an intelligent concrete material system. Background Art

[0002] The concrete material system is a system that integrates multiple technologies to improve the efficiency and quality of concrete production. At present, the concrete material management system in the prior art, such as the Chinese invention patent "publication number CN116402330A, named a construction concrete material management system and management method", constitutes the internal information management system of the construction unit through the background server, the first mobile terminal and the second mobile terminal, completes the integrated and intelligent processes such as unloading, delivery and receipt of concrete materials, and realizes the full process and digital concrete supply process docking between the construction unit and the concrete material supplier through the interaction between the background server and the supplier server. It adopts traditional Internet of Things information control, and its intelligence level needs to be improved. For example, the data mining and analysis capabilities are insufficient, making it difficult to achieve accurate prediction and intelligent decision-making.

[0003] Therefore, it is urgent to propose a concrete intelligent material system with simple logic and high intelligent integration. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a concrete intelligent material system. The technical solution adopted by the present invention is as follows:

[0005] A concrete intelligent material system, comprising:

[0006] The raw material detection module obtains the aggregate data of sand and gravel aggregates in the raw materials of concrete;

[0007] The concrete batching module is connected with the raw material detection module to obtain the aggregate data of sand and gravel aggregates, and obtain the mixing image information using the net slurry rheological threshold algorithm;

[0008] The proportion adjustment module is connected with the concrete batching module to obtain mixing image information and adjust the proportion of concrete to obtain proportion adjustment information;

[0009] The feedback module is connected with the concrete batching module and feeds back the proportion adjustment information to the concrete batching module.

[0010] Furthermore, the raw material detection module uses image processing and deep learning to obtain aggregate data of sand and gravel aggregates in the raw materials of concrete, which includes the following steps:

[0011] Acquire image data of raw materials of concrete and construct a sample data set of sand particle surface images;

[0012] Build a convolutional neural network for deep learning;

[0013] The convolutional neural network is trained using the sand particle surface image sample dataset to fit the relationship between the sand particle surface image features and the grading and stone powder content, and the aggregate data of sand and gravel aggregate is output.

[0014] Furthermore, the concrete batching module adopts a pure slurry rheological threshold algorithm to obtain mixing image information, including the following steps:

[0015] The aggregate data of sand and gravel aggregates are obtained, and the correlation between the mortar rheological threshold and the net paste rheological threshold is established by using the Krieger-Dougherty algorithm;

[0016] Bilinear interpolation is used to plot the mix ratio points of the yield strength threshold and the viscosity threshold into a three-dimensional surface diagram to obtain the stirring image information.

[0017] Furthermore, the correlation between the mortar rheological threshold and the net slurry rheological threshold is established, and its expression is:

[0018]

[0019] Among them, η r,p Indicates the non-dimensional dynamic viscosity of the pure pulp; φ FA represents the volume fraction of fine aggregate in mortar; [η] FA It represents the intrinsic viscosity of the system after adding fine aggregate; It expresses the volume fraction of fine aggregate in mortar under the index m which is related to the shape of cement particles.

[0020] Furthermore, bilinear interpolation is used to draw the mixing ratio points of the yield strength threshold and the viscosity threshold into a three-dimensional surface diagram to obtain stirring image information, including the following steps:

[0021] Select the reference points and use the meshgrid function to create a grid;

[0022] The bilinear interpolation method is used to plot the mix ratio points that meet the yield strength threshold and viscosity threshold into three-dimensional surface graphs.

[0023] Furthermore, the ratio adjustment module obtains mixing image information and adjusts the ratio of concrete to obtain ratio adjustment information, including the following steps:

[0024] Acquire mixing image information and establish the quantitative relationship between image features and working performance of concrete mixing image key frames with different working performances;

[0025] Build an LSTM network model to extract feature information from mixing image information, predict concrete working performance, and provide real-time feedback on the adjusted mix ratio corresponding to the working performance index to obtain mix ratio adjustment information.

[0026] Furthermore, a quantitative relationship between the image features of the concrete mixing image key frames with different working performances and the working performance is established, including the following steps:

[0027] Extract image features of key frames of concrete mixing images;

[0028] Image segmentation technology is used to segment the image features of the key frames of the concrete mixing image;

[0029] The LSTM network model is used for fitting;

[0030] The average height difference between boundary lines is used as the quantitative index of image features, and the quantitative relationship between image features and working performance of key frames of concrete mixing images is obtained.

[0031] A method for implementing a concrete intelligent material system comprises the following steps:

[0032] Obtain aggregate data of sand and gravel aggregates in the raw materials of concrete;

[0033] According to the aggregate data of sand and gravel aggregate, the mixing image information is obtained by using the net slurry rheological threshold algorithm;

[0034] Combining the mixing image information and adjusting the mix ratio of the concrete to obtain mix ratio adjustment information;

[0035] Feedback is given to the ratio adjustment information, and the stirring image information is corrected.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] (1) The present invention detects the raw materials of concrete, fits the relationship between the surface image characteristics of sand particles and the grading and stone powder content, and obtains the aggregate data of sand and gravel aggregates, providing a basis for the concrete mixing ratio and understanding the influencing factors of the sand and gravel aggregate dosage on the various properties of concrete.

[0038] (2) The present invention uses a pure slurry rheological threshold algorithm to obtain mixing image information based on aggregate data of sand and gravel aggregates to improve the accuracy and objectivity of image recognition during the concrete mixing process. In addition, corrections are made based on the ratio adjustment information fed back by the feedback module to reduce the number of trial mixes and improve the reliability of material control.

[0039] (3) The present invention obtains mixing image information by setting a mix ratio adjustment module, and adjusts the mix ratio of concrete to obtain mix ratio adjustment information, so as to achieve closed-loop reliable adjustment.

[0040] (4) The present invention uses a convolutional neural network to fit the relationship between the surface image features of sand particles and the grading and stone powder content, and outputs the aggregate data of sand and gravel aggregates. The advantage of this is that the deep learning model built by the convolutional neural network (CNN) algorithm can automatically identify and analyze the surface image features of sand particles, thereby quickly and accurately fitting the grading and stone powder content of sand particles, reducing manual operation and experience dependence, and improving detection efficiency and accuracy.

[0041] (5) The present invention adopts an LSTM network model to extract feature information from mixing image information, predict the working performance of concrete, and provide real-time feedback on the adjusted mix ratio corresponding to the working performance index to obtain mix ratio adjustment information. The advantage is that the LSTM network is good at capturing long-term dependencies in sequence data, which is particularly important for feature extraction in the concrete mixing process because the mixing process is a dynamic, time series process.

[0042] In summary, the present invention has the advantages of simple logic, accuracy and reliability, and has high practical value and promotion value in the field of concrete material management technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope of protection. For those skilled in the art, other related drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 It is a logic flow chart of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical scheme and advantages of this application clearer, the present invention is further described below in conjunction with the accompanying drawings and embodiments, and the embodiments of the present invention include but are not limited to the following embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0046] In this embodiment, the term "and / or" is merely a term used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone.

[0047] The terms "first" and "second" in the description and claims of this embodiment are used to distinguish different objects rather than to describe a specific order of objects. For example, a first target object and a second target object are used to distinguish different target objects rather than to describe a specific order of target objects.

[0048] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0049] In the description of the embodiments of the present application, unless otherwise specified, the meaning of "multiple" refers to two or more than two. For example, multiple processing units refer to two or more processing units; multiple systems refer to two or more systems.

[0050] like Figure 1 As shown, this embodiment provides a concrete intelligent material system and implementation method, wherein the concrete intelligent material system includes a raw material detection module, a concrete batching module, a mix ratio adjustment module and a feedback module. Specifically, the implementation method is as follows:

[0051] The first step is to use the raw material detection module to obtain aggregate data of sand and gravel aggregates in the raw materials of concrete. Here, the traditional sand particle detection method relies on manual operation and empirical judgment, while this embodiment uses a convolutional neural network to reduce manual intervention, reduce errors caused by human factors, and improve the consistency and reliability of the detection results. The details are as follows:

[0052] (11) Obtain image data of the raw materials of concrete and construct a sand particle surface image sample dataset.

[0053] (12) Build a convolutional neural network for deep learning.

[0054] (13) The convolutional neural network is trained using the sand particle surface image sample dataset to fit the relationship between the sand particle surface image features and the grading and stone powder content, and the aggregate data of sand and gravel aggregate is output.

[0055] The deep learning model built by the convolutional neural network (CNN) algorithm in this embodiment can automatically identify and analyze the surface image features of sand particles, so as to quickly and accurately fit the grading and stone powder content of sand particles, reduce manual operation and experience dependence, and improve detection efficiency and accuracy.

[0056] The second step is to use the concrete batching module to obtain aggregate data of sand and gravel aggregates, and use the net slurry rheological threshold algorithm to obtain mixing image information. The specific steps are as follows:

[0057] (21) The aggregate data of sand and gravel aggregates are obtained, and the Krieger-Dougherty algorithm is used to establish the correlation between the mortar rheological threshold and the net slurry rheological threshold, and the expression is:

[0058]

[0059] Among them, η r,p Indicates the non-dimensional dynamic viscosity of the pure pulp; φ FA represents the volume fraction of fine aggregate in mortar; [η] FA It represents the intrinsic viscosity of the system after adding fine aggregate; It expresses the volume fraction of fine aggregate in mortar under the index m which is related to the shape of cement particles.

[0060] (22) Using bilinear interpolation, the mixing ratio points of the yield strength threshold and the viscosity threshold are plotted into a three-dimensional surface diagram to obtain stirring image information. This includes the following steps:

[0061] (221) Select the reference points and use the meshgrid function to create a grid.

[0062] (222) The bilinear interpolation method was used to plot the mix points that met the yield strength threshold and viscosity threshold into three-dimensional surface graphs.

[0063] The third step is to use the ratio adjustment module to obtain the mixing image information, and adjust the concrete ratio to obtain the ratio adjustment information. In this embodiment, the LSTM network is good at capturing the long-term dependencies in the sequence data, which is particularly important for feature extraction in the concrete mixing process, because the mixing process is a dynamic, time series process. The details are as follows:

[0064] (31) Acquire mixing image information and establish a quantitative relationship between image features of concrete mixing image key frames with different working performances and working performance. Here, the details are as follows:

[0065] (311) Extract image features of key frames of concrete mixing images.

[0066] (312) Using image segmentation technology to segment image features of key frames of concrete mixing images;

[0067] (313) An LSTM network model was used for fitting.

[0068] (314) The average height difference between boundary lines is used as a quantitative index of image features, and the quantitative relationship between image features and working performance of key frames of concrete mixing images is obtained.

[0069] (32) Build an LSTM network model to extract feature information from mixing image information, predict concrete working performance, and provide real-time feedback on the adjusted mix ratio corresponding to the working performance index to obtain mix ratio adjustment information.

[0070] In the fourth step, the feedback module feeds back the mix adjustment information to the concrete batching module and makes mix corrections. This can reduce manual intervention and the number of trial mixes. That is, through the prediction of the LSTM model, the number of actual trial mixes can be reduced, saving materials and time and improving production efficiency.

[0071] The above embodiments are only preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any changes that adopt the design principles of the present invention and are made through non-creative labor on this basis should fall within the protection scope of the present invention.

Claims

1. A concrete intelligent material system, characterized in that: include: The raw material detection module obtains the aggregate data of sand and gravel aggregates in the raw materials of concrete; The concrete batching module is connected with the raw material detection module to obtain the aggregate data of sand and gravel aggregates, and obtain the mixing image information using the net slurry rheological threshold algorithm; The proportion adjustment module is connected with the concrete batching module to obtain mixing image information and adjust the proportion of concrete to obtain proportion adjustment information; The feedback module is connected with the concrete batching module and feeds back the proportion adjustment information to the concrete batching module.

2. The intelligent concrete material system according to claim 1, characterized in that: The raw material detection module uses image processing and deep learning to obtain aggregate data of sand and gravel aggregates in the raw materials of concrete, which includes the following steps: Acquire image data of raw materials of concrete and construct a sample data set of sand particle surface images; Build a convolutional neural network for deep learning; The convolutional neural network is trained using the sand particle surface image sample dataset to fit the relationship between the sand particle surface image features and the grading and stone powder content, and the aggregate data of sand and gravel aggregate is output.

3. A concrete intelligent material system according to claim 2, characterized in that: The concrete batching module uses a pure slurry rheological threshold algorithm to obtain mixing image information, including the following steps: The aggregate data of sand and gravel aggregates are obtained, and the correlation between the mortar rheological threshold and the net paste rheological threshold is established by using the Krieger-Dougherty algorithm; Bilinear interpolation is used to plot the mix ratio points of the yield strength threshold and the viscosity threshold into a three-dimensional surface diagram to obtain the stirring image information.

4. The intelligent concrete material system according to claim 3, characterized in that: The correlation between the mortar rheological threshold and the net slurry rheological threshold is established, and the expression is: Among them, η r,p Indicates the non-dimensional dynamic viscosity of the pure pulp; φ FA represents the volume fraction of fine aggregate in mortar; [η] FA It represents the intrinsic viscosity of the system after adding fine aggregate; It expresses the volume fraction of fine aggregate in mortar under the index m which is related to the shape of cement particles.

5. The intelligent concrete material system according to claim 4, characterized in that: The mixing ratio points of the yield strength threshold and the viscosity threshold are plotted into a three-dimensional surface graph by bilinear interpolation to obtain stirring image information, including the following steps: Select the reference points and use the meshgrid function to create a grid; The bilinear interpolation method is used to plot the mix ratio points that meet the yield strength threshold and viscosity threshold into three-dimensional surface graphs.

6. The intelligent concrete material system according to claim 2, characterized in that: The ratio adjustment module obtains mixing image information and adjusts the ratio of concrete to obtain ratio adjustment information, including the following steps: Acquire mixing image information and establish the quantitative relationship between image features and working performance of concrete mixing image key frames with different working performances; Build an LSTM network model to extract feature information from mixing image information, predict concrete working performance, and provide real-time feedback on the adjusted mix ratio corresponding to the working performance index to obtain mix ratio adjustment information.

7. The intelligent concrete material system according to claim 6, characterized in that: Establishing the quantitative relationship between the image features of the concrete mixing image key frames with different working performances and the working performance includes the following steps: Extract image features of key frames of concrete mixing images; Image segmentation technology is used to segment the image features of the key frames of the concrete mixing image; The LSTM network model is used for fitting; The average height difference between boundary lines is used as the quantitative index of image features, and the quantitative relationship between image features and working performance of key frames of concrete mixing images is obtained.

8. A method for implementing the concrete intelligent material system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Obtain aggregate data of sand and gravel aggregates in the raw materials of concrete; According to the aggregate data of sand and gravel aggregate, the mixing image information is obtained by using the net slurry rheological threshold algorithm; Combining the mixing image information and adjusting the mix ratio of the concrete to obtain mix ratio adjustment information; Feedback is given to the ratio adjustment information, and the stirring image information is corrected.

Images