CN113610160B - Neural network-based reinforcement detection classification method, system and storage medium - Google Patents
Neural network-based reinforcement detection classification method, system and storage medium Download PDFInfo
- Publication number
- CN113610160B CN113610160B CN202110906453.0A CN202110906453A CN113610160B CN 113610160 B CN113610160 B CN 113610160B CN 202110906453 A CN202110906453 A CN 202110906453A CN 113610160 B CN113610160 B CN 113610160B
- Authority
- CN
- China
- Prior art keywords
- steel bar
- information
- neural network
- sample
- evaluation
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 65
- 230000002787 reinforcement Effects 0.000 title claims abstract description 47
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000003860 storage Methods 0.000 title claims abstract description 18
- 229910000831 Steel Inorganic materials 0.000 claims abstract description 235
- 239000010959 steel Substances 0.000 claims abstract description 235
- 238000003062 neural network model Methods 0.000 claims abstract description 96
- 229910001294 Reinforcing steel Inorganic materials 0.000 claims abstract description 65
- 238000011156 evaluation Methods 0.000 claims abstract description 62
- 238000013210 evaluation model Methods 0.000 claims abstract description 62
- 230000007547 defect Effects 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 39
- 238000013507 mapping Methods 0.000 claims description 30
- 238000005452 bending Methods 0.000 claims description 23
- 229910001562 pearlite Inorganic materials 0.000 claims description 19
- 229910000859 α-Fe Inorganic materials 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000010521 absorption reaction Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 6
- 238000002834 transmittance Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 description 7
- 238000012937 correction Methods 0.000 description 4
- 238000005520 cutting process Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003014 reinforcing effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000011800 void material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a method, a system and a storage medium for detecting and classifying reinforcing steel bars based on a neural network, which comprises the following steps: acquiring parameter information of a steel bar sample, and establishing a steel bar evaluation model according to the parameter information; presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model; presetting the steel bar evaluation index threshold, and comparing and judging the evaluation information with the evaluation index threshold to classify the steel bar samples; and establishing a neural network model, importing the parameter information and the evaluation information into the neural network model, and determining the defect of the steel bar sample according to the output result of the neural network model. The invention also carries out precision compensation on the reinforcement evaluation model in the detection process, so that the data processing result is more accurate.
Description
Technical Field
The invention relates to a steel bar detection method, in particular to a steel bar detection classification method, a system and a storage medium based on a neural network.
Background
The steel bars are used as the main structure in the existing construction project, so that the quality of the project is ensured, the occurrence of engineering accidents is avoided, the durability and the safety of the project are improved, the steel bars are required to be detected and classified, and the defective steel bars are required to be classified and selected. In the traditional manual picking scheme, the steel bars can be sorted only roughly through eyes or manual bending, detection and analysis cannot be realized in the steel bars, and therefore the precise sorting of the steel bars cannot be realized.
In order to reasonably and scientifically detect and classify the steel bars and accurately identify the defect information of the steel bars, a system threshold matching is required to be developed, and the system establishes a steel bar evaluation model according to the parameter information by acquiring the parameter information of a steel bar sample; generating evaluation information of the steel bar sample through the steel bar evaluation model; comparing and judging the grading information with an evaluation index threshold value, and classifying the steel bar samples; and (3) establishing a neural network model, importing parameter information and evaluation information into the neural network model, and determining the defects of the steel bar sample according to the output result of the neural network model. In the implementation process of the system, how to generate the evaluation information of the steel bar sample through the steel bar evaluation model and how to determine the defect information of the steel bar sample through the neural network model are all problems which need to be solved.
Disclosure of Invention
In order to solve at least one technical problem, the invention provides a method, a system and a storage medium for detecting and classifying reinforcing steel bars based on a neural network.
The first aspect of the invention provides a method for detecting and classifying reinforcing steel bars based on a neural network, which comprises the following steps:
acquiring length information and cross-sectional area information of a steel bar sample through an electromagnetic wave detection module;
acquiring internal gap information of the steel bar sample through a pulse eddy current detection module;
acquiring ferrite and pearlite content information of a steel bar sample through a terahertz detection module;
acquiring parameter information of the steel bar sample through length information, weight information, cross-sectional area information, internal gap information and ferrite and pearlite content information of the steel bar sample, and establishing a steel bar evaluation model according to the parameter information;
presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model;
presetting the steel bar evaluation index threshold, comparing and judging the evaluation information with the evaluation index threshold, and classifying the steel bar samples;
and determining the defects of the unqualified steel bar samples by analyzing the parameter information of the steel bar samples.
In this scheme, according to the parameter information establishes the reinforcing bar evaluation model, specifically includes:
acquiring parameter information of a steel bar sample, classifying sub-information in the parameter information, extracting information characteristics, and generating corresponding sub-information characteristic data;
carrying out weight processing on the sub-information characteristic data to obtain weight information;
fusing the weight information and the category characteristics to construct the mapping relation between the characteristic data of each sub-information and the category characteristics
And expressing the mapping relation, establishing a reinforcing steel bar evaluation model, and generating evaluation information of the reinforcing steel bar sample through the reinforcing steel bar evaluation model.
In the scheme, a mapping relation between the characteristic data of each piece of sub information and the category characteristic is constructed, and a function expression of the mapping relation is specifically:
wherein G represents the mapping relation between the sub-information feature data and the category feature, lambda represents the proportionality coefficient, p represents the total number of the sub-information feature data, and i represents the sub-information featureThe number of data items, beta represents weight information, f i Represents the i-th sub-information characteristic data, and μ (x) represents the noise function of the reinforcement evaluation model.
In the scheme, a neural network model is established, the parameter information of the steel bar sample is analyzed through the neural network model, and the defect of the unqualified steel bar sample is determined, wherein the establishment of the neural network model is specifically as follows:
establishing an initial neural network model, preprocessing reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, and generating an initial training set;
the initial training set is imported into an initial neural network model for iterative training, and relevant parameters of the initial neural network model are adjusted according to the iterative training;
presetting an error threshold of a neural network model, and calculating the error of the neural network model after multiple iterative training;
when the error is smaller than a preset error threshold, the neural network is proved to be trained, and a trained neural network model is obtained;
and importing the parameter information of the steel bar sample into a trained neural network model, and analyzing the parameter information through the neural network model to generate defect information of the steel bar sample.
In this scheme, carry out the analysis to parameter information through neural network model, include:
scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
importing the parameter information of the steel bar sample into a neural network model;
determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and simultaneously, the internal gap and the optimal bending area are visually displayed through the three-dimensional model of the steel bar, and the position area is marked.
In the scheme, the electromagnetic wave detection module and the pulse eddy current detection module are embedded and integrated in the same area, a square wave signal or a step signal is generated by detecting an excitation source, a terahertz pulse signal is generated by a pulse source in the terahertz detection module, the relation between component information in a steel bar sample and a time waveform is established by acquiring amplitude information and phase information of terahertz pulse, and the absorption coefficient, refractive index and transmittance of the steel bar sample are obtained through the time waveform, so that the ferrite and pearlite contents of the steel bar sample are determined.
The second aspect of the present invention also provides a system for detecting and classifying reinforcing steel bars based on a neural network, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a reinforcing steel bar detection and classification method program based on a neural network, and the reinforcing steel bar detection and classification method program based on the neural network realizes the following steps when being executed by the processor:
acquiring parameter information of a steel bar sample, and establishing a steel bar evaluation model according to the parameter information;
presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model;
presetting the steel bar evaluation index threshold, comparing and judging the evaluation information with the evaluation index threshold, and classifying the steel bar samples;
and determining the defects of the unqualified steel bar samples by analyzing the parameter information of the steel bar samples.
In this scheme, according to the parameter information establishes the reinforcing bar evaluation model, specifically includes:
acquiring parameter information of a steel bar sample, classifying sub-information in the parameter information, extracting information characteristics, and generating corresponding sub-information characteristic data;
carrying out weight processing on the sub-information characteristic data to obtain weight information;
fusing the weight information and the category characteristics to construct the mapping relation between the characteristic data of each sub-information and the category characteristics
And expressing the mapping relation, establishing a reinforcing steel bar evaluation model, and generating evaluation information of the reinforcing steel bar sample through the reinforcing steel bar evaluation model.
In the scheme, a mapping relation between the characteristic data of each piece of sub information and the category characteristic is constructed, and a function expression of the mapping relation is specifically:
wherein G represents the mapping relation between the sub-information feature data and the category feature, lambda represents the proportionality coefficient, p represents the total number of the sub-information feature data, i represents the number of the sub-information feature data items, beta represents the weight information, and f i Represents the i-th sub-information characteristic data, and μ (x) represents the noise function of the reinforcement evaluation model.
In the scheme, a neural network model is established, the parameter information of the steel bar sample is analyzed through the neural network model, and the defect of the unqualified steel bar sample is determined, wherein the establishment of the neural network model is specifically as follows:
establishing an initial neural network model, preprocessing reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, and generating an initial training set;
the initial training set is imported into an initial neural network model for iterative training, and relevant parameters of the initial neural network model are adjusted according to the iterative training;
presetting an error threshold of a neural network model, and calculating the error of the neural network model after multiple iterative training;
when the error is smaller than a preset error threshold, the neural network is proved to be trained, and a trained neural network model is obtained;
and importing the parameter information of the steel bar sample into a trained neural network model, and analyzing the parameter information through the neural network model to generate defect information of the steel bar sample.
In this scheme, carry out the analysis to parameter information through neural network model, include:
scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
importing the parameter information of the steel bar sample into a neural network model;
determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and simultaneously, the internal gap and the optimal bending area are visually displayed through the three-dimensional model of the steel bar, and the position area is marked.
In the scheme, the electromagnetic wave detection module and the pulse eddy current detection module are embedded and integrated in the same area, a square wave signal or a step signal is generated by detecting an excitation source, a terahertz pulse signal is generated by a pulse source in the terahertz detection module, the relation between component information in a steel bar sample and a time waveform is established by acquiring amplitude information and phase information of terahertz pulse, and the absorption coefficient, refractive index and transmittance of the steel bar sample are obtained through the time waveform, so that the ferrite and pearlite contents of the steel bar sample are determined.
The third aspect of the present invention also provides a computer-readable storage medium, in which a neural network-based reinforcement bar detection classification method program is included, which when executed by a processor, implements the steps of the neural network-based reinforcement bar detection classification method as described in any one of the above.
The invention discloses a method, a system and a storage medium for detecting and classifying reinforcing steel bars based on a neural network, which comprises the following steps: acquiring parameter information of a steel bar sample, and establishing a steel bar evaluation model according to the parameter information; presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model; presetting the steel bar evaluation index threshold, and comparing and judging the evaluation information with the evaluation index threshold to classify the steel bar samples; and establishing a neural network model, importing the parameter information and the evaluation information into the neural network model, and determining the defect of the steel bar sample according to the output result of the neural network model. The invention also carries out precision compensation on the reinforcement evaluation model in the detection process, so that the data processing result is more accurate. According to the invention, the reinforcement sample is detected by establishing the reinforcement evaluation model, the defect information and the optimal bending area of the reinforcement sample are determined, the optimal matching of the reinforcement processing scheme is carried out according to the defect information and the optimal bending area, the reinforcement use and management work can be better standardized by reinforcement classification, meanwhile, the classification work does not need manual intervention, the production efficiency is improved, and the safety accident risk is reduced.
Drawings
Fig. 1 shows a flowchart of a method for detecting and classifying reinforcing steel bars based on a neural network according to the present invention;
FIG. 2 is a flow chart of a method for evaluating a rebar sample by establishing a rebar evaluation model in accordance with the present invention;
FIG. 3 is a flow chart of a method for modeling a neural network to analyze the parameter information of a rebar sample in accordance with the present invention;
fig. 4 shows a block diagram of a reinforcing steel bar detection classification system based on a neural network according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a method for detecting and classifying reinforcing steel bars based on a neural network according to the present invention;
as shown in fig. 1, a first aspect of the present invention provides a method for detecting and classifying reinforcing steel bars based on a neural network, including:
s102, acquiring length information and cross-sectional area information of a steel bar sample through an electromagnetic wave detection module, acquiring internal gap information of the steel bar sample through a pulse vortex detection module, and acquiring ferrite and pearlite content information of the steel bar sample through a terahertz detection module;
s104, acquiring parameter information of the steel bar sample through length information, weight information, cross section area information, internal void information, ferrite and pearlite content information of the steel bar sample, and establishing a steel bar evaluation model according to the parameter information;
s106, presetting parameter information evaluation weights, and generating evaluation information of the steel bar sample through the steel bar evaluation model;
s108, presetting the steel bar evaluation index threshold, and comparing and judging the evaluation information with the evaluation index threshold to classify the steel bar samples;
s110, determining defects of the unqualified steel bar samples by analyzing the parameter information of the steel bar samples.
The electromagnetic wave detection module and the pulse eddy current detection module are embedded and integrated in the same area, a square wave signal or a step signal is generated by detecting an excitation source, a terahertz pulse signal is generated by a pulse source in the terahertz detection module, the relation between component information in a steel bar sample and a time waveform is established by acquiring amplitude information and phase information of terahertz pulse, the absorption coefficient, the refractive index and the transmissivity of the steel bar sample are obtained through the time waveform, and the ferrite and pearlite content of the steel bar sample is determined.
The pulsed eddy current detection module is used for acquiring the internal gap information of the steel bar sample, the pulsed eddy current signal is easy to be interfered by the outside, the pulsed eddy current signal is required to be preprocessed, the noise intensity of the pulsed eddy current signal is determined, the estimation of the characteristic quantity is completed by using a weighted average algorithm based on the noise intensity, and the influence of noise on the signal characteristic quantity is restrained; after pretreatment is completed, cutting analysis is carried out on the pulse eddy current signal curve, offset points are removed, characteristic values are obtained through exponential fitting or linear fitting, frequency components are extracted from the characteristic values, and monitoring of internal gap information of the steel bar sample is achieved through analysis of the frequency components.
Fig. 2 shows a flow chart of a method for evaluating a rebar sample by establishing a rebar evaluation model according to the invention.
According to the embodiment of the invention, a reinforcement evaluation model is established according to the parameter information, and the reinforcement evaluation model specifically comprises the following steps:
s202, acquiring parameter information of a steel bar sample, classifying sub-information in the parameter information, extracting information features, and generating corresponding sub-information feature data;
s204, carrying out weight processing on the sub-information characteristic data to obtain weight information;
s206, fusing the weight information and the category characteristics to construct the mapping relation between the characteristic data of each piece of sub-information and the category characteristics;
and S208, representing the mapping relation, establishing a reinforcing steel bar evaluation model, and generating evaluation information of the reinforcing steel bar sample through the reinforcing steel bar evaluation model.
It should be noted that, a mapping relationship between each piece of sub-information feature data and the category feature is constructed, and a functional expression of the mapping relationship is specifically:
wherein G represents the mapping relation between the sub-information feature data and the category feature, lambda represents the proportionality coefficient, p represents the total number of the sub-information feature data, i represents the number of the sub-information feature data items, beta represents the weight information, and f i Represents the i-th sub-information characteristic data, and μ (x) represents the noise function of the reinforcement evaluation model.
In the scheme, a neural network model is established, the parameter information of the steel bar sample is analyzed through the neural network model, and the defect of the unqualified steel bar sample is determined, wherein the establishment of the neural network model is specifically as follows:
establishing an initial neural network model, preprocessing reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, and generating an initial training set;
the initial training set is imported into an initial neural network model for iterative training, and relevant parameters of the initial neural network model are adjusted according to the iterative training;
presetting an error threshold of a neural network model, and calculating the error of the neural network model after multiple iterative training;
when the error is smaller than a preset error threshold, the neural network is proved to be trained, and a trained neural network model is obtained;
and importing the parameter information of the steel bar sample into a trained neural network model, and analyzing the parameter information through the neural network model to generate defect information of the steel bar sample.
It should be noted that, preprocessing the steel bar parameter standard data and the steel bar sample detection data to generate an initial training set specifically includes: acquiring enough reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, or directly connecting a related database, preprocessing the acquired reinforcing steel bar data information by sorting, data analysis and the like, grouping the reinforcing steel bar data information to obtain a plurality of training information data sets, importing the plurality of data sets into an initial neural network model to generate an output result after first learning, analyzing and calculating the initial learning rate of each group of training sets according to the obtained first output result, leading the output result after first learning into a neural network model again, continuously performing N times of learning, adjusting the related parameters of the neural network model according to a plurality of training sets and the loss functions in the process of each learning, outputting the output result after N times of learning of the initial neural network model, setting a neural network model error threshold, comparing and calculating the output result of the plurality of training information data sets to obtain an error value, judging whether the error value is smaller than the preset error threshold, and if the error value is smaller than the preset error threshold, proving that the neural network training is completed after the neural network training is obtained.
Fig. 3 shows a flowchart of a method for modeling a neural network to analyze the parameter information of a rebar sample according to the present invention.
According to an embodiment of the present invention, analyzing parameter information by a neural network model includes:
s302, scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
s304, importing the parameter information of the steel bar sample into a neural network model;
s306, determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
s308, analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
s310, generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and S312, the internal gap and the optimal bending area are visually displayed through the three-dimensional reinforcing steel bar model, and the position area is marked.
The electromagnetic wave detection module and the pulse eddy current detection module are embedded and integrated in the same area, a square wave signal or a step signal is generated by detecting an excitation source, a terahertz pulse signal is generated by a pulse source in the terahertz detection module, the relation between component information in a steel bar sample and a time waveform is established by acquiring amplitude information and phase information of terahertz pulse, the absorption coefficient, the refractive index and the transmissivity of the steel bar sample are obtained through the time waveform, and the ferrite and pearlite content of the steel bar sample is determined.
According to the embodiment of the invention, the precision compensation is also carried out on the reinforcement evaluation model, and the concrete steps are as follows:
acquiring parameter information of a reinforcing steel bar sample through a reinforcing steel bar evaluation model to generate evaluation score information, and generating classification information according to the evaluation score information;
analyzing the parameter information of the steel bar sample through the neural network model, and extracting the characteristic information of the output result of the neural network model;
feeding the characteristic information back to a reinforcement evaluation model, and comparing and analyzing the characteristic information and the classification information to generate a deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value or not;
if the noise interference information is larger than the first threshold value, analyzing the noise interference information, and calculating a correction parameter according to the noise interference information;
and correcting the reinforcement evaluation model according to the correction parameters.
According to the embodiment of the invention, the method can be used for classifying the steel bars according to the processing scheme of matching the optimal bending area of the steel bars, and specifically comprises the following steps:
obtaining defect information of a steel bar sample and position information of an optimal bending area, extracting position characteristic information according to the position information, numbering the steel bar sample, and generating numbering information;
acquiring a reinforcement processing scheme for matching, and extracting scheme characteristic information of the reinforcement processing scheme;
matching the position characteristic information with the scheme characteristic information to obtain matching degree;
presetting a matching degree threshold value, and analyzing and comparing the matching degree with the matching degree threshold value;
obtaining a steel bar sample larger than a preset matching threshold, sorting according to the matching degree from large to small, and selecting according to the quantity information in a steel bar processing scheme;
and if the matching degree is smaller than the matching degree threshold value, temporarily suspending according to the number information of the steel bar samples, and carrying out new round matching according to the number sequencing when a new steel bar processing scheme is accessed.
Fig. 4 shows a block diagram of a reinforcing steel bar detection classification system based on a neural network according to the present invention.
The second aspect of the present invention also provides a reinforcing steel bar detection and classification system 4 based on a neural network, which comprises: the memory 41 and the processor 42, wherein the memory comprises a reinforcing steel bar detection and classification method program based on a neural network, and the reinforcing steel bar detection and classification method program based on the neural network realizes the following steps when being executed by the processor:
acquiring parameter information of a steel bar sample, and establishing a steel bar evaluation model according to the parameter information;
presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model;
presetting the steel bar evaluation index threshold, comparing and judging the evaluation information with the evaluation index threshold, and classifying the steel bar samples;
and determining the defects of the unqualified steel bar samples by analyzing the parameter information of the steel bar samples.
The electromagnetic wave detection module and the pulse eddy current detection module are embedded and integrated in the same area, a square wave signal or a step signal is generated by detecting an excitation source, a terahertz pulse signal is generated by a pulse source in the terahertz detection module, the relation between component information in a steel bar sample and a time waveform is established by acquiring amplitude information and phase information of terahertz pulse, the absorption coefficient, the refractive index and the transmissivity of the steel bar sample are obtained through the time waveform, and the ferrite and pearlite content of the steel bar sample is determined.
The pulsed eddy current detection module is used for acquiring the internal gap information of the steel bar sample, the pulsed eddy current signal is easy to be interfered by the outside, the pulsed eddy current signal is required to be preprocessed, the noise intensity of the pulsed eddy current signal is determined, the estimation of the characteristic quantity is completed by using a weighted average algorithm based on the noise intensity, and the influence of noise on the signal characteristic quantity is restrained; after pretreatment is completed, cutting analysis is carried out on the pulse eddy current signal curve, offset points are removed, characteristic values are obtained through exponential fitting or linear fitting, frequency components are extracted from the characteristic values, and monitoring of internal gap information of the steel bar sample is achieved through analysis of the frequency components.
According to the embodiment of the invention, a reinforcement evaluation model is established according to the parameter information, and the reinforcement evaluation model specifically comprises the following steps:
acquiring parameter information of a steel bar sample, classifying sub-information in the parameter information, extracting information characteristics, and generating corresponding sub-information characteristic data;
carrying out weight processing on the sub-information characteristic data to obtain weight information;
fusing the weight information and the category characteristics to construct the mapping relation between the characteristic data of each sub-information and the category characteristics
And expressing the mapping relation, establishing a reinforcing steel bar evaluation model, and generating evaluation information of the reinforcing steel bar sample through the reinforcing steel bar evaluation model.
It should be noted that, a mapping relationship between each piece of sub-information feature data and the category feature is constructed, and a functional expression of the mapping relationship is specifically:
wherein G represents the mapping relation between the sub-information feature data and the category feature, lambda represents the proportionality coefficient, p represents the total number of the sub-information feature data, i represents the number of the sub-information feature data items, beta represents the weight information, and f i Represents the i-th sub-information characteristic data, and μ (x) represents the noise function of the reinforcement evaluation model.
According to the embodiment of the invention, a neural network model is established, and the defect of the unqualified steel bar sample is determined by analyzing the parameter information of the steel bar sample through the neural network model, wherein the establishment of the neural network model is specifically as follows:
establishing an initial neural network model, preprocessing reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, and generating an initial training set;
the initial training set is imported into an initial neural network model for iterative training, and relevant parameters of the initial neural network model are adjusted according to the iterative training;
presetting an error threshold of a neural network model, and calculating the error of the neural network model after multiple iterative training;
when the error is smaller than a preset error threshold, the neural network is proved to be trained, and a trained neural network model is obtained;
and importing the parameter information of the steel bar sample into a trained neural network model, and analyzing the parameter information through the neural network model to generate defect information of the steel bar sample.
It should be noted that, preprocessing the steel bar parameter standard data and the steel bar sample detection data to generate an initial training set specifically includes: acquiring enough reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, or directly connecting a related database, preprocessing the acquired reinforcing steel bar data information by sorting, data analysis and the like, grouping the reinforcing steel bar data information to obtain a plurality of training information data sets, importing the plurality of data sets into an initial neural network model to generate an output result after first learning, analyzing and calculating the initial learning rate of each group of training sets according to the obtained first output result, leading the output result after first learning into a neural network model again, continuously performing N times of learning, adjusting the related parameters of the neural network model according to a plurality of training sets and the loss functions in the process of each learning, outputting the output result after N times of learning of the initial neural network model, setting a neural network model error threshold, comparing and calculating the output result of the plurality of training information data sets to obtain an error value, judging whether the error value is smaller than the preset error threshold, and if the error value is smaller than the preset error threshold, proving that the neural network training is completed after the neural network training is obtained.
According to the embodiment of the invention, parameter information is analyzed through a neural network model to generate defect information of a steel bar sample, and the method comprises the following steps:
scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
importing the parameter information of the steel bar sample into a neural network model;
determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and simultaneously, the internal gap and the optimal bending area are visually displayed through the three-dimensional model of the steel bar, and the position area is marked.
According to the embodiment of the invention, the precision compensation is also carried out on the reinforcement evaluation model, and the concrete steps are as follows:
acquiring parameter information of a reinforcing steel bar sample through a reinforcing steel bar evaluation model to generate evaluation score information, and generating classification information according to the evaluation score information;
analyzing the parameter information of the steel bar sample through the neural network model, and extracting the characteristic information of the output result of the neural network model;
feeding the characteristic information back to a reinforcement evaluation model, and comparing and analyzing the characteristic information and the classification information to generate a deviation rate;
judging whether the deviation rate is larger than a preset deviation rate threshold value or not;
if the noise interference information is larger than the first threshold value, analyzing the noise interference information, and calculating a correction parameter according to the noise interference information;
and correcting the reinforcement evaluation model according to the correction parameters.
According to the embodiment of the invention, the method can be used for classifying the steel bars according to the processing scheme of matching the optimal bending area of the steel bars, and specifically comprises the following steps:
obtaining defect information of a steel bar sample and position information of an optimal bending area, extracting position characteristic information according to the position information, numbering the steel bar sample, and generating numbering information;
acquiring a reinforcement processing scheme for matching, and extracting scheme characteristic information of the reinforcement processing scheme;
matching the position characteristic information with the scheme characteristic information to obtain matching degree;
presetting a matching degree threshold value, and analyzing and comparing the matching degree with the matching degree threshold value;
obtaining a steel bar sample larger than a preset matching threshold, sorting according to the matching degree from large to small, and selecting according to the quantity information in a steel bar processing scheme;
and if the matching degree is smaller than the matching degree threshold value, temporarily suspending according to the number information of the steel bar samples, and carrying out new round matching according to the number sequencing when a new steel bar processing scheme is accessed.
The third aspect of the present invention also provides a computer-readable storage medium, in which a neural network-based reinforcement bar detection classification method program is included, which when executed by a processor, implements the steps of the neural network-based reinforcement bar detection classification method as described in any one of the above.
The invention discloses a method, a system and a storage medium for detecting and classifying reinforcing steel bars based on a neural network, which comprises the following steps: acquiring parameter information of a steel bar sample, and establishing a steel bar evaluation model according to the parameter information; presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model; presetting the steel bar evaluation index threshold, and comparing and judging the evaluation information with the evaluation index threshold to classify the steel bar samples; and establishing a neural network model, importing the parameter information and the evaluation information into the neural network model, and determining the defect of the steel bar sample according to the output result of the neural network model. The invention also carries out precision compensation on the reinforcement evaluation model in the detection process, so that the data processing result is more accurate. According to the invention, the reinforcement sample is detected by establishing the reinforcement evaluation model, the defect information and the optimal bending area of the reinforcement sample are determined, the optimal matching of the reinforcement processing scheme is carried out according to the defect information and the optimal bending area, the reinforcement use and management work can be better standardized by reinforcement classification, meanwhile, the classification work does not need manual intervention, the production efficiency is improved, and the safety accident risk is reduced.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. The reinforcing steel bar detection and classification method based on the neural network is characterized by comprising the following steps of:
acquiring length information and cross-sectional area information of a steel bar sample through an electromagnetic wave detection module;
acquiring internal gap information of the steel bar sample through a pulse eddy current detection module;
acquiring ferrite and pearlite content information of a steel bar sample through a terahertz detection module;
acquiring parameter information of the steel bar sample through length information, weight information, cross-sectional area information, internal gap information and ferrite and pearlite content information of the steel bar sample, and establishing a steel bar evaluation model according to the parameter information;
presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model;
presetting the steel bar evaluation index threshold, comparing and judging the evaluation information with the evaluation index threshold, and classifying the steel bar samples;
determining defects of the unqualified steel bar samples by analyzing the parameter information of the steel bar samples;
establishing a reinforcement evaluation model according to the parameter information, which specifically comprises the following steps:
acquiring parameter information of a steel bar sample, classifying sub-information in the parameter information, extracting information characteristics, and generating corresponding sub-information characteristic data;
carrying out weight processing on the sub-information characteristic data to obtain weight information;
fusing the weight information and the category characteristics to construct the mapping relation between the characteristic data of each sub-information and the category characteristics
Representing the mapping relation, establishing a reinforcing steel bar evaluation model, and generating evaluation information of a reinforcing steel bar sample through the reinforcing steel bar evaluation model;
constructing a mapping relation between the characteristic data of each piece of sub information and the class characteristics, wherein the function expression of the mapping relation is specifically as follows:
wherein G represents the mapping relation between the sub-information feature data and the category feature, lambda represents the proportionality coefficient, p represents the total number of the sub-information feature data, i represents the number of the sub-information feature data items, beta represents the weight information, and f i Representing the characteristic data of the ith sub-information, and μ (x) represents the noise function of the reinforcement evaluation model;
analyzing the parameter information through the neural network model, including:
scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
importing the parameter information of the steel bar sample into a neural network model;
determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and simultaneously, the internal gap and the optimal bending area are visually displayed through the three-dimensional model of the steel bar, and the position area is marked.
2. The method for detecting and classifying reinforcing steel bars based on the neural network according to claim 1, wherein a neural network model is established, and the defect of the unqualified reinforcing steel bar sample is determined by analyzing the parameter information of the reinforcing steel bar sample through the neural network model, wherein the establishment of the neural network model is specifically as follows:
establishing an initial neural network model, preprocessing reinforcing steel bar parameter standard data and reinforcing steel bar sample detection data, and generating an initial training set;
the initial training set is imported into an initial neural network model for iterative training, and relevant parameters of the initial neural network model are adjusted according to the iterative training;
presetting an error threshold of a neural network model, and calculating the error of the neural network model after multiple iterative training;
when the error is smaller than a preset error threshold, the neural network is proved to be trained, and a trained neural network model is obtained;
and importing the parameter information of the steel bar sample into a trained neural network model, and analyzing the parameter information through the neural network model to generate defect information of the steel bar sample.
3. The method for detecting and classifying the reinforcing steel bars based on the neural network according to claim 1, wherein the electromagnetic wave detection module and the pulse eddy current detection module are embedded and integrated in the same area, a square wave signal or a step signal is generated by a detection excitation source, a terahertz pulse signal is generated by a pulse source in the terahertz detection module, the relation between component information in a reinforcing steel bar sample and a time waveform is established by acquiring amplitude information and phase information of terahertz pulse, and the absorption coefficient, the refractive index and the transmittance of the reinforcing steel bar sample are obtained by the time waveform, so that the ferrite and pearlite contents of the reinforcing steel bar sample are determined.
4. A neural network-based rebar detection classification system, the system comprising: the device comprises a memory and a processor, wherein the memory comprises a neural network-based reinforcement detection and classification method program, and the neural network-based reinforcement detection and classification method program realizes the following steps when being executed by the processor:
acquiring parameter information of a steel bar sample, and establishing a steel bar evaluation model according to the parameter information;
presetting parameter information evaluation weights, and generating evaluation information of the steel bar samples through the steel bar evaluation model;
presetting the steel bar evaluation index threshold, comparing and judging the evaluation information with the evaluation index threshold, and classifying the steel bar samples;
determining defects of the unqualified steel bar samples by analyzing the parameter information of the steel bar samples;
establishing a reinforcement evaluation model according to the parameter information, which specifically comprises the following steps:
acquiring parameter information of a steel bar sample, classifying sub-information in the parameter information, extracting information characteristics, and generating corresponding sub-information characteristic data;
carrying out weight processing on the sub-information characteristic data to obtain weight information;
fusing the weight information and the category characteristics to construct the mapping relation between the characteristic data of each sub-information and the category characteristics
Representing the mapping relation, establishing a reinforcing steel bar evaluation model, and generating evaluation information of a reinforcing steel bar sample through the reinforcing steel bar evaluation model;
constructing a mapping relation between the characteristic data of each piece of sub information and the class characteristics, wherein the function expression of the mapping relation is specifically as follows:
wherein G represents the mapping relation between the sub-information feature data and the category feature, lambda represents the proportionality coefficient, p represents the total number of the sub-information feature data, i represents the number of the sub-information feature data items, beta represents the weight information, and f i Representing the characteristic data of the ith sub-information, and μ (x) represents the noise function of the reinforcement evaluation model;
analyzing the parameter information through the neural network model, including:
scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
importing the parameter information of the steel bar sample into a neural network model;
determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and simultaneously, the internal gap and the optimal bending area are visually displayed through the three-dimensional model of the steel bar, and the position area is marked.
5. The neural network-based rebar detection classification system of claim 4, wherein analyzing the parameter information via a neural network model comprises:
scanning a steel bar sample, and generating a steel bar three-dimensional model by using modeling software;
importing the parameter information of the steel bar sample into a neural network model;
determining the existence of an internal gap in the steel bar sample through the change of the frequency characteristic of the reflected wave in the transmitted wave;
analyzing the brittleness and toughness degree information of the steel bar through the ferrite and pearlite content information of the sample, and determining the optimal bending area of the steel bar sample;
generating defect information of a steel bar sample according to the existence condition of the internal gap and the information of the brittleness and toughness degree of the steel bar and the information of the weight and the cross-sectional area of the steel bar;
and simultaneously, the internal gap and the optimal bending area are visually displayed through the three-dimensional model of the steel bar, and the position area is marked.
6. A computer-readable storage medium, characterized by: the computer readable storage medium includes a neural network-based reinforcement detection and classification method program, which when executed by a processor, implements the steps of a neural network-based reinforcement detection and classification method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110906453.0A CN113610160B (en) | 2021-08-09 | 2021-08-09 | Neural network-based reinforcement detection classification method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110906453.0A CN113610160B (en) | 2021-08-09 | 2021-08-09 | Neural network-based reinforcement detection classification method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610160A CN113610160A (en) | 2021-11-05 |
| CN113610160B true CN113610160B (en) | 2024-03-15 |
Family
ID=78307591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110906453.0A Active CN113610160B (en) | 2021-08-09 | 2021-08-09 | Neural network-based reinforcement detection classification method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610160B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116797053B (en) * | 2023-08-25 | 2023-11-10 | 深圳普菲特信息科技股份有限公司 | Chemical production data analysis method, system and medium based on neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160021336A (en) * | 2014-08-14 | 2016-02-25 | 주식회사 포스코 | Device and method for monitoring slab quality |
| CN109344558A (en) * | 2018-11-30 | 2019-02-15 | 石家庄铁道大学 | A kind of matter-element model evaluation method of the reinforced concrete corrosion based on ideal point method |
| CN110363253A (en) * | 2019-07-25 | 2019-10-22 | 安徽工业大学 | A kind of Surfaces of Hot Rolled Strip defect classification method based on convolutional neural networks |
| CN111444629A (en) * | 2020-04-15 | 2020-07-24 | 中国二冶集团有限公司 | Reinforcing steel bar corrosion parameter prediction method based on support vector machine |
-
2021
- 2021-08-09 CN CN202110906453.0A patent/CN113610160B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160021336A (en) * | 2014-08-14 | 2016-02-25 | 주식회사 포스코 | Device and method for monitoring slab quality |
| CN109344558A (en) * | 2018-11-30 | 2019-02-15 | 石家庄铁道大学 | A kind of matter-element model evaluation method of the reinforced concrete corrosion based on ideal point method |
| CN110363253A (en) * | 2019-07-25 | 2019-10-22 | 安徽工业大学 | A kind of Surfaces of Hot Rolled Strip defect classification method based on convolutional neural networks |
| CN111444629A (en) * | 2020-04-15 | 2020-07-24 | 中国二冶集团有限公司 | Reinforcing steel bar corrosion parameter prediction method based on support vector machine |
Non-Patent Citations (7)
| Title |
|---|
| Prediction of Tool Wear Using Artificial Neural Networks during Turning of Hardened Steel;Paweł Twardowski et al.;《materials》;20191231;全文 * |
| 基于模糊神经网络的既有钢筋混凝土桥梁构件可靠性评估;钟惠萍, 张建仁, 张克波, 郝海霞;公路交通科技(第08期);摘要、第2节 * |
| 浅谈钢筋拉伸强度测量不确定度评定;李鹏;;内蒙古水利(05);全文 * |
| 热轧带肋钢筋力学性能指标偏低的检验分析;程鹏;;科协论坛(下半月)(第09期);全文 * |
| 热轧带肋钢筋表面缺陷分类以及原因分析;江卫国等;《江西冶金》;20200630;全文 * |
| 能力验证用钢筋拉伸试验样品的均匀性评价;桂旭;杨金艳;;理化检验(物理分册)(02);全文 * |
| 钟惠萍,张建仁,张克波,郝海霞.基于模糊神经网络的既有钢筋混凝土桥梁构件可靠性评估.公路交通科技.2005,(第08期),摘要、第2节. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610160A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106951984B (en) | Dynamic analysis and prediction method and device for system health degree | |
| KR101811270B1 (en) | Method and system for checking goods | |
| CN105630743A (en) | Spectrum wave number selection method | |
| CN111340606B (en) | Whole-flow income auditing method and device | |
| CN116112292B (en) | Abnormal behavior detection method, system and medium based on network flow big data | |
| CN113610160B (en) | Neural network-based reinforcement detection classification method, system and storage medium | |
| CN109142251B (en) | LIBS quantitative analysis method of random forest auxiliary artificial neural network | |
| CN113793332A (en) | Experimental instrument defect identification and classification method and system | |
| CN114638498A (en) | ESG evaluation method, ESG evaluation system, electronic equipment and storage equipment | |
| KR102406375B1 (en) | An electronic device including evaluation operation of originated technology | |
| CN115186776B (en) | Method, device and storage medium for classifying ruby producing areas | |
| CN116775741A (en) | Auditing method and related device for completion resolution of engineering | |
| CN115310865A (en) | Product full-quality life cycle quality control platform based on cosmetic detection technology | |
| CN112651433B (en) | Abnormal behavior analysis method for privileged account | |
| CN115455407A (en) | Machine learning-based GitHub sensitive information leakage monitoring method | |
| US20210224674A1 (en) | System and method for processing distorted or inaccurate input data obtained from an environment | |
| CN114238280A (en) | Method and device for constructing financial sensitive information standard library and electronic equipment | |
| CN113962216A (en) | Text processing method and device, electronic equipment and readable storage medium | |
| CN112184415A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113486243B (en) | Automatic mining method and system for false flow black ash production of social network | |
| CN111079344B (en) | Method and system for measuring softness of paper | |
| CN115797069A (en) | Risk account determination method, device, equipment and storage medium | |
| CN114662903A (en) | Automated credit granting method, apparatus, device, medium, and program product | |
| Peng et al. | Research on glass classification prediction model based on machine learning | |
| CN115965445A (en) | Parameter estimation method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |