CN116542956B - Automatic detection method and system for fabric components and readable storage medium - Google Patents
Automatic detection method and system for fabric components and readable storage medium Download PDFInfo
- Publication number
- CN116542956B CN116542956B CN202310595901.9A CN202310595901A CN116542956B CN 116542956 B CN116542956 B CN 116542956B CN 202310595901 A CN202310595901 A CN 202310595901A CN 116542956 B CN116542956 B CN 116542956B
- Authority
- CN
- China
- Prior art keywords
- textile
- information
- acquiring
- production process
- matrix
- 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 113
- 238000003860 storage Methods 0.000 title claims abstract description 16
- 239000004744 fabric Substances 0.000 title claims description 29
- 239000004753 textile Substances 0.000 claims abstract description 239
- 238000004519 manufacturing process Methods 0.000 claims abstract description 128
- 238000012544 monitoring process Methods 0.000 claims abstract description 93
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 46
- 238000005265 energy consumption Methods 0.000 claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 29
- 230000005540 biological transmission Effects 0.000 claims abstract description 28
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims description 100
- 239000011159 matrix material Substances 0.000 claims description 93
- 238000000034 method Methods 0.000 claims description 70
- 238000011282 treatment Methods 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 37
- 230000000007 visual effect Effects 0.000 claims description 25
- 230000002776 aggregation Effects 0.000 claims description 18
- 238000004220 aggregation Methods 0.000 claims description 18
- 238000010586 diagram Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000009467 reduction Effects 0.000 claims description 7
- 238000011221 initial treatment Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 6
- 238000012097 association analysis method Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 4
- 230000008439 repair process Effects 0.000 description 18
- 230000008859 change Effects 0.000 description 6
- 230000005856 abnormality Effects 0.000 description 4
- 238000009941 weaving Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000012806 monitoring device Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- 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
- G06N3/048—Activation functions
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- 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
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to an automatic detection method, a system and a readable storage medium for textile components, which belong to the technical field of textile production detection. The invention fully considers the rationality of the monitoring equipment through information transmission, so that the monitoring information of the monitoring equipment is more reasonable to gather, and the energy consumption is lower. Finally, the invention optimizes the anomaly detection model by introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm into the convolution layer, thereby further greatly reducing the calculated amount of the computer system and reducing the calculation complexity of the computer system.
Description
Technical Field
The invention relates to the technical field of textile production detection, in particular to an automatic detection method and system for fabric components and a readable storage medium.
Background
With the continuous development of image processing technology and the continuous improvement of textile product quality requirements, fabric image recognition is increasingly taking an important role in the textile industry. At present, an intelligent quality inspection scheme for the textile fabrics in the industry is usually carried out in a cloth inspection link, and actual losses cannot be reduced when the detection time is late. In the prior art, when related monitoring equipment is arranged, the monitoring range of the monitoring equipment is not considered, a certain visual field blind area possibly exists, and a convergence point of monitoring information is often needed to converge information when a plurality of monitoring equipment monitors, and finally the information is transmitted to a computer monitoring terminal, so that the energy consumption of the information convergence node of the monitoring equipment is not fully considered in the prior art. Finally, in the prior art, in the process of identifying and detecting textile anomalies, the corresponding detection algorithm has too high computational complexity, so that the computational complexity of a computer system is huge, and the method is unfavorable for the rapid identification and detection of textile anomalies in the production process.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a method, a system and a readable storage medium for automatically detecting fabric components.
In order to achieve the above purpose, the invention adopts the following technical scheme:
The first aspect of the invention provides an automatic detection method for fabric components, comprising the following steps:
acquiring production process flow data information of the current textile, and constructing a monitoring network according to the production process flow data information of the current textile;
acquiring textile production image data information of each textile production process flow based on a monitoring network, and acquiring a target image matrix by preprocessing the textile production image data information;
constructing a textile anomaly detection model based on a neural network, introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm to optimize the textile anomaly detection model, and acquiring detection results for the optimized textile anomaly detection model and a target image matrix;
and generating relevant treatment measures according to the detection result, and performing visual display according to a preset mode.
Further, in a preferred embodiment of the present invention, the monitoring network is constructed according to the current production process flow data information of the textile fabric, and specifically includes the following steps:
dividing the current textile production process flow data information into a plurality of sub-production process flow data information, and acquiring the position information of each sub-production process flow and the outline dimension information of the process equipment of each sub-production process flow;
Acquiring area information of an area to be monitored of corresponding process equipment of each sub-production process flow, and constructing a three-dimensional model diagram of the process equipment of each sub-production process flow according to the outline dimension information of the process equipment of each sub-production process flow;
constructing a virtual scene, inputting a three-dimensional model diagram of process equipment of the sub-production process flow into the virtual scene, and carrying out shooting point simulation analysis in the virtual scene according to the area information to obtain a shooting position point without visual field obstacle;
generating a field-free obstacle shooting area according to the field-free obstacle shooting position points, setting monitoring nodes based on the field-free obstacle shooting area, and constructing a monitoring network according to the monitoring nodes.
Further, in a preferred embodiment of the present invention, a monitoring node is set based on a field-free obstacle shooting area, and a monitoring network is constructed according to the monitoring node, specifically including the following steps:
setting monitoring nodes according to the non-visual field obstacle shooting area, initializing wireless information aggregation nodes, calculating the distance value from one of the monitoring nodes to the wireless information aggregation node, and acquiring the information transmission energy consumption value transmitted from the monitoring node to the wireless information aggregation node when transmitting information;
Acquiring the correlation between the distance value and the information transmission energy consumption value based on the information transmission energy consumption value, calculating the information transmission energy consumption value from other monitoring nodes to the wireless information aggregation node when information is transmitted according to the correlation, and calculating a first total information transmission energy consumption value;
adjusting the positions of the wireless information aggregation nodes, calculating information energy consumption values from each monitoring node to the wireless information aggregation nodes when transmitting information according to the positions of the wireless information aggregation nodes, and calculating a second total information transmission energy consumption value;
according to the rule, the nth total information transmission energy consumption value is calculated, the wireless information sink node corresponding to the minimum total information transmission energy consumption value is obtained to serve as the position of the wireless information sink node, when one monitoring node is added, the position of the wireless information sink node is readjusted, and a monitoring network is built according to the wireless information sink node and the monitoring node.
Further, in a preferred embodiment of the present invention, the target image matrix is obtained by preprocessing the textile production image data information, which specifically includes the following steps:
acquiring the current textile processing technology requirements of the textile, and cutting a non-textile processing technology requirement area through textile production image data information to acquire an interested area of textile production image data;
The method comprises the steps of obtaining a gray matrix of an area of interest of textile production image data by performing gray treatment on the area of interest of the textile production image data, and obtaining textile production image data after primary treatment by performing filtering treatment through a mean value filtering method;
after filtering treatment, carrying out edge extraction on the textile production image data subjected to primary treatment by a canny operator so as to obtain a target image matrix, and outputting the target image matrix.
Further, in a preferred embodiment of the present invention, a linear discriminant analysis algorithm and a singular value decomposition algorithm are introduced to optimize a textile anomaly detection model, and a detection result is obtained for the optimized textile anomaly detection model and a target image matrix, which specifically includes the following steps:
acquiring a large number of textile abnormal sample sets, inputting the textile abnormal sample sets into a convolution layer, and introducing a linear discriminant analysis algorithm to perform dimension reduction treatment on the textile abnormal sample sets to acquire an inter-class scattering matrix and an intra-class scattering matrix;
generating a covariance matrix by combining an inter-class scattering matrix and an intra-class scattering matrix, introducing a singular value decomposition algorithm to decompose eigenvalues of the covariance matrix, taking out eigenvectors corresponding to the largest n eigenvalues, and normalizing the eigenvectors to form an eigenvector matrix;
Converting the textile abnormal sample data set according to the feature vector matrix to generate a new abnormal sample data set, inputting the new abnormal sample data set into the pooling layer and the full-connection layer, and identifying through an output vector;
and finally classifying by Softmax, storing model parameters, outputting an optimized textile anomaly detection model, and acquiring a detection result according to the optimized textile anomaly detection model and a target image matrix.
Further, in a preferred embodiment of the present invention, relevant treatment measures are generated according to the detection result, and visual display is performed according to a preset manner, which specifically includes the following steps:
acquiring historical textile abnormal condition information of the current textile production process flow, constructing keyword data according to the historical textile abnormal condition information, searching through big data based on the keyword data, acquiring running state information corresponding to each textile abnormal condition information and related treatment measures, storing the running state information and the related treatment measures in a database, and updating the running state information and the related treatment measures regularly;
by arranging visual display equipment in each sub-production process flow, judging whether the detection result is an abnormal detection result, if so, acquiring abnormal information of the detection result, and acquiring running state information of each textile equipment in the current sub-production process flow;
Calculating association degree information of abnormal information of the detection result and running state information of each textile device in the current sub-production process flow through a gray association analysis method, obtaining textile devices with association degree information larger than preset association degree information, and taking the textile devices as abnormal textile devices;
the method comprises the steps of obtaining textile abnormal condition information of current abnormal textile equipment, inputting the textile abnormal condition information of the current abnormal textile equipment into a database for matching, obtaining relevant treatment measures corresponding to the textile abnormal condition information of the current abnormal textile equipment, and displaying the relevant treatment measures in a visual display device according to a preset mode to provide a reference.
The second aspect of the present invention provides an automatic detection system for fabric components, the detection system comprising a memory and a processor, the memory containing an automatic detection method program for fabric components, the automatic detection method program for fabric components, when executed by the processor, implementing the steps of:
acquiring production process flow data information of the current textile, and constructing a monitoring network according to the production process flow data information of the current textile;
acquiring textile production image data information of each textile production process flow based on a monitoring network, and acquiring a target image matrix by preprocessing the textile production image data information;
Constructing a textile anomaly detection model based on a neural network, introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm to optimize the textile anomaly detection model, and acquiring detection results for the optimized textile anomaly detection model and a target image matrix;
and generating relevant treatment measures according to the detection result, and performing visual display according to a preset mode.
In this embodiment, the monitoring network is constructed according to the current production process flow data information of the textile fabric, and specifically includes the following steps:
dividing the current textile production process flow data information into a plurality of sub-production process flow data information, and acquiring the position information of each sub-production process flow and the outline dimension information of the process equipment of each sub-production process flow;
acquiring area information of an area to be monitored of corresponding process equipment of each sub-production process flow, and constructing a three-dimensional model diagram of the process equipment of each sub-production process flow according to the outline dimension information of the process equipment of each sub-production process flow;
constructing a virtual scene, inputting a three-dimensional model diagram of process equipment of the sub-production process flow into the virtual scene, and carrying out shooting point simulation analysis in the virtual scene according to the area information to obtain a shooting position point without visual field obstacle;
Generating a field-free obstacle shooting area according to the field-free obstacle shooting position points, setting monitoring nodes based on the field-free obstacle shooting area, and constructing a monitoring network according to the monitoring nodes.
In this embodiment, a linear discriminant analysis algorithm and a singular value decomposition algorithm are introduced to optimize a textile anomaly detection model, and detection results are obtained for the optimized textile anomaly detection model and a target image matrix, and specifically include the following steps:
acquiring a large number of textile abnormal sample sets, inputting the textile abnormal sample sets into a convolution layer, and introducing a linear discriminant analysis algorithm to perform dimension reduction treatment on the textile abnormal sample sets to acquire an inter-class scattering matrix and an intra-class scattering matrix;
generating a covariance matrix by combining an inter-class scattering matrix and an intra-class scattering matrix, introducing a singular value decomposition algorithm to decompose eigenvalues of the covariance matrix, taking out eigenvectors corresponding to the largest n eigenvalues, and normalizing the eigenvectors to form an eigenvector matrix;
converting the textile abnormal sample data set according to the feature vector matrix to generate a new abnormal sample data set, inputting the new abnormal sample data set into the pooling layer and the full-connection layer, and identifying through an output vector;
And finally classifying by Softmax, storing model parameters, outputting an optimized textile anomaly detection model, and acquiring a detection result according to the optimized textile anomaly detection model and a target image matrix.
A third aspect of the present invention provides a computer-readable storage medium including a textile component automatic detection method program which, when executed by a processor, implements the steps of any one of the textile component automatic detection methods.
The invention solves the defects existing in the background technology and has the following beneficial effects:
according to the textile production process monitoring method, the production process flow data information of the current textile is obtained, a monitoring network is constructed according to the production process flow data information of the current textile, textile production image data information of each textile production process flow is further obtained based on the monitoring network, the textile production image data information is preprocessed, a target image matrix is obtained, a textile abnormality detection model is further constructed based on a neural network, a linear discriminant analysis algorithm and a singular value decomposition algorithm are introduced to optimize the textile abnormality detection model, detection results are obtained for the optimized textile abnormality detection model and the target image matrix, relevant treatment measures are generated according to the detection results, and visual display is carried out according to a preset mode. The method fully considers the arrangement condition of the monitoring equipment in the monitoring network, so that the monitoring equipment can monitor the spinning process in all directions; and secondly, the rationality of the monitoring equipment through information transmission is fully considered, so that the monitoring information of the monitoring equipment is more reasonable to gather, and the energy consumption is lower. Finally, the invention optimizes the anomaly detection model by introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm into the convolution layer, thereby further greatly reducing the calculated amount of the computer system and reducing the calculation complexity of the computer system.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows an overall process flow diagram of a method for automatically detecting fabric components;
FIG. 2 shows a first method flow chart of a method for automatically detecting a fabric component;
FIG. 3 shows a second method flow chart of a method for automatically detecting a fabric component;
fig. 4 shows a system block diagram of an automatic fabric component detection system.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and 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 application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention provides an automatic detection method for fabric components, comprising the following steps:
s102, acquiring production process flow data information of the current textile, and constructing a monitoring network according to the production process flow data information of the current textile;
s104, acquiring textile production image data information of each textile production process flow based on a monitoring network, and acquiring a target image matrix by preprocessing the textile production image data information;
s106, constructing a textile anomaly detection model based on a neural network, introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm to optimize the textile anomaly detection model, and acquiring detection results of the optimized textile anomaly detection model and a target image matrix;
s108, generating relevant treatment measures according to the detection result, and performing visual display according to a preset mode.
The method is characterized in that the arrangement condition of the monitoring equipment in the monitoring network is fully considered, so that the monitoring equipment can monitor the spinning process in an omnibearing manner; and secondly, the rationality of the monitoring equipment through information transmission is fully considered, so that the monitoring information of the monitoring equipment is more reasonable to gather, and the energy consumption is lower. Finally, the invention optimizes the anomaly detection model by introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm into the convolution layer, thereby further greatly reducing the calculated amount of the computer system and reducing the calculation complexity of the computer system.
As shown in fig. 2, in a preferred embodiment of the present invention, in step S102, the method specifically includes the following steps:
s202, dividing the production process flow data information of the current textile into a plurality of sub-production process flow data information, and acquiring the position information of each sub-production process flow and the outline dimension information of the process equipment of each sub-production process flow;
the external dimension information of the process equipment comprises external dimension information of each part of the production equipment, such as data of external dimension of a motor, external dimension of a belt wheel and the like.
S204, obtaining area information of an area to be monitored of each sub-production process corresponding to the process equipment, and constructing a three-dimensional model diagram of the process equipment of each sub-production process according to the outline dimension information of the process equipment of each sub-production process;
illustratively, in this step, a three-dimensional model map of the process equipment of each sub-production process flow is constructed from the form dimension information by three-dimensional modeling software (such as SolidWorks, UG, maya). Each textile device has a textile processing area, which is the area information of the area to be monitored.
S206, constructing a virtual scene, inputting a three-dimensional model diagram of process equipment of the sub-production process flow into the virtual scene, and carrying out shooting point simulation analysis in the virtual scene according to the area information to obtain shooting position points without visual field obstacles;
for example, in the present embodiment, the shooting condition of the camera in the virtual scene is simulated by AR or VR technology, so that the point of the non-view field obstacle shooting position is selected.
S208, generating a field-free obstacle shooting area according to the field-free obstacle shooting position points, setting monitoring nodes based on the field-free obstacle shooting area, and constructing a monitoring network according to the monitoring nodes.
For example, in this step, the view-field-obstacle-free shooting location points form a view-field-obstacle-free shooting area, and monitoring devices can be randomly set in the view-field-obstacle-free shooting area to meet the monitoring requirements.
It should be noted that, in the steps S202 to S208, the four steps fully consider the arrangement situation of the monitoring devices in the monitoring network, so that the monitoring devices can monitor the textile process in all directions.
Further, in a preferred embodiment of the present invention, in step S208, the method specifically includes the following steps:
Setting monitoring nodes according to the non-visual field obstacle shooting area, initializing wireless information aggregation nodes, calculating the distance value from one of the monitoring nodes to the wireless information aggregation node, and acquiring the information transmission energy consumption value transmitted from the monitoring node to the wireless information aggregation node when transmitting information;
acquiring the correlation between the distance value and the information transmission energy consumption value based on the information transmission energy consumption value, calculating the information transmission energy consumption value from other monitoring nodes to the wireless information aggregation node when information is transmitted according to the correlation, and calculating a first total information transmission energy consumption value;
adjusting the positions of the wireless information aggregation nodes, calculating information energy consumption values from each monitoring node to the wireless information aggregation nodes when transmitting information according to the positions of the wireless information aggregation nodes, and calculating a second total information transmission energy consumption value;
according to the rule, the nth total information transmission energy consumption value is calculated, the wireless information sink node corresponding to the minimum total information transmission energy consumption value is obtained to serve as the position of the wireless information sink node, when one monitoring node is added, the position of the wireless information sink node is readjusted, and a monitoring network is built according to the wireless information sink node and the monitoring node.
The invention fully considers the rationality of the monitoring equipment through information transmission, so that the monitoring information of the monitoring equipment is more reasonable to assemble and the energy consumption is lower.
Further, in a preferred embodiment of the present invention, in step S104, the method specifically includes the following steps:
acquiring the current textile processing technology requirements of the textile, and cutting a non-textile processing technology requirement area through textile production image data information to acquire an interested area of textile production image data;
the method comprises the steps of obtaining a gray matrix of an area of interest of textile production image data by performing gray treatment on the area of interest of the textile production image data, and obtaining textile production image data after primary treatment by performing filtering treatment through a mean value filtering method;
after filtering treatment, carrying out edge extraction on the textile production image data subjected to primary treatment by a canny operator so as to obtain a target image matrix, and outputting the target image matrix.
Further, in a preferred embodiment of the present invention, in step S106, the steps specifically include the following steps:
s302, acquiring a large number of textile abnormal sample sets, inputting the textile abnormal sample sets into a convolution layer, and introducing a linear discriminant analysis algorithm to perform dimension reduction treatment on the textile abnormal sample sets to acquire an inter-class scattering matrix and an intra-class scattering matrix;
S304, generating a covariance matrix by combining an inter-class scattering matrix and an intra-class scattering matrix, introducing a singular value decomposition algorithm to decompose eigenvalues of the covariance matrix, taking out eigenvectors corresponding to the largest n eigenvalues, and normalizing the eigenvectors to form an eigenvector matrix;
s306, converting the textile abnormal sample data set according to the feature vector matrix to generate a new abnormal sample data set, inputting the new abnormal sample data set into the pooling layer and the full-connection layer, and identifying through an output vector;
and S308, finally, classifying by Softmax, storing model parameters, outputting an optimized textile anomaly detection model, and obtaining a detection result according to the optimized textile anomaly detection model and a target image matrix.
In this embodiment, the feature vector matrix satisfies the following relationship:
wherein H is B The inter-class scattering matrix is obtained after the dimension reduction by a linear discriminant analysis algorithm; h W Is an intra-class scattering matrix;the whole is represented as covariance matrix; v is a eigenvector matrix composed of eigenvectors according to columns, which are obtained after the eigenvalue decomposition of the covariance matrix; v (V) T Representing the adaptation value after matrix transposition; sigma (sigma) 2 Representation->A diagonal matrix formed by covariance matrices.
Through the relational expression, the intra-class information and the inter-class information of the linear discriminant analysis algorithm are fully utilized, the covariance matrix is degraded again by combining the singular value decomposition algorithm, the data are further processed, the calculated amount of a computer system is greatly reduced, the calculation complexity of the computer system is reduced, and the recognition speed of the abnormal condition of the textile is further improved.
It should be noted that the abnormal sample number set of the textile includes textile products having flaws, defects or not meeting the process requirements.
Further, in a preferred embodiment of the present invention, relevant treatment measures are generated according to the detection result, and visual display is performed according to a preset manner, which specifically includes the following steps:
acquiring historical textile abnormal condition information of the current textile production process flow, constructing keyword data according to the historical textile abnormal condition information, searching through big data based on the keyword data, acquiring running state information corresponding to each textile abnormal condition information and related treatment measures, storing the running state information and the related treatment measures in a database, and updating the running state information and the related treatment measures regularly;
By arranging visual display equipment in each sub-production process flow, judging whether the detection result is an abnormal detection result, if so, acquiring abnormal information of the detection result, and acquiring running state information of each textile equipment in the current sub-production process flow;
calculating association degree information of abnormal information of the detection result and running state information of each textile device in the current sub-production process flow through a gray association analysis method, obtaining textile devices with association degree information larger than preset association degree information, and taking the textile devices as abnormal textile devices;
the method comprises the steps of obtaining textile abnormal condition information of current abnormal textile equipment, inputting the textile abnormal condition information of the current abnormal textile equipment into a database for matching, obtaining relevant treatment measures corresponding to the textile abnormal condition information of the current abnormal textile equipment, and displaying the relevant treatment measures in a visual display device according to a preset mode to provide a reference.
It should be noted that, for the factor between two systems, a measure of the magnitude of the correlation that varies with time or with different objects is called a degree of correlation. In the system development process, if the trend of the two factor changes has consistency, namely the synchronous change degree is higher, the association degree of the two factors is higher; otherwise, it is lower. Therefore, the gray correlation analysis method is a method for measuring the degree of correlation between factors according to the degree of similarity or dissimilarity of the development trends between the factors, i.e. "gray correlation". When the association degree information is larger than the preset association degree information, the correlation between the abnormal information of the detection result and the running state information of a certain textile device is very high, and the possibility that the device generates abnormality is indicated.
In addition, the method can further comprise the following steps:
acquiring historical abnormal characteristic data information of abnormal textile products in the textile production process, counting historical repair condition data of the historical abnormal characteristic data information, calculating the repair success rate of each abnormal characteristic data according to the historical repair condition data, and updating the repair success rate regularly;
acquiring abnormal characteristic data information of abnormal textile products in the current textile production process, and acquiring the repair success rate of each abnormal textile product according to the abnormal characteristic data information of the abnormal textile products in the current textile production process;
judging whether the repair success rate is greater than a preset repair success rate, and if the repair success rate is greater than a preset modification success rate, distributing repair textile equipment of the abnormal textile product according to the abnormal characteristic data information;
and if the repair success rate is not greater than the preset modification success rate, scrapping the abnormal textile product in the current textile production process.
It should be noted that the method fully considers the possibility of repairing abnormal characteristic data information, and is beneficial to the post-treatment of abnormal textile products.
The repair textile equipment for the abnormal textile product is distributed according to the abnormal characteristic data information, and the repair textile equipment specifically comprises:
acquiring historical textile precision change data information of textile equipment in a current textile workshop, constructing a textile precision change prediction model based on deep learning, and inputting the historical textile precision change data information into the textile precision change prediction model for coding learning;
acquiring textile precision data information of textile equipment in a current textile workshop through the textile precision change prediction model, and retrieving repair precision requirement data through big data according to the abnormal characteristic data information;
judging whether the repair precision requirement data is lower than the textile precision data information, and selecting the repair textile equipment to perform task allocation when the repair precision requirement data is lower than the textile precision data information;
and if the repair precision requirement data is not lower than the weaving precision data information of all the weaving equipment in the current weaving workshop, scrapping the abnormal weaving product.
The method can further improve the possibility of abnormal repair of the abnormal textile product, judge the possibility, and improve the success rate of repairing the abnormal textile product.
As shown in fig. 4, the second aspect of the present invention provides an automatic fabric component detecting system 4, wherein the detecting system 4 includes a memory 41 and a processor 62, and the memory 41 contains an automatic fabric component detecting method program, and when the automatic fabric component detecting method program is executed by the processor 62, the following steps are implemented:
acquiring production process flow data information of the current textile, and constructing a monitoring network according to the production process flow data information of the current textile;
acquiring textile production image data information of each textile production process flow based on a monitoring network, and acquiring a target image matrix by preprocessing the textile production image data information;
constructing a textile anomaly detection model based on a neural network, introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm to optimize the textile anomaly detection model, and acquiring detection results for the optimized textile anomaly detection model and a target image matrix;
and generating relevant treatment measures according to the detection result, and performing visual display according to a preset mode.
In this embodiment, the monitoring network is constructed according to the current production process flow data information of the textile fabric, and specifically includes the following steps:
Dividing the current textile production process flow data information into a plurality of sub-production process flow data information, and acquiring the position information of each sub-production process flow and the outline dimension information of the process equipment of each sub-production process flow;
acquiring area information of an area to be monitored of corresponding process equipment of each sub-production process flow, and constructing a three-dimensional model diagram of the process equipment of each sub-production process flow according to the outline dimension information of the process equipment of each sub-production process flow;
constructing a virtual scene, inputting a three-dimensional model diagram of process equipment of the sub-production process flow into the virtual scene, and carrying out shooting point simulation analysis in the virtual scene according to the area information to obtain a shooting position point without visual field obstacle;
generating a field-free obstacle shooting area according to the field-free obstacle shooting position points, setting monitoring nodes based on the field-free obstacle shooting area, and constructing a monitoring network according to the monitoring nodes.
In this embodiment, a linear discriminant analysis algorithm and a singular value decomposition algorithm are introduced to optimize a textile anomaly detection model, and detection results are obtained for the optimized textile anomaly detection model and a target image matrix, and specifically include the following steps:
Acquiring a large number of textile abnormal sample sets, inputting the textile abnormal sample sets into a convolution layer, and introducing a linear discriminant analysis algorithm to perform dimension reduction treatment on the textile abnormal sample sets to acquire an inter-class scattering matrix and an intra-class scattering matrix;
generating a covariance matrix by combining an inter-class scattering matrix and an intra-class scattering matrix, introducing a singular value decomposition algorithm to decompose eigenvalues of the covariance matrix, taking out eigenvectors corresponding to the largest n eigenvalues, and normalizing the eigenvectors to form an eigenvector matrix;
converting the textile abnormal sample data set according to the feature vector matrix to generate a new abnormal sample data set, inputting the new abnormal sample data set into the pooling layer and the full-connection layer, and identifying through an output vector;
and finally classifying by Softmax, storing model parameters, outputting an optimized textile anomaly detection model, and acquiring a detection result according to the optimized textile anomaly detection model and a target image matrix.
A third aspect of the present invention provides a computer-readable storage medium including a textile component automatic detection method program which, when executed by a processor, implements the steps of any one of the textile component automatic detection methods.
In the several embodiments provided by the present 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 application 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 of 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 embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (8)
1. An automatic detection method for fabric components is characterized by comprising the following steps:
acquiring production process flow data information of the current textile, and constructing a monitoring network according to the production process flow data information of the current textile;
acquiring textile production image data information of each textile production process flow based on the monitoring network, and acquiring a target image matrix by preprocessing the textile production image data information;
constructing a textile anomaly detection model based on a neural network, introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm to optimize the textile anomaly detection model, and acquiring detection results for the optimized textile anomaly detection model and a target image matrix;
generating relevant treatment measures according to the detection result, and performing visual display according to a preset mode;
The method comprises the following steps of:
dividing the current textile production process flow data information into a plurality of sub-production process flow data information, and acquiring the position information of each sub-production process flow and the outline dimension information of the process equipment of each sub-production process flow;
acquiring area information of an area to be monitored of corresponding process equipment of each sub-production process, and constructing a three-dimensional model diagram of the process equipment of each sub-production process according to the outline dimension information of the process equipment of each sub-production process;
constructing a virtual scene, inputting a three-dimensional model diagram of process equipment of the sub-production process flow into the virtual scene, and carrying out shooting point simulation analysis in the virtual scene according to the area information of the area to obtain shooting position points without visual field obstacles;
generating a view-field-free obstacle shooting area according to the view-field-free obstacle shooting position points, setting monitoring nodes based on the view-field-free obstacle shooting area, and constructing a monitoring network according to the monitoring nodes.
2. The automatic detection method of fabric components according to claim 1, wherein a monitoring node is set based on the field-free obstacle shooting area, and a monitoring network is constructed according to the monitoring node, specifically comprising the following steps:
Setting monitoring nodes according to the non-visual field obstacle shooting area, initializing wireless information sink nodes, calculating the distance value between one of the monitoring nodes and the wireless information sink node, and acquiring the information transmission energy consumption value transmitted from the monitoring node to the wireless information sink node when transmitting information;
acquiring the correlation between the distance value and the information transmission energy consumption value based on the information transmission energy consumption value, calculating the information transmission energy consumption value from other monitoring nodes to the wireless information aggregation node when information is transmitted according to the correlation, and calculating a first total information transmission energy consumption value;
the position of the wireless information aggregation node is adjusted, the information energy consumption value from each monitoring node to the wireless information aggregation node when information is transmitted is calculated according to the position of the wireless information aggregation node, and a second total information transmission energy consumption value is calculated;
according to the rule, the nth total information transmission energy consumption value is calculated, the wireless information sink node corresponding to the minimum total information transmission energy consumption value is obtained to serve as the position of the wireless information sink node, when one monitoring node is added, the position of the wireless information sink node is readjusted, and a monitoring network is built according to the wireless information sink node and the monitoring node.
3. The automatic detection method of fabric composition according to claim 1, wherein the target image matrix is obtained by preprocessing the textile production image data information, comprising the steps of:
acquiring the current textile processing technology requirements of the textile, and cutting a non-textile processing technology requirement area through the textile production image data information to acquire an interested area of the textile production image data;
the method comprises the steps of obtaining a gray matrix of an area of interest of textile production image data by carrying out gray treatment on the area of interest of the textile production image data, and obtaining textile production image data after primary treatment by carrying out filtering treatment through a mean value filtering method;
after filtering treatment, carrying out edge extraction on the textile production image data subjected to primary treatment by a canny operator so as to obtain a target image matrix, and outputting the target image matrix.
4. The automatic detection method of textile components according to claim 1, wherein a linear discriminant analysis algorithm and a singular value decomposition algorithm are introduced to optimize a textile anomaly detection model, and detection results are obtained for the optimized textile anomaly detection model and a target image matrix, and specifically comprising the following steps:
Acquiring a large number of textile abnormal sample sets, inputting the textile abnormal sample sets into a convolution layer, and introducing a linear discriminant analysis algorithm to perform dimension reduction on the textile abnormal sample sets to acquire an inter-class scattering matrix and an intra-class scattering matrix;
generating a covariance matrix by combining the inter-class scattering matrix and the intra-class scattering matrix, introducing a singular value decomposition algorithm to decompose eigenvalues of the covariance matrix, taking out eigenvectors corresponding to the largest n eigenvalues, and normalizing the eigenvectors to form an eigenvector matrix;
converting the textile abnormal sample data set according to the feature vector matrix to generate a new abnormal sample data set, inputting the new abnormal sample data set into a pooling layer and a full-connection layer, and identifying through an output vector;
and finally classifying by Softmax, storing model parameters, outputting an optimized textile anomaly detection model, and acquiring a detection result according to the optimized textile anomaly detection model and a target image matrix.
5. The automatic detection method of fabric components according to claim 1, wherein the related treatment measures are generated according to the detection result and are visually displayed according to a preset mode, and the method specifically comprises the following steps:
Acquiring historical textile abnormal condition information of the current textile production process flow, constructing keyword data according to the historical textile abnormal condition information, searching through big data based on the keyword data, acquiring running state information corresponding to each textile abnormal condition information and related treatment measures, storing the running state information and the related treatment measures in a database, and updating the running state information and the related treatment measures regularly;
judging whether the detection result is an abnormal detection result or not by arranging visual display equipment in each sub-production process flow, if the detection result is the abnormal detection result, acquiring abnormal information of the detection result, and acquiring running state information of each textile device in the current sub-production process flow;
calculating association degree information of abnormal information of the detection result and running state information of each textile device in the current sub-production process flow through a gray association analysis method, acquiring textile devices with association degree information larger than preset association degree information, and taking the textile devices as abnormal textile devices;
obtaining the textile abnormal condition information of the current abnormal textile equipment, inputting the textile abnormal condition information of the current abnormal textile equipment into the database for matching, obtaining relevant treatment measures corresponding to the textile abnormal condition information of the current abnormal textile equipment, and displaying the relevant treatment measures in the visual display equipment according to a preset mode to provide a reference.
6. An automatic fabric component detection system, comprising a memory and a processor, wherein the memory contains an automatic fabric component detection method program, and the automatic fabric component detection method program is executed by the processor to realize the following steps:
acquiring production process flow data information of the current textile, and constructing a monitoring network according to the production process flow data information of the current textile;
acquiring textile production image data information of each textile production process flow based on the monitoring network, and acquiring a target image matrix by preprocessing the textile production image data information;
constructing a textile anomaly detection model based on a neural network, introducing a linear discriminant analysis algorithm and a singular value decomposition algorithm to optimize the textile anomaly detection model, and acquiring detection results for the optimized textile anomaly detection model and a target image matrix;
generating relevant treatment measures according to the detection result, and performing visual display according to a preset mode;
the method comprises the following steps of:
Dividing the current textile production process flow data information into a plurality of sub-production process flow data information, and acquiring the position information of each sub-production process flow and the outline dimension information of the process equipment of each sub-production process flow;
acquiring area information of an area to be monitored of corresponding process equipment of each sub-production process, and constructing a three-dimensional model diagram of the process equipment of each sub-production process according to the outline dimension information of the process equipment of each sub-production process;
constructing a virtual scene, inputting a three-dimensional model diagram of process equipment of the sub-production process flow into the virtual scene, and carrying out shooting point simulation analysis in the virtual scene according to the area information of the area to obtain shooting position points without visual field obstacles;
generating a view-field-free obstacle shooting area according to the view-field-free obstacle shooting position points, setting monitoring nodes based on the view-field-free obstacle shooting area, and constructing a monitoring network according to the monitoring nodes.
7. The automatic detection system for textile components according to claim 6, wherein a linear discriminant analysis algorithm and a singular value decomposition algorithm are introduced to optimize a textile anomaly detection model, and the detection result is obtained for the optimized textile anomaly detection model and a target image matrix, and specifically comprising the steps of:
Acquiring a large number of textile abnormal sample sets, inputting the textile abnormal sample sets into a convolution layer, and introducing a linear discriminant analysis algorithm to perform dimension reduction on the textile abnormal sample sets to acquire an inter-class scattering matrix and an intra-class scattering matrix;
generating a covariance matrix by combining the inter-class scattering matrix and the intra-class scattering matrix, introducing a singular value decomposition algorithm to decompose eigenvalues of the covariance matrix, taking out eigenvectors corresponding to the largest n eigenvalues, and normalizing the eigenvectors to form an eigenvector matrix;
converting the textile abnormal sample data set according to the feature vector matrix to generate a new abnormal sample data set, inputting the new abnormal sample data set into a pooling layer and a full-connection layer, and identifying through an output vector;
and finally classifying by Softmax, storing model parameters, outputting an optimized textile anomaly detection model, and acquiring a detection result according to the optimized textile anomaly detection model and a target image matrix.
8. A computer readable storage medium, characterized in that the computer readable storage medium comprises a textile component automatic detection method program, which, when executed by a processor, implements the steps of the textile component automatic detection method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310595901.9A CN116542956B (en) | 2023-05-25 | 2023-05-25 | Automatic detection method and system for fabric components and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310595901.9A CN116542956B (en) | 2023-05-25 | 2023-05-25 | Automatic detection method and system for fabric components and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116542956A CN116542956A (en) | 2023-08-04 |
| CN116542956B true CN116542956B (en) | 2023-11-17 |
Family
ID=87445224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310595901.9A Active CN116542956B (en) | 2023-05-25 | 2023-05-25 | Automatic detection method and system for fabric components and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116542956B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116931534B (en) * | 2023-09-19 | 2023-12-01 | 深圳市俱进纸品包装有限公司 | Embroidery product production control method and system based on Internet of Things |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN111709492A (en) * | 2020-07-03 | 2020-09-25 | 大连东软教育科技集团有限公司 | Dimension reduction visualization method and device for high-dimensional electronic medical record list and storage medium |
| CN112836671A (en) * | 2021-02-26 | 2021-05-25 | 西北工业大学 | Data dimension reduction method based on maximization ratio and linear discriminant analysis |
| WO2021151276A1 (en) * | 2020-05-20 | 2021-08-05 | 平安科技（深圳）有限公司 | Oct image-based image recognition method and apparatus, and device and storage medium |
| CN113887600A (en) * | 2021-09-26 | 2022-01-04 | 浙江理工大学 | Improved LDA-GSVD-based fabric image defect classification method and system |
| CN114569129A (en) * | 2022-01-20 | 2022-06-03 | 内蒙古工业大学 | Livestock and poultry emotion monitoring method and livestock and poultry emotion monitoring device |
| CN114638779A (en) * | 2021-07-29 | 2022-06-17 | 广州机智云物联网科技有限公司 | Textile quality inspection system, method and device, computer equipment and storage medium |
| CN115578015A (en) * | 2022-12-07 | 2023-01-06 | 华南理工大学 | Sewage treatment overall process supervision method and system based on Internet of things and storage medium |
| CN115880466A (en) * | 2023-02-14 | 2023-03-31 | 山东省地质测绘院 | Urban engineering surveying and mapping method and system based on unmanned aerial vehicle remote sensing |
| CN116091883A (en) * | 2023-04-10 | 2023-05-09 | 深圳市普雷德科技有限公司 | Target detection and identification method, system and storage medium based on multi-source information fusion |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019161362A (en) * | 2018-03-09 | 2019-09-19 | 京セラドキュメントソリューションズ株式会社 | Monitoring system |
| CN111599001B (en) * | 2020-05-14 | 2023-03-14 | 星际（重庆）智能装备技术研究院有限公司 | Unmanned aerial vehicle navigation map construction system and method based on image three-dimensional reconstruction technology |
| KR20220014086A (en) * | 2020-07-28 | 2022-02-04 | 한국전자통신연구원 | Method and Apparatus for Intelligent Operation Management of Infrastructure |
-
2023
- 2023-05-25 CN CN202310595901.9A patent/CN116542956B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| WO2021151276A1 (en) * | 2020-05-20 | 2021-08-05 | 平安科技（深圳）有限公司 | Oct image-based image recognition method and apparatus, and device and storage medium |
| CN111709492A (en) * | 2020-07-03 | 2020-09-25 | 大连东软教育科技集团有限公司 | Dimension reduction visualization method and device for high-dimensional electronic medical record list and storage medium |
| CN112836671A (en) * | 2021-02-26 | 2021-05-25 | 西北工业大学 | Data dimension reduction method based on maximization ratio and linear discriminant analysis |
| WO2022178978A1 (en) * | 2021-02-26 | 2022-09-01 | 西北工业大学 | Data dimensionality reduction method based on maximum ratio and linear discriminant analysis |
| CN114638779A (en) * | 2021-07-29 | 2022-06-17 | 广州机智云物联网科技有限公司 | Textile quality inspection system, method and device, computer equipment and storage medium |
| CN113887600A (en) * | 2021-09-26 | 2022-01-04 | 浙江理工大学 | Improved LDA-GSVD-based fabric image defect classification method and system |
| CN114569129A (en) * | 2022-01-20 | 2022-06-03 | 内蒙古工业大学 | Livestock and poultry emotion monitoring method and livestock and poultry emotion monitoring device |
| CN115578015A (en) * | 2022-12-07 | 2023-01-06 | 华南理工大学 | Sewage treatment overall process supervision method and system based on Internet of things and storage medium |
| CN115880466A (en) * | 2023-02-14 | 2023-03-31 | 山东省地质测绘院 | Urban engineering surveying and mapping method and system based on unmanned aerial vehicle remote sensing |
| CN116091883A (en) * | 2023-04-10 | 2023-05-09 | 深圳市普雷德科技有限公司 | Target detection and identification method, system and storage medium based on multi-source information fusion |
Non-Patent Citations (2)
| Title |
|---|
| 矩阵奇异值分解及其在高维数据处理中的应用;尹芳黎;杨雁莹;王传栋;王士鹏;;数学的实践与认识(15);173-179 * |
| 钱叶魁 ; 陈鸣 ; .基于奇异值分解更新的多元在线异常检测方法.电子与信息学报.2010,(10),122-127. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116542956A (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104778481B (en) | A kind of construction method and device of extensive face pattern analysis sample storehouse | |
| CN105139004B (en) | Facial expression recognizing method based on video sequence | |
| CN111832608B (en) | Iron spectrum image multi-abrasive particle identification method based on single-stage detection model yolov3 | |
| CN110110707A (en) | Artificial intelligence CNN, LSTM neural network dynamic identifying system | |
| CN110232499A (en) | A kind of power distribution network information physical side method for prewarning risk and system | |
| CN116542956B (en) | Automatic detection method and system for fabric components and readable storage medium | |
| CN107341505B (en) | Scene classification method based on image significance and Object Bank | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN111127631A (en) | Single image-based three-dimensional shape and texture reconstruction method, system and storage medium | |
| CN112367400B (en) | Intelligent inspection method and system for power internet of things with edge cloud coordination | |
| CN117156442B (en) | Cloud data security protection method and system based on 5G network | |
| CN113537180B (en) | Tree obstacle identification method and device, computer equipment and storage medium | |
| CN111723749A (en) | Method, system and equipment for identifying wearing of safety helmet | |
| CN115856756A (en) | Fault assessment method for electric energy metering box | |
| CN114022671A (en) | Intelligent ropeway cable position identification method based on residual error neural network | |
| CN117095247B (en) | Numerical control machining-based machining gesture operation optimization method, system and medium | |
| CN117475431B (en) | Food safety supervision method and system based on digital twin technology | |
| CN117726322A (en) | Intelligent management method and system for probe test equipment | |
| CN116912774A (en) | Infrared image target identification method, electronic device and storage medium of power transmission and transformation equipment based on edge calculation | |
| CN111158338A (en) | Chemical risk monitoring method based on principal component analysis | |
| CN116204846A (en) | Method for rapidly positioning abnormal sensor data of power distribution network based on visible graph | |
| CN112580442B (en) | Behavior identification method based on multi-dimensional pyramid hierarchical model | |
| CN111429436B (en) | Intrinsic image analysis method based on multi-scale attention and label loss | |
| CN117633615B (en) | Identification method, device, equipment and storage medium for power regulation sensitive data | |
| CN117519449B (en) | Method, device and equipment for controlling power supply of server main board |
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 |