CN116619780A - Intelligent production method and system of phenolic composite material - Google Patents
Intelligent production method and system of phenolic composite material Download PDFInfo
- Publication number
- CN116619780A CN116619780A CN202310709768.5A CN202310709768A CN116619780A CN 116619780 A CN116619780 A CN 116619780A CN 202310709768 A CN202310709768 A CN 202310709768A CN 116619780 A CN116619780 A CN 116619780A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- feature
- composite material
- classification
- bubble distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000002131 composite material Substances 0.000 title claims abstract description 66
- ISWSIDIOOBJBQZ-UHFFFAOYSA-N phenol group Chemical group C1(=CC=CC=C1)O ISWSIDIOOBJBQZ-UHFFFAOYSA-N 0.000 title claims abstract description 65
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 55
- 238000009826 distribution Methods 0.000 claims abstract description 85
- 238000012545 processing Methods 0.000 claims abstract description 72
- 238000012544 monitoring process Methods 0.000 claims abstract description 61
- 238000009210 therapy by ultrasound Methods 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 30
- 230000000694 effects Effects 0.000 claims abstract description 18
- 239000011159 matrix material Substances 0.000 claims description 88
- 239000013598 vector Substances 0.000 claims description 85
- 238000012546 transfer Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 20
- 230000004044 response Effects 0.000 claims description 19
- 230000007246 mechanism Effects 0.000 claims description 13
- 230000004043 responsiveness Effects 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 15
- 238000013135 deep learning Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000013473 artificial intelligence Methods 0.000 abstract description 4
- 238000000527 sonication Methods 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 7
- 239000000126 substance Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000011176 pooling Methods 0.000 description 5
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- KXGFMDJXCMQABM-UHFFFAOYSA-N 2-methoxy-6-methylphenol Chemical compound [CH]OC1=CC=CC([CH])=C1O KXGFMDJXCMQABM-UHFFFAOYSA-N 0.000 description 3
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 229920001568 phenolic resin Polymers 0.000 description 3
- 239000005011 phenolic resin Substances 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 229920001342 Bakelite® Polymers 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 239000004637 bakelite Substances 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 229920003023 plastic Polymers 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 229920001187 thermosetting polymer Polymers 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C70/00—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts
- B29C70/04—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts comprising reinforcements only, e.g. self-reinforcing plastics
- B29C70/28—Shaping operations therefor
- B29C70/40—Shaping or impregnating by compression not applied
- B29C70/42—Shaping or impregnating by compression not applied for producing articles of definite length, i.e. discrete articles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C70/00—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts
- B29C70/04—Shaping composites, i.e. plastics material comprising reinforcements, fillers or preformed parts, e.g. inserts comprising reinforcements only, e.g. self-reinforcing plastics
- B29C70/28—Shaping operations therefor
- B29C70/54—Component parts, details or accessories; Auxiliary operations, e.g. feeding or storage of prepregs or SMC after impregnation or during ageing
-
- 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
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Composite Materials (AREA)
- Mechanical Engineering (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
Abstract
An intelligent production method of phenolic composite material and a system thereof, which acquire ultrasonic processing monitoring video of a preset time period acquired by a camera and power values of an ultrasonic generating device of a plurality of preset time points in the preset time period; by adopting an artificial intelligence technology based on deep learning, the distribution condition of surface bubbles in the ultrasonic treatment process is monitored in real time, and whether bubbles need to be removed is judged, so that the ultrasonic treatment effect and efficiency are improved.
Description
Technical Field
The application relates to the technical field of intelligent production, in particular to an intelligent production method and system of a phenolic composite material.
Background
Phenolic resin is commonly called bakelite powder, is one of the most long-history plastics and the most important thermosetting plastics in the world, and is widely used as an electric insulating material, a furniture part, a commodity, an artwork, a building material and the like.
The phenolic resin prepared by the prior art has poor hardness and mechanical strength (especially impact resistance), and for this reason, patent CN106147120B provides a preparation method of a phenolic resin matrix composite material, and the preparation method can effectively improve the hardness, tensile strength and bending strength of the composite material.
However, in the actual process of preparing phenolic composite materials, a great deal of bubbles are found to be formed during the treatment process because of the strong cavitation generated by the ultrasonic waves. If the bubbles are too many, the treatment effect is affected, so that the number and the size of the bubbles need to be controlled carefully, and the bubbles need to be removed in time. For this, a viable solution is expected.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides an intelligent production method and system of a phenolic composite material, wherein the intelligent production method and system of the phenolic composite material acquire ultrasonic processing monitoring videos of a preset time period acquired by a camera, and power values of an ultrasonic generating device at a plurality of preset time points in the preset time period; by adopting an artificial intelligence technology based on deep learning, the distribution condition of surface bubbles in the ultrasonic treatment process is monitored in real time, and whether bubbles need to be removed is judged, so that the ultrasonic treatment effect and efficiency are improved.
In a first aspect, an intelligent production method of a phenolic composite material is provided, which comprises the following steps: acquiring ultrasonic treatment monitoring videos of the processed phenolic composite material acquired by a camera in a preset time period, and power values of an ultrasonic generating device at a plurality of preset time points in the preset time period; and
and determining whether to discharge the air bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic generating devices at a plurality of preset time points.
In the above-mentioned intelligent production method of phenolic composite material, determining whether to discharge bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic wave generating devices at the plurality of predetermined time points includes: extracting a surface bubble distribution time sequence feature vector from the ultrasonic processing monitoring video; extracting power timing feature vectors from power values of the ultrasonic wave generating devices at the plurality of predetermined time points; obtaining a classification feature matrix based on a responsiveness estimate between the surface bubble distribution time sequence feature vector and the power time sequence feature vector; and determining whether to discharge bubbles or not based on the classification feature matrix.
In the above-mentioned intelligent production method of phenolic composite material, extracting the surface bubble distribution time sequence feature vector from the ultrasonic processing monitoring video includes: extracting a plurality of ultrasonic processing monitoring key frames from the ultrasonic processing monitoring video; respectively extracting image features of the ultrasonic processing monitoring key frames to obtain a plurality of ultrasonic processing surface bubble distribution feature matrixes; and generating the surface bubble distribution time sequence feature vector based on the plurality of ultrasonic processing surface bubble distribution feature matrices.
In the above-mentioned intelligent production method of phenolic composite material, image feature extraction is performed on the plurality of ultrasonic processing monitoring key frames to obtain a plurality of ultrasonic processing surface bubble distribution feature matrices, respectively, including: and respectively obtaining a plurality of ultrasonic processing surface bubble distribution characteristic matrixes by using the convolution neural network model of the spatial attention mechanism through the plurality of ultrasonic processing monitoring key frames.
In the above-mentioned intelligent production method of phenolic composite material, generating the surface bubble distribution time sequence feature vector based on the plurality of ultrasonic processing surface bubble distribution feature matrices includes: calculating transfer matrixes between every two adjacent ultrasonic treatment surface bubble distribution characteristic matrixes in the ultrasonic treatment surface bubble distribution characteristic matrixes, and calculating the global average value of each transfer matrix to obtain a surface bubble distribution time sequence characteristic vector consisting of the global average values of the plurality of transfer matrixes.
In the above-mentioned intelligent production method of phenolic composite material, extracting power timing characteristic vectors from power values of the ultrasonic wave generating devices at the plurality of predetermined time points includes: and arranging the power values of the ultrasonic generating devices at a plurality of preset time points into input vectors according to the time dimension, and then obtaining power time sequence feature vectors through a one-dimensional convolutional neural network model.
In the above-mentioned intelligent production method of phenolic composite material, obtaining a classification feature matrix based on the estimation of responsiveness between the surface bubble distribution time sequence feature vector and the power time sequence feature vector includes: and calculating the response estimation of the surface bubble distribution time sequence feature vector relative to the power time sequence feature vector to obtain the classification feature matrix.
In the above-mentioned intelligent production method of phenolic composite material, determining whether to discharge bubbles based on the classification feature matrix includes: optimizing the position information expression effect of the classification feature matrix to obtain an optimized classification feature matrix; and passing the optimized classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether bubbles need to be removed or not.
In the above-mentioned intelligent production method of phenolic composite material, optimizing the position information expression effect of the classification feature matrix to obtain an optimized classification feature matrix includes: calculating a location information schema attention response factor for the feature value for each location of the classification feature matrix with the following optimization formula to obtain a plurality of location information schema attention response factors; wherein, the optimization formula is:
wherein->And->Representing the mapping of three-dimensional and two-dimensional real numbers as a function of one-dimensional real numbers, respectively, < >>And->The width and the height of the classification feature matrix are respectively +.>For each eigenvalue of the classification eigenvalue matrix +.>Coordinates of->Is the characteristic value of each position in the classification characteristic matrix, and +.>Is the global mean value of all feature values of the classification feature matrix,/for>Representing a base 2 logarithmic function; and weighting each feature value of the classification feature matrix with the plurality of location information schema attention response factors to obtain the optimized classification feature matrix.
In a second aspect, there is provided an intelligent production system for phenolic composite material, comprising: the ultrasonic processing monitoring video acquisition module is used for acquiring ultrasonic processing monitoring videos of the processed phenolic composite material acquired by the camera in a preset time period and power values of the ultrasonic generating device at a plurality of preset time points in the preset time period; and
and a bubble discharge determining module for determining whether to discharge bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic wave generating devices at the plurality of predetermined time points.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent production method of phenolic composite material according to an embodiment of the application.
Fig. 2 is a schematic diagram of an intelligent production method of phenolic composite material according to an embodiment of the application.
FIG. 3 is a flow chart of the sub-steps of step 120 in the intelligent production method of phenolic composite material according to an embodiment of the present application.
Fig. 4 is a flow chart of the sub-steps of step 121 in the intelligent production method of phenolic composite material according to an embodiment of the present application.
FIG. 5 is a flow chart of the sub-steps of step 124 in the intelligent production method of phenolic composite material according to an embodiment of the present application.
FIG. 6 is a block diagram of an intelligent production system for phenolic composite in accordance with an embodiment of the present application.
Fig. 7 is a schematic view of a scenario of an intelligent production method of a phenolic composite material according to an embodiment of the present application.
Description of the embodiments
The following description of the technical solutions according to the embodiments of the present application will be given with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In describing embodiments of the present application, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the application described herein may be practiced in sequences other than those illustrated or described herein.
In one embodiment of the application, FIG. 1 is a flow chart of a method for intelligent production of phenolic composite materials according to an embodiment of the application. As shown in fig. 1, a method 100 for intelligently producing a phenolic composite material according to an embodiment of the present application includes: 110, acquiring ultrasonic treatment monitoring videos of the processed phenolic composite material acquired by a camera in a preset time period, and power values of an ultrasonic generating device at a plurality of preset time points in the preset time period; and 120, determining whether to discharge bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic generating devices at the plurality of preset time points.
Specifically, in step 110, an ultrasonic treatment monitoring video of the phenolic composite material to be treated acquired by the camera for a predetermined period of time and power values of the ultrasonic wave generating device at a plurality of predetermined time points within the predetermined period of time are acquired. Aiming at the technical problems, the technical conception of the application is to comprehensively utilize ultrasonic treatment monitoring videos and power values of ultrasonic wave generating devices at a plurality of preset time points, monitor the distribution condition of surface bubbles in the ultrasonic treatment process in real time based on deep learning and artificial intelligence technology, and judge whether the bubbles need to be removed or not, thereby improving the effect and efficiency of ultrasonic treatment.
Specifically, in the technical scheme of the application, firstly, an ultrasonic processing monitoring video of a preset time period acquired by a camera is acquired, and power values of an ultrasonic generating device at a plurality of preset time points in the preset time period are acquired. Here, the ultrasonic treatment monitoring video acquired by the camera may reflect the bubble distribution and variation in the ultrasonic treatment process. Meanwhile, the power value can present a dynamic change in the time dimension, and acquiring the power values of the ultrasonic generating device at a plurality of preset time points in the preset time period is an important premise for exploring the influence of the power values of the ultrasonic generating device on the bubble distribution of the ultrasonic treatment surface.
The method comprises the steps of acquiring an ultrasonic processing monitoring video of a preset time period acquired by a camera, and determining the power values of an ultrasonic generating device of a plurality of preset time points in the preset time period, wherein the position and the direction of the camera are firstly confirmed so as to ensure that the situation of the processed phenolic composite material can be completely shot. Then, the position of the ultrasonic wave generating device and the position of the power value monitoring apparatus are confirmed to ensure that the power value of the ultrasonic wave generating device can be accurately monitored.
The ultrasonic wave generator is a device for generating ultrasonic waves, and converts electric energy into mechanical vibration to generate ultrasonic waves. Ultrasonic treatment is a process of processing and modifying a substance with ultrasonic waves that, when propagating in the substance, produce acoustic effects, such as reflections, refractions, scattering, etc., of the ultrasonic waves, which can be used to alter the properties and structure of the substance.
The sonication monitoring video is a video used to monitor the condition and changes of the substance during sonication. Information such as morphology and color of the surface of the substance may be recorded, or information such as structure and properties of the inside of the substance may be recorded. By analyzing and comparing the ultrasonic treatment monitoring videos, the influence and effect of ultrasonic treatment on the substances can be known, so that parameters and processes of ultrasonic treatment are optimized.
Specifically, in step 120, it is determined whether to discharge bubbles based on the ultrasonic processing monitor video and the power values of the ultrasonic wave generating means at the plurality of predetermined time points. The method can improve the accuracy and efficiency of bubble discharge, and avoid the defect that bubbles are required to be observed manually in the traditional method. Fig. 2 is a schematic diagram of an intelligent production method of phenolic composite material according to an embodiment of the application. FIG. 3 is a flow chart of the sub-steps of step 120 in the intelligent production method of phenolic composite material according to an embodiment of the present application. As shown in fig. 2 and 3, determining whether to discharge bubbles based on the ultrasonic processing monitor video and the power values of the ultrasonic wave generating means at the plurality of predetermined time points includes: 121, extracting a surface bubble distribution time sequence feature vector from the ultrasonic processing monitoring video; 122 extracting power timing feature vectors from power values of the ultrasonic wave generating means at the plurality of predetermined time points; 123, obtaining a classification feature matrix based on the responsiveness estimation between the surface bubble distribution time sequence feature vector and the power time sequence feature vector; 124, determining whether to discharge the air bubble based on the classification feature matrix.
First, in step 121, a surface bubble distribution timing feature vector is extracted from the sonication surveillance video. It is considered that if the whole video is analyzed directly, a lot of time and resources are consumed. In the technical scheme of the application, a plurality of ultrasonic processing monitoring key frames are extracted from the ultrasonic processing monitoring video so as to reduce the calculated amount and improve the efficiency. Fig. 4 is a flow chart of the sub-steps of step 121 in the intelligent production method of phenolic composite material according to an embodiment of the present application. As shown in fig. 4, extracting a surface bubble distribution timing feature vector from the ultrasonic processing monitor video includes: 1211, extracting a plurality of sonication monitoring key frames from the sonication monitoring video; 1212, respectively extracting image features of the ultrasonic processing monitoring key frames to obtain a plurality of ultrasonic processing surface bubble distribution feature matrixes; and 1213 generating the surface bubble distribution timing feature vector based on the plurality of sonicated surface bubble distribution feature matrices.
Specifically, a plurality of sonication monitoring key frames are extracted from the sonication monitoring video. Each frame in the sonication surveillance video contains a distribution of surface bubbles, but not every frame is useful for analysis and processing. Therefore, there is a need to extract a plurality of sonication monitoring key frames from a sonication monitoring video in order to better analyze and process the surface bubble distribution.
Firstly, preprocessing is carried out on the ultrasonic processing monitoring video, including denoising, enhancement, edge detection and the like, so as to better identify the distribution condition of surface bubbles. Then, the surface bubbles in each frame of video are segmented and extracted through an image processing technology, and a binarized image of the surface bubbles is obtained. Then, selecting some key frames for extraction according to the distribution condition of the surface bubbles, wherein the selection of the key frames can be judged according to the quantity, distribution density, change trend and other factors of the surface bubbles. And finally, storing and backing up the obtained plurality of ultrasonic processing monitoring key frames for subsequent analysis and processing.
Further, image feature extraction is performed on the plurality of ultrasonic processing monitoring key frames to obtain a plurality of ultrasonic processing surface bubble distribution feature matrixes, including: and respectively obtaining a plurality of ultrasonic processing surface bubble distribution characteristic matrixes by using the convolution neural network model of the spatial attention mechanism through the plurality of ultrasonic processing monitoring key frames.
And respectively obtaining a plurality of ultrasonic processing surface bubble distribution characteristic matrixes by using the convolution neural network model of the spatial attention mechanism through the plurality of ultrasonic processing monitoring key frames. Here, the convolutional neural network model using the spatial attention mechanism can effectively extract the characteristics of bubble distribution on the ultrasonic processing surface, highlight the information of bubble areas and inhibit the information of other irrelevant areas, so that a plurality of characteristic matrixes of bubble distribution on the ultrasonic processing surface are obtained.
It should be understood that the convolutional neural network model of the spatial attention mechanism is a deep learning model for image recognition and segmentation, and is mainly characterized in that the spatial attention mechanism is introduced, and attention weights can be distributed between different feature maps in a self-adaptive manner, so that the recognition accuracy and the robustness of the model are improved.
The convolutional neural network model of the spatial attention mechanism comprises: and the convolution layer is used for extracting the characteristics of the image, and the image can be subjected to convolution operation through a plurality of convolution check images to obtain a plurality of characteristic images. The spatial attention mechanism is used for adaptively distributing attention weights, so that the recognition accuracy and the robustness of the model are improved. And the pooling layer is used for reducing the dimension of the feature map, reducing the model parameters and improving the robustness of the model. And the full-connection layer converts the feature map into a classification result or a segmentation result.
The channel attention mechanism is mainly used for carrying out self-adaptive weighting on different feature graphs, so that the robustness of the model is improved. Specifically, the channel attention mechanism obtains a channel weight vector by global pooling of each feature map, and then weights the vector with the original feature map to obtain a new feature map. The spatial attention mechanism is mainly used for carrying out self-adaptive weighting on the interior of the same feature map, so that the recognition accuracy of the model is improved. The convolutional neural network model of the spatial attention mechanism has the characteristics of high efficiency, accuracy and robustness, and can be applied to the fields of image recognition, segmentation and the like.
Still further, generating the surface bubble distribution timing feature vector based on the plurality of sonicated surface bubble distribution feature matrices, comprises: calculating transfer matrixes between every two adjacent ultrasonic treatment surface bubble distribution characteristic matrixes in the ultrasonic treatment surface bubble distribution characteristic matrixes, and calculating the global average value of each transfer matrix to obtain a surface bubble distribution time sequence characteristic vector consisting of the global average values of the plurality of transfer matrixes.
In order to capture the dynamic change of the surface bubble distribution during the ultrasonic treatment, the effect of the ultrasonic treatment is reflected. In the technical scheme of the application, a transfer matrix between every two adjacent ultrasonic treatment surface bubble distribution feature matrices in the ultrasonic treatment surface bubble distribution feature matrices is calculated, and the global average value of each transfer matrix is calculated to obtain a surface bubble distribution time sequence feature vector consisting of the global average values of the transfer matrices. Here, the transfer matrix may be used to quantify the correlation between the surface bubble distribution feature matrices. That is, the trend of the change in the surface bubble distribution during the ultrasonic treatment is reflected by calculating the transfer matrix between each two adjacent surface bubble distribution feature matrices. Meanwhile, in order to reduce the dimension and extract key information, a global average value operation can be performed.
Global average refers to the average of all data in a set of data. Here, the global average value of the plurality of transfer matrices, that is, the value obtained by dividing the total number of elements by adding each element in the plurality of transfer matrices is calculated. This global average can be used to represent the global features of multiple transfer matrices, which are an integral part of the surface bubble distribution timing feature vector.
In one embodiment of the application, it is assumed that there areNA plurality of ultrasonic treatment surface bubble distribution feature matrices, each feature matrix having dimensions ofM×KWhereinMThe size of the time window is indicated,Kindicating the number of surface bubbles.
Firstly, it is necessary to calculate a transfer matrix between every two adjacent feature matrices, assuming that the two feature matrices are respectivelyXiAndXi+1, then the transfer matrix between themTiThe calculation can be made by the following formula:。
wherein, the liquid crystal display device comprises a liquid crystal display device,representing multiplication of matrix>Representation->Is a transposed matrix of (a).
Next, the global mean of all transfer matrices needs to be calculated, as follows:。
wherein, the liquid crystal display device comprises a liquid crystal display device,representing the global average of all transfer matrices. Finally, will->And (3) expanding the surface bubble distribution time sequence feature vector into a vector, wherein the obtained vector is a surface bubble distribution time sequence feature vector formed by a plurality of transfer matrix global average values. The dimension of the vector is->WhereinIndicating the number of surface bubbles.
Then, in step 122, power timing feature vectors are extracted from power values of the ultrasonic wave generating devices at the plurality of predetermined time points. It comprises the following steps: and arranging the power values of the ultrasonic generating devices at a plurality of preset time points into input vectors according to the time dimension, and then obtaining power time sequence feature vectors through a one-dimensional convolutional neural network model.
That is, the power values of the ultrasonic wave generating devices at a plurality of preset time points are arranged into input vectors according to the time dimension, and then the input vectors are passed through a one-dimensional convolutional neural network model to obtain power time sequence feature vectors. Here, the one-dimensional convolutional neural network model (1D-CNN) is a deep learning algorithm capable of effectively processing sequence data, and can extract local features in the sequence. Specifically, the power value of the ultrasonic wave generating device is a time-varying sequence reflecting the energy input condition during ultrasonic treatment. By taking the sequence as the input of a one-dimensional convolutional neural network model, a convolutional kernel can be utilized to slide in the time dimension, the variation trend and mode of power values can be captured, and a power time sequence characteristic vector is generated and used for describing the energy characteristic in the ultrasonic processing process.
In one embodiment of the present application, power values of the ultrasonic wave generating means at a plurality of predetermined time points are arranged in a time dimension as an input vector, the length of which is the number of predetermined time points; preprocessing the input vector, such as normalizing, smoothing, denoising and the like, so as to improve the stability and accuracy of the model; and inputting the preprocessed input vector into a one-dimensional convolutional neural network model for processing. Specifically, in the first layer of the model, a one-dimensional convolution operation is used to extract features in the input vector. The convolution operation can be understood as performing sliding window processing on the input vector, performing product operation on data in the window and a convolution kernel to obtain a new characteristic value, and then moving the window to the right by one unit, and continuing the product operation until the whole input vector is covered; after the convolution operation, a pooling operation is used to reduce the dimensionality of the feature vector. The pooling operation can be understood as performing downsampling processing on the input vector, performing statistics and summarization on data in the window to obtain a new characteristic value, and then moving the window to the right by one unit, and continuing the statistics and summarization until the whole input vector is covered; nonlinear activation functions are used to increase the nonlinear capabilities of the model, common activation functions include ReLU, sigmoid, tanh, etc. The power timing feature vector contains time sequence information in the input vector and is processed by a one-dimensional convolutional neural network model for subsequent analysis and processing.
The one-dimensional convolutional neural network model is a deep learning model, similar to the traditional convolutional neural network model, but is only carried out in one direction during the convolutional operation, namely, the convolutional operation is only carried out on a time axis. One-dimensional convolutional neural network models typically include components such as a convolutional layer for extracting timing features, a pooling layer for reducing dimensions, and a fully connected layer for classification or regression tasks. When time sequence data is processed, the one-dimensional convolutional neural network model can capture local modes and long-term dependency relations in the sequence.
Next, in step 123, a classification feature matrix is derived based on the responsiveness estimate between the surface bubble distribution timing feature vector and the power timing feature vector. It comprises the following steps: and calculating the response estimation of the surface bubble distribution time sequence feature vector relative to the power time sequence feature vector to obtain the classification feature matrix.
Further, a responsiveness estimate of the surface bubble distribution timing feature vector relative to the power timing feature vector is calculated to obtain a classification feature matrix. Here, the responsiveness estimation may be used to measure the correlation between two vectors. Specifically, the responsiveness estimate may reflect the extent to which the power variation of the ultrasonic wave generating device affects the bubble distribution of the ultrasonic treatment surface.
Wherein the responsiveness estimation is used for measuring the correlation between the surface bubble distribution time sequence characteristic vector and the power time sequence characteristic vector, namely the influence degree of the power change of the ultrasonic generating device on the ultrasonic treatment surface bubble distribution. In one embodiment of the application, the responsiveness estimation may be achieved by calculating a correlation coefficient between two vectors. The correlation coefficient is a value between-1 and 1 reflecting the degree of linear relationship between the two variables. When the correlation coefficient is positive, the positive correlation relationship exists between the two variables, namely when one variable is increased, the other variable is also increased; when the correlation coefficient is negative, it means that there is a negative correlation between two variables, i.e., when one variable increases, the other variable decreases; when the correlation coefficient is close to 0, it means that there is no linear relationship between the two variables.
By means of the response estimation, the influence degree of the power change of the ultrasonic wave generating device on the surface bubble distribution time sequence characteristic vector can be known, so that the behavior of the system can be better understood and predicted, and more effective management and coping strategies can be formulated.
Finally, in step 124, it is determined whether to expel the air bubbles based on the classification feature matrix. FIG. 5 is a flowchart of the substep of step 124 in the method for intelligently producing phenolic composite according to an embodiment of the present application, as shown in FIG. 5, for determining whether to discharge air bubbles based on the classification feature matrix, including: 1241, performing position information expression effect optimization on the classification feature matrix to obtain an optimized classification feature matrix; and 1242, passing the optimized classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether bubbles need to be removed.
And then, the classification feature matrix is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether bubbles need to be removed or not. The classifier can output a classification result according to the input of the classification feature matrix, and indicates whether bubbles need to be removed or not. In a subsequent application, the production process may be guided based on the classification result. That is, the classification result is an effective indication signal, which can help personnel preparing the phenolic composite material to take measures for eliminating bubbles in time so as to ensure the effect of ultrasonic treatment and the quality of the material.
In the technical scheme of the application, when the classification feature matrix is obtained by calculating the response estimation of the surface bubble distribution time sequence feature vector relative to the power time sequence feature vector based on a Gaussian density map, the response estimation variance matrix of the Gaussian density map is obtained based on the self variance matrix of the surface bubble distribution time sequence feature vector and the power time sequence feature vector, and the feature value arrangement of each position of the surface bubble distribution time sequence feature vector and the power time sequence feature vector accords with the feature distribution in the time sequence direction, so that the variance value of each position of the response estimation variance matrix has a corresponding time sequence distribution position attribute, and therefore, when the classification feature matrix is further obtained by Gaussian discretization, the feature value of each position of the classification feature matrix also has a corresponding position attribute. However, when the classification feature matrix is subjected to classification regression by a classifier, the classification feature matrix needs to be expanded into feature vectors, that is, rearrangement transformation based on position attribute related to feature values of the classification feature matrix, so in order to promote the position information expression effect of each feature value of the classification feature matrix in arrangement transformation, a position information schema attention response factor of the feature value of each position of the classification feature matrix is calculated, specifically expressed as: calculating a location information schema attention response factor for the feature value for each location of the classification feature matrix with the following optimization formula to obtain a plurality of location information schema attention response factors; wherein, the optimization formula is:
wherein->And->Representing the mapping of three-dimensional and two-dimensional real numbers as a function of one-dimensional real numbers, respectively, < >>And->The width and the height of the classification feature matrix are respectively +.>For each eigenvalue of the classification eigenvalue matrix +.>Coordinates of->Is the characteristic value of each position in the classification characteristic matrix, and +.>Is the global mean value of all feature values of the classification feature matrix,/for>Representing a base 2 logarithmic function; and weighting each feature value of the classification feature matrix with the plurality of location information schema attention response factors to obtain the optimized classification feature matrix.
Here, the positional information schema attention response factor is represented by schema information modeling relative geometric directions and relative geometric distances of pixel values with respect to high-dimensional spatial locations of the global feature distribution, capturing global shape weights of feature manifolds of the high-dimensional feature distribution of the classification feature matrix while achieving a per-position aggregation of feature values with respect to the global feature distribution, such that manifold shapes of the classification feature matrix are highly responsive to shape information of respective sub-manifolds to obtain an arrangement invariance (permutation invariance) property of the high-dimensional feature manifolds. Therefore, by weighting each feature value of the classification feature matrix by the position information schema attention response factor, the position information expression effect of each feature value of the feature vector obtained after the expansion of the classification feature matrix on the feature value of the classification feature matrix during arrangement transformation can be improved, and the accuracy of the classification result obtained by the classification feature matrix through the classifier can be improved.
Further, in one embodiment of the present application, the optimized classification feature matrix is passed through a classifier using a conventional machine learning algorithm to obtain a classification result, such as algorithms of a Support Vector Machine (SVM), decision Tree (Decision Tree), random Forest (Random Forest), etc., and the optimized classification feature matrix is used as an input to train a classifier, and then the classifier is used to classify new data. The classification result indicates whether or not the air bubble needs to be removed.
In another embodiment of the present application, the optimized classification feature matrix is passed through a classifier using a deep learning algorithm to obtain classification results, such as convolutional neural network (Convolutional Neural Network, CNN) and cyclic neural network (Recurrent Neural Network, RNN) algorithms, the optimized classification feature matrix is used as input, a classifier is trained, and the classifier is used to classify new data, where the classification results indicate whether bubbles need to be removed.
Wherein the classifier is a machine learning algorithm for classifying data in the dataset into different categories or labels. Common classifiers include decision trees, naive Bayes classifiers, logistic regression, support vector machines, deep learning models, and the like.
The application has the following technical effects: 1. provides an intelligent production scheme of the phenolic composite material, and more particularly relates to an intelligent bubble removal scheme. 2. According to the scheme, the ultrasonic processing monitoring video and the power values of the ultrasonic generating devices at a plurality of preset time points are comprehensively utilized, the distribution condition of surface bubbles in the ultrasonic processing process can be monitored in real time, and whether the bubbles need to be removed or not is judged, so that the ultrasonic processing effect and efficiency are improved.
In summary, the method 100 for intelligent production of phenolic composite material according to the embodiment of the present application is illustrated, which obtains the ultrasonic processing monitoring video of a predetermined time period collected by the camera, and the power values of the ultrasonic generating device at a plurality of predetermined time points within the predetermined time period; by adopting an artificial intelligence technology based on deep learning, the distribution condition of surface bubbles in the ultrasonic treatment process is monitored in real time, and whether bubbles need to be removed is judged, so that the ultrasonic treatment effect and efficiency are improved.
In one embodiment of the application, FIG. 6 is a block diagram of an intelligent production system for phenolic composites in accordance with an embodiment of the application. As shown in fig. 6, an intelligent production system 200 of phenolic composite material according to an embodiment of the present application includes: an ultrasonic processing monitoring video acquisition module 210, configured to acquire ultrasonic processing monitoring videos of the phenolic composite material to be processed acquired by the camera in a predetermined time period, and power values of the ultrasonic generating device at a plurality of predetermined time points in the predetermined time period; and a bubble discharge determination module 220 for determining whether to discharge bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic wave generating means at the plurality of predetermined time points. Here, it will be understood by those skilled in the art that the specific functions and operations of the respective units and modules in the above-described intelligent production system of phenolic composite material have been described in detail in the above description of the intelligent production method of phenolic composite material with reference to fig. 1 to 5, and thus, repetitive descriptions thereof will be omitted.
As described above, the intelligent production system 200 of the phenolic composite material according to the embodiment of the present application may be implemented in various terminal devices, for example, a server for intelligent production of the phenolic composite material, and the like. In one example, the intelligent production system 200 of phenolic composite materials in accordance with embodiments of the present application may be integrated into the terminal device as a software module and/or hardware module. For example, the smart production system 200 for phenolic composite may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the phenolic composite intelligent production system 200 could equally be one of the numerous hardware modules of the end device.
Alternatively, in another example, the phenolic composite intelligent production system 200 and the end device may be separate devices, and the phenolic composite intelligent production system 200 may be connected to the end device via a wired and/or wireless network and communicate the interactive information in accordance with a agreed data format.
Fig. 7 is a schematic view of a scenario of an intelligent production method of a phenolic composite material according to an embodiment of the present application. As shown in fig. 7, in this application scenario, first, an ultrasonic processing monitoring video (e.g., C1 as illustrated in fig. 7) of a predetermined period of time acquired by a camera is acquired, and power values (e.g., C2 as illustrated in fig. 7) of an ultrasonic wave generating device (e.g., M as illustrated in fig. 7) at a plurality of predetermined points of time within the predetermined period of time; the acquired sonication monitoring video and power values are then input into a server (e.g., S as illustrated in fig. 7) deployed with an intelligent production algorithm of phenolic composite material, wherein the server is capable of processing the sonication monitoring video and the power values based on the intelligent production algorithm of phenolic composite material to generate a classification result indicating whether or not bubble removal is required.
The block diagrams of the devices, apparatuses, devices, systems referred to in the present application are only illustrative examples and are not intended to require or imply that the connections, arrangements, configurations must be made in the manner shown in the block diagrams. As will be appreciated by one of skill in the art, the devices, apparatuses, devices, systems may be connected, arranged, configured in any manner. Words such as "including," "comprising," "having," and the like are words of openness and mean "including but not limited to," and are used interchangeably therewith. The terms "or" and "as used herein refer to and are used interchangeably with the term" and/or "unless the context clearly indicates otherwise. The term "such as" as used herein refers to, and is used interchangeably with, the phrase "such as, but not limited to.
It is also noted that in the apparatus, devices and methods of the present application, the components or steps may be disassembled and/or assembled. Such decomposition and/or recombination should be considered as equivalent aspects of the present application.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the application. Thus, the present application is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing description has been presented for purposes of illustration and description. Furthermore, this description is not intended to limit embodiments of the application to the form disclosed herein. Although a number of example aspects and embodiments have been discussed above, a person of ordinary skill in the art will recognize certain variations, modifications, alterations, additions, and subcombinations thereof.
Claims (10)
1. An intelligent production method of a phenolic composite material is characterized by comprising the following steps: acquiring ultrasonic treatment monitoring videos of the processed phenolic composite material acquired by a camera in a preset time period, and power values of an ultrasonic generating device at a plurality of preset time points in the preset time period; and determining whether to discharge the air bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic generating devices at the plurality of predetermined time points.
2. The intelligent production method of the phenolic composite material according to claim 1, wherein determining whether to discharge the air bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic wave generating devices at the plurality of predetermined time points includes: extracting a surface bubble distribution time sequence feature vector from the ultrasonic processing monitoring video; extracting power timing feature vectors from power values of the ultrasonic wave generating devices at the plurality of predetermined time points; obtaining a classification feature matrix based on a responsiveness estimate between the surface bubble distribution time sequence feature vector and the power time sequence feature vector; and determining whether to discharge bubbles or not based on the classification feature matrix.
3. The intelligent production method of the phenolic composite material according to claim 2, wherein extracting the surface bubble distribution timing feature vector from the ultrasonic treatment monitoring video comprises: extracting a plurality of ultrasonic processing monitoring key frames from the ultrasonic processing monitoring video; respectively extracting image features of the ultrasonic processing monitoring key frames to obtain a plurality of ultrasonic processing surface bubble distribution feature matrixes; and generating the surface bubble distribution time sequence feature vector based on the plurality of ultrasonic processing surface bubble distribution feature matrices.
4. The intelligent production method of the phenolic composite material according to claim 3, wherein the image feature extraction is performed on the plurality of ultrasonic treatment monitoring key frames to obtain a plurality of ultrasonic treatment surface bubble distribution feature matrices, respectively, and the method comprises the following steps: and respectively obtaining a plurality of ultrasonic processing surface bubble distribution characteristic matrixes by using the convolution neural network model of the spatial attention mechanism through the plurality of ultrasonic processing monitoring key frames.
5. The method of intelligent production of phenolic composite material of claim 4, wherein generating the surface bubble distribution timing feature vector based on the plurality of ultrasonic processed surface bubble distribution feature matrices comprises: calculating transfer matrixes between every two adjacent ultrasonic treatment surface bubble distribution characteristic matrixes in the ultrasonic treatment surface bubble distribution characteristic matrixes, and calculating the global average value of each transfer matrix to obtain a surface bubble distribution time sequence characteristic vector consisting of the global average values of the plurality of transfer matrixes.
6. The method of intelligent production of phenolic composite material of claim 5, wherein extracting power timing feature vectors from power values of the ultrasonic wave generating means at the plurality of predetermined points in time comprises: and arranging the power values of the ultrasonic generating devices at a plurality of preset time points into input vectors according to the time dimension, and then obtaining power time sequence feature vectors through a one-dimensional convolutional neural network model.
7. The method of intelligent production of phenolic composite material of claim 6, wherein deriving a classification feature matrix based on a responsiveness estimate between the surface bubble distribution timing feature vector and the power timing feature vector, comprises: and calculating the response estimation of the surface bubble distribution time sequence feature vector relative to the power time sequence feature vector to obtain the classification feature matrix.
8. The intelligent production method of the phenolic composite material according to claim 7, wherein determining whether to discharge air bubbles based on the classification feature matrix comprises: optimizing the position information expression effect of the classification feature matrix to obtain an optimized classification feature matrix; and passing the optimized classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether bubbles need to be removed or not.
9. The intelligent production method of the phenolic composite material according to claim 8, wherein optimizing the position information expression effect of the classification feature matrix to obtain an optimized classification feature matrix comprises: calculating a location information schema attention response factor for the feature value for each location of the classification feature matrix with the following optimization formula to obtain a plurality of location information schema attention response factors; wherein, the optimization formula is:
wherein->And->Representing the mapping of three-dimensional and two-dimensional real numbers as a function of one-dimensional real numbers, respectively, < >>And->The width and the height of the classification feature matrix are respectively +.>For each eigenvalue of the classification eigenvalue matrix +.>Coordinates of->Is the characteristic value of each position in the classification characteristic matrix, and +.>Is the global mean value of all feature values of the classification feature matrix,/for>Representing a base 2 logarithmic function; andthe individual eigenvalues of the classification feature matrix are weighted with the plurality of location information schema attention response factors to obtain the optimized classification feature matrix.
10. An intelligent production system of phenolic composite material, characterized by comprising: the ultrasonic processing monitoring video acquisition module is used for acquiring ultrasonic processing monitoring videos of the processed phenolic composite material acquired by the camera in a preset time period and power values of the ultrasonic generating device at a plurality of preset time points in the preset time period; and a bubble discharge determination module for determining whether to discharge bubbles based on the ultrasonic processing monitoring video and the power values of the ultrasonic wave generating devices at the plurality of predetermined time points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310709768.5A CN116619780A (en) | 2023-06-15 | 2023-06-15 | Intelligent production method and system of phenolic composite material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310709768.5A CN116619780A (en) | 2023-06-15 | 2023-06-15 | Intelligent production method and system of phenolic composite material |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116619780A true CN116619780A (en) | 2023-08-22 |
Family
ID=87641797
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310709768.5A Pending CN116619780A (en) | 2023-06-15 | 2023-06-15 | Intelligent production method and system of phenolic composite material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116619780A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117283743A (en) * | 2023-11-23 | 2023-12-26 | 绵阳华远同创科技有限公司 | Resin production molding processing flow prediction control system and method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106064445A (en) * | 2016-07-15 | 2016-11-02 | 罗海灵 | A kind of material conveyor and use the injection machine of this device |
| CN115578676A (en) * | 2022-10-27 | 2023-01-06 | 浙江宇鑫纺织印染有限公司 | Green energy-saving intelligent dyeing and finishing process and system thereof |
| CN115863193A (en) * | 2022-12-27 | 2023-03-28 | 江西蓝微电子科技有限公司 | Gold-plated palladium-copper-based bonding wire and preparation method thereof |
| CN116030897A (en) * | 2023-01-31 | 2023-04-28 | 北京宏科庆能科技有限公司 | Separation method and system for oilfield associated gas |
-
2023
- 2023-06-15 CN CN202310709768.5A patent/CN116619780A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106064445A (en) * | 2016-07-15 | 2016-11-02 | 罗海灵 | A kind of material conveyor and use the injection machine of this device |
| CN115578676A (en) * | 2022-10-27 | 2023-01-06 | 浙江宇鑫纺织印染有限公司 | Green energy-saving intelligent dyeing and finishing process and system thereof |
| CN115863193A (en) * | 2022-12-27 | 2023-03-28 | 江西蓝微电子科技有限公司 | Gold-plated palladium-copper-based bonding wire and preparation method thereof |
| CN116030897A (en) * | 2023-01-31 | 2023-04-28 | 北京宏科庆能科技有限公司 | Separation method and system for oilfield associated gas |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117283743A (en) * | 2023-11-23 | 2023-12-26 | 绵阳华远同创科技有限公司 | Resin production molding processing flow prediction control system and method |
| CN117283743B (en) * | 2023-11-23 | 2024-02-02 | 绵阳华远同创科技有限公司 | Resin production molding processing flow prediction control system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| He et al. | Application of deep learning in integrated pest management: A real-time system for detection and diagnosis of oilseed rape pests | |
| Wang et al. | A comparative study of encoding, pooling and normalization methods for action recognition | |
| Li et al. | Activity recognition using dynamic subspace angles | |
| Hu | Design and implementation of abnormal behavior detection based on deep intelligent analysis algorithms in massive video surveillance | |
| CN104346503A (en) | Human face image based emotional health monitoring method and mobile phone | |
| CN116619780A (en) | Intelligent production method and system of phenolic composite material | |
| Avola et al. | Real-time deep learning method for automated detection and localization of structural defects in manufactured products | |
| Bose et al. | In-situ recognition of hand gesture via Enhanced Xception based single-stage deep convolutional neural network | |
| CN115294563A (en) | 3D point cloud analysis method and device based on Transformer and capable of enhancing local semantic learning ability | |
| CN113673465A (en) | Image detection method, device, equipment and readable storage medium | |
| Li et al. | Gabor Log-Euclidean Gaussian and its fusion with deep network based on self-attention for face recognition | |
| Cui et al. | Dimension reduction and defect recognition of strip surface defects based on intelligent information processing | |
| Zeng et al. | Domestic activities classification from audio recordings using multi-scale dilated depthwise separable convolutional network | |
| CN113537240B (en) | Deformation zone intelligent extraction method and system based on radar sequence image | |
| Kabakus | A novel sketch recognition model based on convolutional neural networks | |
| Li et al. | Research on hybrid information recognition algorithm and quality of golf swing | |
| Chitaliya et al. | Comparative analysis using fast discrete Curvelet transform via wrapping and discrete Contourlet transform for feature extraction and recognition | |
| CN108664919A (en) | A kind of Activity recognition and detection method based on single sample | |
| Chun-man et al. | Face expression recognition based on improved MobileNeXt | |
| Lu et al. | Face recognition based on weighted wavelet transform and compressed sensing | |
| CN113887509A (en) | Rapid multi-modal video face recognition method based on image set | |
| Qiao et al. | Lung nodule classification using curvelet transform, LDA algorithm and BAT-SVM algorithm | |
| Jabshetti et al. | Object detection using Regionlet transform | |
| Xu-Dong et al. | Control Chart Recognition Method Based on Transfer Learning | |
| CN115063870B (en) | Fake video portrait detection method based on facial action unit |
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 |