CN116463079A - Intelligent preparation method and system of adhesive - Google Patents
Intelligent preparation method and system of adhesive Download PDFInfo
- Publication number
- CN116463079A CN116463079A CN202310527598.9A CN202310527598A CN116463079A CN 116463079 A CN116463079 A CN 116463079A CN 202310527598 A CN202310527598 A CN 202310527598A CN 116463079 A CN116463079 A CN 116463079A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- stirring resistance
- stirring
- feature vector
- resistance value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 239000000853 adhesive Substances 0.000 title claims abstract description 91
- 230000001070 adhesive effect Effects 0.000 title claims abstract description 91
- 238000002360 preparation method Methods 0.000 title claims abstract description 58
- 238000003756 stirring Methods 0.000 claims abstract description 429
- 239000000203 mixture Substances 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims abstract description 35
- 239000006087 Silane Coupling Agent Substances 0.000 claims abstract description 23
- 238000010438 heat treatment Methods 0.000 claims abstract description 18
- 239000003795 chemical substances by application Substances 0.000 claims abstract description 16
- 230000003712 anti-aging effect Effects 0.000 claims abstract description 14
- 239000003054 catalyst Substances 0.000 claims abstract description 14
- 229920000459 Nitrile rubber Polymers 0.000 claims abstract description 13
- 229920002635 polyurethane Polymers 0.000 claims abstract description 13
- 239000004814 polyurethane Substances 0.000 claims abstract description 13
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 239000004005 microsphere Substances 0.000 claims abstract description 9
- 229920000642 polymer Polymers 0.000 claims abstract description 9
- 239000012744 reinforcing agent Substances 0.000 claims abstract description 9
- 229920002725 thermoplastic elastomer Polymers 0.000 claims abstract description 9
- 239000012745 toughening agent Substances 0.000 claims abstract description 9
- 239000004890 Hydrophobing Agent Substances 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 324
- 230000008859 change Effects 0.000 claims description 163
- 230000004927 fusion Effects 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000002156 mixing Methods 0.000 claims description 9
- 238000005538 encapsulation Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 7
- 238000013019 agitation Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000003068 static effect Effects 0.000 description 6
- 230000014509 gene expression Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 239000002699 waste material Substances 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000015654 memory Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004078 waterproofing Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004026 adhesive bonding Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B01—PHYSICAL OR CHEMICAL PROCESSES OR APPARATUS IN GENERAL
- B01F—MIXING, e.g. DISSOLVING, EMULSIFYING OR DISPERSING
- B01F33/00—Other mixers; Mixing plants; Combinations of mixers
- B01F33/80—Mixing plants; Combinations of mixers
- B01F33/836—Mixing plants; Combinations of mixers combining mixing with other treatments
- B01F33/8362—Mixing plants; Combinations of mixers combining mixing with other treatments with chemical reactions
-
- C—CHEMISTRY; METALLURGY
- C09—DYES; PAINTS; POLISHES; NATURAL RESINS; ADHESIVES; COMPOSITIONS NOT OTHERWISE PROVIDED FOR; APPLICATIONS OF MATERIALS NOT OTHERWISE PROVIDED FOR
- C09J—ADHESIVES; NON-MECHANICAL ASPECTS OF ADHESIVE PROCESSES IN GENERAL; ADHESIVE PROCESSES NOT PROVIDED FOR ELSEWHERE; USE OF MATERIALS AS ADHESIVES
- C09J109/00—Adhesives based on homopolymers or copolymers of conjugated diene hydrocarbons
- C09J109/02—Copolymers with acrylonitrile
-
- C—CHEMISTRY; METALLURGY
- C09—DYES; PAINTS; POLISHES; NATURAL RESINS; ADHESIVES; COMPOSITIONS NOT OTHERWISE PROVIDED FOR; APPLICATIONS OF MATERIALS NOT OTHERWISE PROVIDED FOR
- C09J—ADHESIVES; NON-MECHANICAL ASPECTS OF ADHESIVE PROCESSES IN GENERAL; ADHESIVE PROCESSES NOT PROVIDED FOR ELSEWHERE; USE OF MATERIALS AS ADHESIVES
- C09J175/00—Adhesives based on polyureas or polyurethanes; Adhesives based on derivatives of such polymers
- C09J175/04—Polyurethanes
-
- C—CHEMISTRY; METALLURGY
- C09—DYES; PAINTS; POLISHES; NATURAL RESINS; ADHESIVES; COMPOSITIONS NOT OTHERWISE PROVIDED FOR; APPLICATIONS OF MATERIALS NOT OTHERWISE PROVIDED FOR
- C09J—ADHESIVES; NON-MECHANICAL ASPECTS OF ADHESIVE PROCESSES IN GENERAL; ADHESIVE PROCESSES NOT PROVIDED FOR ELSEWHERE; USE OF MATERIALS AS ADHESIVES
- C09J201/00—Adhesives based on unspecified macromolecular compounds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- 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
- G06N3/047—Probabilistic or stochastic networks
-
- 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
-
- C—CHEMISTRY; METALLURGY
- C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
- C08L—COMPOSITIONS OF MACROMOLECULAR COMPOUNDS
- C08L2205/00—Polymer mixtures characterised by other features
- C08L2205/14—Polymer mixtures characterised by other features containing polymeric additives characterised by shape
- C08L2205/18—Spheres
-
- C—CHEMISTRY; METALLURGY
- C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
- C08L—COMPOSITIONS OF MACROMOLECULAR COMPOUNDS
- C08L2207/00—Properties characterising the ingredient of the composition
- C08L2207/04—Thermoplastic elastomer
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Organic Chemistry (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Adhesives Or Adhesive Processes (AREA)
Abstract
Discloses an intelligent preparation method and system of an adhesive. The method comprises the following steps: placing nitrile rubber and modified polyurethane into a reaction kettle, heating and uniformly stirring to obtain a first mixture; adding a thermoplastic elastomer, polymer microspheres and a silane coupling agent into the first mixture, and heating and stirring to obtain a second mixture; adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture, and carrying out vacuum stirring to obtain a third mixture; and adding a silane coupling agent, an organotin catalyst and an anti-aging agent into the third mixture, and carrying out vacuum stirring to obtain an adhesive finished product. In this way, an adhesive is prepared.
Description
Technical Field
The application relates to the field of intelligent preparation, and more particularly relates to an intelligent preparation method and system of an adhesive.
Background
Building waterproofing is a measure taken in building materials and construction to prevent water from penetrating into certain parts of a building, wherein a waterproof roll is used as a first barrier for waterproofing the whole project, and plays a vital role in the whole project. However, the adhesive for waterproof coiled materials is time-consuming to construct on a wet base layer, has poor waterproof performance in a long-term wet environment, is easy to lose waterproof capability, and causes resource waste and use cost improvement.
Thus, an optimized intelligent preparation scheme of the adhesive is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides an intelligent preparation method and system of an adhesive. The method comprises the following steps: placing nitrile rubber and modified polyurethane into a reaction kettle, heating and uniformly stirring to obtain a first mixture; adding a thermoplastic elastomer, polymer microspheres and a silane coupling agent into the first mixture, and heating and stirring to obtain a second mixture; adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture, and carrying out vacuum stirring to obtain a third mixture; and adding a silane coupling agent, an organotin catalyst and an anti-aging agent into the third mixture, and carrying out vacuum stirring to obtain an adhesive finished product. In this way, an adhesive is prepared.
According to one aspect of the present application, there is provided an intelligent preparation method of an adhesive, including:
placing nitrile rubber and modified polyurethane into a reaction kettle, heating and uniformly stirring to obtain a first mixture;
adding a thermoplastic elastomer, polymer microspheres and a silane coupling agent into the first mixture, and heating and stirring to obtain a second mixture;
Adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture, and carrying out vacuum stirring to obtain a third mixture; and adding the silane coupling agent, the organotin catalyst and the anti-aging agent into the third mixture, and carrying out vacuum stirring to obtain an adhesive finished product.
In the above-mentioned intelligent preparation method of the adhesive, adding a silane coupling agent, an organotin catalyst and an anti-aging agent into the third mixture, and stirring in vacuum to obtain a finished adhesive product, comprising:
obtaining stirring resistance values of a plurality of preset time points in a preset time period in the stirring process;
arranging the stirring resistance values at a plurality of preset time points into a stirring resistance time sequence input vector according to a time dimension;
calculating the difference value between stirring resistance values of every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value change time sequence input vector;
passing the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector;
Fusing the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector to obtain a classification feature vector; and passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether stirring is stopped.
In the above-mentioned method for intelligently preparing an adhesive, passing the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector through a time sequence feature extractor including a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector, including:
using a first convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a first-scale stirring resistance time sequence feature vector and a first-scale stirring resistance value change time sequence feature vector;
using a second convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a second-scale stirring resistance time sequence feature vector and a second-scale stirring resistance value change time sequence feature vector; and cascading the first-scale stirring resistance time sequence feature vector and the second-scale stirring resistance time sequence feature vector to obtain the stirring resistance time sequence feature vector, and cascading the first-scale stirring resistance value change time sequence feature vector and the second-scale stirring resistance value change time sequence feature vector to obtain the stirring resistance value change time sequence feature vector.
In the above-mentioned method for preparing an adhesive in an intelligent manner, the first convolution layer of the time sequence feature extractor uses a one-dimensional convolution kernel having a first scale, the second convolution layer of the time sequence feature extractor uses a one-dimensional convolution kernel having a second scale, and the first scale is not equal to the second scale.
In the above-mentioned intelligent preparation method of the adhesive, fusing the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector to obtain a classification feature vector includes:
carrying out deep space encapsulation semantic matching fusion on the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector by using the following optimization formula to obtain the classification feature vector;
wherein, the optimization formula is:
wherein V is 1 Is the time sequence characteristic vector of the stirring resistance, V 2 Is the time sequence characteristic vector of the change of the stirring resistance value, II 1 And II 2 Represents the first norm and the second norm of the vector respectively, ω and ε are the weight and bias hyper-parameters respectively, D (V 1 ,V 2 ) Representing the stirring resistance time sequence characteristic vector and the stirring resistance time sequence characteristic vectorA position-by-position distance matrix between the time sequence characteristic vectors of the stirring resistance value change, wherein I is an identity matrix, As indicated by the letter, "" indicates addition by position, subtraction by position and multiplication by position, V c Is the classification feature vector.
In the above-mentioned intelligent preparation method of the adhesive, the classification feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether stirring is stopped, and the method includes:
performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
According to another aspect of the present application, there is provided an intelligent preparation system of an adhesive, comprising:
the first mixing module is used for taking nitrile rubber and modified polyurethane, heating the nitrile rubber and the modified polyurethane in the reaction kettle, and uniformly stirring the nitrile rubber and the modified polyurethane to obtain a first mixture;
the second mixing module is used for adding the thermoplastic elastomer, the polymer microsphere and the silane coupling agent into the first mixture, and heating and stirring the mixture to obtain a second mixture;
the third mixing module is used for adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture and carrying out vacuum stirring to obtain a third mixture; and the vacuum stirring module is used for adding the silane coupling agent, the organotin catalyst and the anti-aging agent into the third mixture to perform vacuum stirring so as to obtain an adhesive finished product.
In the above-mentioned intelligent preparation system of gluing agent, vacuum stirring module includes:
a resistance value acquisition unit for acquiring stirring resistance values at a plurality of predetermined time points in a predetermined period of time in a stirring process;
a vector arrangement unit for arranging the stirring resistance values of the plurality of predetermined time points into a stirring resistance time sequence input vector according to a time dimension;
a difference value calculation unit for calculating a difference value between stirring resistance values at every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value change time sequence input vector;
a time sequence feature extraction unit for passing the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector;
the fusion unit is used for fusing the stirring resistance time sequence characteristic vector and the stirring resistance value change time sequence characteristic vector to obtain a classification characteristic vector; and the classification unit is used for enabling the classification feature vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether stirring is stopped or not.
In the above-mentioned intelligent preparation system of adhesive, the time sequence feature extraction unit is used for:
using a first convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a first-scale stirring resistance time sequence feature vector and a first-scale stirring resistance value change time sequence feature vector;
using a second convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a second-scale stirring resistance time sequence feature vector and a second-scale stirring resistance value change time sequence feature vector; and cascading the first-scale stirring resistance time sequence feature vector and the second-scale stirring resistance time sequence feature vector to obtain the stirring resistance time sequence feature vector, and cascading the first-scale stirring resistance value change time sequence feature vector and the second-scale stirring resistance value change time sequence feature vector to obtain the stirring resistance value change time sequence feature vector.
In the above-mentioned intelligent preparation system of an adhesive, the first convolution layer of the timing sequence feature extractor uses a one-dimensional convolution kernel having a first scale, and the second convolution layer of the timing sequence feature extractor uses a one-dimensional convolution kernel having a second scale, and the first scale is not equal to the second scale.
Compared with the prior art, the intelligent preparation method and the system of the adhesive provided by the application comprise the following steps: placing nitrile rubber and modified polyurethane into a reaction kettle, heating and uniformly stirring to obtain a first mixture; adding a thermoplastic elastomer, polymer microspheres and a silane coupling agent into the first mixture, and heating and stirring to obtain a second mixture; adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture, and carrying out vacuum stirring to obtain a third mixture; and adding a silane coupling agent, an organotin catalyst and an anti-aging agent into the third mixture, and carrying out vacuum stirring to obtain an adhesive finished product. In this way, an adhesive is prepared.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly introduced below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. The following drawings are not intended to be drawn to scale, with emphasis instead being placed upon illustrating the principles of the present application.
Fig. 1 is a flowchart of an intelligent preparation method of an adhesive according to an embodiment of the present application.
Fig. 2 is an application scenario diagram of sub-step S140 in the method for intelligently preparing an adhesive according to an embodiment of the present application.
Fig. 3 is a flowchart of a substep S140 in the method for intelligently preparing an adhesive according to an embodiment of the present application.
Fig. 4 is a schematic diagram of the architecture of the substep S140 in the method for intelligently preparing the adhesive according to the embodiment of the application.
Fig. 5 is a flowchart of substep S144 of the intelligent preparation method of the adhesive according to the embodiment of the present application.
Fig. 6 is a flowchart of substep S146 of the intelligent preparation method of the adhesive according to the embodiment of the present application.
FIG. 7 is a block diagram of an intelligent adhesive preparation system according to an embodiment of the present application.
Fig. 8 is a block diagram of the vacuum stirring module in the intelligent preparation system of an adhesive according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present application without making any inventive effort, are also within the scope of the present application.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As described above, the adhesive for waterproof coiled materials is time-consuming to construct on a wet base layer, has poor waterproof performance in a long-term wet environment, is easy to lose waterproof capability, and causes resource waste and use cost improvement. Thus, an optimized intelligent preparation scheme of the adhesive is desired.
Specifically, in the technical scheme of the application, an intelligent preparation method of an adhesive is provided, as shown in fig. 1, which includes: s110, placing nitrile rubber and modified polyurethane into a reaction kettle, heating and uniformly stirring to obtain a first mixture; s120, adding a thermoplastic elastomer, polymer microspheres and a silane coupling agent into the first mixture, and heating and stirring to obtain a second mixture; s130, adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture, and stirring in vacuum to obtain a third mixture; and S140, adding a silane coupling agent, an organotin catalyst and an anti-aging agent into the third mixture, and carrying out vacuum stirring to obtain an adhesive finished product.
Accordingly, when the silane coupling agent, the organotin catalyst and the anti-aging agent are added into the third mixture to be subjected to vacuum stirring in the preparation process of the adhesive in practice, the control of the stirring time is particularly critical, if the stirring time is too long, the waste of energy sources is caused, and if the stirring time is too short, the performance of the adhesive does not reach the standard. Therefore, in the technical scheme of the application, whether the performance of the adhesive meets the preset requirement or not is expected to be judged through the resistance sensed in the stirring process, so that the stirring can be stopped timely. However, since the stirring resistance value has a dynamic change law of time sequence in the time dimension, and such time sequence change characteristics are weak change information of a small scale with respect to the stirring resistance value, it is difficult to perform sufficient capturing and extraction, resulting in low accuracy for stirring control. Therefore, in this process, the difficulty lies in how to mine the time sequence dynamic change characteristic information of the stirring resistance value, so as to perform the self-adaptive control of stirring based on the actual adhesive performance change condition, further optimize the preparation efficiency and quality of the adhesive, and save energy and cost.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. The development of deep learning and neural networks provides a new solution idea and scheme for mining time sequence dynamic change characteristic information of the stirring resistance value.
Specifically, in the technical scheme of the present application, first, stirring resistance values at a plurality of predetermined time points in a predetermined period of time in a stirring process are obtained. Then, considering that the stirring resistance value has a dynamic change rule in a time dimension, in order to extract the change characteristic information of the stirring resistance value in the time dimension, in the technical scheme of the application, the stirring resistance values at a plurality of preset time points are arranged into a stirring resistance time sequence input vector according to the time dimension, so that the distribution information of the stirring resistance value in the time sequence is integrated.
Further, in order to adaptively and accurately control the stirring duration, it is necessary to extract dynamic change characteristics of the stirring resistance value in the time dimension, and considering that the change information of the stirring resistance value in the time dimension is weak, the weak change characteristics are small-scale change characteristic information relative to the stirring resistance value, if the time-sequence dynamic change characteristics of the stirring resistance value are extracted by absolute change information, the calculated amount is large, and the small-scale weak change characteristics of the stirring resistance value in the time dimension are difficult to be perceived, so that the accuracy of subsequent classification is affected.
Based on the above, in the technical solution of the present application, the time sequence change feature extraction of the stirring resistance value is performed comprehensively by adopting the time sequence relative dynamic change feature and the absolute static change feature of the stirring resistance value. Specifically, first, the difference between the stirring resistance values at every two positions in the stirring resistance time series input vector is calculated to obtain a stirring resistance value change time series input vector.
Then, considering that the stirring resistance value has fluctuation and uncertainty in the time dimension, the time sequence relative change information and the time sequence absolute change information of the stirring resistance value show different time sequence change rules under different time period spans. Therefore, in the technical solution of the present application, in order to enable sufficient expression of the time-series variation feature of the stirring resistance value, the stirring resistance time-series input vector and the stirring resistance value variation time-series input vector are passed through a time-series feature extractor including a first convolution layer and a second convolution layer to obtain a stirring resistance time-series feature vector and a stirring resistance value variation time-series feature vector. In particular, here, a first convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a first scale and a second convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a second scale, the first scale not being equal to the second scale. In this way, the characteristic mining of the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector is respectively performed by using the convolution layers with one-dimensional convolution kernels of different scales, so that the time sequence relative change information and the time sequence absolute change information of the stirring resistance value can be extracted to obtain multi-scale time sequence related characteristic information under different time spans.
Then, since there is a correlation between the time-series relatively dynamic change characteristic and the time-series absolute static change characteristic of the stirring resistance value, there is a time-series change characteristic concerning the stirring resistance value. Therefore, in order to fully explore the change rule of the stirring resistance value in the time dimension so as to accurately control the stirring duration, in the technical scheme of the application, the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector are further fused to obtain the classification feature vector. Therefore, the time sequence multi-scale relative dynamic change characteristic information and the time sequence multi-scale absolute static change characteristic information of the stirring resistance value can be fused, so that the change characteristic information of the stirring resistance value on the time sequence can be more fully captured.
Further, the classification feature vector is subjected to classification processing in a classifier to obtain a classification result for indicating whether stirring is stopped. That is, in the technical solution of the present application, the label of the classifier includes stopping stirring (first label) and not stopping stirring (second label), wherein the classifier determines to which classification label the classification feature vector belongs through a soft maximum function. It should be noted that the first tag p1 and the second tag p2 do not include a manually set concept, and in fact, during the training process, the computer model does not have a concept of "whether stirring is stopped", which is only two kinds of classification tags, and the probability that the output characteristics are under the two classification tags, that is, the sum of p1 and p2 is one. Therefore, the classification result of whether to stop stirring is actually a classification probability distribution converted into a classification conforming to the natural law by classifying the labels, and the physical meaning of the natural probability distribution of the labels is essentially used instead of the language text meaning of whether to stop stirring. It should be understood that, in the technical scheme of the application, the classification label of the classifier is a control strategy label for stopping stirring, so after the classification result is obtained, the self-adaptive control of stirring can be performed based on the classification result, thereby optimizing the preparation efficiency and quality of the adhesive, and saving energy and cost.
In particular, in the technical solution of the present application, the stirring resistance time series feature vector and the stirring resistance value change time series feature vector express time series associated semantic features of an absolute value of stirring resistance and a change value of stirring resistance respectively, and although they all basically follow a time series distribution, the expressed feature semantics are different, so, in order to better fuse the stirring resistance time series feature vector and the stirring resistance value change time series feature vector, the applicant of the present application performs fusion on a feature semantic level on the stirring resistance time series feature vector and the stirring resistance value change time series feature vector by deep space encapsulation semantic matching fusion.
Specifically, the stirring resistance time sequence characteristic vector V 1 And the stirring resistance value change time sequence characteristic vector V 2 Performing deep space encapsulation semantic matching fusion to obtain classified feature vectors, for example, marked as V c Wherein the feature vector V is classified c The concrete steps are as follows:
‖·‖ 1 and II 2 Represents the first norm and the second norm of the vector respectively, ω and ε are the weight and bias hyper-parameters respectively, D (V 1 ,V 2 ) Representing the stirring resistance time sequence characteristic vector V 1 And the stirring resistance value change time sequence characteristic vector V 2 Matrix of distances by location, D ij =d(v 1i ,v 2j ) And I is an identity matrix.
Here, for the stirring resistance timing characteristic vector V in the depth characteristic space 1 And the stirring resistance value change time sequence characteristic vector V 2 The semantic expression is packaged into a deep space, so that fine-grained features in the overall distribution of the feature vector simultaneously comprise low-level semantic distribution and high-level semantic distribution, thereby, through the deep space packaging semantic matching fusion, the matching of semantic levels of classification mode layers can be carried out through balancing the low-level semantic distribution and the high-level semantic distribution, so as to realize the semantic controlled compiling fusion of the features in the feature space, and further, the stirring resistance time sequence feature vector V is obtained 1 And the stirring resistance value change time sequence characteristic vector V 2 Semantic collaboration in a feature fusion space improves the classification feature vector V c For the stirring resistance time sequence characteristic vector V 1 And the stirring resistance value change time sequence characteristic vector V 2 The semantic fusion effect of the classification feature vector is improved, so that the accuracy of the classification result obtained by the classification feature vector through the classifier is improved. Therefore, the self-adaptive control of stirring can be performed based on the actual adhesive performance change condition, so that the preparation efficiency and quality of the adhesive are optimized, and the energy and cost are saved.
Fig. 2 is an application scenario diagram of sub-step S140 in the method for intelligently preparing an adhesive according to an embodiment of the present application. As shown in fig. 2, in this application scenario, first, stirring resistance values at a plurality of predetermined time points in a predetermined period of time during stirring (for example, D illustrated in fig. 2) are acquired, and then, the stirring resistance values at the plurality of predetermined time points are input to a server in which an intelligent preparation algorithm of an adhesive is deployed (for example, S illustrated in fig. 2), wherein the server can process the stirring resistance values at the plurality of predetermined time points using the intelligent preparation algorithm of the adhesive to obtain a classification result for indicating whether stirring is stopped.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Fig. 3 is a flowchart of a substep S140 in the method for intelligently preparing an adhesive according to an embodiment of the present application. As shown in fig. 3, according to the intelligent preparation method of the adhesive in the embodiment of the application, a silane coupling agent, an organotin catalyst and an anti-aging agent are added into the third mixture, and vacuum stirring is performed to obtain a finished adhesive product, which comprises the following steps: s141, obtaining stirring resistance values of a plurality of preset time points in a preset time period in the stirring process; s142, arranging the stirring resistance values of the plurality of preset time points into a stirring resistance time sequence input vector according to a time dimension; s143, calculating the difference value between stirring resistance values of every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value change time sequence input vector; s144, passing the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector; s145, fusing the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector to obtain a classification feature vector; and S146, passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether stirring is stopped.
Fig. 4 is a schematic diagram of the architecture of the substep S140 in the method for intelligently preparing the adhesive according to the embodiment of the application. As shown in fig. 4, in the network architecture, first, stirring resistance values at a plurality of predetermined time points in a predetermined period of time during stirring are acquired; then, arranging the stirring resistance values of the plurality of preset time points into a stirring resistance time sequence input vector according to a time dimension; then, calculating the difference value between stirring resistance values of every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value change time sequence input vector; then, the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector are passed through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector; then, fusing the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector to obtain a classification feature vector; and finally, the classification feature vector passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether stirring is stopped.
More specifically, in step S141, stirring resistance values at a plurality of predetermined time points in a predetermined period of time during stirring are acquired. In the preparation process of the adhesive, when the silane coupling agent, the organotin catalyst and the anti-aging agent are added into the third mixture for vacuum stirring to obtain a finished adhesive product, the control of the stirring time is particularly critical, if the stirring time is too long, the waste of energy sources can be caused, and if the stirring time is too short, the performance of the adhesive cannot reach the standard. Therefore, in the technical scheme of the application, whether the performance of the adhesive meets the preset requirement can be judged through the resistance felt in the stirring process, so that the stirring can be stopped timely.
More specifically, in step S142, the stirring resistance values at the plurality of predetermined time points are arranged in the time dimension as a stirring resistance timing input vector. In order to extract the change characteristic information of the stirring resistance value in the time dimension, in the technical scheme of the application, the stirring resistance values at a plurality of preset time points are arranged into stirring resistance time sequence input vectors according to the time dimension, so that the distribution information of the stirring resistance values in the time sequence is integrated.
More specifically, in step S143, the difference between the stirring resistance values at every two positions in the stirring resistance timing input vector is calculated to obtain a stirring resistance value variation timing input vector. In order to perform adaptive accurate control on the stirring duration, it is necessary to extract dynamic change characteristics of the stirring resistance value in the time dimension, and considering that the change information of the stirring resistance value in the time dimension is weak, the weak change characteristics are small-scale change characteristic information relative to the stirring resistance value, if the time sequence dynamic change characteristic extraction of the stirring resistance value is performed by absolute change information, the calculated amount is large, and the small-scale weak change characteristics of the stirring resistance value in the time dimension are difficult to be perceived, so that the accuracy of subsequent classification is affected. Based on the above, in the technical solution of the present application, the time sequence change feature extraction of the stirring resistance value is performed comprehensively by adopting the time sequence relative dynamic change feature and the absolute static change feature of the stirring resistance value.
More specifically, in step S144, the agitation resistance timing input vector and the agitation resistance value variation timing input vector are passed through a timing feature extractor including a first convolution layer and a second convolution layer to obtain an agitation resistance timing feature vector and an agitation resistance value variation timing feature vector. Because the stirring resistance value has fluctuation and uncertainty in the time dimension, the time sequence relative change information and the time sequence absolute change information of the stirring resistance value show different time sequence change rules under different time period spans. Therefore, in the technical solution of the present application, in order to enable sufficient expression of the time-series variation feature of the stirring resistance value, the stirring resistance time-series input vector and the stirring resistance value variation time-series input vector are passed through a time-series feature extractor including a first convolution layer and a second convolution layer to obtain a stirring resistance time-series feature vector and a stirring resistance value variation time-series feature vector.
Accordingly, in one specific example, as shown in fig. 5, passing the stirring resistance timing input vector and the stirring resistance value variation timing input vector through a timing feature extractor including a first convolution layer and a second convolution layer to obtain a stirring resistance timing feature vector and a stirring resistance value variation timing feature vector, includes: s1441, performing one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector by using a first convolution layer of the time sequence feature extractor to obtain a first-scale stirring resistance time sequence feature vector and a first-scale stirring resistance value change time sequence feature vector; s1442, performing one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector by using a second convolution layer of the time sequence feature extractor to obtain a second-scale stirring resistance time sequence feature vector and a second-scale stirring resistance value change time sequence feature vector; and S1443, cascading the first scale stirring resistance time sequence feature vector and the second scale stirring resistance time sequence feature vector to obtain the stirring resistance time sequence feature vector, and cascading the first scale stirring resistance value change time sequence feature vector and the second scale stirring resistance value change time sequence feature vector to obtain the stirring resistance value change time sequence feature vector.
Accordingly, in one particular example, a first convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a first scale and a second convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a second scale, the first scale not being equal to the second scale.
More specifically, in step S145, the agitation resistance time series feature vector and the agitation resistance value variation time series feature vector are fused to obtain a classification feature vector. Since there is a correlation between the time-series relatively dynamic change characteristic and the time-series absolute static change characteristic of the stirring resistance value, the time-series change characteristic is related to the stirring resistance value. Therefore, in order to fully explore the change rule of the stirring resistance value in the time dimension so as to accurately control the stirring duration, in the technical scheme of the application, the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector are further fused to obtain the classification feature vector. Therefore, the time sequence multi-scale relative dynamic change characteristic information and the time sequence multi-scale absolute static change characteristic information of the stirring resistance value can be fused, so that the change characteristic information of the stirring resistance value on the time sequence can be more fully captured.
In particular, in the technical solution of the present application, the stirring resistance time series feature vector and the stirring resistance value change time series feature vector express time series associated semantic features of an absolute value of stirring resistance and a change value of stirring resistance respectively, and although they all basically follow a time series distribution, the expressed feature semantics are different, so, in order to better fuse the stirring resistance time series feature vector and the stirring resistance value change time series feature vector, the applicant of the present application performs fusion on a feature semantic level on the stirring resistance time series feature vector and the stirring resistance value change time series feature vector by deep space encapsulation semantic matching fusion. Specifically, deep space encapsulation semantic matching fusion is carried out on the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector so as to obtain a classification feature vector.
Accordingly, in one specific example, fusing the stirring resistance time series feature vector and the stirring resistance value change time series feature vector to obtain a classification feature vector includes: carrying out deep space encapsulation semantic matching fusion on the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector by using the following optimization formula to obtain the classification feature vector; wherein, the optimization formula is:
Wherein V is 1 Is the time sequence characteristic vector of the stirring resistance, V 2 Is the time sequence characteristic vector of the change of the stirring resistance value, II 1 And II 2 Represents the first norm and the second norm of the vector respectively, ω and ε are the weight and bias hyper-parameters respectively, D (V 1 ,V 2 ) A position-by-position distance matrix representing the stirring resistance time sequence characteristic vector and the stirring resistance value change time sequence characteristic vector, wherein I is an identity matrix, and,As indicated by the letter, "" indicates addition by position, subtraction by position and multiplication by position, V c Is the classification feature vector.
Here, for the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector in the depth feature space, semantic expressions of the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector are packaged into the depth space, so that fine granularity features in the overall distribution of the feature vector simultaneously comprise low-level semantic distribution and high-level semantic distribution, matching and fusion of semantic levels of a classification mode layer can be performed through the deep space packaging semantic distribution and the high-level semantic distribution in a balanced mode, so that semantic controlled compiling and fusion of features in the feature space can be achieved, semantic cooperation of the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector in a feature fusion space can be obtained, semantic fusion effect of the classification feature vector on the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector can be improved, expression effect of the classification feature vector can be improved, and accuracy of classification results obtained by the classifier of the classification feature vector can be improved. Therefore, the self-adaptive control of stirring can be performed based on the actual adhesive performance change condition, so that the preparation efficiency and quality of the adhesive are optimized, and the energy and cost are saved.
More specifically, in step S146, the classification feature vector is passed through a classifier to obtain a classification result indicating whether stirring is stopped. After the classification result is obtained, the self-adaptive control of stirring can be performed based on the classification result, so that the preparation efficiency and quality of the adhesive are optimized, and the energy and cost are saved.
It should be appreciated that the role of the classifier is to learn the classification rules and classifier using a given class, known training data, and then classify (or predict) the unknown data. Logistic regression (logistics), SVM, etc. are commonly used to solve the classification problem, and for multi-classification problems (multi-class classification), logistic regression or SVM can be used as well, but multiple bi-classifications are required to compose multiple classifications, but this is error-prone and inefficient, and the commonly used multi-classification method is the Softmax classification function.
Accordingly, in one specific example, as shown in fig. 6, the classification feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether stirring is stopped, and the method includes: s1461, performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and S1462, inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
In summary, according to the method for intelligently preparing the adhesive according to the embodiment of the application, stirring resistance values at a plurality of preset time points in a preset time period in a stirring process are firstly obtained, then the stirring resistance values at the preset time points are arranged into stirring resistance time sequence input vectors according to a time dimension, then a difference value between stirring resistance values at every two positions in the stirring resistance time sequence input vectors is calculated to obtain stirring resistance value change time sequence input vectors, then the stirring resistance time sequence input vectors and the stirring resistance value change time sequence input vectors pass through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain stirring resistance time sequence feature vectors and stirring resistance value change time sequence feature vectors, then the stirring resistance time sequence feature vectors and the stirring resistance value change time sequence feature vectors are fused to obtain classification feature vectors, and finally the classification feature vectors pass through a classifier to obtain classification results for indicating whether stirring is stopped.
Fig. 7 is a block diagram of an intelligent adhesive preparation system 100 according to an embodiment of the present application. As shown in fig. 7, an intelligent preparation system 100 of an adhesive according to an embodiment of the present application includes: the first mixing module 110 is used for heating and uniformly stirring nitrile rubber and modified polyurethane in a reaction kettle to obtain a first mixture; a second mixing module 120 for adding the thermoplastic elastomer, the polymer microsphere and the silane coupling agent to the first mixture and heating and stirring the mixture to obtain a second mixture; a third mixing module 130 for adding a hydrophobizing agent, a reinforcing agent, a toughening agent and a tackifier to the second mixture and performing vacuum stirring to obtain a third mixture; and a vacuum stirring module 140 for adding the silane coupling agent, the organotin catalyst and the anti-aging agent into the third mixture for vacuum stirring to obtain an adhesive finished product.
In one example, in the intelligent preparation system 100 of the adhesive, as shown in fig. 8, the vacuum stirring module 140 includes: a resistance value acquisition unit 141 for acquiring stirring resistance values at a plurality of predetermined time points in a predetermined period of time during stirring; a vector arrangement unit 142 for arranging the stirring resistance values at the plurality of predetermined time points in a time dimension as a stirring resistance time sequence input vector; a difference value calculating unit 143 for calculating a difference value between stirring resistance values at every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value variation time sequence input vector; a timing feature extraction unit 144 for passing the stirring resistance timing input vector and the stirring resistance value variation timing input vector through a timing feature extractor including a first convolution layer and a second convolution layer to obtain a stirring resistance timing feature vector and a stirring resistance value variation timing feature vector; a fusion unit 145 for fusing the stirring resistance time sequence feature vector and the stirring resistance value variation time sequence feature vector to obtain a classification feature vector; and a classification unit 146 for passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether stirring is stopped.
In one example, in the intelligent preparation system 100 of an adhesive, the timing feature extraction unit 144 is configured to: using a first convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a first-scale stirring resistance time sequence feature vector and a first-scale stirring resistance value change time sequence feature vector; using a second convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a second-scale stirring resistance time sequence feature vector and a second-scale stirring resistance value change time sequence feature vector; and cascading the first-scale stirring resistance time sequence feature vector and the second-scale stirring resistance time sequence feature vector to obtain the stirring resistance time sequence feature vector, and cascading the first-scale stirring resistance value change time sequence feature vector and the second-scale stirring resistance value change time sequence feature vector to obtain the stirring resistance value change time sequence feature vector.
In one example, in the above-described adhesive intelligent preparation system 100, the first convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a first scale and the second convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a second scale, the first scale not being equal to the second scale.
In one example, in the intelligent preparation system 100 of the adhesive, the fusing unit 145 is configured to: carrying out deep space encapsulation semantic matching fusion on the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector by using the following optimization formula to obtain the classification feature vector; wherein, the optimization formula is:
wherein V is 1 Is the time sequence characteristic vector of the stirring resistance, V 2 Is the time sequence characteristic vector of the change of the stirring resistance value, II 1 And II 2 Represents the first norm and the second norm of the vector respectively, ω and ε are the weight and bias hyper-parameters respectively, D (V 1 ,V 2 ) A position-by-position distance matrix representing the stirring resistance time sequence characteristic vector and the stirring resistance value change time sequence characteristic vector, wherein I is an identity matrix, and,As indicated by the letter, "" indicates addition by position, subtraction by position and multiplication by position, V c Is the classification feature vector.
In one example, in the intelligent preparation system 100 of the adhesive, the classification unit 146 is configured to: performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
Here, it will be understood by those skilled in the art that the specific functions and operations of the respective modules in the above-described intelligent preparation system 100 of adhesives have been described in detail in the above description of the intelligent preparation method of adhesives with reference to fig. 1 to 6, and thus, repetitive descriptions thereof will be omitted.
As described above, the intelligent preparation system 100 of an adhesive according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server having an intelligent preparation algorithm of an adhesive, or the like. In one example, the intelligent preparation system 100 of an adhesive according to embodiments of the present application may be integrated into a wireless terminal as one software module and/or hardware module. For example, the intelligent preparation system 100 of the adhesive may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the intelligent preparation system 100 of the adhesive may also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the adhesive intelligent preparation system 100 and the wireless terminal may be separate devices, and the adhesive intelligent preparation system 100 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information according to an agreed data format.
According to another aspect of the present application, there is also provided a non-volatile computer-readable storage medium having stored thereon computer-readable instructions which, when executed by a computer, can perform a method as described above.
Program portions of the technology may be considered to be "products" or "articles of manufacture" in the form of executable code and/or associated data, embodied or carried out by a computer readable medium. A tangible, persistent storage medium may include any memory or storage used by a computer, processor, or similar device or related module. Such as various semiconductor memories, tape drives, disk drives, or the like, capable of providing storage functionality for software.
All or a portion of the software may sometimes communicate over a network, such as the internet or other communication network. Such communication may load software from one computer device or processor to another. For example: a hardware platform loaded from a server or host computer of the video object detection device to a computer environment, or other computer environment implementing the system, or similar functioning system related to providing information needed for object detection. Thus, another medium capable of carrying software elements may also be used as a physical connection between local devices, such as optical, electrical, electromagnetic, etc., propagating through cable, optical cable, air, etc. Physical media used for carrier waves, such as electrical, wireless, or optical, may also be considered to be software-bearing media. Unless limited to a tangible "storage" medium, other terms used herein to refer to a computer or machine "readable medium" mean any medium that participates in the execution of any instructions by a processor.
This application uses specific words to describe embodiments of the application. Reference to "a first/second embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present application may be combined as suitable.
Furthermore, those skilled in the art will appreciate that the various aspects of the invention are illustrated and described in the context of a number of patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The foregoing is illustrative of the present invention and is not to be construed as limiting thereof. Although a few exemplary embodiments of this invention have been described, those skilled in the art will readily appreciate that many modifications are possible in the exemplary embodiments without materially departing from the novel teachings and advantages of this invention. Accordingly, all such modifications are intended to be included within the scope of this invention as defined in the following claims. It is to be understood that the foregoing is illustrative of the present invention and is not to be construed as limited to the specific embodiments disclosed, and that modifications to the disclosed embodiments, as well as other embodiments, are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.
Claims (10)
1. An intelligent preparation method of an adhesive is characterized by comprising the following steps:
placing nitrile rubber and modified polyurethane into a reaction kettle, heating and uniformly stirring to obtain a first mixture;
adding a thermoplastic elastomer, polymer microspheres and a silane coupling agent into the first mixture, and heating and stirring to obtain a second mixture;
adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture, and carrying out vacuum stirring to obtain a third mixture; and adding the silane coupling agent, the organotin catalyst and the anti-aging agent into the third mixture, and carrying out vacuum stirring to obtain an adhesive finished product.
2. The intelligent preparation method of the adhesive according to claim 1, wherein adding a silane coupling agent, an organotin catalyst and an anti-aging agent into the third mixture to perform vacuum stirring to obtain an adhesive finished product, comprises:
obtaining stirring resistance values of a plurality of preset time points in a preset time period in the stirring process;
arranging the stirring resistance values at a plurality of preset time points into a stirring resistance time sequence input vector according to a time dimension;
calculating the difference value between stirring resistance values of every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value change time sequence input vector;
Passing the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector;
fusing the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector to obtain a classification feature vector; and passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether stirring is stopped.
3. The method of intelligentized preparing an adhesive according to claim 2, wherein passing the stirring resistance time series input vector and the stirring resistance value change time series input vector through a time series feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time series feature vector and a stirring resistance value change time series feature vector, comprises:
using a first convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a first-scale stirring resistance time sequence feature vector and a first-scale stirring resistance value change time sequence feature vector;
Using a second convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a second-scale stirring resistance time sequence feature vector and a second-scale stirring resistance value change time sequence feature vector; and cascading the first-scale stirring resistance time sequence feature vector and the second-scale stirring resistance time sequence feature vector to obtain the stirring resistance time sequence feature vector, and cascading the first-scale stirring resistance value change time sequence feature vector and the second-scale stirring resistance value change time sequence feature vector to obtain the stirring resistance value change time sequence feature vector.
4. The method of intelligent preparation of an adhesive of claim 3, wherein a first convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a first scale and a second convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a second scale, the first scale not being equal to the second scale.
5. The method of intelligent preparation of an adhesive according to claim 4, wherein fusing the stirring resistance time series feature vector and the stirring resistance value variation time series feature vector to obtain a classification feature vector, comprises:
Carrying out deep space encapsulation semantic matching fusion on the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector by using the following optimization formula to obtain the classification feature vector;
wherein, the optimization formula is:
wherein V is 1 Is the time sequence characteristic vector of the stirring resistance, V 2 Is the time sequence characteristic vector of the change of the stirring resistance value, I.I 1 And|| | 2 Represents the first norm and the second norm of the vector respectively, ω and ε are the weight and bias hyper-parameters respectively, D (V 1 ,V 2 ) Representing a per-position distance matrix between the stirring resistance time sequence feature vector and the stirring resistance value change time sequence feature vector, wherein I is an identity matrix,as indicated above, V is the sum by position, the subtraction by position and the multiplication by position c Is the classification feature vector.
6. The method for the intelligent preparation of an adhesive according to claim 5, wherein the step of passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for indicating whether stirring is stopped, comprises the steps of:
performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain coded classification feature vectors; and inputting the coding classification feature vector into a Softmax classification function of the classifier to obtain the classification result.
7. An intelligent preparation system of an adhesive, which is characterized by comprising:
the first mixing module is used for taking nitrile rubber and modified polyurethane, heating the nitrile rubber and the modified polyurethane in the reaction kettle, and uniformly stirring the nitrile rubber and the modified polyurethane to obtain a first mixture;
the second mixing module is used for adding the thermoplastic elastomer, the polymer microsphere and the silane coupling agent into the first mixture, and heating and stirring the mixture to obtain a second mixture;
the third mixing module is used for adding a hydrophobing agent, a reinforcing agent, a toughening agent and a tackifier into the second mixture and carrying out vacuum stirring to obtain a third mixture; and the vacuum stirring module is used for adding the silane coupling agent, the organotin catalyst and the anti-aging agent into the third mixture to perform vacuum stirring so as to obtain an adhesive finished product.
8. The intelligent preparation system of an adhesive according to claim 7, wherein the vacuum stirring module comprises:
a resistance value acquisition unit for acquiring stirring resistance values at a plurality of predetermined time points in a predetermined period of time in a stirring process;
a vector arrangement unit for arranging the stirring resistance values of the plurality of predetermined time points into a stirring resistance time sequence input vector according to a time dimension;
A difference value calculation unit for calculating a difference value between stirring resistance values at every two positions in the stirring resistance time sequence input vector to obtain a stirring resistance value change time sequence input vector;
a time sequence feature extraction unit for passing the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector through a time sequence feature extractor comprising a first convolution layer and a second convolution layer to obtain a stirring resistance time sequence feature vector and a stirring resistance value change time sequence feature vector;
the fusion unit is used for fusing the stirring resistance time sequence characteristic vector and the stirring resistance value change time sequence characteristic vector to obtain a classification characteristic vector; and the classification unit is used for enabling the classification feature vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether stirring is stopped or not.
9. The intelligent preparation system of an adhesive according to claim 8, wherein the timing feature extraction unit is configured to:
using a first convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a first-scale stirring resistance time sequence feature vector and a first-scale stirring resistance value change time sequence feature vector;
Using a second convolution layer of the time sequence feature extractor to perform one-dimensional convolution coding on the stirring resistance time sequence input vector and the stirring resistance value change time sequence input vector respectively so as to obtain a second-scale stirring resistance time sequence feature vector and a second-scale stirring resistance value change time sequence feature vector; and cascading the first-scale stirring resistance time sequence feature vector and the second-scale stirring resistance time sequence feature vector to obtain the stirring resistance time sequence feature vector, and cascading the first-scale stirring resistance value change time sequence feature vector and the second-scale stirring resistance value change time sequence feature vector to obtain the stirring resistance value change time sequence feature vector.
10. The intelligent preparation system of adhesive according to claim 9, wherein a first convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a first scale and a second convolution layer of the timing feature extractor uses a one-dimensional convolution kernel having a second scale, the first scale not being equal to the second scale.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310527598.9A CN116463079A (en) | 2023-05-10 | 2023-05-10 | Intelligent preparation method and system of adhesive |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310527598.9A CN116463079A (en) | 2023-05-10 | 2023-05-10 | Intelligent preparation method and system of adhesive |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116463079A true CN116463079A (en) | 2023-07-21 |
Family
ID=87173689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310527598.9A Withdrawn CN116463079A (en) | 2023-05-10 | 2023-05-10 | Intelligent preparation method and system of adhesive |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116463079A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116726788A (en) * | 2023-08-10 | 2023-09-12 | 克拉玛依市紫光技术有限公司 | Preparation method of cross-linking agent for fracturing |
CN117021409A (en) * | 2023-07-25 | 2023-11-10 | 杭州帝凯工业布有限公司 | Reinforced nylon composite material and preparation method thereof |
-
2023
- 2023-05-10 CN CN202310527598.9A patent/CN116463079A/en not_active Withdrawn
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117021409A (en) * | 2023-07-25 | 2023-11-10 | 杭州帝凯工业布有限公司 | Reinforced nylon composite material and preparation method thereof |
CN117021409B (en) * | 2023-07-25 | 2024-03-08 | 杭州帝凯工业布有限公司 | Reinforced nylon composite material and preparation method thereof |
CN116726788A (en) * | 2023-08-10 | 2023-09-12 | 克拉玛依市紫光技术有限公司 | Preparation method of cross-linking agent for fracturing |
CN116726788B (en) * | 2023-08-10 | 2023-11-10 | 克拉玛依市紫光技术有限公司 | Preparation method of cross-linking agent for fracturing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116463079A (en) | Intelligent preparation method and system of adhesive | |
US20180268292A1 (en) | Learning efficient object detection models with knowledge distillation | |
Guo et al. | Supplier selection based on hierarchical potential support vector machine | |
CN116010713A (en) | Innovative entrepreneur platform service data processing method and system based on cloud computing | |
EP4167130A1 (en) | Neural network training method and related device | |
US11741398B2 (en) | Multi-layered machine learning system to support ensemble learning | |
CN116204266A (en) | Remote assisted information creation operation and maintenance system and method thereof | |
US20210256387A1 (en) | Model Training with Retrospective Loss | |
CN114912612A (en) | Bird identification method and device, computer equipment and storage medium | |
CN115456789B (en) | Abnormal transaction detection method and system based on transaction pattern recognition | |
CN116577677A (en) | Discharging test system and method for retired power battery | |
CN116824481B (en) | Substation inspection method and system based on image recognition | |
CN116992226A (en) | Water pump motor fault detection method and system | |
CN116704431A (en) | On-line monitoring system and method for water pollution | |
CN116596556A (en) | Beef cattle traceability management system and method | |
CN116482524A (en) | Power transmission and distribution switch state detection method and system | |
CN116624903A (en) | Intelligent monitoring method and system for oil smoke pipeline | |
CN111598113A (en) | Model optimization method, data identification method and data identification device | |
CN116402777B (en) | Power equipment detection method and system based on machine vision | |
CN116910621A (en) | Decision support system and method for textile chemical fiber supply chain management | |
CN116611453A (en) | Intelligent order-distributing and order-following method and system based on big data and storage medium | |
CN116502899A (en) | Risk rating model generation method, device and storage medium based on artificial intelligence | |
CN116596581A (en) | ERP management system and method thereof | |
CN116309596A (en) | CTC cell detection method and system based on micro-fluidic chip | |
CN116108363A (en) | Incomplete multi-view multi-label classification method and system based on label guidance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230721 |