CN116619562A - Concrete preparation mixing device and method thereof - Google Patents
Concrete preparation mixing device and method thereof Download PDFInfo
- Publication number
- CN116619562A CN116619562A CN202310497448.8A CN202310497448A CN116619562A CN 116619562 A CN116619562 A CN 116619562A CN 202310497448 A CN202310497448 A CN 202310497448A CN 116619562 A CN116619562 A CN 116619562A
- Authority
- CN
- China
- Prior art keywords
- amplitude
- vibration
- vibration frequency
- matrix
- classification
- 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.)
- Withdrawn
Links
- 239000004567 concrete Substances 0.000 title claims abstract description 145
- 238000002156 mixing Methods 0.000 title claims abstract description 70
- 238000002360 preparation method Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 69
- 239000000203 mixture Substances 0.000 claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 22
- 239000004568 cement Substances 0.000 claims abstract description 6
- 239000010881 fly ash Substances 0.000 claims abstract description 6
- 239000000843 powder Substances 0.000 claims abstract description 6
- 229910021487 silica fume Inorganic materials 0.000 claims abstract description 6
- 239000002893 slag Substances 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 164
- 239000011159 matrix material Substances 0.000 claims description 136
- 238000012544 monitoring process Methods 0.000 claims description 71
- 230000000694 effects Effects 0.000 claims description 57
- 238000013527 convolutional neural network Methods 0.000 claims description 45
- 230000003287 optical effect Effects 0.000 claims description 40
- 230000004043 responsiveness Effects 0.000 claims description 32
- 230000003247 decreasing effect Effects 0.000 claims description 20
- 238000005457 optimization Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 9
- 238000011176 pooling Methods 0.000 claims description 9
- 238000012546 transfer Methods 0.000 claims description 8
- 230000002708 enhancing effect Effects 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 description 22
- 238000009826 distribution Methods 0.000 description 15
- 230000006870 function Effects 0.000 description 7
- 230000004044 response Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000006073 displacement reaction Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 238000009415 formwork Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 230000000670 limiting effect Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B28—WORKING CEMENT, CLAY, OR STONE
- B28C—PREPARING CLAY; PRODUCING MIXTURES CONTAINING CLAY OR CEMENTITIOUS MATERIAL, e.g. PLASTER
- B28C5/00—Apparatus or methods for producing mixtures of cement with other substances, e.g. slurries, mortars, porous or fibrous compositions
- B28C5/003—Methods for mixing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/50—Reuse, recycling or recovery technologies
- Y02W30/91—Use of waste materials as fillers for mortars or concrete
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Computational Linguistics (AREA)
- Structural Engineering (AREA)
- Mechanical Engineering (AREA)
- Image Processing (AREA)
Abstract
A concrete preparation mixing apparatus and a method thereof are disclosed. The method comprises the following steps: mixing cement, fly ash, slag powder and silica fume to obtain a cementing material mixture; mixing the fine aggregate and the coarse aggregate to obtain an aggregate mixture; adding the cementing material mixture and the aggregate mixture into a concrete mixer for processing to obtain a concrete mixture; and pouring the concrete mixture into a template, and vibrating and curing to obtain the concrete. Thus, a concrete excellent in performance can be obtained.
Description
Technical Field
The application relates to the field of intelligent preparation, and more particularly relates to a concrete preparation mixing device and a method thereof.
Background
Concrete is a commonly used building material, and has high strength, good durability, convenient construction and the like, so that the concrete is widely applied to modern buildings. The performance of concrete is affected by the formulation of concrete on one hand and the preparation process of concrete on the other hand, which are two existing technical routes for optimizing the performance of concrete.
Optimizing the performance of concrete from a manufacturing process perspective is more deterministic and operable than optimizing the performance of concrete from a formulation perspective.
Thus, an optimized preparation scheme for concrete is desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a concrete preparation mixing device and a method thereof. The method comprises the following steps: mixing cement, fly ash, slag powder and silica fume to obtain a cementing material mixture; mixing the fine aggregate and the coarse aggregate to obtain an aggregate mixture; adding the cementing material mixture and the aggregate mixture into a concrete mixer for processing to obtain a concrete mixture; and pouring the concrete mixture into a template, and vibrating and curing to obtain the concrete. Thus, a concrete excellent in performance can be obtained.
According to one aspect of the present application, there is provided a concrete preparation mixing method, comprising:
mixing cement, fly ash, slag powder and silica fume to obtain a cementing material mixture;
mixing the fine aggregate and the coarse aggregate to obtain an aggregate mixture;
Adding the cementing material mixture and the aggregate mixture into a concrete mixer for processing to obtain a concrete mixture; and
pouring the concrete mixture into a template, and vibrating and curing to obtain the concrete.
In the above concrete preparation mixing method, pouring the concrete mixture into a template, and vibrating and curing to obtain concrete, comprising:
acquiring vibration monitoring video of a preset time period acquired by a camera;
acquiring vibration frequency values and amplitude values of a plurality of preset time points in the preset time period;
after arranging the vibration frequency values and the amplitude values of the plurality of preset time points into vibration frequency input vectors and amplitude input vectors according to time dimensions, carrying out association coding on the vibration frequency input vectors and the amplitude input vectors so as to obtain a vibration frequency-amplitude association matrix;
the vibration frequency-amplitude correlation matrix is passed through a convolutional neural network model serving as a filter to obtain a vibration frequency-amplitude correlation eigenvector;
extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames;
The sequence of the optical flow images passes through a time flow characteristic extractor based on a three-dimensional convolutional neural network model to obtain a time flow characteristic vector with a vibration effect;
calculating the responsiveness estimation of the vibration effect time flow characteristic vector relative to the vibration frequency-amplitude correlation characteristic vector to obtain a classification characteristic matrix;
regularization enhancement is carried out on the classification feature matrix to obtain an optimized classification feature matrix; and
and passing the optimized classification characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point is increased or decreased.
In the concrete preparation mixing method, performing association coding on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix, wherein the method comprises the following steps:
performing association coding on the vibration frequency input vector and the amplitude input vector by using the following coding formula to obtain the vibration frequency-amplitude association matrix;
wherein, the coding formula is:
wherein V is 1 Representing the vibration frequency input vector,a transpose vector representing the vibration frequency input vector, V 2 Representing the amplitude input vector, M a Representing the vibration frequency-amplitude correlation matrix, < >>Representing matrix multiplication.
In the above concrete preparation mixing method, passing the vibration frequency-amplitude correlation matrix through a convolutional neural network model as a filter to obtain a vibration frequency-amplitude correlation eigenvector, comprising:
each layer of the convolutional neural network model used as the filter performs the following steps on input data in forward transfer of the layer:
carrying out convolution processing on the input data to obtain a convolution characteristic diagram;
carrying out mean pooling treatment based on a feature matrix on the convolution feature map to obtain a pooled feature map; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
wherein the output of the last layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation eigenvector, and the input of the first layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation matrix.
In the above concrete preparation mixing method, extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames, includes: the plurality of vibration monitoring key frames are extracted from the vibration monitoring video at a predetermined sampling frequency.
In the above concrete preparation mixing method, the step of passing the sequence of optical flow images through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a vibration effect time flow feature vector comprises the following steps:
using each layer of the three-dimensional convolution neural network model-based time flow feature extractor to respectively perform convolution processing, pooling processing and nonlinear activation processing based on three-dimensional convolution kernels on the sequence of the optical flow images in forward transfer of the layers so as to take the last layer output of the three-dimensional convolution neural network model-based time flow feature extractor as a feature map; and
and performing dimension reduction on the feature map to obtain the vibration effect time flow feature vector.
In the above concrete preparation mixing method, calculating a responsiveness estimate of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector to obtain a classification eigenvector comprises:
calculating the responsiveness estimation of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector by the following responsiveness formula to obtain the classification eigenvector;
wherein, the responsiveness formula is:
Wherein V is a Representing the time flow characteristic vector, V of the vibration effect b Representing the vibration frequency-amplitude correlation eigenvector, M c Representing the matrix of the classification characteristic,representing matrix multiplication.
In the above concrete preparation mixing method, the regularization enhancement is performed on the classification feature matrix to obtain an optimized classification feature matrix, including:
the classification feature matrix is regularly enhanced according to the following optimization formula to obtain the optimized classification feature matrix;
wherein, the optimization formula is:
m i ′ ,j =(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein M represents the classification feature matrix, mu and sigma are the mean and standard deviation of feature value sets at each position in the classification feature matrix, M i,j Is the eigenvalue, m, of the (i, j) th position of the classification eigenvalue matrix i ′ ,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
In the above concrete preparation mixing method, the optimizing classification feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate that the amplitude value of the current time point should be increased or decreased, and the method includes:
expanding the optimized classification feature matrix into an optimized classification feature vector according to a row vector or a column vector;
performing full-connection coding on the optimized classification feature vector by using a plurality of full-connection layers of the classifier to obtain a coded optimized classification feature vector; and
And the coding optimization classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present application, there is provided a concrete preparation mixing apparatus comprising:
the video acquisition module is used for acquiring vibration monitoring videos in a preset time period acquired by the camera;
the data acquisition module is used for acquiring vibration frequency values and amplitude values of a plurality of preset time points in the preset time period;
the association coding module is used for performing association coding on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix after arranging the vibration frequency values and the amplitude values of the plurality of preset time points into the vibration frequency input vector and the amplitude input vector according to the time dimension;
the first feature extraction module is used for enabling the vibration frequency-amplitude correlation matrix to pass through a convolutional neural network model serving as a filter so as to obtain a vibration frequency-amplitude correlation feature vector;
the key frame extraction module is used for extracting a plurality of vibration monitoring key frames from the vibration monitoring video and extracting sequences of optical flow images from the vibration monitoring key frames;
The second feature extraction module is used for enabling the sequence of the optical flow images to pass through a time flow feature extractor based on a three-dimensional convolutional neural network model so as to obtain a time flow feature vector with a vibration effect;
the responsiveness estimation module is used for calculating responsiveness estimation of the vibration effect time flow characteristic vector relative to the vibration frequency-amplitude correlation characteristic vector so as to obtain a classification characteristic matrix;
the regularization enhancement module is used for regularizing and enhancing the classification feature matrix to obtain an optimized classification feature matrix; and
and the amplitude control result generation module is used for passing the optimized classification characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point should be increased or decreased.
Compared with the prior art, the concrete preparation mixing device and the method thereof provided by the application comprise the following steps: mixing cement, fly ash, slag powder and silica fume to obtain a cementing material mixture; mixing the fine aggregate and the coarse aggregate to obtain an aggregate mixture; adding the cementing material mixture and the aggregate mixture into a concrete mixer for processing to obtain a concrete mixture; and pouring the concrete mixture into a template, and vibrating and curing to obtain the concrete. Thus, a concrete excellent in performance can be obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort to a person of ordinary skill in the art. The following drawings are not intended to be drawn to scale, emphasis instead being placed upon illustrating the principles of the application.
Fig. 1 is a flowchart of a concrete preparation mixing method according to an embodiment of the present application.
Fig. 2 is an application scenario diagram of substep S140 of the concrete preparation mixing method according to an embodiment of the present application.
Fig. 3 is a flowchart of sub-step S140 of the concrete preparation mixing method according to an embodiment of the present application.
Fig. 4 is a schematic diagram of the architecture of substep S140 of the concrete preparation mixing method according to an embodiment of the present application.
Fig. 5 is a flowchart of sub-step S146 of the concrete preparation mixing method according to an embodiment of the present application.
Fig. 6 is a flowchart of sub-step S149 of the concrete preparation mixing method according to an embodiment of the present application.
Fig. 7 is a block diagram of a concrete preparation mixing apparatus according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are also within the scope of the application.
As used in the specification and in the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
A flowchart is used in the present application to describe the operations performed by a system according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Based on the above technical needs, the present application provides a concrete preparation mixing method, as shown in fig. 1, comprising the steps of: s110, mixing cement, fly ash, slag powder and silica fume to obtain a cementing material mixture; s120, mixing the fine aggregate and the coarse aggregate to obtain an aggregate mixture; s130, adding the cementing material mixture and the aggregate mixture into a concrete mixer for processing to obtain a concrete mixture; and S140, pouring the concrete mixture into a template, and vibrating and curing to obtain concrete.
In the implementation of the above preparation process, it was found that in the step of "pouring the concrete mixture into a form and vibrating and curing to obtain concrete", the mode of vibration has an influence on the performance of the concrete. Specifically, if the vibration frequency is too high, air inside the concrete cannot be effectively discharged; if the vibration frequency is too low, the aggregate in the concrete cannot be fully deposited, so that the quality of the concrete is affected, and if the vibration amplitude is too large, the aggregate in the concrete is separated, and if the vibration amplitude is too small, the air bubbles in the concrete cannot be effectively removed. Therefore, in the technical solution of the present application, if the vibration mode can be adaptively controlled based on the state of the concrete mix, it is apparent that the properties of the finally produced concrete can be optimized.
Specifically, first, a vibration monitoring video of a predetermined period acquired by a camera is acquired. In the concrete preparation process, vibration is an important process, and the effect of the vibration is to remove air in the concrete in the formwork through mechanical vibration, so that the compactness and strength of the concrete are improved. Therefore, it is important to monitor and adjust the vibrating process in real time. The vibration monitoring video of the preset time period acquired by the camera is acquired, so that the real-time monitoring and recording of the vibration process can be realized. The state of the concrete mixture can be obtained by analyzing the image information in the video, and a plurality of parameters such as the vibration effect, the aggregate distribution condition and the like can be monitored so as to analyze the preparation quality of the concrete and perform optimization adjustment.
Meanwhile, vibration frequency values and vibration amplitude values of a plurality of preset time points in the preset time period are obtained.
It should be understood that vibration is an important process for removing air from concrete in a form by mechanical vibration during the preparation of concrete, thereby improving the compactness and strength of the concrete. The vibration frequency and the vibration amplitude in the vibration process are important factors influencing the preparation quality of the concrete, and different values of the vibration frequency and the vibration amplitude can generate different vibration effects, so that the compactness and the strength of the concrete are influenced. Therefore, in the technical scheme of the application, the vibration frequency values and the vibration amplitude values of a plurality of preset time points in the preset time period are obtained.
And then, arranging the vibration frequency values and the amplitude values of the plurality of preset time points into a vibration frequency input vector and an amplitude input vector according to the time dimension, and carrying out association coding on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix. As previously described, the frequency and amplitude of vibration of the vibrator are important factors affecting the compactness and strength of the concrete during the preparation of the concrete. By collecting vibration frequency and amplitude data at a plurality of predetermined time points within a predetermined period of time and arranging them in a time dimension into a vibration frequency input vector and an amplitude input vector, a time-series vector representation of the vibration frequency and a time-series vector representation of the amplitude can be obtained. Further, the vibration frequency input vector and the amplitude input vector are associated and encoded to establish an association between the vibration frequency and the amplitude, and the association between the vibration frequency and the amplitude is analyzed.
The vibration frequency-amplitude correlation matrix is then passed through a convolutional neural network model as a filter to obtain a vibration frequency-amplitude correlation eigenvector. That is, in the technical scheme of the present application, the characteristic filtering based on the convolution kernel is performed on the vibration frequency-amplitude correlation matrix using a convolution neural network model having excellent performance in the field of local characteristic extraction to capture correlation pattern characteristics of vibration frequency-amplitude in the local time domain and correlation pattern characteristics based on channels.
And simultaneously extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the vibration monitoring key frames. Since there are a lot of vibrations and deformations in the vibrating process, it is very important to monitor and adjust the vibrating process in real time. By extracting a plurality of vibration monitoring key frames from the vibration monitoring video and extracting an optical flow image sequence from the vibration monitoring key frames, the deformation condition and the vibration effect of concrete in the vibration process can be more comprehensively known. Since the optical flow method can be used to analyze the pixel displacement between successive frames, the deformation of different areas during vibration can be identified.
And then, the sequence of the optical flow images is passed through a time flow characteristic extractor based on a three-dimensional convolutional neural network model to obtain a vibration effect time flow characteristic vector. That is, through the time flow characteristic extractor based on the three-dimensional convolutional neural network model, pixel displacement information between continuous frames in the optical flow image sequence can be effectively utilized to extract time flow characteristic information of vibration effect, including characteristics of deformation condition, vibration range and the like of concrete at different moments, and the time flow characteristic information can comprehensively reflect the change of concrete state in the vibration process.
After the vibration effect time flow characteristic vector and the vibration frequency-amplitude related characteristic vector are obtained, the vibration mode characteristic is due in consideration of the effect of the vibration effect characteristic, and therefore, the vibration effect time flow characteristic vector and the vibration frequency-amplitude related characteristic vector have a logical association in a high-dimensional characteristic space. Based on the above, in the technical scheme of the application, the responsiveness estimation of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector is calculated to obtain a classification eigenvector. That is, the logical implicit association of the two in the high-dimensional feature space is represented by a responsive logical association, namely, in the technical scheme of the application, the responsiveness refers to the association degree between the vibration effect time flow feature vector and the vibration frequency-amplitude association feature vector. It should be appreciated that there is a complex nonlinear relationship between the vibration effect time flow eigenvector and the vibration frequency-amplitude correlation eigenvector, and that by calculating the responsiveness estimate, the degree of correlation between them can be quantitatively assessed, and a comprehensive classification eigenvector can be established therefrom.
Finally, the classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point should be increased or decreased. That is, a classifier is used to determine class probability tags to which the classification feature matrix belongs, the class probability tags including that the amplitude value of the current time point should be increased (first class probability tags) and that the amplitude value of the current time point should be decreased (second class probability tags). It should be noted that the class probability tag is a vibration mode control policy tag, and thus, after the classification result is obtained, adaptive control of the amplitude can be achieved based on the classification result. In this way, the vibration mode is adaptively controlled based on the state of the concrete mix to optimize the properties of the finally produced concrete.
In particular, in the technical scheme of the application, when the response estimation of the vibration effect time flow feature vector relative to the vibration frequency-amplitude correlation feature vector is calculated to obtain the classification feature matrix, considering that the vibration effect time flow feature vector expresses time-sequence correlation image semantic distribution based on the optical flow image of the vibration monitoring key frame, and the vibration frequency-amplitude correlation feature vector expresses filter channel distribution of cross-time-sequence correlation distribution of vibration frequency values and vibration amplitude values, the response estimation between the vibration effect time flow feature vector and the vibration frequency-amplitude correlation feature vector has position-by-position deviation in terms of time-sequence correlation and channel correlation angles of image type data and parameter type data type differences of source data or feature distribution, so that the regularization degree of the integral feature distribution of the classification feature matrix in the response fusion feature space is low. In addition, due to the random characteristic introduced by Gaussian discretization in the responsiveness estimation process based on the Gaussian density map, the regularization degree of the overall feature distribution of the classification feature matrix can be further reduced, so that the classification accuracy of the classification feature matrix is affected.
Based on this, the applicant of the present application performs secondary regularization on the gaussian probability density parameter of the manifold curved surface, for example denoted as M, specifically expressed as:
m′ i,j =(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein μ and σ are the eigenvalue set m i,j E means of MAnd standard deviation, and m' i,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix M'.
Specifically, in order to solve the problem of irregular distribution of high-dimensional feature distribution of the feature set of the classification feature matrix M in a high-dimensional feature space with fused responsiveness, secondary regularization of feature values is performed on each feature value of the classification feature matrix M according to likelihood of gaussian probability density parameters of class probability distribution of a classifier, so that equidistant distribution in a parameter space of gaussian probability density parameters based on target class probability is subjected to smooth constraint of feature values, and regularization reformation of an original probability density likelihood function expressed by a manifold curved surface of the high-dimensional feature in the parameter space is obtained, so that the regularity of the feature distribution of the optimized classification feature matrix M 'is improved, and the classification accuracy of the optimized classification feature matrix M' passing through the classifier is improved.
Fig. 2 is an application scenario diagram of substep S140 of the concrete preparation mixing method according to an embodiment of the present application. As shown in fig. 2, in this application scenario, first, a vibration monitoring video (e.g., D1 shown in fig. 2) of a predetermined period of time acquired by a camera (e.g., C shown in fig. 2) is acquired, and vibration frequency values (e.g., D2 shown in fig. 2) and amplitude values (e.g., D3 shown in fig. 2) of a plurality of predetermined points of time within the predetermined period of time are acquired, and then, the vibration monitoring video and the vibration frequency values and the amplitude values of the plurality of predetermined points of time are input to a server (e.g., S shown in fig. 2) where a concrete preparation mixing algorithm is deployed, wherein the server is able to process the vibration frequency values and the amplitude values of the vibration monitoring video and the plurality of predetermined points of time using the concrete preparation mixing algorithm to obtain a classification result indicating that the amplitude values of a current point of time should be increased or decreased.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Fig. 3 is a flowchart of sub-step S140 of the concrete preparation mixing method according to an embodiment of the present application. As shown in fig. 3, the concrete mixture is poured into a form, and vibrated and cured to obtain concrete, comprising the steps of: s141, acquiring vibration monitoring videos of a preset time period acquired by a camera; s142, obtaining vibration frequency values and amplitude values of a plurality of preset time points in the preset time period; s143, arranging the vibration frequency values and the amplitude values of the plurality of preset time points into a vibration frequency input vector and an amplitude input vector according to a time dimension respectively, and performing association coding on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix; s144, the vibration frequency-amplitude correlation matrix is passed through a convolutional neural network model serving as a filter to obtain a vibration frequency-amplitude correlation eigenvector; s145, extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames; s146, passing the sequence of the optical flow images through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a time flow feature vector with a vibration effect; s147, calculating the response estimation of the vibration effect time flow characteristic vector relative to the vibration frequency-amplitude correlation characteristic vector to obtain a classification characteristic matrix; s148, regularization enhancement is carried out on the classification characteristic matrix to obtain an optimized classification characteristic matrix; and S149, passing the optimized classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point is increased or decreased.
Fig. 4 is a schematic diagram of the architecture of substep S140 of the concrete preparation mixing method according to an embodiment of the present application. As shown in fig. 4, in the network architecture, first, a vibration monitoring video of a predetermined period acquired by a camera is acquired; next, obtaining vibration frequency values and amplitude values of a plurality of preset time points in the preset time period; then, arranging the vibration frequency values and the amplitude values of the plurality of preset time points into vibration frequency input vectors and amplitude input vectors according to a time dimension respectively, and performing association coding on the vibration frequency input vectors and the amplitude input vectors to obtain a vibration frequency-amplitude association matrix; then, the vibration frequency-amplitude correlation matrix is passed through a convolutional neural network model serving as a filter to obtain a vibration frequency-amplitude correlation eigenvector; then, extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames; then, the sequence of the optical flow images passes through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a time flow feature vector with a vibration effect; then, calculating the response estimation of the vibration effect time flow characteristic vector relative to the vibration frequency-amplitude correlation characteristic vector to obtain a classification characteristic matrix; then, regularization enhancement is carried out on the classification feature matrix so as to obtain an optimized classification feature matrix; finally, the optimized classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point should be increased or decreased.
More specifically, in step S141, a vibration monitoring video of a predetermined period of time acquired by a camera is acquired. In the concrete preparation process, vibration is an important process, and the effect of the vibration is to remove air in the concrete in the formwork through mechanical vibration, so that the compactness and strength of the concrete are improved. Therefore, it is important to monitor and adjust the vibrating process in real time. The vibration monitoring video of the preset time period acquired by the camera is acquired, so that the real-time monitoring and recording of the vibration process can be realized. The state of the concrete mixture can be obtained by analyzing the image information in the video, and a plurality of parameters such as the vibration effect, the aggregate distribution condition and the like can be monitored so as to analyze the preparation quality of the concrete and perform optimization adjustment.
More specifically, in step S142, vibration frequency values and amplitude values at a plurality of predetermined time points within the predetermined period of time are acquired. In the concrete preparation process, vibration is an important process for removing air in a formwork by mechanical vibration, so that the compactness and strength of the concrete are improved. The vibration frequency and the vibration amplitude in the vibration process are important factors influencing the preparation quality of the concrete, and different values of the vibration frequency and the vibration amplitude can generate different vibration effects, so that the compactness and the strength of the concrete are influenced.
More specifically, in step S143, after the vibration frequency values and the amplitude values at the plurality of predetermined time points are arranged into a vibration frequency input vector and an amplitude input vector in the time dimension, respectively, the vibration frequency input vector and the amplitude input vector are subjected to association encoding to obtain a vibration frequency-amplitude association matrix. In the preparation of concrete, the vibration frequency and amplitude of vibration are important factors affecting the compactness and strength of the concrete. By collecting vibration frequency and amplitude data at a plurality of predetermined time points within a predetermined period of time and arranging them in a time dimension into a vibration frequency input vector and an amplitude input vector, a time-series vector representation of the vibration frequency and a time-series vector representation of the amplitude can be obtained. Further, the vibration frequency input vector and the amplitude input vector are associated and encoded to establish an association between the vibration frequency and the amplitude, and the association between the vibration frequency and the amplitude is analyzed.
Accordingly, in one specific example, the association encoding of the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix includes: performing association coding on the vibration frequency input vector and the amplitude input vector by using the following coding formula to obtain the vibration frequency-amplitude association matrix; wherein, the coding formula is:
Wherein V is 1 Representing the vibration frequency input vector,a transpose vector representing the vibration frequency input vector, V 2 Representing the amplitude input vector, M a Representing the vibration frequency-amplitude correlation matrix, < >>Representing matrix multiplication.
More specifically, in step S144, the vibration frequency-amplitude correlation matrix is passed through a convolutional neural network model as a filter to obtain a vibration frequency-amplitude correlation eigenvector. That is, in the technical scheme of the present application, the characteristic filtering based on the convolution kernel is performed on the vibration frequency-amplitude correlation matrix using a convolution neural network model having excellent performance in the field of local characteristic extraction to capture correlation pattern characteristics of vibration frequency-amplitude in the local time domain and correlation pattern characteristics based on channels.
It should be appreciated that convolutional neural network (Convolutional Neural Network, CNN) is an artificial neural network and has wide application in the fields of image recognition and the like. The convolutional neural network may include an input layer, a hidden layer, and an output layer, where the hidden layer may include a convolutional layer, a pooling layer, an activation layer, a full connection layer, etc., where the previous layer performs a corresponding operation according to input data, outputs an operation result to the next layer, and obtains a final result after the input initial data is subjected to a multi-layer operation.
Accordingly, in one specific example, passing the vibration frequency-amplitude correlation matrix through a convolutional neural network model as a filter to obtain a vibration frequency-amplitude correlation eigenvector comprises: each layer of the convolutional neural network model used as the filter performs the following steps on input data in forward transfer of the layer: carrying out convolution processing on the input data to obtain a convolution characteristic diagram; carrying out mean pooling treatment based on a feature matrix on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; wherein the output of the last layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation eigenvector, and the input of the first layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation matrix.
More specifically, in step S145, a plurality of vibration monitoring key frames are extracted from the vibration monitoring video, and a sequence of optical flow images is extracted from the plurality of vibration monitoring key frames. Since there are a lot of vibrations and deformations in the vibrating process, it is very important to monitor and adjust the vibrating process in real time. By extracting a plurality of vibration monitoring key frames from the vibration monitoring video and extracting an optical flow image sequence from the vibration monitoring key frames, the deformation condition and the vibration effect of concrete in the vibration process can be more comprehensively known. Since the optical flow method can be used to analyze the pixel displacement between successive frames, the deformation of different areas during vibration can be identified.
Accordingly, in one specific example, extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames, includes: the plurality of vibration monitoring key frames are extracted from the vibration monitoring video at a predetermined sampling frequency.
More specifically, in step S146, the sequence of optical flow images is passed through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a vibration effect time flow feature vector. That is, through the time flow characteristic extractor based on the three-dimensional convolutional neural network model, pixel displacement information between continuous frames in the optical flow image sequence can be effectively utilized to extract time flow characteristic information of vibration effect, including characteristics of deformation condition, vibration range and the like of concrete at different moments, and the time flow characteristic information can comprehensively reflect the change of concrete state in the vibration process.
Accordingly, in a specific example, as shown in fig. 5, passing the sequence of optical flow images through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a vibration effect time flow feature vector, including: s1461, performing convolution processing, pooling processing and nonlinear activation processing based on a three-dimensional convolution kernel on the sequence of the optical flow images in forward transfer of layers by using each layer of the three-dimensional convolution neural network model based time flow feature extractor to output a feature map by the last layer of the three-dimensional convolution neural network model based time flow feature extractor; and S1462, performing dimension reduction on the feature map to obtain the vibration effect time flow feature vector.
More specifically, in step S147, a responsiveness estimate of the vibration effect time flow feature vector with respect to the vibration frequency-amplitude correlation feature vector is calculated to obtain a classification feature matrix. The logical implicit association of the two in the high-dimensional feature space is represented by a responsive logical association, namely, in the technical scheme of the application, the responsiveness refers to the association degree between the vibration effect time flow feature vector and the vibration frequency-amplitude association feature vector.
It should be appreciated that there is a complex nonlinear relationship between the vibration effect time flow eigenvector and the vibration frequency-amplitude correlation eigenvector, and that by calculating the responsiveness estimate, the degree of correlation between them can be quantitatively assessed, and a comprehensive classification eigenvector can be established therefrom.
Accordingly, in one specific example, calculating a responsiveness estimate of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude associated eigenvector to obtain a classification eigenvector comprises: calculating the responsiveness estimation of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector by the following responsiveness formula to obtain the classification eigenvector; wherein, the responsiveness formula is:
Wherein V is a Representing the time flow characteristic vector, V of the vibration effect b Representing the vibration frequency-amplitude correlation eigenvector, M c Representing the matrix of the classification characteristic,representing matrix multiplication.
More specifically, in step S148, the classification feature matrix is regularized and enhanced to obtain an optimized classification feature matrix.
Accordingly, in a specific example, regularization enhancement is performed on the classification feature matrix to obtain an optimized classification feature matrix, including: the classification feature matrix is regularly enhanced according to the following optimization formula to obtain the optimized classification feature matrix; wherein, the optimization formula is:
m i ′ ,j =(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein M represents the classification feature matrix, mu and sigma are the mean and standard deviation of feature value sets at each position in the classification feature matrix, M i,j Is the eigenvalue, m, of the (i, j) th position of the classification eigenvalue matrix i ′ ,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
More specifically, in step S149, the optimized classification feature matrix is passed through a classifier to obtain a classification result indicating whether the amplitude value of the current time point should be increased or decreased. In this way, the vibration mode is adaptively controlled based on the state of the concrete mix to optimize the properties of the finally produced concrete.
That is, in the technical solution of the present application, the labels of the classifier include that the amplitude value of the current time point should be increased (first label) and that the amplitude value of the current time point should be decreased (second label), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include the concept of artificial setting, and in fact, during the training process, the computer model does not have the concept of "the amplitude value of the current time point should be increased or should be decreased", which is only two kinds of classification tags, and the probability that the output feature is under the two kinds of classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result that the amplitude value of the current time point should be increased or decreased is actually converted into a classification probability distribution conforming to the natural rule by classifying the tag, and the physical meaning of the natural probability distribution of the tag is essentially used instead of the language text meaning that the amplitude value of the current time point should be increased or decreased. It should be understood that, in the technical solution of the present application, the classification label of the classifier is a detection evaluation label that the amplitude value of the current time point should be increased or decreased, so that after the classification result is obtained, the amplitude value of the current time point may be increased or decreased based on the classification result.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
Accordingly, in one specific example, as shown in fig. 6, the optimizing the classification feature matrix is passed through a classifier to obtain a classification result, where the classification result is used to indicate that the amplitude value of the current time point should be increased or should be decreased, and includes:
s1491, expanding the optimized classification feature matrix into an optimized classification feature vector according to a row vector or a column vector; s1492, performing full-connection coding on the optimized classification feature vector by using a plurality of full-connection layers of the classifier to obtain a coded optimized classification feature vector; and S1493, passing the coding optimization classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
In summary, in the concrete preparation mixing method according to the embodiment of the application, the concrete mixture is poured into a template, and vibration and maintenance are performed to obtain concrete, which firstly obtains vibration monitoring videos of a preset time period collected by a camera, and vibration frequency values and amplitude values of a plurality of preset time points in the preset time period, then, the vibration frequency values and the amplitude values of the preset time points are respectively arranged according to a time dimension to form a vibration frequency input vector and an amplitude input vector, then, association coding is performed on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix, then, the vibration frequency-amplitude association matrix is processed through a convolutional neural network model serving as a filter to obtain a vibration frequency-amplitude association feature vector, then, a plurality of vibration monitoring key frames are extracted from the vibration monitoring videos, and sequences of optical flow images are extracted from the plurality of vibration monitoring key frames, then, the sequences of the optical flow images are processed through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a vibration frequency input vector and an amplitude input vector, the time flow feature vector is calculated, and then, the time flow feature is reduced or the time flow feature value is processed through a convolutional neural network model to obtain a feature value, and finally, the feature value is classified and the feature value is improved.
Fig. 7 is a block diagram of a concrete preparation mixing apparatus 100 according to an embodiment of the present application. As shown in fig. 7, the concrete preparing and mixing apparatus 100 according to an embodiment of the present application includes: a video acquisition module 110, configured to acquire a vibration monitoring video of a predetermined period acquired by a camera; a data acquisition module 120, configured to acquire vibration frequency values and amplitude values at a plurality of predetermined time points within the predetermined time period; the association encoding module 130 is configured to arrange the vibration frequency values and the amplitude values at the plurality of predetermined time points into a vibration frequency input vector and an amplitude input vector according to a time dimension, and then perform association encoding on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix; a first feature extraction module 140, configured to pass the vibration frequency-amplitude correlation matrix through a convolutional neural network model serving as a filter to obtain a vibration frequency-amplitude correlation feature vector; a key frame extracting module 150, configured to extract a plurality of vibration monitoring key frames from the vibration monitoring video, and extract a sequence of optical flow images from the plurality of vibration monitoring key frames; a second feature extraction module 160, configured to pass the sequence of optical flow images through a time flow feature extractor based on a three-dimensional convolutional neural network model to obtain a time flow feature vector of a vibration effect; a responsiveness estimation module 170, configured to calculate a responsiveness estimate of the vibration effect time flow feature vector relative to the vibration frequency-amplitude correlation feature vector to obtain a classification feature matrix; the regularization enhancing module 180 is configured to perform regularization enhancement on the classification feature matrix to obtain an optimized classification feature matrix; and an amplitude control result generating module 190, configured to pass the optimized classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate that the amplitude value of the current time point should be increased or decreased.
In one example, in the concrete preparation mixing apparatus 100, the association coding module 130 is configured to: performing association coding on the vibration frequency input vector and the amplitude input vector by using the following coding formula to obtain the vibration frequency-amplitude association matrix; wherein, the coding formula is:
wherein V is 1 Representing the vibration frequency input vector,a transpose vector representing the vibration frequency input vector, V 2 Representing the amplitude input vector, M a Representing the vibration frequency-amplitude correlation matrix, < >>Representing matrix multiplication.
In one example, in the concrete preparation mixing apparatus 100, the first feature extraction module 140 is configured to: each layer of the convolutional neural network model used as the filter performs the following steps on input data in forward transfer of the layer: carrying out convolution processing on the input data to obtain a convolution characteristic diagram; carrying out mean pooling treatment based on a feature matrix on the convolution feature map to obtain a pooled feature map; performing nonlinear activation on the pooled feature map to obtain an activated feature map; wherein the output of the last layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation eigenvector, and the input of the first layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation matrix.
In one example, in the concrete preparation mixing apparatus 100, the key frame extraction module 150 is configured to: the plurality of vibration monitoring key frames are extracted from the vibration monitoring video at a predetermined sampling frequency.
In one example, in the concrete preparation mixing apparatus 100, the second feature extraction module 160 is configured to: using each layer of the three-dimensional convolution neural network model-based time flow feature extractor to respectively perform convolution processing, pooling processing and nonlinear activation processing based on three-dimensional convolution kernels on the sequence of the optical flow images in forward transfer of the layers so as to take the last layer output of the three-dimensional convolution neural network model-based time flow feature extractor as a feature map; and dimension reduction is carried out on the feature map so as to obtain the vibration effect time flow feature vector.
In one example, in the concrete preparation mixing apparatus 100, the responsiveness estimation module 170 is configured to: calculating the responsiveness estimation of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector by the following responsiveness formula to obtain the classification eigenvector; wherein, the responsiveness formula is:
Wherein V is a Representing the time flow characteristic vector, V of the vibration effect b Representing the vibration frequency-amplitude correlation eigenvector, M c Representing the matrix of the classification characteristic,representing matrix multiplication.
In one example, in the concrete preparation mixing apparatus 100, the regularization enhancing module 180 is configured to: the classification feature matrix is regularly enhanced according to the following optimization formula to obtain the optimized classification feature matrix; wherein, the optimization formula is:
m i i ,j =(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein M represents the classification feature matrix, mu and sigma are the mean and standard deviation of feature value sets at each position in the classification feature matrix, M i,j Is the eigenvalue, m, of the (i, j) th position of the classification eigenvalue matrix i ′ ,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
In one example, in the concrete preparation mixing apparatus 100, the amplitude control result generating module 190 is configured to: expanding the optimized classification feature matrix into an optimized classification feature vector according to a row vector or a column vector; performing full-connection coding on the optimized classification feature vector by using a plurality of full-connection layers of the classifier to obtain a coded optimized classification feature vector; and passing the coding optimization classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described concrete preparation mixing apparatus 100 have been described in detail in the above description of the concrete preparation mixing method with reference to fig. 2 to 6, and thus, repetitive descriptions thereof will be omitted.
As described above, the concrete preparation mixing apparatus 100 according to the embodiment of the present application may be implemented in various wireless terminals, such as a server having a concrete preparation mixing algorithm, and the like. In one example, the concrete preparation mixing apparatus 100 according to an embodiment of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the concrete preparation mixing apparatus 100 may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the concrete mixing apparatus 100 may also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the concrete preparation mixing apparatus 100 and the wireless terminal may be separate devices, and the concrete preparation mixing apparatus 100 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a contracted data format.
According to another aspect of the present application there is also provided a non-volatile computer readable storage medium having stored thereon computer readable instructions which when executed by a computer can perform a method as described above.
Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.
All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may load software from one computer device or processor to another. For example: a hardware platform loaded from a server or host computer of the video object detection device to a computer environment, or other computer environment implementing the system, or similar functioning system related to providing information needed for object detection. Thus, another medium capable of carrying software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic, etc., propagating through cable, optical cable, air, etc. Physical media used for carrier waves, such as electrical, wireless, or optical, may also be considered to be software-bearing media. Unless limited to a tangible "storage" medium, other terms used herein to refer to a computer or machine "readable medium" mean any medium that participates in the execution of any instructions by a processor.
The application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the application are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (10)
1. A concrete preparation mixing method, characterized by comprising:
mixing cement, fly ash, slag powder and silica fume to obtain a cementing material mixture;
mixing the fine aggregate and the coarse aggregate to obtain an aggregate mixture;
adding the cementing material mixture and the aggregate mixture into a concrete mixer for processing to obtain a concrete mixture; and
pouring the concrete mixture into a template, and vibrating and curing to obtain the concrete.
2. The concrete preparation mixing method according to claim 1, wherein the concrete mixture is poured into a form and vibrated and cured to obtain concrete, comprising:
acquiring vibration monitoring video of a preset time period acquired by a camera;
acquiring vibration frequency values and amplitude values of a plurality of preset time points in the preset time period;
after arranging the vibration frequency values and the amplitude values of the plurality of preset time points into vibration frequency input vectors and amplitude input vectors according to time dimensions, carrying out association coding on the vibration frequency input vectors and the amplitude input vectors so as to obtain a vibration frequency-amplitude association matrix;
The vibration frequency-amplitude correlation matrix is passed through a convolutional neural network model serving as a filter to obtain a vibration frequency-amplitude correlation eigenvector;
extracting a plurality of vibration monitoring key frames from the vibration monitoring video, and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames;
the sequence of the optical flow images passes through a time flow characteristic extractor based on a three-dimensional convolutional neural network model to obtain a time flow characteristic vector with a vibration effect;
calculating the responsiveness estimation of the vibration effect time flow characteristic vector relative to the vibration frequency-amplitude correlation characteristic vector to obtain a classification characteristic matrix;
regularization enhancement is carried out on the classification feature matrix to obtain an optimized classification feature matrix; and
and passing the optimized classification characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point is increased or decreased.
3. The concrete preparation mixing method according to claim 2, wherein the association encoding of the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix comprises:
performing association coding on the vibration frequency input vector and the amplitude input vector by using the following coding formula to obtain the vibration frequency-amplitude association matrix;
Wherein, the coding formula is:
wherein V is 1 Representing the vibration frequency input vector,a transpose vector representing the vibration frequency input vector, V 2 Representing the amplitude input vector, M a Representing the vibration frequency-amplitude correlation matrix, < >>Representing matrix multiplication.
4. A concrete preparation mixing method according to claim 3, wherein passing the vibration frequency-amplitude correlation matrix through a convolutional neural network model as a filter to obtain a vibration frequency-amplitude correlation eigenvector comprises:
each layer of the convolutional neural network model used as the filter performs the following steps on input data in forward transfer of the layer:
carrying out convolution processing on the input data to obtain a convolution characteristic diagram;
carrying out mean pooling treatment based on a feature matrix on the convolution feature map to obtain a pooled feature map; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
wherein the output of the last layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation eigenvector, and the input of the first layer of the convolutional neural network model as a filter is the vibration frequency-amplitude correlation matrix.
5. The concrete preparation mixing method of claim 4, wherein extracting a plurality of vibration monitoring key frames from the vibration monitoring video and extracting a sequence of optical flow images from the plurality of vibration monitoring key frames comprises: the plurality of vibration monitoring key frames are extracted from the vibration monitoring video at a predetermined sampling frequency.
6. The concrete preparation mixing method according to claim 5, wherein passing the sequence of optical flow images through a three-dimensional convolutional neural network model-based time flow feature extractor to obtain a vibration effect time flow feature vector, comprises:
using each layer of the three-dimensional convolution neural network model-based time flow feature extractor to respectively perform convolution processing, pooling processing and nonlinear activation processing based on three-dimensional convolution kernels on the sequence of the optical flow images in forward transfer of the layers so as to take the last layer output of the three-dimensional convolution neural network model-based time flow feature extractor as a feature map; and
and performing dimension reduction on the feature map to obtain the vibration effect time flow feature vector.
7. The concrete preparation mixing method according to claim 6, wherein calculating a responsiveness estimate of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector to obtain a classification eigenvector comprises:
Calculating the responsiveness estimation of the vibration effect time flow eigenvector relative to the vibration frequency-amplitude correlation eigenvector by the following responsiveness formula to obtain the classification eigenvector;
wherein, the responsiveness formula is:
wherein V is a Representing the time flow characteristic vector, V of the vibration effect b Representing the vibration frequency-amplitude correlation eigenvector, M c Representing the matrix of the classification characteristic,representing matrix multiplication.
8. The concrete preparation mixing method according to claim 7, wherein regularizing and enhancing the classification feature matrix to obtain an optimized classification feature matrix comprises:
the classification feature matrix is regularly enhanced according to the following optimization formula to obtain the optimized classification feature matrix;
wherein, the optimization formula is:
m i ′ ,j =(μσ)m i,j 2 +m i,j μ+(m i,j -σ)μ 2
wherein M represents the classification feature matrix, mu and sigma are the mean and standard deviation of feature value sets at each position in the classification feature matrix, M i,j Is the eigenvalue, m, of the (i, j) th position of the classification eigenvalue matrix i ′ ,j Is the eigenvalue of the (i, j) th position of the optimized classification eigenvalue matrix.
9. The concrete preparation mixing method according to claim 8, wherein the optimizing the classification feature matrix to obtain a classification result by a classifier, the classification result being used to indicate that the amplitude value of the current time point should be increased or decreased, comprises:
Expanding the optimized classification feature matrix into an optimized classification feature vector according to a row vector or a column vector;
performing full-connection coding on the optimized classification feature vector by using a plurality of full-connection layers of the classifier to obtain a coded optimized classification feature vector; and
and the coding optimization classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
10. A concrete preparation mixing device, comprising:
the video acquisition module is used for acquiring vibration monitoring videos in a preset time period acquired by the camera;
the data acquisition module is used for acquiring vibration frequency values and amplitude values of a plurality of preset time points in the preset time period;
the association coding module is used for performing association coding on the vibration frequency input vector and the amplitude input vector to obtain a vibration frequency-amplitude association matrix after arranging the vibration frequency values and the amplitude values of the plurality of preset time points into the vibration frequency input vector and the amplitude input vector according to the time dimension;
the first feature extraction module is used for enabling the vibration frequency-amplitude correlation matrix to pass through a convolutional neural network model serving as a filter so as to obtain a vibration frequency-amplitude correlation feature vector;
The key frame extraction module is used for extracting a plurality of vibration monitoring key frames from the vibration monitoring video and extracting sequences of optical flow images from the vibration monitoring key frames;
the second feature extraction module is used for enabling the sequence of the optical flow images to pass through a time flow feature extractor based on a three-dimensional convolutional neural network model so as to obtain a time flow feature vector with a vibration effect;
the responsiveness estimation module is used for calculating responsiveness estimation of the vibration effect time flow characteristic vector relative to the vibration frequency-amplitude correlation characteristic vector so as to obtain a classification characteristic matrix;
the regularization enhancement module is used for regularizing and enhancing the classification feature matrix to obtain an optimized classification feature matrix; and
and the amplitude control result generation module is used for passing the optimized classification characteristic matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating that the amplitude value of the current time point should be increased or decreased.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310497448.8A CN116619562A (en) | 2023-05-05 | 2023-05-05 | Concrete preparation mixing device and method thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310497448.8A CN116619562A (en) | 2023-05-05 | 2023-05-05 | Concrete preparation mixing device and method thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116619562A true CN116619562A (en) | 2023-08-22 |
Family
ID=87596491
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310497448.8A Withdrawn CN116619562A (en) | 2023-05-05 | 2023-05-05 | Concrete preparation mixing device and method thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116619562A (en) |
-
2023
- 2023-05-05 CN CN202310497448.8A patent/CN116619562A/en not_active Withdrawn
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108304795B (en) | Human skeleton behavior identification method and device based on deep reinforcement learning | |
CN107529650B (en) | Closed loop detection method and device and computer equipment | |
EP3620990A1 (en) | Capturing network dynamics using dynamic graph representation learning | |
CN109218134B (en) | Test case generation system based on neural style migration | |
CN116832588B (en) | Acid regeneration flue gas purifying device and method thereof | |
CN112418387A (en) | Quantum data processing method and apparatus | |
CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
CN109446897B (en) | Scene recognition method and device based on image context information | |
CN116580029B (en) | Quality inspection control system and method for aluminum alloy casting finished product | |
CN116704431A (en) | On-line monitoring system and method for water pollution | |
CN117784710B (en) | Remote state monitoring system and method for numerical control machine tool | |
CN117308077A (en) | Water supply control system for evaporator of nuclear power unit of reactor | |
CN117676099B (en) | Security early warning method and system based on Internet of things | |
CN117227005A (en) | Production control system and method for concrete raw material processing | |
CN114008666A (en) | Dynamic image resolution assessment | |
CN117586838A (en) | Cleaning agent for train brake valve and preparation method thereof | |
CN116619562A (en) | Concrete preparation mixing device and method thereof | |
CN116523711A (en) | Education supervision system and method based on artificial intelligence | |
Wei et al. | Auto-generating neural networks with reinforcement learning for multi-purpose image forensics | |
KR20210035535A (en) | Method of learning brain connectivity and system threrfor | |
JP2020177287A (en) | Specimen evaluation system and method for constructing the same | |
CN116681428B (en) | Intelligent recycling management system and method for electronic equipment | |
CN117253318B (en) | Intelligent self-service payment terminal system and method | |
CN112364892B (en) | Image identification method and device based on dynamic model | |
CN117067042B (en) | Grinder and control method thereof |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230822 |
|
WW01 | Invention patent application withdrawn after publication |