Preparation method and device of concrete and electronic equipment

Abstract

The invention discloses a preparation method and device of concrete and electronic equipment. The method comprises the steps that attribute information corresponding to gangue aggregate and binding materials of to-be-prepared target concrete is obtained, strength information of the target concrete is obtained, and the attribute information is influence factors influencing the bearing strength of the target concrete; the strength information is used for representing the bearing strength of the target concrete in the hardened state; using a prediction model to predict water-binder ratio data of the target concrete based on the attribute information and the strength information, the prediction model being obtained by training an initial model by using an attribute information sample, a strength information sample and a water-binder ratio data sample; and obtaining yield information of the gangue aggregate, and mixing the gangue aggregate, water and a cementing material based on the yield information and the water-binder ratio data to prepare target concrete. The technical problem that the preparation accuracy of concrete is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete engineering, and in particular to a method, device and electronic equipment for preparing concrete. Background Art

[0002] At present, concrete is a widely used building material. The strength of concrete can directly affect the safety and durability of building structures. Most concrete is made of cementitious materials, water, gangue aggregate and possible additives.

[0003] In the related art, the preparation of concrete that meets the corresponding strength requirements mostly relies on personnel experience to mix gangue aggregate, water and cementitious materials according to certain water-cement ratio data (water-cement ratio). However, relying on personnel experience cannot guarantee the accuracy of the water-cement ratio, and there will be repeated trial and error adjustments, and the above three materials are prone to waste. For example, if there is too much cementitious material in the mixed concrete, more water is needed to fully hydrate the cementitious material, which may cause the water-cement ratio to increase and affect the strength of the concrete. For another example, too little cementitious material cannot provide sufficient bonding force, resulting in a decrease in the strength of the concrete, affecting the quality of the concrete, and it is necessary to add cementitious material to the mixed concrete. Therefore, there is still a technical problem of low accuracy in the preparation of concrete.

[0004] Currently, no effective solution has been proposed for the above technical problems. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and electronic equipment for preparing concrete, so as to at least solve the technical problem of low accuracy in preparing concrete.

[0006] According to one aspect of an embodiment of the present invention, a method for preparing concrete is provided. The method may include: obtaining the attribute information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared, and obtaining the strength information of the target concrete, wherein the attribute information is the influencing factor affecting the bearing strength of the target concrete; the strength information is used to indicate the bearing strength of the target concrete in a hardened state; using a prediction model, based on the attribute information and the strength information, predicting the water-cement ratio data of the target concrete, wherein the prediction model is obtained by training the initial model using the attribute information sample, the strength information sample and the water-cement ratio data sample, and the water-cement ratio data is used to indicate the proportion of water and cementitious material required to prepare the target concrete in the target concrete; obtaining the output information of the gangue aggregate, and mixing the gangue aggregate, water and cementitious material based on the output information and the water-cement ratio data to prepare the target concrete.

[0007] Optionally, the method may also include: formulating attribute information samples, strength information samples and water-cement ratio data samples, wherein the attribute information samples of gangue aggregate include the particle size of gangue aggregate, the strength of gangue aggregate and the water absorption rate of gangue aggregate, and the attribute information samples of cementitious material include the mass ratio of cementitious material to gangue aggregate; using the attribute information samples, strength information samples and water-cement ratio data samples to train the initial model to obtain a prediction model.

[0008] Optionally, attribute information samples, strength information samples and water-cement ratio data samples are formulated, including: obtaining attribute information samples, strength information samples and water-cement ratio data samples under different concrete mix ratios, wherein the concrete mix ratio is used to indicate the proportions of gangue aggregate, cementitious material and water in preparing the corresponding concrete.

[0009] Optionally, the initial model includes a deep belief network model, a particle swarm optimization model and a support vector regression algorithm model, and the model parameters of the initial model include local search capability parameters, global search capability parameters, maximum population evolution amount and maximum population number, wherein the initial model is trained using attribute information samples, strength information samples and water-cement ratio data samples to obtain a prediction model, including: inputting the attribute information samples, strength information samples and water-cement ratio data samples into the initial model, adjusting the local search capability parameters, global search capability parameters, maximum population evolution amount and maximum population number to obtain adjustment results; from the adjustment results, screening out target model parameters, and determining the prediction model corresponding to the target model parameters.

[0010] Optionally, target model parameters are screened out from the adjustment results to obtain a prediction model corresponding to the target model parameters, including: using the screened adjustment results whose fitness is greater than a fitness threshold as the target model parameters, and using the initial model corresponding to the target model parameters as the prediction model.

[0011] Optionally, the method may further include: in response to the existence of a target concrete mix other than the concrete mix for training the initial model, updating the attribute information samples, strength information samples and water-cement ratio data samples for training the initial model using the attribute information samples, strength information samples and water-cement ratio data samples corresponding to the target concrete mix to obtain an updated sample set; inputting the updated sample set into the prediction model, training the prediction model to obtain a target prediction model, wherein the target prediction model is obtained by training the prediction model using the updated sample set.

[0012] According to another aspect of an embodiment of the present invention, a concrete preparation device is also provided. The device may include: an acquisition unit, used to acquire the attribute information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared, and acquire the strength information of the target concrete, wherein the attribute information is the influencing factor affecting the bearing strength of the target concrete; the strength information is used to indicate the bearing strength of the target concrete in a hardened state; a prediction unit, used to predict the water-cement ratio data of the target concrete based on the attribute information and the strength information using a prediction model, wherein the prediction model is obtained by training the initial model using attribute information samples, strength information samples and water-cement ratio data samples, and the water-cement ratio data is used to indicate the proportion of water and cementitious material required to prepare the target concrete in the target concrete; a preparation unit, used to acquire the output information of the gangue aggregate, and based on the output information and the water-cement ratio data, mix the gangue aggregate, water and cementitious material to prepare the target concrete.

[0013] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute a method for preparing concrete.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the concrete preparation method of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a processor is further provided, wherein the processor is used to run a program, wherein when the program is run, the method for preparing concrete according to an embodiment of the present invention is executed.

[0016] According to another aspect of the embodiments of the present invention, a computer program product is provided, which includes a computer program, and when the computer program is executed by a processor, the method for preparing concrete according to the embodiments of the present application is implemented.

[0017] In an embodiment of the present invention, if concrete is to be prepared, the property information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared can be obtained, and the strength information of the target concrete can be obtained; the prediction model is used to predict the water-cement ratio data of the target concrete based on the property information and the strength information, and the output information of the gangue aggregate is obtained. Based on the output information and the water-cement ratio data, the gangue aggregate, water and cementitious material are mixed to prepare the target concrete. In this embodiment, by collecting the property information corresponding to the gangue aggregate and cementitious material, and the strength information of the target concrete, the proportion of water and cementitious material required for preparing the target concrete in the target concrete predicted by the prediction model is adjusted, and the gangue aggregate, water and cementitious material are mixed according to the adjusted proportion and the output information of the gangue aggregate to prepare the target concrete. Compared with the preparation of concrete based on human experience, which cannot guarantee the accuracy of water-cement ratio data and may result in excessive amount of prepared concrete due to repeated trial and error adjustments, the target concrete prepared by the method of the present invention is more objective and can also prevent the amount of prepared concrete from being excessive, thereby achieving the technical effect of improving the accuracy of concrete preparation and solving the technical problem of low accuracy of concrete preparation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0019] Figure 1 is a flow chart of a method for preparing concrete according to an embodiment of the present invention;

[0020] Figure 2 is a flow chart of a method for predicting water-binder ratio of concrete with different types of gangue aggregate according to an embodiment of the present invention;

[0021] Figure 3 Schematic diagram of a concrete preparation device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] According to an embodiment of the present invention, an embodiment of a method for preparing concrete is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0025] Figure 1 is a flow chart of a method for preparing concrete according to an embodiment of the present invention, such as Figure 1 As shown, the method may include the following steps:

[0026] Step S102, obtaining the property information corresponding to the gangue aggregate and the cementitious material of the target concrete to be prepared, and obtaining the strength information of the target concrete.

[0027] In the technical solution provided in the above step S102 of the present invention, the attribute information can be an influencing factor affecting the bearing strength of the target concrete; the strength information can be used to indicate the bearing strength of the target concrete in a hardened state. Gangue aggregate is coal gangue (a hard rock or mineral, usually rich in carbon but with lower energy content than coal) produced during coal mining and processing. After processing, it is used as aggregate in building materials such as concrete, mortar or road construction. Aggregate (also known as aggregate) is one of the main components of building materials such as concrete, mortar, asphalt mixture, etc., and can provide most of the volume and strength of building materials. Aggregates of different particle sizes have a significant impact on the performance of concrete. Aggregates can be divided into two categories: fine aggregate (sand) and coarse aggregate (stone or crushed stone). For example, aggregates with a particle size of usually 4.75mm to 20mm or larger can be coarse aggregates; aggregates with a particle size of less than 4.75mm can be fine aggregates. Cementitious materials can be cement.

[0028] In this embodiment, if it is necessary to select and proportion materials for preparing concrete (for example, gangue aggregate, cementitious material and water) to improve the strength performance of concrete and the quality of products made of concrete (for example, roads, buildings), the property information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared can be obtained, and the strength information of the target concrete can be obtained.

[0029] For example, accurate information on the properties of coal gangue aggregates such as particle size, strength, water absorption, and the type and quality of cementitious materials can be obtained through national or industry standards, supplier test reports, on-site assessments, etc.

[0030] It should be noted that the above method of obtaining the property information of the target concrete is only an example and is not specifically limited here. As long as it is a method that can be used to obtain the property information corresponding to the gangue aggregate to be prepared for the target concrete, it is within the protection scope of the embodiment of the present invention.

[0031] For example, the target concrete can be subjected to compressive strength tests, on-site inspections and monitoring to obtain strength information of the target concrete, that is, the expected compressive strength, to ensure that the prepared concrete can meet the bearing requirements of the engineering design.

[0032] For another example, for a high-rise building with a large expected load and located in an earthquake zone, the columns and beams of the building may require concrete with a compressive strength of at least 40 MPa or 50 MPa. In this case, it is necessary to select a suitable ratio of cementitious materials, gangue aggregate and water, as well as possible admixtures when preparing the concrete. The ratio can be verified and adjusted through laboratory compressive strength tests to determine the final concrete strength information.

[0033] It should be noted that the above method of obtaining the strength information of the target concrete is only an example and is not specifically limited here. As long as it is an acquisition method that can be used to obtain the strength information of the target concrete, it is within the protection scope of the embodiment of the present invention.

[0034] Step S104: using the prediction model to predict the water-cement ratio data of the target concrete based on the attribute information and the strength information.

[0035] In the technical solution provided in the above step S104 of the present invention, after obtaining the attribute information corresponding to the gangue aggregate and the cementitious material of the target concrete to be prepared, and obtaining the strength information of the target concrete, the prediction model can be used to predict the water-cement ratio data of the target concrete based on the attribute information and the strength information. The prediction model is obtained by training the initial model using the attribute information sample, the strength information sample and the water-cement ratio data sample, and the water-cement ratio data is used to indicate the proportion of water and cementitious material required to prepare the target concrete in the target concrete.

[0036] In this embodiment, the prediction model can be a Deep Belief Network-Particle Swarm Optimization-Support Vector Regression (DBN-PSO-SVR) prediction model. The DBN-PSO-SVR prediction model can accurately predict the strength and appropriate water-cement ratio data of the target concrete based on the particle size, strength, water absorption rate of the gangue aggregate, the mass ratio of cement to gangue aggregate and the strength information of the target concrete, thereby reducing the pre-experimental cost while improving the efficiency and quality of concrete preparation.

[0037] Optionally, the water-cement ratio data can be the weight ratio of water to cementitious materials (usually mainly cement, but also other cementitious materials such as fly ash and silica fume) in the concrete mixture. The water-cement ratio has a direct and significant impact on the properties of concrete, such as strength, durability, fluidity, etc. By using the water-cement ratio data predicted by the prediction model, engineers and construction personnel can more accurately control the concrete preparation process and ensure that the concrete reaches the expected performance indicators.

[0038] Step S106, obtaining the output information of gangue aggregate, and mixing the gangue aggregate, water and cementitious material based on the output information and water-cement ratio data to prepare target concrete.

[0039] In the technical solution of the above step S106 of the present invention, after using the prediction model to predict the water-cement ratio data of the target concrete based on the attribute information and the strength information, the production information of the gangue aggregate can be obtained, and based on the production information and the water-cement ratio data, the gangue aggregate, water and cementitious material are mixed to prepare the target concrete.

[0040] In this embodiment, the output information of gangue aggregate can be determined according to specific scenarios of different roads and buildings made of concrete. This is only an example and is not specifically limited here.

[0041] Optionally, according to the gangue aggregate production and water-cement ratio data, the required water and cementitious materials can be calculated based on the mass ratio and volume ratio principles, and the gangue aggregate, cementitious materials and water can be mixed in proportion to prepare the target concrete efficiently and accurately to meet the bearing requirements of the engineering design.

[0042] In the above steps S102 to S106 of the present application, if concrete is to be prepared, the property information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared can be obtained, and the strength information of the target concrete can be obtained; the prediction model is used to predict the water-cement ratio data of the target concrete based on the property information and the strength information, and the output information of the gangue aggregate is obtained, and the gangue aggregate, water and cementitious material are mixed based on the output information and the water-cement ratio data to prepare the target concrete. In this embodiment, by collecting the property information corresponding to the gangue aggregate and the cementitious material, and the strength information of the target concrete, the proportion of water and cementitious material required for preparing the target concrete in the target concrete predicted by the prediction model is adjusted, and the gangue aggregate, water and cementitious material are mixed according to the adjusted proportion and the output information of the gangue aggregate to prepare the target concrete. Compared with the preparation of concrete based on human experience, which cannot guarantee the accuracy of water-cement ratio data and may result in excessive amount of prepared concrete due to repeated trial and error adjustments, the target concrete prepared by the method of the present invention is more objective and can also prevent the amount of prepared concrete from being excessive, thereby achieving the technical effect of improving the accuracy of concrete preparation and solving the technical problem of low accuracy of concrete preparation.

[0043] The above method of this embodiment is further introduced below.

[0044] As an optional implementation method, attribute information samples, strength information samples and water-cement ratio data samples are formulated, wherein the attribute information samples of gangue aggregate include the particle size of gangue aggregate, the strength of gangue aggregate and the water absorption rate of gangue aggregate, and the attribute information samples of cementitious material include the mass ratio of cementitious material to gangue aggregate; the initial model is trained using the attribute information samples, strength information samples and water-cement ratio data samples to obtain a prediction model.

[0045] In this embodiment, attribute information samples, strength information samples and water-cement ratio data samples are formulated, and the initial model is trained using the attribute information samples, strength information samples and water-cement ratio data samples to obtain a prediction model. Among them, the attribute information samples of gangue aggregate include the particle size of gangue aggregate, the strength of gangue aggregate and the water absorption rate of gangue aggregate, and the attribute information samples of cementitious material include the mass ratio of cementitious material to gangue aggregate. The particle size of gangue aggregate can be the particle size of coal gangue. The strength of gangue aggregate can be the strength of bulk coal gangue. The water absorption rate of gangue aggregate can be the water absorption rate of coal gangue. The attribute information samples of cementitious material include the mass ratio of cementitious material to gangue aggregate, that is, the mass ratio of cement to coal gangue.

[0046] Optionally, a large number of attribute information samples including the particle size, strength, water absorption rate of gangue aggregate, and the mass ratio of cement to gangue aggregate are collected and sorted, and the corresponding concrete strength information samples and water-cement ratio data samples are recorded. The initial model can be trained to obtain a prediction model.

[0047] As an optional implementation method, attribute information samples, strength information samples and water-cement ratio data samples are formulated, including: obtaining attribute information samples, strength information samples and water-cement ratio data samples under different concrete mix ratios, wherein the concrete mix ratio is used to indicate the proportions of gangue aggregate, cementitious material and water in preparing the corresponding concrete.

[0048] In this embodiment, in the process of formulating attribute information samples, strength information samples and water-cement ratio data samples, attribute information samples, strength information samples and water-cement ratio data samples under different concrete mix ratios can be obtained. The concrete mix ratio can be used to indicate the proportions of gangue aggregate, cementitious material and water in preparing the corresponding concrete.

[0049] Optionally, by collecting or updating the data of coal gangue particle size, loose coal gangue strength, coal gangue water absorption, cement-to-gangue mass ratio, and water-binder ratio under different concrete mix ratios, a DBN-PSO-SVR prediction model can be constructed, so that the DBN-PSO-SVR prediction model can accurately predict the water-binder ratio of concrete with different types of coal gangue aggregates. By collecting data samples under different mix ratios, a wide range of concrete preparation scenarios can be covered, thereby improving the accuracy of the model in predicting the water-binder ratio of various concretes.

[0050] As an optional implementation method, the initial model includes a deep belief network model, a particle swarm optimization model and a support vector regression algorithm model, and the model parameters of the initial model include local search capability parameters, global search capability parameters, maximum population evolution amount and maximum population number, wherein the initial model is trained using attribute information samples, strength information samples and water-cement ratio data samples to obtain a prediction model, including: inputting the attribute information samples, strength information samples and water-cement ratio data samples into the initial model, adjusting the local search capability parameters, global search capability parameters, maximum population evolution amount and maximum population number to obtain adjustment results; from the adjustment results, screening out the target model parameters, and determining the prediction model corresponding to the target model parameters.

[0051] In this embodiment, in the process of training the initial model using the attribute information samples, the strength information samples and the water-cement ratio data samples to obtain the prediction model, the attribute information samples, the strength information samples and the water-cement ratio data samples can be input into the initial model, and the local search capability parameters, the global search capability parameters, the maximum evolution amount of the population and the maximum number of the population can be adjusted to obtain the adjustment results; the target model parameters can be screened out from the adjustment results, and the prediction model corresponding to the target model parameters can be determined. Among them, the initial model can include a deep belief network model, a particle swarm optimization model and a support vector regression algorithm model, and the model parameters of the initial model can include a local search capability parameter, a global search capability parameter, a maximum evolution amount of the population and a maximum number of the population.

[0052] Optionally, the Deep Belief Network (DBN) model is an unsupervised learning neural network model that can be used to preprocess input data, extract high-level features of gangue aggregate and concrete mix ratio through multi-layer nonlinear transformation, and provide more effective data representation for subsequent predictions. The Particle Swarm Optimization (PSO) model is a global optimization algorithm that can be used to optimize the parameters of the Deep Belief Network-Support Vector Regression (SVR) model, such as the kernel function parameters, local search capability parameters, global search capability parameters, maximum population evolution amount and maximum population size of SVR. The SVR model can establish a water-cement ratio prediction model based on the features extracted by DBN. Through the parameters optimized by PSO, SVR can more accurately predict the water-cement ratio of different types of gangue aggregate concrete, thereby achieving effective prediction of concrete performance.

[0053] Optionally, in the model parameters of the initial model, the local search capability parameter c1 can be set to 1, the global search capability parameter c2 can be set to 1, and the population maximum evolution amount gen maxCan be set to 40, the maximum size of the population pop Can be set to 40.

[0054] As an optional implementation method, the target model parameters are screened out from the adjustment results to obtain a prediction model corresponding to the target model parameters, including: using the screened adjustment results whose fitness is greater than the fitness threshold as the target model parameters, and using the initial model corresponding to the target model parameters as the prediction model.

[0055] In this embodiment, in the process of screening out the target model parameters from the adjustment results and obtaining the prediction model corresponding to the target model parameters, the screened adjustment results whose fitness is greater than the fitness threshold can be used as the target model parameters, and the initial model corresponding to the target model parameters can be used as the prediction model.

[0056] Optionally, the parameters corresponding to the maximum fitness of the DBN-PSO-SVR prediction model are selected. The local search capability parameter c1 can be 1.5, the global search capability parameter c2 can be 1.5, and the population maximum evolution amount gen max It can be 50, the maximum size of the population pop It can be 50, thus completing the concrete water-cement ratio DBN-PSO-SVR algorithm prediction model.

[0057] As an optional implementation method, in response to the existence of a target concrete mix other than the concrete mix for training the initial model, the attribute information samples, strength information samples and water-cement ratio data samples corresponding to the target concrete mix are used to update the attribute information samples, strength information samples and water-cement ratio data samples for training the initial model to obtain an updated sample set; the updated sample set is input into the prediction model, the prediction model is trained to obtain a target prediction model, wherein the target prediction model is obtained by training the prediction model using the updated sample set.

[0058] In this embodiment, if there is a target concrete mix ratio other than the concrete mix ratio for training the initial model, the attribute information samples, strength information samples and water-binder ratio data samples corresponding to the target concrete mix ratio can be used to update the attribute information samples, strength information samples and water-binder ratio data samples for training the initial model to obtain an updated sample set; the updated sample set can be input into the prediction model to train the prediction model to obtain the target prediction model. The target prediction model can be obtained by training the prediction model using the updated sample set.

[0059] Optionally, after collecting concrete data of other groups, the attribute information samples, strength information samples and water-cement ratio data samples of the initial model can be updated, and then the prediction model can be trained to obtain the target prediction model.

[0060] In an embodiment of the present invention, if concrete is to be prepared, the property information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared can be obtained, and the strength information of the target concrete can be obtained; the prediction model is used to predict the water-cement ratio data of the target concrete based on the property information and the strength information, and the output information of the gangue aggregate is obtained. Based on the output information and the water-cement ratio data, the gangue aggregate, water and cementitious material are mixed to prepare the target concrete. In this embodiment, by collecting the property information corresponding to the gangue aggregate and cementitious material, and the strength information of the target concrete, the proportion of water and cementitious material required for preparing the target concrete in the target concrete predicted by the prediction model is adjusted, and the gangue aggregate, water and cementitious material are mixed according to the adjusted proportion and the output information of the gangue aggregate to prepare the target concrete. Compared with the preparation of concrete based on human experience, which cannot guarantee the accuracy of water-cement ratio data and may result in excessive amount of prepared concrete due to repeated trial and error adjustments, the target concrete prepared by the method of the present invention is more objective and can also prevent the amount of prepared concrete from being excessive, thereby achieving the technical effect of improving the accuracy of concrete preparation and solving the technical problem of low accuracy of concrete preparation.

[0061] The technical solution of the embodiment of the present invention is illustrated below in conjunction with preferred implementation modes.

[0062] At present, the output of coal gangue in my country accounts for about 10% to 15% of the raw coal output. Its output is huge. The long-term natural stacking of coal gangue will have adverse effects on the ecological environment. In recent years, my country has fully realized the availability of coal gangue resources, and it has been widely used in the production of underground filling materials in mines. The occurrence conditions of coal seams in my country are complex. The properties of coal gangue are affected by time, space and geographical distribution. Different types of coal gangue have different water absorption rates. When making concrete materials, a large number of preliminary experiments are required to determine the specific water-binder ratio, and it is difficult to determine its approximate range.

[0063] Therefore, the present invention provides a method for predicting the water-binder ratio of concrete with different types of gangue aggregates. The data sets of gangue particle size, loose gangue strength, gangue water absorption, mass ratio of cement to gangue, water-binder ratio and finished concrete strength under different concrete ratios are input, collected or updated into an initial model for predicting the water-binder ratio of concrete using a DBN-PSO-SVR algorithm. The model parameters under the maximum fitness are determined by continuous iteration and update, so as to obtain a DBN-PSO-SVR algorithm prediction model that can predict the water-binder ratio of concrete with different types of gangue aggregates.

[0064] The present invention continuously collects and updates concrete water-binder ratio data under different mix ratios, finds model parameters under maximum fitness through particle swarm algorithm, and continuously improves the accuracy of the concrete water-binder ratio prediction model of DBN-PSO-SVR algorithm. It can provide effective reference values ​​for the selection of water-binder ratio of gangue aggregate concrete, save raw material consumption, reduce trial and error costs, and improve the accuracy of concrete water-binder ratio, thereby achieving the technical effect of improving the preparation accuracy of concrete and solving the technical problem of low preparation accuracy of concrete.

[0065] The embodiments of the present invention are further described below.

[0066] In an embodiment of the present invention, Figure 2 is a flow chart of a method for predicting water-binder ratio of different types of gangue aggregate concrete according to an embodiment of the present invention. Figure 2 As shown, the method mainly includes the following steps:

[0067] Step S201, collecting concrete data.

[0068] In this embodiment, the coal gangue particle size, bulk coal gangue strength, coal gangue water absorption rate, cement to coal gangue mass ratio, water-binder ratio and finished concrete strength data set under different concrete mix ratios can be collected or updated.

[0069] Table 1 is a data table of water-binder ratios of concrete under 30 different proportions according to an embodiment of the present invention. As shown in Table 1, 30 groups of water-binder ratio data of concrete under different proportions are included. The particle size of coal gangue can be 0-25 mm, the strength of loose coal gangue can be 10-20 MPa, the water absorption rate of coal gangue can be 2%-6%, the mass ratio of cement to coal gangue can be 60%-80%, the water-binder ratio can be 0.35-0.45, and the strength of the finished concrete can be 20-60 MPa.

[0070] Table 1 Data table of water-cement ratio of concrete under 30 different mix ratios

[0071]

[0072] Step S202, establishing an initial model for concrete water-binder ratio prediction using the DBN-PSO-SVR algorithm and setting parameters.

[0073] In this embodiment, the initial model of concrete water-cement ratio prediction by DBN-PSO-SVR algorithm can be established, and four initial parameters can be set: the local search capability parameter c1 can be 1, the global search capability parameter c2 can be 1, and the population maximum evolution amount gen max It can be 40, the maximum size of the population pop , that is, the number of population particles in the PSO algorithm can be 40.

[0074] Step S203, inputting concrete data into the algorithm prediction model.

[0075] In this embodiment, the 30 groups of concrete data in Table 1 can be entered into the DBN-PSO-SVR algorithm prediction model, and the local search capability parameters, global search capability parameters, maximum population evolution amount and maximum population size can be adjusted.

[0076] Optionally, the adjustment range of the local search capability parameter c1 can be 0 to 2, the adjustment range of the global search capability parameter c2 can be 0 to 2, and the maximum evolution amount of the population gen max The adjustment range can be 30 to 80, the maximum population size pop The adjustment range can be 30~80.

[0077] Step S204, screening the DBN-PSO-SVR algorithm prediction model, and completing the DBN-PSO-SVR algorithm prediction model for concrete water-cement ratio.

[0078] In this embodiment, the local search capability parameter c1 corresponding to the maximum fitness of the DBN-PSO-SVR algorithm prediction model can be screened out, which can be 1.5, the global search capability parameter c2 can be 1.5, and the population maximum evolution amount gen max , which can be 50, the maximum population size pop , can be 50, thus completing the concrete water-cement ratio DBN-PSO-SVR algorithm prediction model.

[0079] Step S205: updating concrete data.

[0080] In this embodiment, after collecting concrete data of other groups, the concrete data is updated in step S201, and steps S202 to S204 are repeated.

[0081] Step S206, obtaining the required water-binder ratio of the gangue aggregate concrete.

[0082] In this embodiment, the required predicted gangue particle size, loose gangue strength, gangue water absorption, cement to gangue mass ratio and target concrete strength can be entered into the concrete water-binder ratio DBN-PSO-SVR algorithm prediction model to obtain the required gangue aggregate concrete water-binder ratio.

[0083] In an embodiment of the present invention, if concrete is to be prepared, the property information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared can be obtained, and the strength information of the target concrete can be obtained; the prediction model is used to predict the water-cement ratio data of the target concrete based on the property information and the strength information, and the output information of the gangue aggregate is obtained. Based on the output information and the water-cement ratio data, the gangue aggregate, water and cementitious material are mixed to prepare the target concrete. In this embodiment, by collecting the property information corresponding to the gangue aggregate and cementitious material, and the strength information of the target concrete, the proportion of water and cementitious material required for preparing the target concrete in the target concrete predicted by the prediction model is adjusted, and the gangue aggregate, water and cementitious material are mixed according to the adjusted proportion and the output information of the gangue aggregate to prepare the target concrete. Compared with the preparation of concrete based on human experience, which cannot guarantee the accuracy of water-cement ratio data and may result in excessive amount of prepared concrete due to repeated trial and error adjustments, the target concrete prepared by the method of the present invention is more objective and can also prevent the amount of prepared concrete from being excessive, thereby achieving the technical effect of improving the accuracy of concrete preparation and solving the technical problem of low accuracy of concrete preparation.

[0084] According to an embodiment of the present invention, a concrete preparation device is also provided. It should be noted that the concrete preparation device can be used to execute the concrete preparation method in the above embodiment.

[0085] Figure 3 Schematic diagram of a concrete preparation device according to an embodiment of the present invention. Figure 3 As shown, the concrete preparation device 300 may include: an acquisition unit 302 , a prediction unit 304 and a preparation unit 306 .

[0086] The acquisition unit 302 is used to obtain the attribute information corresponding to the gangue aggregate and the cementitious material of the target concrete to be prepared, and to obtain the strength information of the target concrete, wherein the attribute information is the influencing factor affecting the bearing strength of the target concrete; the strength information is used to indicate the bearing strength of the target concrete in a hardened state.

[0087] The prediction unit 304 is used to predict the water-cement ratio data of the target concrete based on the attribute information and the strength information using the prediction model, wherein the prediction model is obtained by training the initial model using the attribute information samples, the strength information samples and the water-cement ratio data samples, and the water-cement ratio data is used to represent the proportion of water and cementitious materials required to prepare the target concrete in the target concrete.

[0088] The preparation unit 306 is used to obtain the output information of the gangue aggregate, and based on the output information and the water-cement ratio data, mix the gangue aggregate, water and cementitious materials to prepare the target concrete.

[0089] In the embodiment of the present invention, the acquisition unit 302 acquires the attribute information corresponding to the gangue aggregate and cementitious material of the target concrete to be prepared, and acquires the strength information of the target concrete, wherein the attribute information is the influencing factor affecting the bearing strength of the target concrete; the strength information is used to represent the bearing strength of the target concrete in a hardened state; the prediction unit 304 uses a prediction model to predict the water-cement ratio data of the target concrete based on the attribute information and the strength information, wherein the prediction model is obtained by training an initial model using attribute information samples, strength information samples and water-cement ratio data samples, and the water-cement ratio data is used to represent the proportion of water and cementitious material required for preparing the target concrete in the target concrete; the preparation unit 306 acquires the output information of the gangue aggregate, and based on the output information and the water-cement ratio data, the gangue aggregate, water and cementitious material are mixed to prepare the target concrete, thereby achieving the technical effect of improving the preparation accuracy of the concrete and solving the technical problem of low preparation accuracy of the concrete.

[0090] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute a method for preparing concrete.

[0091] According to an embodiment of the present invention, a computer-readable storage medium is further provided. The storage medium includes a stored program, wherein the program executes the method for preparing concrete in the above embodiment.

[0092] According to an embodiment of the present invention, a processor is further provided, and the processor is used to run a program, wherein the method for preparing concrete in the above embodiment is executed when the program is run.

[0093] The embodiment of the present application further provides a computer program product. Optionally, in the present embodiment, the computer program product may include a computer program, and when the computer program is executed by a processor, the concrete preparation method of the embodiment of the present application is implemented.

[0094] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units 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 units or modules, which can be electrical or other forms.

[0096] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0097] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0098] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for 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 method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, Read-Only Memory (ROM), Random Access Memory (RAM), mobile hard disk, magnetic disk or optical disk, etc., various media that can store program codes.

[0099] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for preparing concrete, characterized in that: include: Acquire the property information corresponding to the gangue aggregate and the cementitious material of the target concrete to be prepared, and acquire the strength information of the target concrete, wherein the property information is the influencing factor affecting the bearing strength of the target concrete; the strength information is used to represent the bearing strength of the target concrete in a hardened state; Using a prediction model, based on the attribute information and the strength information, predicting water-cement ratio data of the target concrete, wherein the prediction model is obtained by training an initial model using attribute information samples, strength information samples, and water-cement ratio data samples, and the water-cement ratio data is used to represent the proportion of water required to prepare the target concrete and the cementitious material in the target concrete; The output information of the gangue aggregate is obtained, and based on the output information and the water-cement ratio data, the gangue aggregate, the water and the cementitious material are mixed to prepare the target concrete.

2. The method according to claim 1, characterized in that The method further comprises: Formulate the attribute information sample, the strength information sample and the water-cement ratio data sample, wherein the attribute information sample of the gangue aggregate includes the particle size of the gangue aggregate, the strength of the gangue aggregate and the water absorption rate of the gangue aggregate, and the attribute information sample of the cementitious material includes the mass ratio of the cementitious material to the gangue aggregate; The initial model is trained using the attribute information samples, the strength information samples and the water-cement ratio data samples to obtain the prediction model.

3. The method according to claim 2, characterized in that Formulating the attribute information sample, the strength information sample and the water-cement ratio data sample includes: The attribute information samples, the strength information samples and the water-cement ratio data samples under different concrete mix ratios are obtained, wherein the concrete mix ratio is used to indicate the proportions of the gangue aggregate, the cementitious material and the water used to prepare the corresponding concrete.

4. The method according to claim 3, characterized in that The initial model includes a deep belief network model, a particle swarm optimization model and a support vector regression algorithm model, and the model parameters of the initial model include a local search capability parameter, a global search capability parameter, a population maximum evolution amount and a population maximum number, wherein the initial model is trained using the attribute information sample, the strength information sample and the water-cement ratio data sample to obtain the prediction model, including: Inputting the attribute information sample, the strength information sample and the water-cement ratio data sample into the initial model, adjusting the local search capability parameter, the global search capability parameter, the maximum evolution amount of the population and the maximum number of the population to obtain an adjustment result; Target model parameters are screened out from the adjustment results, and the prediction model corresponding to the target model parameters is determined.

5. The method according to claim 4, characterized in that Filtering out target model parameters from the adjustment results to obtain the prediction model corresponding to the target model parameters includes: The screened adjustment results whose fitness is greater than the fitness threshold are used as the target model parameters, and the initial model corresponding to the target model parameters is used as the prediction model.

6. The method according to claim 3, characterized in that The method further comprises: In response to the existence of a target concrete mix other than the concrete mix for training the initial model, the attribute information samples, the strength information samples, and the water-binder ratio data samples corresponding to the target concrete mix are used to update the attribute information samples, the strength information samples, and the water-binder ratio data samples for training the initial model to obtain an updated sample set; The updated sample set is input into the prediction model, and the prediction model is trained to obtain a target prediction model, wherein the target prediction model is obtained by training the prediction model using the updated sample set.

7. A concrete preparation device, characterized in that: include: an acquisition unit, used to acquire attribute information corresponding to the gangue aggregate and the cementitious material of the target concrete to be prepared, and acquire strength information of the target concrete, wherein the attribute information is an influencing factor affecting the bearing strength of the target concrete; and the strength information is used to represent the bearing strength of the target concrete in a hardened state; a prediction unit, configured to predict water-cement ratio data of the target concrete based on the attribute information and the strength information by using a prediction model, wherein the prediction model is obtained by training an initial model by using attribute information samples, strength information samples and water-cement ratio data samples, and the water-cement ratio data is used to represent the proportion of water required to prepare the target concrete and the cementitious material in the target concrete; A preparation unit is used to obtain the output information of the gangue aggregate, and based on the output information and the water-cement ratio data, mix the gangue aggregate, the water and the cementitious material to prepare the target concrete.

8. An electronic device, comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for preparing concrete according to any one of claims 1 to 6.

9. A processor, characterized in that: The processor is used to run a program, wherein the program, when run by the processor, executes the method for preparing concrete according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the method for preparing concrete according to any one of claims 1 to 6.

Images