CN114242182A - Desert sand concrete strength prediction method, device, equipment and storage medium - Google Patents
Desert sand concrete strength prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN114242182A CN114242182A CN202111330779.XA CN202111330779A CN114242182A CN 114242182 A CN114242182 A CN 114242182A CN 202111330779 A CN202111330779 A CN 202111330779A CN 114242182 A CN114242182 A CN 114242182A
- Authority
- CN
- China
- Prior art keywords
- strength
- desert sand
- concrete
- sand concrete
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000004576 sand Substances 0.000 title claims abstract description 233
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000003062 neural network model Methods 0.000 claims abstract description 89
- 239000013598 vector Substances 0.000 claims abstract description 61
- 238000001514 detection method Methods 0.000 claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 53
- 238000013507 mapping Methods 0.000 claims abstract description 9
- 230000015654 memory Effects 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 14
- 230000006835 compression Effects 0.000 claims description 8
- 238000007906 compression Methods 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims 2
- 238000004891 communication Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/38—Concrete; Lime; Mortar; Gypsum; Bricks; Ceramics; Glass
- G01N33/383—Concrete or cement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Immunology (AREA)
- Ceramic Engineering (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Databases & Information Systems (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Crystallography & Structural Chemistry (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The invention discloses a desert sand concrete strength prediction method, a device, equipment and a storage medium, belonging to the technical field of strength prediction, wherein the method comprises the following steps: acquiring historical detection data of the desert sand concrete strength; acquiring characteristic text values corresponding to the different types of desert sand concrete aiming at the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; training a neural network model by using the four-dimensional vector and the historical detection data to obtain a trained neural network model; and predicting the strength of the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested. The invention trains the neural network model by using the historical detection data of the desert sand concrete, and the strength of the desert sand concrete can be predicted by using the neural network model after the training is finished, thereby realizing the efficient and accurate strength prediction of the desert sand concrete.
Description
Technical Field
The invention relates to the technical field of strength prediction, in particular to a desert sand concrete strength prediction method, device, equipment and storage medium.
Background
In the related art, the conventional strength detection method generally detects the strength value by manually operating a testing machine and other devices, has complex operation steps, high cost and low efficiency, and focuses on detecting the strength value of common concrete.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for predicting the strength of desert sand concrete, and solves the problems of complicated operation steps and low cost and high efficiency in strength detection in the prior art.
According to a first aspect of the present invention, there is provided a method for predicting desert sand concrete strength, comprising:
acquiring historical detection data of different types of desert sand concrete; the historical detection data comprises the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions;
acquiring characteristic text values corresponding to the different types of desert sand concrete aiming at the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; the four-dimensional vector is used for representing the type of the desert sand concrete;
training a neural network model by using the four-dimensional vector and the historical detection data to obtain a trained neural network model;
and predicting the strength of the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
Optionally, before obtaining the historical detection data of the desert sand concrete strength, the method further comprises:
and detecting the strength values of the concrete with different strength grades and obtaining the strength mean value of the concrete with different strength grades according to the detection result.
Optionally, before obtaining the historical detection data of the desert sand concrete strength, the method further comprises:
adding desert sand with different preset replacement proportions into the concrete with different strength grades to obtain the desert sand concrete;
and detecting the strength value of the desert sand concrete and obtaining the strength average value of the desert sand concrete according to the detection result.
Optionally, the detecting the strength values of the concrete with different strength grades and obtaining the strength average value of the concrete with different strength grades according to the detection result includes:
detecting the compressive strength of the concrete with different strength grades by using a pressure tester;
detecting the tensile strength of the concrete with different strength grades by using a uniaxial testing machine and taking the breaking load as an evaluation index;
detecting the static compression elastic modulus of the concrete with different strength grades by using a uniaxial testing machine and load and strain evaluation indexes;
and obtaining the strength average value of the concrete with different strength grades according to the compressive strength, the tensile strength and the static compression elastic modulus.
Optionally, the training a neural network model by using the four-dimensional vector and the historical detection data to obtain a trained neural network model includes:
setting initial weights and initial biases of the neural network model;
obtaining an input vector according to the four-dimensional vector and the historical detection data, and training and optimizing the neural network model by taking the strength average value of the desert sand concrete as an output vector to obtain a training result; the input vector comprises the strength mean value of the concrete with different strength grades, the doped desert sand proportion and the four-dimensional vector;
if the error between the training result and the preset expected value is smaller than or equal to a preset error threshold value, stopping training, wherein the obtained neural network model is the trained neural network model;
and if the error between the training result and the preset expected value is larger than the preset error threshold, adjusting the weight and the bias of the neural network model to obtain an updated neural network model, returning to execute the steps of obtaining an input vector according to the four-dimensional vector and the historical detection data, and training and optimizing the neural network model by taking the strength mean value of the desert sand concrete as an output vector until the error between the training result and the preset expected value is smaller than or equal to the preset error threshold.
Optionally, the predicting the strength of the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested includes:
acquiring prediction data of the desert sand concrete to be detected; the prediction data comprise the strength average value of original concrete corresponding to the desert sand concrete to be detected, the desert sand doping proportion and the four-dimensional vector of the desert sand concrete to be detected;
and inputting the prediction data into the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
Optionally, after the prediction data is input into the trained neural network model to obtain the predicted value of the strength of the desert sand concrete to be tested, the method further includes:
and generating a desert sand concrete strength prediction statistical table according to the predicted strength value of the desert sand concrete to be detected and the prediction data.
According to a second aspect of the present invention, there is provided a desert sand concrete strength prediction apparatus comprising:
the data acquisition module is used for acquiring historical detection data of different types of desert sand concrete; the historical detection data comprises the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions;
the characteristic extraction module is used for acquiring characteristic text values corresponding to the different types of desert sand concrete according to the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; the four-dimensional vector is used for representing the type of the desert sand concrete;
the model training module is used for training a neural network model by utilizing the four-dimensional vector and the historical detection data to obtain a trained neural network model;
and the strength prediction module is used for predicting the strength of the desert sand concrete to be tested by utilizing the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
According to a third aspect of the present invention, there is provided a desert sand concrete strength prediction apparatus comprising: a memory, a processor and a desert sand concrete strength prediction program stored on the memory and executable on the processor, the desert sand concrete strength prediction program, when executed by the processor, implementing the steps set forth in any one of the possible implementations of the first aspect or the second aspect.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium having stored thereon a desert sand concrete strength prediction program which, when executed by a processor, implements the various steps set forth in any one of the possible implementations of the first or second aspect.
The embodiment of the invention provides a method, a device, equipment and a storage medium for predicting the strength of desert sand concrete, wherein historical detection data of the strength of the desert sand concrete is obtained through desert sand concrete strength predicting equipment; acquiring characteristic text values corresponding to the different types of desert sand concrete aiming at the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; training a neural network model by using the historical detection data to obtain a trained neural network model; and predicting the strength of the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
The method comprises the steps of obtaining historical detection data of the desert sand concrete strength; training a neural network model by using the concrete strength mean value, the doped desert sand proportion, the desert sand concrete strength mean value obtained after doping the desert sand and the corresponding characteristic four-dimensional value; and finally, predicting the strength of the desert sand concrete to be tested by using the trained neural network. The method is different from the prior art that the operation steps are complicated when the strength is detected, the cost is high, the efficiency is low, and the method focuses on the condition of detecting the strength value of common concrete, the neural network model is trained by using the historical detection data of the desert sand concrete, and the strength of the desert sand concrete can be predicted by using the neural network model after the training is finished, so that the high-efficiency and accurate strength prediction of the desert sand concrete is realized, and the safety of the desert sand concrete is further ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a schematic structural diagram of a desert sand concrete strength prediction device of a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a desert sand concrete strength prediction method according to a first embodiment of the present invention;
FIG. 3 is a flowchart illustrating a process before step S201 in FIG. 2 according to the present invention;
FIG. 4 is a flowchart illustrating an embodiment of the step S301 in FIG. 3 according to the present invention;
FIG. 5 is a flowchart illustrating an embodiment of the step S203 in FIG. 2 according to the present invention;
FIG. 6 is a flowchart illustrating an embodiment of the step S204 in FIG. 2 according to the present invention;
fig. 7 is a functional block schematic diagram of a desert sand concrete strength prediction device according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The main solution of the embodiment of the invention is as follows: acquiring historical detection data of the desert sand concrete strength; acquiring characteristic text values corresponding to the different types of desert sand concrete aiming at the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; training a neural network model by using the historical detection data to obtain a trained neural network model; and predicting the strength of the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
In the prior art, the conventional strength detection method generally detects the strength value through manually operating a testing machine and other equipment, has complex operation steps, high cost and low efficiency, and focuses on detecting the strength value of common concrete.
The invention provides a solution, which is used for desert sand concrete strength prediction equipment, and historical detection data of desert sand concrete strength is obtained through the desert sand concrete strength prediction equipment; training a neural network model by using the concrete strength mean value, the doped desert sand proportion, the desert sand concrete strength mean value obtained after doping the desert sand and the corresponding characteristic four-dimensional value; and finally, predicting the strength of the desert sand concrete to be tested by using the trained neural network. The method is different from the prior art that the operation steps are complicated when the strength is detected, the cost is high, the efficiency is low, and the method focuses on the condition of detecting the strength value of common concrete, the neural network model is trained by using the historical detection data of the desert sand concrete, and the strength of the desert sand concrete can be predicted by using the neural network model after the training is finished, so that the high-efficiency and accurate strength prediction of the desert sand concrete is realized, and the safety of the desert sand concrete is further ensured.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Where "first" and "second" are used in the description and claims of embodiments of the invention to distinguish between similar elements and not necessarily for describing a particular sequential or chronological order, it is to be understood that such data may be interchanged where appropriate so that embodiments described herein may be implemented in other sequences than those illustrated or described herein.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a desert sand concrete strength prediction device of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the desert sand concrete strength predicting apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the structure shown in fig. 1 does not constitute a limitation of the desert sand concrete strength prediction apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, the memory 1005, which is a storage medium, may include an operating system, a data determination module, a model training module, a strength prediction module, and a desert sand concrete strength prediction program, wherein the data determination module may be further refined into a data acquisition module and a feature extraction module.
In the desert sand concrete strength predicting apparatus shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the desert sand concrete strength prediction device of the present invention may be disposed in the desert sand concrete strength prediction device, and the desert sand concrete strength prediction device calls the desert sand concrete strength prediction program stored in the memory 1005 through the processor 1001 and executes the desert sand concrete strength prediction method provided by the embodiment of the present invention.
Based on the above hardware structure but not limited to the above hardware structure, the present invention provides a first embodiment of a desert sand concrete strength prediction method. Referring to fig. 2, fig. 2 is a schematic flow chart of a desert sand concrete strength prediction method according to a first embodiment of the present invention.
In this embodiment, the method includes:
step S201, acquiring historical detection data of different types of desert sand concrete; the historical detection data comprises the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions;
in this embodiment, the execution subject is desert sand concrete strength prediction equipment, which can be used to obtain historical detection data of different types of desert sand concrete strength, and then send the data as a training set to a neural network model for strength prediction to train the neural network model. The historical detection data comprise the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions; in addition, water usage, sand rate, air content, and the like may be included.
Step S202, acquiring characteristic text values corresponding to the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; the four-dimensional vector is used for representing the type of the desert sand concrete;
because the characteristics of different types of desert sand concrete are different, in order to improve the accuracy of subsequent prediction, the types of different types of desert sand concrete can be represented by a group of four-dimensional vectors, which can be obtained by presetting a preset relationship, for example, for the case of distributing desert sand in a warehouse, the types of desert sand concrete can be represented by a group of four-dimensional vectors (1,0,0,0) corresponding to the 4 th input unit input 1, the 5 th input unit input 0, the 6 th input unit input 0 and the 7 th input unit input 0, so that the types of desert sand concrete can be represented by a group of simple four-dimensional vectors, the input layer which needs to input complex variables originally becomes simple, the robustness and the stability of a prediction model are improved, and the workload of an entity experiment is greatly reduced.
Step S203, training a neural network model by using the four-dimensional vector and the historical detection data to obtain a trained neural network model;
after the historical detection data of the desert sand concrete strength and the four-dimensional vectors for representing different desert sand concrete types are obtained, the known data information can be used as a training set for training a neural network model.
In an embodiment, referring to fig. 5, fig. 5 is a flowchart illustrating an embodiment of the step S203 in fig. 2 according to the present invention, where the training a neural network model by using the four-dimensional vector and the historical detection data to obtain the trained neural network model includes:
b10, setting initial weight and initial bias of the neural network model;
the weight and the bias are two important parameters of the neural network model, and before the neural network model is trained, the weight, the bias, the learning rate and the number of hidden layers of the deep neural network of the neural network model are initialized.
B20, obtaining an input vector according to the four-dimensional vector and the historical detection data, and training and optimizing the neural network model by taking the strength average value of the desert sand concrete as an output vector to obtain a training result; the input vector comprises the strength mean value of the concrete with different strength grades, the doped desert sand proportion and the four-dimensional vector;
in this embodiment, the strength of the desert sand concrete is predicted according to the strength value of the original concrete and the proportion of the doped desert sand, so that the model is trained by using the strength mean value of the concrete with different strength grades, the proportion of the doped desert sand, the water consumption, the sand rate, the air content, four-dimensional vectors for representing different types of the desert sand concrete, and the like as input vectors and using the strength mean value of the desert sand concrete as an output vector.
B30, if the error between the training result and the preset expected value is less than or equal to a preset error threshold value, stopping training, and obtaining the neural network model which is the trained neural network model;
in this embodiment, the user may set the output expected value and the error threshold according to actual needs, and may set the accuracy to be achieved by training in addition, and when the error between the training result and the preset expected value is less than or equal to the preset error threshold or reaches the required accuracy, the training may be stopped, so as to obtain the required trained neural network model.
B40, if the error between the training result and the preset expected value is larger than the preset error threshold, adjusting the weight and the bias of the neural network model to obtain an updated neural network model, returning to execute the steps of obtaining input vectors according to the four-dimensional vectors and the historical detection data, and training and optimizing the neural network model by taking the strength mean value of the desert sand concrete as an output vector until the error between the training result and the preset expected value is smaller than or equal to the preset error threshold.
After a user sets an output expected value and an error threshold value according to actual needs to start training, if the error between a training result and the preset expected value is larger than the preset error threshold value, the requirement of the neural network model is not met, if the neural network model is used for predicting the strength of the desert sand concrete, the error is possibly overlarge, on the basis, the weight and the offset of the neural network model are required to be adjusted, and then training is continued until the error is smaller than or equal to the preset error threshold value. In fact, the process of adjusting the weights and the bias is the learning and training process of the neural network model.
Step S204, utilizing the trained neural network model to predict the strength of the desert sand concrete to be tested, and obtaining a predicted strength value of the desert sand concrete to be tested;
after the trained neural network model is obtained, as mentioned above, the error between the output value and the actual value of the neural network model is less than or equal to the error threshold preset according to the requirement, that is, within the error allowable range, the strength of the desert sand concrete can be predicted by using the neural network model.
In an embodiment, referring to fig. 6, fig. 6 is a flowchart illustrating an embodiment of the step S204 in fig. 2 of the present invention, where the performing strength prediction on the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested includes:
step C10, acquiring the prediction data of the desert sand concrete to be detected; the prediction data comprise the strength average value of original concrete corresponding to the desert sand concrete to be detected, the desert sand doping proportion and the four-dimensional vector of the desert sand concrete to be detected;
in the embodiment, in order to predict the strength of the desert sand concrete, the strength of the desert sand concrete is predicted according to the strength value of the original concrete, the proportion of the doped desert sand, the corresponding four-dimensional vector and other data, and therefore, the predicted data is obtained first.
And step C20, inputting the prediction data into the trained neural network model to obtain the predicted value of the strength of the desert sand concrete to be tested.
And inputting the obtained prediction data into a trained neural network model, and obtaining the predicted strength value of the desert sand concrete to be tested by the neural network model according to the data and corresponding calculation.
And S205, generating a desert sand concrete strength prediction statistical table according to the predicted value of the strength of the desert sand concrete to be detected and the prediction data.
And (3) counting the obtained data of the predicted desert sand concrete strength value, the concrete strength mean value, the four-dimensional vector, the desert sand doping proportion and the like to generate a desert sand concrete strength prediction statistical table, wherein a user can select a desert sand concrete material meeting the strength requirement by comparing the table, and can further verify the data on the table by equipment such as a testing machine and the like.
The strength of the desert sand concrete is predicted by the neural network model which meets the requirements through training, the complexity of manual operation is greatly reduced, the high-efficiency and accurate strength prediction of the desert sand concrete is realized, and the safety of the desert sand concrete is further ensured.
As an example, referring to fig. 3, fig. 3 is a schematic flow chart before the step of S201 in fig. 2 according to the present invention, where the historical detection data of the desert sand concrete strength is obtained; the historical detection data comprises the strength average values of concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions, and the method further comprises the following steps:
step S301, detecting the strength values of the concrete with different strength grades and obtaining the strength mean value of the concrete with different strength grades according to the detection result;
as described above, in order to train the neural network model by using the historical test data of the desert sand concrete strength, the historical test data is obtained first, and before the desert sand is doped into the concrete, the strength value of the original concrete not doped with the desert sand is detected first.
In an embodiment, referring to fig. 4, fig. 4 is a flowchart illustrating an embodiment of the step S301 in fig. 3 of the present invention, detecting the strength values of the concrete with different strength grades and obtaining the strength average value of the concrete with different strength grades according to the detection result, including:
step A10, detecting the compressive strength of the concrete with different strength grades by using a compression testing machine;
step A20, detecting the tensile strength of the concrete with different strength grades by using a single-shaft testing machine and taking the breaking load as an evaluation index;
step A30, detecting static compression elastic modulus of the concrete with different strength grades by using a single-axis testing machine and load and strain evaluation indexes;
and A40, obtaining the strength average value of the concrete with different strength grades according to the compressive strength, the tensile strength and the static compression elastic modulus.
The compressive strength, the tensile strength and the static compression elastic modulus are important mechanical property indexes which can be used for describing the strength of the desert sand concrete, a user can detect one or more of the indexes according to actual requirements, and the strength average value of the concrete is obtained according to the detection result.
Step S302, adding desert sand with different preset replacement proportions into the concrete with different strength grades to obtain the desert sand concrete;
and step S303, detecting the strength value of the desert sand concrete and obtaining the strength average value of the desert sand concrete according to the detection result.
After the strength values of the concrete with different strength grades are detected, adding the desert sand with a preset replacement proportion into the concrete to obtain the desert sand concrete, recording the strength value of the original concrete corresponding to the desert sand concrete and the added desert sand proportion, then carrying out strength detection on the desert sand concrete, finally obtaining the strength average value of the desert sand concrete, and also recording the strength average value to obtain historical detection data of the desert sand concrete strength.
Based on the same inventive concept, an embodiment of the present invention further provides a desert sand concrete strength prediction apparatus, as shown in fig. 7, including:
the data acquisition module is used for acquiring historical detection data of different types of desert sand concrete; the historical detection data comprises the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions;
the characteristic extraction module is used for acquiring characteristic text values corresponding to the different types of desert sand concrete according to the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; the four-dimensional vector is used for representing the type of the desert sand concrete;
the model training module is used for training a neural network model by utilizing the four-dimensional vector and the historical detection data to obtain a trained neural network model;
and the strength prediction module is used for predicting the strength of the desert sand concrete to be tested by utilizing the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
As an alternative embodiment, the desert sand concrete strength prediction apparatus may further include:
and the parameter setting module is used for setting the initial weight and the initial bias of the neural network model.
As an alternative embodiment, the desert sand concrete strength prediction apparatus may further include:
and the strength statistical module is used for generating a desert sand concrete strength prediction statistical table according to the predicted strength value of the desert sand concrete to be detected and the prediction data.
Furthermore, in an embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and the computer program is executed by a processor to implement the steps of the method in the foregoing first embodiment.
In some embodiments, the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories. The computer may be a variety of computing devices including intelligent terminals and servers.
In some embodiments, executable instructions may be written in any form of programming language (including compiled or interpreted languages), in the form of programs, software modules, scripts or code, and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
By way of example, executable instructions may correspond, but do not necessarily have to correspond, to files in a file system, may be stored in a portion of a file that holds other programs or data, e.g., in one or more scripts in a hypertext Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub-programs, or portions of code).
By way of example, executable instructions may be deployed to be executed on one computing device or on multiple computing devices at one site or distributed across multiple sites and interconnected by a communication network.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method for predicting the strength of desert sand concrete is characterized by comprising the following steps:
acquiring historical detection data of different types of desert sand concrete; the historical detection data comprises the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions;
acquiring characteristic text values corresponding to the different types of desert sand concrete aiming at the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; the four-dimensional vector is used for representing the type of the desert sand concrete;
training a neural network model by using the four-dimensional vector and the historical detection data to obtain a trained neural network model;
and predicting the strength of the desert sand concrete to be tested by using the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
2. The method of claim 1, wherein before obtaining the historical inspection data of the different types of desert sand concrete, the method further comprises:
and detecting the strength values of the concrete with different strength grades and obtaining the strength mean value of the concrete with different strength grades according to the detection result.
3. The method of claim 1, wherein before obtaining the historical inspection data of the different types of desert sand concrete, the method further comprises:
adding desert sand with different preset replacement proportions into the concrete with different strength grades to obtain the desert sand concrete;
and detecting the strength value of the desert sand concrete and obtaining the strength average value of the desert sand concrete according to the detection result.
4. The method according to claim 2, wherein the detecting the strength values of the concrete with different strength grades and obtaining the strength average value of the concrete with different strength grades according to the detection result comprises:
detecting the compressive strength of the concrete with different strength grades by using a pressure tester;
detecting the tensile strength of the concrete with different strength grades by using a uniaxial testing machine and taking the breaking load as an evaluation index;
detecting the static compression elastic modulus of the concrete with different strength grades by using a uniaxial testing machine and load and strain evaluation indexes;
and obtaining the strength average value of the concrete with different strength grades according to the compressive strength, the tensile strength and the static compression elastic modulus.
5. The method of claim 1, wherein the training a neural network model using the four-dimensional vectors and the historical test data to obtain a trained neural network model comprises:
setting initial weights and initial biases of the neural network model;
obtaining an input vector according to the four-dimensional vector and the historical detection data, and training and optimizing the neural network model by taking the strength average value of the desert sand concrete as an output vector to obtain a training result; the input vector comprises the strength mean value of the concrete with different strength grades, the doped desert sand proportion and the four-dimensional vector;
if the error between the training result and the preset expected value is smaller than or equal to a preset error threshold value, stopping training, wherein the obtained neural network model is the trained neural network model;
and if the error between the training result and the preset expected value is larger than the preset error threshold, adjusting the weight and the bias of the neural network model to obtain an updated neural network model, returning to execute the steps of obtaining an input vector according to the four-dimensional vector and the historical detection data, and training and optimizing the neural network model by taking the strength mean value of the desert sand concrete as an output vector until the error between the training result and the preset expected value is smaller than or equal to the preset error threshold.
6. The method as claimed in claim 1, wherein the using the trained neural network model to perform strength prediction on the desert sand concrete to be tested to obtain a predicted strength value of the desert sand concrete to be tested comprises:
acquiring prediction data of the desert sand concrete to be detected; the prediction data comprise the strength average value of original concrete corresponding to the desert sand concrete to be detected, the desert sand doping proportion and the four-dimensional vector of the desert sand concrete to be detected;
and inputting the prediction data into the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
7. The method as claimed in claim 6, wherein after inputting the prediction data into the trained neural network model to obtain the predicted strength value of the sand concrete for the desert under test, the method further comprises:
and generating a desert sand concrete strength prediction statistical table according to the predicted strength value of the desert sand concrete to be detected and the prediction data.
8. A desert sand concrete strength prediction device, characterized in that the device comprises:
the data acquisition module is used for acquiring historical detection data of different types of desert sand concrete; the historical detection data comprises the strength average values of the concrete with different strength grades, the doped desert sand proportion and the strength average value of the desert sand concrete detected after the doping of the desert sand with different proportions;
the characteristic extraction module is used for acquiring characteristic text values corresponding to the different types of desert sand concrete according to the different types of desert sand concrete, and converting the characteristic text values into corresponding four-dimensional vectors according to a preset mapping mode; the four-dimensional vector is used for representing the type of the desert sand concrete;
the model training module is used for training a neural network model by utilizing the four-dimensional vector and the historical detection data to obtain a trained neural network model;
and the strength prediction module is used for predicting the strength of the desert sand concrete to be tested by utilizing the trained neural network model to obtain the predicted strength value of the desert sand concrete to be tested.
9. A desert sand concrete strength prediction apparatus comprising a memory, a processor, and a desert sand concrete strength prediction program stored on the memory and executable on the processor, the desert sand concrete strength prediction program when executed by the processor implementing the steps of the desert sand concrete strength prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a desert sand concrete strength prediction program, which when executed by a processor, implements the steps of the desert sand concrete strength prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111330779.XA CN114242182A (en) | 2021-11-10 | 2021-11-10 | Desert sand concrete strength prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111330779.XA CN114242182A (en) | 2021-11-10 | 2021-11-10 | Desert sand concrete strength prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114242182A true CN114242182A (en) | 2022-03-25 |
Family
ID=80748998
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111330779.XA Pending CN114242182A (en) | 2021-11-10 | 2021-11-10 | Desert sand concrete strength prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114242182A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117074164A (en) * | 2023-06-08 | 2023-11-17 | 广州市盛通建设工程质量检测有限公司 | Dry-hard concrete detection method and system for water conservancy construction site |
-
2021
- 2021-11-10 CN CN202111330779.XA patent/CN114242182A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117074164A (en) * | 2023-06-08 | 2023-11-17 | 广州市盛通建设工程质量检测有限公司 | Dry-hard concrete detection method and system for water conservancy construction site |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108427632B (en) | Automatic test method and device | |
| US10108535B2 (en) | Web application test script generation to test software functionality | |
| US20130117855A1 (en) | Apparatus for automatically inspecting security of applications and method thereof | |
| EP2643753B1 (en) | Method to measure software reuse and corresponding computer program product | |
| CN110704304B (en) | Application program testing method and device, storage medium and server | |
| CN111598879A (en) | Method, system and equipment for evaluating structural fatigue accumulated damage | |
| CN113268403B (en) | Time series analysis and prediction method, device, equipment and storage medium | |
| CN104731698A (en) | Abnormal test case automatic generation processing method and device based on automatic tests | |
| CN114242182A (en) | Desert sand concrete strength prediction method, device, equipment and storage medium | |
| CN105488307A (en) | Evaluation method of slope monitoring and early warning system based on Big Dipper | |
| CN115329326A (en) | Artificial intelligence safety evaluation method and system | |
| Mollineaux et al. | Structural health monitoring of progressive damage | |
| Roubos et al. | Finite element-based reliability assessment of quay walls | |
| CN114242181A (en) | Desert sand concrete strength prediction model training method, device, equipment and medium | |
| CN111813632A (en) | CPU power consumption test method, test device, test equipment and storage medium | |
| Cantagallo et al. | A probability-based approach for the definition of the expected seismic damage evaluated with non-linear time-history analyses | |
| CN111400199A (en) | Software aging detection method and device and computer readable storage medium | |
| CN116136950A (en) | Chip verification method, device, system, electronic equipment and storage medium | |
| CN116089891A (en) | Method and system for diagnosing safety condition of pile foundation structure | |
| CN115544633A (en) | Method, device and equipment for determining reliability grade of slide-resistant pile and readable storage medium | |
| Khokhlov et al. | Data security and quality evaluation framework: Implementation empirical study on android devices | |
| Galvis et al. | Simulation‐based methodology to identify damage indicators and safety thresholds for post‐earthquake evaluation of structures | |
| CN107391367B (en) | Keyword driving test method of deformation monitoring system | |
| CN113515684A (en) | Abnormal data detection method and device | |
| CN111444093A (en) | Method and device for determining quality of project development process and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |