CN205688082U - Yarn qualities predictor - Google Patents
Yarn qualities predictor Download PDFInfo
- Publication number
- CN205688082U CN205688082U CN201620360307.7U CN201620360307U CN205688082U CN 205688082 U CN205688082 U CN 205688082U CN 201620360307 U CN201620360307 U CN 201620360307U CN 205688082 U CN205688082 U CN 205688082U
- Authority
- CN
- China
- Prior art keywords
- module
- data
- yarn
- rejecting
- transcoding
- 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.)
- Expired - Fee Related
Links
Landscapes
- Filamentary Materials, Packages, And Safety Devices Therefor (AREA)
Abstract
This utility model relates to a kind of yarn qualities predictor, including: acquisition module, for gathering the qualitative data of yarn on spinning process;The rejecting module being connected with described acquisition module, for rejecting the fluctuating margin data beyond predetermined value from the data that described acquisition module gathers;The transcoding module being connected with described rejecting module, the data exceeding predetermined value for described rejecting module is rejected fluctuating margin carry out transcoding;The linear block being connected with described transcoding module, the linear relationship of the data after obtaining described transcoding module transcoding;The Quality Forecasting module being connected with described linear block, the linear relationship for obtaining according to described linear block forecasts the quality of described yarn.This utility model can prevent yarn qualities during yarn production from going wrong with the qualitative data of Real-time Collection yarn.
Description
Technical field
This utility model relates to yarn application, particularly relates to a kind of yarn qualities predictor.
Background technology
Yarn qualities forecast is to solve to exist between yarn quality index and Raw Cotton Property index and yarning process parameter
A large amount of non-linear relations.Along with the development of science and technology, artificial neural network technology is applied to yarn qualities and forecasts by people
Attention.Conventional utilize neutral net limited, hence without enough numbers to the data volume studied yarn prediction and gathered
Neutral net is trained according to amount.
Along with the Internet and the progress of computer technology, and the analysis of big data and the raising of disposal ability, data are deposited
Storage technology and the available value of data are more and more important.Traditional number utilizing neutral net to be gathered to study yarn to predict
Limited according to amount, train neutral net hence without enough data volumes.
Therefore, using conventional big data and memory technology to carry out yarn qualities forecast is that the technology needing solution badly is asked
Topic.
Utility model content
Based on this, it is necessary to provide a kind of yarn qualities predictor, in time yarn qualities is forecast, prevent yarn
Break down in process of production.
A kind of yarn qualities predictor, including:
Acquisition module, for gathering the qualitative data of yarn on spinning process;
The rejecting module being connected with described acquisition module, for rejecting fluctuation width from the data that described acquisition module gathers
Degree is beyond the data of predetermined value;
The transcoding module being connected with described rejecting module, for rejecting fluctuating margin beyond predetermined value by described rejecting module
Data carry out transcoding;
The linear block being connected with described transcoding module, the linear pass of the data after obtaining described transcoding module transcoding
System;
The Quality Forecasting module being connected with described linear block, for the linear relationship obtained according to described linear block
Forecast the quality of described yarn.
Wherein in an embodiment, described acquisition module includes Temperature Humidity Sensor.
Wherein in an embodiment, described rejecting module includes:
Screening unit, for filtering out the fluctuating margin number beyond predetermined value from the data that described acquisition module gathers
According to;
The culling unit being connected with described screening unit, for rejecting described sieve from the data that described acquisition module gathers
The fluctuating margin of menu unit screening is beyond the data of predetermined value.
Wherein in an embodiment, also include:
The memory module being connected with described Quality Forecasting module, for storing the described yarn of described Quality Forecasting module forecast
The quality of line.
The above yarn qualities predictor, during yarn production, can with the qualitative data of Real-time Collection yarn,
Prevent yarn qualities during yarn production from going wrong.
Accompanying drawing explanation
Fig. 1 is the structural representation of an embodiment yarn qualities predictor.
Detailed description of the invention
In order to make the purpose of this utility model, technical scheme and advantage clearer, below in conjunction with accompanying drawing and enforcement
Example, is further elaborated to this utility model.Should be appreciated that specific embodiment described herein is only in order to explain
This utility model, is not used to limit this utility model.
As it is shown in figure 1, the yarn qualities predictor of an embodiment includes that acquisition module 110 is connected with acquisition module 110
Rejecting module 120 with reject linear block 140 that the transcoding module 130 that is connected of module 120 is connected with transcoding module 130 and
The Quality Forecasting module 150 being connected with linear block 140.
Acquisition module 110 is for gathering the qualitative data of yarn on spinning process.
In the present embodiment, acquisition module 110 can be Temperature Humidity Sensor or other need gather yarn qualities data
Collecting device, in the present embodiment, yarn qualities data can also include rings specifications and models, wire loop number in processing apparatus
Number, winder speed, the form of groove drum, the fineness etc. of yarn.Wherein, the qualitative data gathered can also be carried out point by the present embodiment
Class, as classified qualitative data according to collected object correspondence.
Reject module 120 for rejecting the fluctuating margin data beyond predetermined value from the data that acquisition module gathers.
In the present embodiment, reject module 120 and include screening unit and the culling unit being connected with screening unit.Screening is single
Unit is for filtering out the fluctuating margin data beyond predetermined value from the data of acquisition module collection.Culling unit, for from adopting
In the data that collection module gathers, the fluctuating margin of rejecting screening unit screening is beyond the data of predetermined value.Generally acquisition module collection
Qualitative data include the data conformed to quality requirements and do not meet the data of prescription.Such as, in yarn production process
In, the running speed of equipment may cause yarn because of the supply of electric power or the running speed of other special circumstances equipment
Qualitative data unstable, even part data are beyond the maximum predetermined value allowed in normal production, such as, maximum predetermined
Value can be the maximum etc. of predetermined temperature.It is thus typically necessary to these data are rejected from normal creation data,
Prevent the follow-up quality to yarn from carrying out pre-generation mistake forecast of giving the correct time.
Transcoding module 130 is for carrying out transcoding by rejecting the module rejecting fluctuating margin data beyond predetermined value.
Delete after fluctuating margin is beyond the data of predetermined value in qualitative data, can carry out follow-up data being transcoded into permissible
Input the data to model.For example, it is preferable to, after the present embodiment can use RBF (Radial Basis Function Neural) to transcoding
Data carry out following model conversion, therefore, follow-up data can be transcoded into by transcoding module and can input to RBF model
Corresponding data.It is pointed out that the realization of the present embodiment is all based on routine techniques, transcoding module realize process
To be realized by conventional transcoding means.
The linear relationship of the linear block 140 data after obtaining transcoding module transcoding.
In the present embodiment, by RBF model, the qualitative data after transcoding can be converted to have corresponding linear relation
Data.In the present embodiment, RBF model include having the hidden layer of Radial Basis Function neural unit and one there is the defeated of linear neuron
Going out layer, the input of neuron is that the distance between input vector and weights is multiplied by threshold value.Input signal is delivered to hidden layer, and hidden layer has
Neuron, node function is Gaussian function, and output layer has neuron, and node function is simple linear function.Radially base is neural
The number of unit is equal with the number of input vector, has 7 neurons.Circulation each time only produces a neuron, and often increases
Add a radially base neuron, can farthest reduce error, if not up to required precision, continue to increase neuron,
Until meeting required precision.In the present embodiment, radially the threshold value of basic unit can be set as 0.8326/spread, so that weighting
Input for during ± spread radially basic unit be output as 0.5.It is pointed out that the realization of the present embodiment is the data of routine
Select, non-the present embodiment data to be protected special case.The possible data of the non-specific of the present embodiment protection realizes, but linear mould
Annexation between block and transcoding module.
In the present embodiment, the realization of linear block is based on routine techniques, and what the present embodiment was protected is linear block and turns
Annexation between code module, the present embodiment is not related to the improvement of concrete software view.
The quality of the Quality Forecasting module 150 linear relationship forecast yarn for obtaining according to linear block.
Generally, the linear relationship of acquisition includes the state of yarn qualities, such as, can know currently according to linear relationship
The filoplume quality of yarn is with the relation of thickness of yarn, thus judges whether current yarn meets the requirements.Quality Forecasting module root
The quality condition of yarn can be obtained according to this linear relationship, know the quality condition of yarn aborning in time.
The above yarn qualities predictor, during yarn production, can with the qualitative data of Real-time Collection yarn,
Prevent yarn qualities during yarn production from going wrong.
As shown in the table, for using RBF model prediction cotton yarn 14.5tex, 15 groups of data samples, as test data, draw
Predictive value and measured value do error analysis:
As shown in below table, under identical device and process conditions, it was predicted that value contrasts feelings respectively with the filoplume of measured value
Condition, according to experimental data, error is in the range of 0.01~0.03, it will be apparent that, the present embodiment has preferable approximation capability.
In the present embodiment, the quality of the yarn of quality forecast module forecast can be stored, concrete, the present embodiment
Yarn qualities predictor also include the memory module that is connected with Quality Forecasting module, be used for storing the forecast of Quality Forecasting module
The quality of yarn.Memory module can store the linear quality that Quality Forecasting module is forecast according to linear relationship, the most secondary
During product, if produce same or like linear relationship, the linear quality situation that can store according to memory module, and
The quality problems that Shi Faxian yarn exists.
Each technical characteristic of embodiment described above can combine arbitrarily, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic executed in example is all described, but, as long as the combination of these technical characteristics is not deposited
In contradiction, all it is considered to be the scope that this specification is recorded.
Embodiment described above only have expressed several embodiments of the present utility model, and it describes more concrete and detailed,
But therefore can not be interpreted as the restriction to utility model patent scope.It should be pointed out that, for the common skill of this area
For art personnel, without departing from the concept of the premise utility, it is also possible to make some deformation and improvement, these broadly fall into
Protection domain of the present utility model.Therefore, the protection domain of this utility model patent should be as the criterion with claims.
Claims (4)
1. a yarn qualities predictor, it is characterised in that including:
Acquisition module, for gathering the qualitative data of yarn on spinning process;
The rejecting module being connected with described acquisition module, surpasses for rejecting fluctuating margin from the data that described acquisition module gathers
Go out the data of predetermined value;
The transcoding module being connected with described rejecting module, for rejecting the fluctuating margin number beyond predetermined value by described rejecting module
According to carrying out transcoding;
The linear block being connected with described transcoding module, the linear relationship of the data after obtaining described transcoding module transcoding;
The Quality Forecasting module being connected with described linear block, forecasts institute for the linear relationship obtained according to described linear block
State the quality of yarn.
Yarn qualities predictor the most according to claim 1, it is characterised in that described acquisition module includes that humiture passes
Sensor.
Yarn qualities predictor the most according to claim 1, it is characterised in that described rejecting module includes:
Screening unit, for filtering out the fluctuating margin data beyond predetermined value from the data that described acquisition module gathers;
The culling unit being connected with described screening unit, single for rejecting described screening from the data that described acquisition module gathers
The fluctuating margin of unit's screening is beyond the data of predetermined value.
Yarn qualities predictor the most according to claim 1, it is characterised in that also include:
The memory module being connected with described Quality Forecasting module, for storing the described yarn of described Quality Forecasting module forecast
Quality.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201620360307.7U CN205688082U (en) | 2016-04-26 | 2016-04-26 | Yarn qualities predictor |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201620360307.7U CN205688082U (en) | 2016-04-26 | 2016-04-26 | Yarn qualities predictor |
Publications (1)
Publication Number | Publication Date |
---|---|
CN205688082U true CN205688082U (en) | 2016-11-16 |
Family
ID=57264180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201620360307.7U Expired - Fee Related CN205688082U (en) | 2016-04-26 | 2016-04-26 | Yarn qualities predictor |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN205688082U (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107169565A (en) * | 2017-04-27 | 2017-09-15 | 西安工程大学 | Yarn quality prediction method based on fireworks algorithm improvement BP neural network |
TWI816062B (en) * | 2020-10-30 | 2023-09-21 | 財團法人工業技術研究院 | Parameter control method of textile process |
-
2016
- 2016-04-26 CN CN201620360307.7U patent/CN205688082U/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107169565A (en) * | 2017-04-27 | 2017-09-15 | 西安工程大学 | Yarn quality prediction method based on fireworks algorithm improvement BP neural network |
CN107169565B (en) * | 2017-04-27 | 2020-06-19 | 西安工程大学 | Spinning quality prediction method for improving BP neural network based on firework algorithm |
TWI816062B (en) * | 2020-10-30 | 2023-09-21 | 財團法人工業技術研究院 | Parameter control method of textile process |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107194803A (en) | P2P net loan borrower credit risk assessment device | |
CN108366045A (en) | A kind of setting method and device of air control scorecard | |
CN111614491B (en) | Power monitoring system oriented safety situation assessment index selection method and system | |
WO2016082263A1 (en) | Plan-based multi-target assistant decision-making platform and implementation method thereof | |
CN104463359A (en) | Dredging operation yield prediction model analysis method based on BP neural network | |
CN104113452B (en) | Network quality Forecasting Methodology and device | |
CN104408667A (en) | Method and system for comprehensively evaluating power quality | |
Anezakis et al. | Hybrid soft computing analytics of cardiorespiratory morbidity and mortality risk due to air pollution | |
CN205688082U (en) | Yarn qualities predictor | |
CN112087442A (en) | Time sequence related network intrusion detection method based on attention mechanism | |
CN110288144A (en) | A kind of deep basal pit security assessment method based on utility theory and D-S evidential reasoning | |
CN108319672A (en) | Mobile terminal malicious information filtering method and system based on cloud computing | |
CN116205355B (en) | Power load prediction method, device and storage medium | |
CN110198453A (en) | Live content filter method, storage medium, equipment and system based on barrage | |
CN115222303B (en) | Industry risk data analysis method and system based on big data and storage medium | |
CN111986027A (en) | Abnormal transaction processing method and device based on artificial intelligence | |
Gurav et al. | Survey on automated system for fake news detection using NLP & machine learning approach | |
AU2021106280A4 (en) | A Method of Water Environment Risk Assessment Based on Fuzzy Integral Model | |
CN110650124A (en) | Network flow abnormity detection method based on multilayer echo state network | |
CN110807174B (en) | Effluent analysis and abnormity identification method for sewage plant group based on statistical distribution | |
CN105021888B (en) | Harmonic data monitoring method based on data clusters | |
CN111460796A (en) | Accidental sensitive word discovery method based on word network | |
CN116316699A (en) | Large power grid frequency security situation prediction method, device and storage medium | |
Wang et al. | Research of the early warning analysis of crop diseases and insect pests | |
CN111414945A (en) | Method and device for identifying fluctuation of model efficiency |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20161116 Termination date: 20180426 |
|
CF01 | Termination of patent right due to non-payment of annual fee |