CN108319809A - A kind of device and method of on-line checking polymer plasticization degree - Google Patents
A kind of device and method of on-line checking polymer plasticization degree Download PDFInfo
- Publication number
- CN108319809A CN108319809A CN201810106920.XA CN201810106920A CN108319809A CN 108319809 A CN108319809 A CN 108319809A CN 201810106920 A CN201810106920 A CN 201810106920A CN 108319809 A CN108319809 A CN 108319809A
- Authority
- CN
- China
- Prior art keywords
- polymer
- ultrasonic transducer
- sample
- neural network
- ultrasonic
- 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
Classifications
-
- 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
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/30—Prediction of properties of chemical compounds, compositions or mixtures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Extrusion Moulding Of Plastics Or The Like (AREA)
Abstract
The invention discloses a kind of device and method of on-line checking polymer plasticization degree, which is arranged on screw extruder；The device includes the temperature sensor and pressure sensor being arranged in the head of screw extruder, ultrasonic transducer and the interior information processing centre for storing neural network model in the head exit of screw extruder is arranged；Temperature sensor, pressure sensor and ultrasonic transducer are used to obtain the detection data of polymer to be tested；The detection data is the velocity of wave that the polymer to be tested temperature value of synchronization, pressure value and ultrasonic wave in plasticizing process penetrate polymer to be tested；Information processing centre is all connected with temperature sensor, pressure sensor and ultrasonic transducer, and the detection data of the polymer to be tested for acquisition is input to neural network model, determines the effect of the plasticizing grade of polymer to be tested.It, being capable of on-line checking polymer plasticization degree raising production efficiency using device or method provided by the invention.
Description
Technical field
The present invention relates to polymer material moldings to process detection field, more particularly to a kind of on-line checking polymer plasticization
The device and method of degree.
Background technology
High molecular material plays an increasingly important role in human lives, and product is almost related to each neck
Domain, such as the fields such as communication, medicine, aerospace, automobile, ship, chemical industry, building or even food, military project, people are to high score
The requirement that sub- material product quality is continuously improved, accurate process control just seem most important.
Traditional polymer plasticization quality determining method depends on the experience of producers more, or directly to production sample
Carry out offline inspection.Since most of detection method needs are manually sampled from machining production line, then in experiment detection device
On the sample of acquisition is detected, will result in the delay of detection time in this way, make measurement result do not have timeliness, can not
The reasonability of process conditions is made and is timely judged, to generate certain influence to production efficiency.Therefore, how one is obtained
The device of kind on-line checking polymer plasticization degree is that the technology that polymer material molding processing detection field is badly in need of solving is asked
Topic.
Invention content
The object of the present invention is to provide a kind of device and methods of on-line checking polymer plasticization degree, being capable of on-line checking
Polymer plasticization degree, avoids detection time from postponing, and so that measurement result is had timeliness, can be done to the reasonability of process conditions
Go out and timely judge, improves production efficiency.
To achieve the above object, the present invention provides following schemes：
A kind of device of on-line checking polymer plasticization degree, described device are arranged on screw extruder；Described device
Including temperature sensor, pressure sensor, for transmitting and receiving ultrasonic transducer of ultrasonic signal and information processing
Center；The temperature sensor, the pressure sensor are arranged in the head of the screw extruder, the ultrasonic waves
Energy device is arranged in the head exit of the screw extruder；Described information processing center and the temperature sensor, the pressure
Force snesor and the ultrasonic transducer are all connected with.
Optionally, described device further includes bracket institution；The ultrasonic transducer is fixed on by the bracket institution
The head exit of the screw extruder.
Optionally, the bracket institution includes pedestal, supporting rod, sliding block and the card slot being fixed on the supporting rod；
The intermediate position of the pedestal is equipped with slideway, and the sliding block is arranged in the slideway；The supporting rod has two, respectively
One supporting rod and second support bar；The first support bar is fixed on one end of the slideway, and the second support bar is fixed on
It is installed on the sliding block in the slideway；The head of the screw extruder is located at the first support bar and described second
Between supporting rod；The sliding block is for adjusting distance between the first support bar and the second support bar.
Optionally, the card slot includes two, respectively the first card slot and the second card slot；First card slot is fixed on institute
It states in first support bar, second card slot is fixed in the second support bar；Between first card slot and the pedestal
Distance and second card slot it is equal with the distance between the pedestal.
Optionally, the ultrasonic transducer is two, respectively the first ultrasonic transducer, the second ultrasonic wave transducer
Device；First ultrasonic transducer is for emitting ultrasonic signal；Second ultrasonic transducer is for receiving ultrasonic wave
Signal；First ultrasonic transducer is mounted in first card slot；Second ultrasonic transducer is mounted on described
In second card slot；First ultrasonic transducer, second ultrasonic transducer are located at apart from the screw extruder
Head exports at 20mm, and is arranged in the position of the horizontal symmetrical perpendicular to melt flows direction and apart from the melt 10mm
It sets.
Optionally, the first support bar and the second support bar are telescopic rod；The telescopic rod is for adjusting institute
The height for stating the first ultrasonic transducer, second ultrasonic transducer, make first ultrasonic transducer center and
The center of second ultrasonic transducer is with the center of the head of the screw extruder in same level height.
Optionally, first ultrasonic transducer, second ultrasonic transducer are Air Coupling ultrasonic waves
It can device.
The present invention also provides a kind of method of on-line checking polymer plasticization degree, the method is applied to described online
The device for detecting polymer plasticization degree, the method includes：
Obtain multigroup sample data；
Neural network model is established using neural network algorithm according to multigroup sample data；
Obtain the detection data of polymer to be tested；The detection data is the polymer to be tested in plasticizing process
Temperature value, pressure value and the ultrasonic wave of synchronization penetrate the velocity of wave of the polymer to be tested；
The detection data of the polymer to be tested is input to the neural network model, determines the polymerization to be tested
The plasticizing grade of object.
Optionally, described to obtain multigroup sample data, it specifically includes：
Obtain multigroup sample polymeric detection data；The sample polymeric detection data are that the sample polymer is being moulded
The temperature value of synchronization, pressure value and ultrasonic wave penetrate the velocity of wave of the sample polymer during change；
Mechanics Performance Testing is carried out to all sample polymer, determines the corresponding mechanics of each sample polymer
Performance number；
According to the corresponding mechanical properties value of the sample polymer, the plasticizing grade of the sample polymer is divided；It is described
Sample data includes that the sample polymer temperature value of synchronization, pressure value and ultrasonic wave in plasticizing process penetrate institute
State the velocity of wave of sample polymer, the plasticizing grade of the sample polymer.
Optionally, described that it is specific to be established using neural network algorithm according to multigroup sample data for neural network model
Including：
Multigroup sample polymeric detection data are normalized, multigroup learning sample data are obtained；
Build the neural network structure of 3*7*3；The first layer of the neural network structure is input layer, the neural network
The second layer of structure is hidden layer, and the third layer of the neural network structure is output layer；
Using the learning sample data as input value, with the plasticizing etc. of the corresponding sample polymer of the learning sample data
Grade is output valve, and using neural network algorithm, the training neural network structure obtains neural network model.
According to specific embodiment provided by the invention, the invention discloses following technique effects：
The present invention provides a kind of device and method of on-line checking polymer plasticization degree, device setting is squeezed in screw rod
Go out on machine；The device includes temperature sensor, pressure sensor, ultrasonic transducer and information processing centre；Temperature sensing
Device, pressure sensor are arranged in the head of screw extruder, and ultrasonic transducer is arranged the head in screw extruder and goes out
At mouthful；Trained neural network model is stored in information processing centre；Temperature sensor, pressure sensor and ultrasonic waves
It can detection data of the device for obtaining polymer to be tested；The detection data is polymer to be tested same a period of time in plasticizing process
Temperature value, pressure value and the ultrasonic wave at quarter penetrate the velocity of wave of polymer to be tested；Temperature sensor, pressure sensor and super
Acoustic wave transducer is connect with information processing centre, realizes the detection data of polymer to be tested being input to neural network mould
Type determines the effect of the plasticizing grade of polymer to be tested.Therefore, device or method provided by the invention, being capable of on-line checking
Polymer plasticization degree, avoids detection time from postponing, and so that measurement result is had timeliness, can be done to the reasonability of process conditions
Go out and timely judge, improves production efficiency.
Description of the drawings
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the structural schematic diagram of on-line checking polymer plasticization degree device of the embodiment of the present invention；
Fig. 2 is that the device of ultrasonic wave on-line measurement polymer melt gelation degree of the present invention is connected on screw extruder
Schematic diagram；
Fig. 3 is the structural schematic diagram of bracket institution of the present invention；
Fig. 4 is the flow diagram of on-line checking polymer plasticization degree method of the embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide a kind of device and methods of on-line checking polymer plasticization degree, being capable of on-line checking
Polymer plasticization degree, avoids detection time from postponing, and so that measurement result is had timeliness, can be done to the reasonability of process conditions
Go out and timely judge, improves production efficiency.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is the structural schematic diagram of on-line checking polymer plasticization degree device of the embodiment of the present invention, and Fig. 2 is that the present invention is super
The device of sound wave on-line measurement polymer melt gelation degree is connected to the schematic diagram on screw extruder；As illustrated in fig. 1 and 2,
The device of on-line checking polymer plasticization degree provided by the invention is arranged on screw extruder.
The device includes the ultrasonic waves of temperature sensor 1, pressure sensor 2, ultrasonic signal for transmitting and receiving
It can device 3, information processing centre and bracket institution 4；The temperature sensor 1, the pressure sensor 2 are arranged at the spiral shell
In the head 5 of bar extruder, the ultrasonic transducer 3 is arranged in the exit of the head 5 of the screw extruder, specially
The ultrasonic transducer 3 is fixed on the exit of the head 5 of the screw extruder by the bracket institution 4；The letter
Breath processing center is all connected with the temperature sensor 1, the pressure sensor 2 and the ultrasonic transducer 3.The letter
Trained neural network model is stored in breath processing center.
Wherein, the ultrasonic transducer 3 is two, respectively the first ultrasonic transducer, the second ultrasonic transducer；
First ultrasonic transducer is for emitting ultrasonic signal；Second ultrasonic transducer is for receiving ultrasonic wave letter
Number.First ultrasonic transducer, second ultrasonic transducer are Air Coupling ultrasonic transducer.
Fig. 2 is the structural schematic diagram of bracket institution of the present invention, as shown in Fig. 2, the bracket institution 4 includes pedestal 41, branch
Strut 42, sliding block 43 and the card slot 44 being fixed on the supporting rod 42.The intermediate position of the pedestal 41 is equipped with slideway, institute
Sliding block 43 is stated to be arranged in the slideway.
The supporting rod 42 has two, respectively first support bar and second support bar；The first support bar is fixed on
One end of the slideway, the second support bar are fixed on the sliding block 43 being installed in the slideway.Pass through sliding block 43
Adjustable distance between the first support bar and the second support bar.The head 5 of the screw extruder is located at described the
Between one supporting rod and the second support bar.The first support bar and the second support bar are telescopic rod.
The card slot 44 includes two, respectively the first card slot and the second card slot；First card slot is fixed on described
On one supporting rod, second card slot is fixed in the second support bar.First ultrasonic transducer is mounted on described
In first card slot；Second ultrasonic transducer is mounted in second card slot.Adjust the first support bar and described
The height of second support bar makes the distance between first card slot and the pedestal and second card slot and the pedestal
The distance between it is equal, ensure first ultrasonic transducer, second ultrasonic transducer center with the spiral shell
The center of the head 5 of bar extruder is in same level height.The position for adjusting detection device, makes ultrasonic transducer be located at screw rod
The head 5 of extruder exports at 20mm, adjusts the position of sliding block 43, makes first ultrasonic transducer, second ultrasound
Wave transducer is located on the position of the horizontal symmetrical perpendicular to melt flows direction and apart from the melt 10mm.
The operating process of above-mentioned apparatus on-line measurement polymer plasticization degree includes the following steps：
(1) in process of production, after screw extruder stabilization, collecting sample polymer, test sample polymer mechanics
Performance, according to mechanical performance data and knowhow to gelation degree divided rank, grade includes：It is not plasticized completely, completely
Plasticizing is crossed in plasticizing.The output desired value of neural network model is set according to plasticizing grade.
(2) while collecting sample polymer, using the device of above-mentioned online characterization screw extruder gelation degree, i.e.,
On-line checking polymer plasticization degree device provided by the invention detects temperature, pressure and the ultrasonic wave of synchronization melt
Through the speed of sample polymer, the characteristic parameter as characterization plasticizing.
(3) using the characteristic parameter obtained as evaluation index, and parameter normalization processing is carried out, normalized feature
It is worth the data as learning sample.
(4) neural network structure of 3*7*3 is built, first layer is input layer, and the second layer is hidden layer, and third layer is output
Layer, random initializtion network weight, selection neuron operation function, the maximum frequency of training of setting, the parameters such as least mean-square error,
Training neural network makes error function reach minimum value, to obtain the network connection weights of optimization.
(5) characteristic parameter in polymer processing to be tested is read in real time, by the feature of these polymer to be tested
Parameter is input in trained neural network model, and the polymer for judging that screw extruder squeezes out is distinguished according to output result
It is plasticized grade.
Illustrate technical solution provided by the invention below by a specific embodiment.
The polymer material of the present embodiment selects polypropylene (PP), and the mistake of melt gelation degree is identified based on BP neural network
The implementation steps of journey are as follows：
Step 1：Mounting temperature sensor 1, pressure sensor 1 in the head 5 of screw extruder, in 5 exit of head
It is supported by bracket institution 4 and places ultrasonic transducer 3, change process conditions, synchronization in test polymer plasticizing process
Temperature, pressure and ultrasonic wave penetrate the velocity of wave of extruded material, at the same time, are carried out to extruded material according to standard formulation batten
Mechanics Performance Testing classifies to gelation degree according to test result, and specific data see the table below 1.
1 sample data of table corresponds to table
Step 2：Utilize the characteristic parameter (temperature, pressure and ultrasound of synchronization during polymer plasticization of acquisition
Wave penetrates the velocity of wave of extruded material) it is used as evaluation index, and parameter normalization processing is carried out, as shown by the equation：Parameter value wherein after X ' expressions normalized, X indicate original parameter value, XminIndicate the parameter at this
Minimum value in sample space, XmaxMaximum value of the parameter in this sample space is indicated, using normalized characteristic value as
The data of sample are practised, the characteristic value after normalization see the table below 2.
Sample data after table 2 normalizes corresponds to table
Step 3：According to the mechanical property of sample polymer, the gelation degree of melt is divided into 3 classes：Not plasticizing completely, it is complete
Overall plasticization is crossed and is plasticized；Therefore output neuron number is determined as 3.
The desired output of three classes gelation degree is：
Not plasticizing completely：[0.999,0.001,0.001]；
Plasticizing completely:[0.001,0.999,0.001]；
Cross plasticizing:[0.001.0.001.0.999]；
Step 4：Build the BP neural network model of three-decker, input layer number is 3, melt temperature, pressure and
For ultrasonic propagation velocity 3 as input, output layer number of nodes is 3, and the gelation degree (plasticizing grade) of polymer is as defeated
Go out.Rule of thumb formula s=2m+1 (wherein, s, m are respectively hidden layer, input layer number) sets node in hidden layer as 7,
Maximum frequency of training is 1000, least mean-square error 1e-8, and the transmission function of neural network hidden layer neuron uses logarithm
Type transmission function logsig, output layer use linear activation primitive purelin.Network training code is as follows：
clc
clear
close all
N1=[0.000 1.000 0.000；
0.043 0.916 0.022；
0.111 0.897 0.133；
0.171 0.845 0.200；
0.191 0.819 0.289；
0.296 0.781 0.222；
0.372 0.690 0.378；
0.379 0.465 0.333；
0.403 0.439 0.244；
0.438 0.290 0.467；
0.484 0.265 0.511；
0.582 0.213 0.511；
0.607 0.161 0.711；
0.735 0.135 0.600；
0.774 0.116 0.689；
0.815 0.161 0.756；
0.825 0.000 0.911；
1.000 0.019 1.000]’；
X1=[0.999,0.001,0.001；0.999,0.001,0.001；0.999,0.001,0.001；
0.001,0.999,0.001；0.001,0.999,0.001；0.001,0.999,0.001；
0.001.0.001.0.999；0.001.0.001.0.999；0.001.0.001.0.999]’；
Xn_train=n1；% training samples
Dn_train=x1；% training objectives
% function interface assignment
NodeNum=7；% node in hidden layer
TypeNum=3；Export dimension
P1=xn_train；Training input
T1=dn_train；Training output
Epochs=1000；% frequency of training
Network parameter is arranged in %
TF1=' logsig '；TF2=' purelin '；
Net=newff (minmax (p1), [NodeNum TypeNum], { TF1 TF2 }, ' trainlm ')；
Net.trainParam.epochs=Epochs；% maximum frequency of training
Net.trainParam.goal=1e-8；Least mean-square error
Net.trainParam.min_grad=1e-20；% minimal gradients
Net.trainParam.show=200；% training displays interval
Net.trainParam.time=inf；The % maximum training times
Step 5) characteristic parameter in polymer processing to be tested, such as the following table 3 are read in real time.
3 polymer features parameter list to be tested of table
| Serial number | Temperature | Pressure | Velocity of wave |
| 1 | 202.3 | 18.7 | 824 |
| 2 | 230.0 | 7.9 | 860 |
| 3 | 250.1 | 5.4 | 860 |
Such as the following table 4 after normalized.
Polymer features parameter list to be tested after table 4 normalizes
| Serial number | Temperature | Pressure | Velocity of wave |
| 1 | 0.027 | 0.877 | 0.089 |
| 2 | 0.597 | 0.181 | 0.889 |
| 3 | 1.010 | 0.019 | 0.889 |
These parameters are input in trained neural network, judge that screw extruder squeezes out according to output result differentiation
It is plasticized grade：
% training and test
Net=train (net, p1, t1) % is trained
P=[0.027 0.877 0.089；
0.597 0.181 0.889；
1.010 0.019 0.889]’；
X=sim (net, P)；% is detected, and is exported as test result
X=full (compet (X)) % competition outputs
Output is：
X=0.999,0.001,0.001
0.001,0.999,0.001
0.001.0.001.0.999
According to output as a result, it is respectively not modeling completely that can obtain the corresponding polymer melt plasticizing grade of above-mentioned three kinds of operating modes
Change, be plasticized completely, cross plasticizing.
To achieve the above object, the present invention also provides a kind of method of on-line checking polymer plasticization degree, the sides
Method is applied to the device of the on-line checking polymer plasticization degree.
Fig. 4 is the flow diagram of on-line checking polymer plasticization degree method of the embodiment of the present invention, as shown in figure 4, institute
The method of stating includes：
Step 401：Obtain multigroup sample data.
Step 402：Neural network model is established using neural network algorithm according to multigroup sample data.
Step 403：Obtain the detection data of polymer to be tested；The detection data is that the polymer to be tested is being moulded
The temperature value of synchronization, pressure value and ultrasonic wave penetrate the velocity of wave of the polymer to be tested during change.
Step 404：The detection data of the polymer to be tested is input to the neural network model, is waited for described in determination
The plasticizing grade of test polymer.
Wherein step 401 specifically includes：
Obtain multigroup sample polymeric detection data；The sample polymeric detection data are that the sample polymer is being moulded
The temperature value of synchronization, pressure value and ultrasonic wave penetrate the velocity of wave of the sample polymer during change.
Mechanics Performance Testing is carried out to all sample polymer, determines the corresponding mechanics of each sample polymer
Performance number.
According to the corresponding mechanical properties value of the sample polymer, the plasticizing grade of the sample polymer is divided；It is described
Sample data includes that the sample polymer temperature value of synchronization, pressure value and ultrasonic wave in plasticizing process penetrate institute
State the velocity of wave of sample polymer, the plasticizing grade of the sample polymer.
Step 402 specifically includes：
Multigroup sample polymeric detection data are normalized, multigroup learning sample data are obtained.
Build the neural network structure of 3*7*3；The first layer of the neural network structure is input layer, the neural network
The second layer of structure is hidden layer, and the third layer of the neural network structure is output layer.
Using the learning sample data as input value, with the plasticizing etc. of the corresponding sample polymer of the learning sample data
Grade is output valve, and using neural network algorithm, the training neural network structure obtains neural network model.
It is offline that ocular estimate, mechanics properties testing method, solvent method etc. are mostly used greatly to the detection of polymer plasticization degree at present
Detection method depends on the judgement of test result the knowhow of operating personnel more, and temporal delay makes test tie
Fruit does not have timeliness, can not make to the improvement of process conditions and timely judge, to cause the wave of raw material in production process
Take, increases cost.And device provided by the invention and and its method, can with real-time online detect material gelation degree, realize
Work in-process continuously detects and characterizes and do not had an impact to production process, can carry out process monitoring and quality inspection at any time
It surveys, provides foundation in time to change technological parameter, to reduce the waste of raw material, reduce production cost, improve product quality, it is excellent
Change production process, the market competitiveness of enterprise.
In addition, previous contact ultrasonic probe needs to be connected directly between on process equipment, two aspects can be faced in this way
Difficulty：When between probe and production equipment junction sound insulation problem；Second is that the high temperature that probe is born in the production line is high
Press strip part；And device provided by the invention is not directly contacted with using Air Coupling ultrasonic probe with tested material, effectively
Solve the problems, such as it is above-mentioned, particularly suitable for PVC classes thermosensitive polymer and to shear, be detained requirement it is harsh containing can polymerize
The plasticizing of object material detects.
And detection method provided by the invention is based on neural network, learning rules are simple, realized convenient for computer, Ke Yishi
Existing measurement data and the Nonlinear Mapping for being plasticized grade, quantization signifying the plasticizing grade of polymer melt, test result are simple
It is understandable.It is expected to provide a kind of experiment measurement means of completely new universality for the gelation degree research of polymer product, there is pole
Big market application prospect and market popularization value.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.
Principle and implementation of the present invention are described for specific case used herein, and above example is said
The bright method and its core concept for being merely used to help understand the present invention；Meanwhile for those of ordinary skill in the art, foundation
The thought of the present invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of device of on-line checking polymer plasticization degree, which is characterized in that described device is arranged on screw extruder；
Described device include temperature sensor, pressure sensor, for transmitting and receiving the ultrasonic transducer of ultrasonic signal and
Information processing centre；The temperature sensor, the pressure sensor are arranged in the head of the screw extruder, described
Ultrasonic transducer is arranged in the head exit of the screw extruder；Described information processing center and the temperature sensing
Device, the pressure sensor and the ultrasonic transducer are all connected with.
2. the apparatus according to claim 1, which is characterized in that described device further includes bracket institution；The ultrasonic waves
Energy device is fixed on the head exit of the screw extruder by the bracket institution.
3. the apparatus of claim 2, which is characterized in that the bracket institution include pedestal, supporting rod, sliding block and
The card slot being fixed on the supporting rod；The intermediate position of the pedestal is equipped with slideway, and the sliding block is arranged in the slideway；
The supporting rod has two, respectively first support bar and second support bar；The first support bar is fixed on the slideway
One end, the second support bar are fixed on the sliding block being installed in the slideway；The head position of the screw extruder
Between the first support bar and the second support bar；The sliding block is for adjusting the first support bar and described second
Distance between supporting rod.
4. device according to claim 3, which is characterized in that the card slot includes two, respectively the first card slot and the
Two draw-in groove；First card slot is fixed in the first support bar, and second card slot is fixed in the second support bar；
The distance between first card slot and the pedestal and second card slot are equal with the distance between the pedestal.
5. device according to claim 4, which is characterized in that the ultrasonic transducer is two, respectively the first is surpassed
Acoustic wave transducer, the second ultrasonic transducer；First ultrasonic transducer is for emitting ultrasonic signal；It is described the second to surpass
Acoustic wave transducer is used for received ultrasonic signal；First ultrasonic transducer is mounted in first card slot；Described
Two ultrasonic transducers are mounted in second card slot；First ultrasonic transducer, second ultrasonic transducer
At the head outlet 20mm apart from the screw extruder, and it is arranged in perpendicular to melt flows direction and apart from institute
On the position for stating the horizontal symmetrical of melt 10mm.
6. device according to claim 5, which is characterized in that the first support bar and the second support bar are to stretch
Contracting bar；The telescopic rod is used to adjust the height of first ultrasonic transducer, second ultrasonic transducer, makes described
The center of first ultrasonic transducer and the center of second ultrasonic transducer with the head of the screw extruder
Center is in same level height.
7. device according to claim 5, which is characterized in that first ultrasonic transducer, second ultrasonic wave
Energy converter is Air Coupling ultrasonic transducer.
8. a kind of method of on-line checking polymer plasticization degree, which is characterized in that the method is applied to claim 1-7 and appoints
The device of on-line checking polymer plasticization degree described in meaning one, the method includes：
Obtain multigroup sample data；
Neural network model is established using neural network algorithm according to multigroup sample data；
Obtain the detection data of polymer to be tested；The detection data is that the polymer to be tested is same in plasticizing process
Temperature value, pressure value and the ultrasonic wave at moment penetrate the velocity of wave of the polymer to be tested；
The detection data of the polymer to be tested is input to the neural network model, determines the polymer to be tested
It is plasticized grade.
9. according to the method described in claim 8, it is characterized in that, the multigroup sample data of acquisition, specifically includes：
Obtain multigroup sample polymeric detection data；The sample polymeric detection data are that the sample polymer had been plasticized
The temperature value of synchronization, pressure value and ultrasonic wave penetrate the velocity of wave of the sample polymer in journey；
Mechanics Performance Testing is carried out to all sample polymer, determines the corresponding mechanical property of each sample polymer
Value；
According to the corresponding mechanical properties value of the sample polymer, the plasticizing grade of the sample polymer is divided；The sample
Data include that the sample polymer temperature value of synchronization, pressure value and ultrasonic wave in plasticizing process penetrate the sample
The plasticizing grade of the velocity of wave of this polymer, the sample polymer.
10. according to the method described in claim 9, it is characterized in that, described according to multigroup sample data, using nerve net
Network algorithm is established neural network model and is specifically included：
Multigroup sample polymeric detection data are normalized, multigroup learning sample data are obtained；
Build the neural network structure of 3*7*3；The first layer of the neural network structure is input layer, the neural network structure
The second layer be hidden layer, the third layer of the neural network structure is output layer；
Using the learning sample data as input value, the plasticizing grade with the corresponding sample polymer of the learning sample data is
Output valve, using neural network algorithm, the training neural network structure obtains neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810106920.XA CN108319809A (en) | 2018-02-02 | 2018-02-02 | A kind of device and method of on-line checking polymer plasticization degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810106920.XA CN108319809A (en) | 2018-02-02 | 2018-02-02 | A kind of device and method of on-line checking polymer plasticization degree |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108319809A true CN108319809A (en) | 2018-07-24 |
Family
ID=62901764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810106920.XA Pending CN108319809A (en) | 2018-02-02 | 2018-02-02 | A kind of device and method of on-line checking polymer plasticization degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108319809A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113635527A (en) * | 2021-08-13 | 2021-11-12 | 中南大学 | Novel ultrasonic plasticizing forming device and control method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101762639A (en) * | 2010-01-07 | 2010-06-30 | 中北大学 | Mixed state ultrasound on-line monitoring method in polymer production process |
| CN107003220A (en) * | 2014-10-01 | 2017-08-01 | 先进的聚合物监测技术股份有限公司 | Control for polymer reaction and the system and method using the processing automatically continuously monitored on-line |
| CN206546223U (en) * | 2017-03-16 | 2017-10-10 | 珠海市菲唯瑞特五金制品有限公司 | One kind straightens diameter spring fixture for testing |
| CN206696128U (en) * | 2017-01-20 | 2017-12-01 | 华南理工大学 | A kind of device of on-line measurement polymer melt density |
-
2018
- 2018-02-02 CN CN201810106920.XA patent/CN108319809A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101762639A (en) * | 2010-01-07 | 2010-06-30 | 中北大学 | Mixed state ultrasound on-line monitoring method in polymer production process |
| CN107003220A (en) * | 2014-10-01 | 2017-08-01 | 先进的聚合物监测技术股份有限公司 | Control for polymer reaction and the system and method using the processing automatically continuously monitored on-line |
| CN206696128U (en) * | 2017-01-20 | 2017-12-01 | 华南理工大学 | A kind of device of on-line measurement polymer melt density |
| CN206546223U (en) * | 2017-03-16 | 2017-10-10 | 珠海市菲唯瑞特五金制品有限公司 | One kind straightens diameter spring fixture for testing |
Non-Patent Citations (3)
| Title |
|---|
| Z. SUN ETC.: "Application of Ultrasound in the Determination of Fundamental Extrusion Performance: Residence Time Distribution Measurement", 《POLYMER ENGINEERING AND SCIENCE》 * |
| 许红: "基于超声波的聚合物熔体关键参数测量方法的研究", 《中国博士学位论文全文数据库 工程科技Ⅰ辑》 * |
| 钟龙: "高温高压下基于超声波响应特性对聚合物熔体密度测量方法的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113635527A (en) * | 2021-08-13 | 2021-11-12 | 中南大学 | Novel ultrasonic plasticizing forming device and control method |
| CN113635527B (en) * | 2021-08-13 | 2022-05-13 | 中南大学 | Ultrasonic plasticizing forming device and control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US5433112A (en) | Ultrasonic characterization of polymer melts under processing conditions | |
| CN103954685B (en) | Device and method for ultrasonically measuring flow orientation of polymer melt on line | |
| CN113063930B (en) | Neural network-based 3D printed concrete mechanical property online monitoring method | |
| Goubert et al. | Comparison of measurement techniques for evaluating the pressure dependence of the viscosity | |
| Köpplmayr et al. | A novel online rheometer for elongational viscosity measurement of polymer melts | |
| CN108319809A (en) | A kind of device and method of on-line checking polymer plasticization degree | |
| CN206696128U (en) | A kind of device of on-line measurement polymer melt density | |
| CN102601951B (en) | Method for detecting die cavity pressure in injection molding process based on ultrasonic signals | |
| CN113111570A (en) | Lead bonding quality prediction control method based on machine learning | |
| CN103499639B (en) | A kind of online characterizing method of sulfidation ultrasonic wave | |
| Gupta et al. | Elongational rheometers | |
| CN106596331B (en) | Device and method for online measurement of polymer melt density | |
| CN102053137A (en) | Testing device for fermenting and slaking process of dough | |
| CN108120651B (en) | Automatic detection device of rut tester and control method | |
| WO1999002965A1 (en) | A method of analyzing a sample of a product having a starch content, and an apparatus for such analyze | |
| Barczewski et al. | The in-line detection method of sharkskin melt flow instability during polyethylene extrusion based on pressure analysis | |
| CN106970202A (en) | A kind of disintegration test comprehensive analysis device and its verification method | |
| CN106680375A (en) | Air-coupled ultrasonic testing method for determining elastic modulus of material | |
| Sun et al. | Application of ultrasound and neural networks in the determination of filler dispersion during polymer extrusion processes | |
| Georgantopoulos et al. | Investigation of melt flow instabilities in SBR: Influence of MWD and microstructure at in situ pressure fluctuations as detected by capillary rheology | |
| Gon | Investigation of pressure-volume-temperature relationship by ultrasonic technique and its application for the quality prediction of injection molded parts | |
| Abu-Zahra et al. | In-process density control of extruded foam PVC using wavelet packet analysis of ultrasound waves | |
| McMaster et al. | Measurement of rheological and ultrasonic properties of food and synthetic polymer melts | |
| WO2003004998A1 (en) | Method and apparatus for measuring the elasticity of fluids | |
| CN110000947A (en) | A kind of device and method that effect being blended for on-line checking eccentric rotor extruder |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180724 |
|
| RJ01 | Rejection of invention patent application after publication |