CN112926938A - Dual spinning process recommendation system based on case reasoning - Google Patents

Dual spinning process recommendation system based on case reasoning Download PDF

Info

Publication number
CN112926938A
CN112926938A CN202110230961.1A CN202110230961A CN112926938A CN 112926938 A CN112926938 A CN 112926938A CN 202110230961 A CN202110230961 A CN 202110230961A CN 112926938 A CN112926938 A CN 112926938A
Authority
CN
China
Prior art keywords
case
spinning process
similarity
spinning
recommendation system
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
Application number
CN202110230961.1A
Other languages
Chinese (zh)
Inventor
叶争
薛文良
马颜雪
钱竞芳
沈子明
沈建锋
沈子泉
张佳敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huzhou Gaosheng Wool Spinning Co ltd
Original Assignee
Huzhou Gaosheng Wool Spinning Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huzhou Gaosheng Wool Spinning Co ltd filed Critical Huzhou Gaosheng Wool Spinning Co ltd
Priority to CN202110230961.1A priority Critical patent/CN112926938A/en
Publication of CN112926938A publication Critical patent/CN112926938A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Strategic Management (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Artificial Intelligence (AREA)
  • General Business, Economics & Management (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Manufacturing & Machinery (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention discloses a double spinning process recommendation system based on case reasoning, which comprises a spinning process case base, wherein the spinning process case base is connected with a spinning process recommendation module; the case learning module is also connected with the spinning process case library. The invention adopts double similarity to express the approaching degree of two spinning process cases, adopts an analytic hierarchy process and an expert marking system to endow fixed weight to part of characteristic attributes, can enlarge the user range, reduce certain manual operation influence, reduce the time for repeatedly adjusting the weight, and thus can effectively improve the efficiency. The method has the characteristic of efficiently and accurately recommending the process case with the highest similarity.

Description

Dual spinning process recommendation system based on case reasoning
Technical Field
The invention relates to a spinning process recommendation system, in particular to a double spinning process recommendation system based on case reasoning.
Background
With the development of social economy, people tend to diversify and customize product requirements, and the production characteristics of textile enterprises tend to be small-batch and multi-variety more and more, which puts higher requirements on the production capacity of the textile enterprises, namely that the enterprises have the capacity of quickly responding and adjusting the manufacturing process. The spinning method is characterized by multiple machine stations, multiple processes and long flow, and mainly comprises the steps of raw material selection, dyeing, mixing, carding, drawing, drafting, twisting, yarn cleaning, doubling, double twisting and the like, wherein the related process parameters are multiple, the processing mechanism is complex, and the process design efficiency is easy to reduce. Generally, before the design of the spinning process is started, a craftsman can search for a similar process from the historical process and modify the process on the basis of the similar process to form a new process. However, due to the characteristics of small batch and multiple varieties, various spinning process cases can be accumulated into a large number with time, so that it is very important to accurately position required cases from the process cases.
The existing case reasoning is mainly applied to textile intelligent process design and virtual processing systems developed by professor teams of the Yang Jian nations of the university of east China, aims at wool spinning enterprises and relates to top dyeing, spinning and weaving, and can predict design results by using a quality prediction model after similar process cases are retrieved and modified. The system has wide related range, but lacks pertinence, neglects many factors influencing the spinning process design, and under the condition of a large number of process cases, the process case with the highest similarity is difficult to find out accurately. And the method of giving retrieval feature weight completely and autonomously has the defects that although the openness is strong, the feature weight is unreasonable, and a lot of time is consumed in the process of repeatedly adjusting the weight. Therefore, the prior art has the characteristic that the process case with the highest similarity cannot be efficiently and accurately found.
Disclosure of Invention
The invention aims to provide a double spinning process recommendation system based on case reasoning. The method has the characteristic of efficiently and accurately recommending the process case with the highest similarity.
The technical scheme of the invention is as follows: a double spinning process recommendation system based on case reasoning comprises a spinning process case library, wherein the spinning process case library is connected with a spinning process recommendation module, the spinning process recommendation module is connected with a similar process reuse module, and the similar process reuse module is connected with a case learning module; the case learning module is also connected with the spinning process case library.
In the case reasoning-based dual spinning process recommendation system, the spinning process case library comprises a yarn basic information unit, a raw material data unit, a spinning process parameter unit of each process and a finished product quality data unit.
In the case reasoning-based dual spinning process recommendation system, the spinning process recommendation module comprises a new product feature attribute value and weight input unit, each feature attribute similarity calculation unit, a case similarity calculation unit and a similar case selection unit.
In the case-reasoning-based dual spinning process recommendation system, each feature attribute similarity calculation unit calculates according to the feature attribute data type by using a corresponding similarity calculation formula, where the similarity calculation formula is as follows:
accurate matching formula:
Figure BDA0002958005380000021
numerical matching formula:
Figure BDA0002958005380000031
string type matching formula:
Figure BDA0002958005380000032
in the formula, sim (x)i，yi) Similarity of feature attributes for 2 cases; x is the number ofi,yiThe values of the ith characteristic attribute of the two cases respectively; k has a value range of [0,1 ]](ii) a Distance represents a character string xi,yiThe edit distance between; length (x)i) As a string xiLength of (d); length (y)i) As a character string yiLength of (d).
In the case-based reasoning double spinning process recommendation system, the case similarity calculation unit divides the characteristic attributes into a first part of characteristic attributes and a second part of characteristic attributes according to the characteristics of the characteristic attributes, such as the spinning mode, the yarn specification, the yarn application and indexes of all fibers forming the yarn, and respectively calculates the similarity of the cases to obtain corresponding first repeated similarity and second repeated similarity;
the calculation formula of the first re-similarity is as follows:
Figure BDA0002958005380000033
the second similarity is calculated by the following formula:
Figure BDA0002958005380000034
in the formula, sim1、sim2Respectively shows the similarity between the first and second cases, wiRepresenting the weight of the ith characteristic attribute.
In the case-based reasoning double spinning process recommendation system, the first double similarity adopts an analytic hierarchy process and an expert scoring system, professionals of enterprises and schools are selected to score the first part of characteristic attributes, and the weight of each characteristic attribute in the first part of characteristic attributes is determined;
and determining the weight of each characteristic attribute in the second part of characteristic attributes by the second weight similarity in a mode of giving weight by the user independently.
In the case reasoning-based dual spinning process recommendation system, the similar case selection unit sorts the similarity between the new product and each process case in the spinning process case library from large to small according to the first heavy similarity, and selects the process cases with the ranks in the top ten to form a similar process case sequence.
In the case reasoning-based double spinning process recommendation system, the similar process reuse module selects the process case which is most suitable for the spinning process of the new product from the similar process case sequence, modifies the process in the selected process case according to the requirements of the new product, selects a suitable spinning machine, and adjusts the process parameters to obtain the final spinning process of the new product.
In the case reasoning-based dual spinning process recommendation system, the case learning module can store the final new product spinning process obtained in the similar process reuse module into the spinning process case library as the standard spinning process case of the new product.
Compared with the prior art, the method adopts double similarity to express the approaching degree of two spinning process cases, not only considers the influence of the spinning mode, the yarn specification, the application and the raw material type on the similarity of the two spinning processes, but also considers the influence of the performance indexes of all components in the blended yarn on the design of the spinning process, thereby being capable of more accurately recommending the process which is closer to a new product. In addition, an analytic hierarchy process and an expert marking system are adopted, fixed weights are given to part of characteristic attributes, the user range can be enlarged, certain manual operation influence is reduced, time for repeatedly adjusting the weights is shortened, and therefore efficiency can be effectively improved. In conclusion, the method has the characteristic of efficiently and accurately recommending the process case with the highest similarity.
Drawings
Fig. 1 is a schematic structural view of the present invention.
The labels in the figures are: 1-spinning process case library, 2-spinning process recommendation module, 3-similar process reuse module, 4-case learning module, 101-yarn basic information unit, 102-raw material data unit, 103-spinning process parameter unit of each procedure, 104-finished product quality data unit, 201-new product characteristic attribute value and weight input unit, 202-each characteristic attribute similarity calculation unit, 203-case similarity calculation unit and 204-similar case selection unit.
Detailed Description
The invention is further illustrated by the following figures and examples, which are not to be construed as limiting the invention.
Examples are given. A double spinning process recommendation system based on case reasoning is formed as shown in a figure 1 and comprises a spinning process case base 1, wherein the spinning process case base 1 is connected with a spinning process recommendation module 2, the spinning process recommendation module 2 is connected with a similar process reuse module 3, and the similar process reuse module 3 is connected with a case learning module 4; the case learning module 4 is also connected with the spinning process case library 1.
The spinning process case library 1 comprises a yarn basic information unit 101, a raw material data unit 102, a spinning process parameter unit 103 of each process and a finished product quality data unit 104.
The spinning process recommending module 2 comprises a new product feature attribute value and weight input unit 201, a feature attribute similarity calculating unit 202, a case similarity calculating unit 203 and a similar case selecting unit 204.
Each feature attribute similarity calculation unit 202 calculates according to the feature attribute data type by using a corresponding similarity calculation formula, which is as follows:
accurate matching formula:
Figure BDA0002958005380000051
numerical matching formula:
Figure BDA0002958005380000061
string type matching formula:
Figure BDA0002958005380000062
in the formula, sim (x)i，yi) Similarity of feature attributes for 2 cases; x is the number ofi,yiThe values of the ith characteristic attribute of the two cases respectively; k has a value range of [0,1 ]]The larger the number of the general characteristic values is, the smaller the value range of k is; dis distance represents a string xi,yiThe edit distance between; length (x)i) As a string xiLength of (d); length (y)i) As a character string yiLength of (d).
The case similarity calculation unit 203 divides the characteristic attributes into a first part of characteristic attributes (spinning mode, yarn specification and yarn application) and a second part of characteristic attributes (each fiber index of the formed yarn) according to the characteristics of the characteristic attributes, namely the yarn and the fiber, of the spinning mode, the yarn specification (name, yarn count, single twist, strand twist and number of combined yarns), the yarn application and each fiber index of the formed yarn, and respectively calculates the similarity of the cases to obtain corresponding first repeated similarity and second repeated similarity;
the calculation formula of the first re-similarity is as follows:
Figure BDA0002958005380000063
the second similarity is calculated by the following formula:
Figure BDA0002958005380000064
in the formula, sim1、sim2Respectively shows the similarity between the first and second cases, wiRepresenting the weight of the ith characteristic attribute.
The first re-similarity adopts an analytic hierarchy process and an expert scoring system, professionals of enterprises and schools are selected to score the first part of characteristic attributes, and the weight of each characteristic attribute in the first part of characteristic attributes is determined;
and determining the weight of each characteristic attribute in the second part of characteristic attributes by the second weight similarity in a mode of giving weight by the user independently.
The similar case selecting unit 204 sorts the similarity between the new product and each process case in the spinning process case library from large to small according to the first re-similarity, and selects the process case with the ranking in the first ten to form a similar process case sequence.
And the similar process reusing module 3 selects the process case which is most suitable for the new product spinning process from the similar process case sequence, modifies the process in the selected process case according to the requirements of the new product, selects a suitable spinning machine table, and adjusts the process parameters to obtain the final new product spinning process. Before large-batch spinning production, a new product is generally subjected to trial spinning, the effect of process design is confirmed by combining the result of the trial spinning, and if the result does not meet the production target, the process parameters are modified, so that the final spinning process scheme is obtained.
The case learning module 4 can save the final new product spinning process obtained in the similar process reusing module 3 into the spinning process case library as the standard spinning process case of the new product. In the case learning module, a user can add a new spinning process case, various information (basic information, raw material data, spinning process parameters of each procedure and finished product quality data) of a new product is perfected, and the subsequent utilization is facilitated.
The principle of the spinning process case library construction is as follows: (1) spinning process cases are from the ordinary accumulation of enterprises or the introduction of spinning process cases of other enterprises on the premise of being similar to the parameters of the production equipment of the enterprises. (2) The spinning process case should be selected with certain difference. (3) Each case should contain the data items accurately and completely.
In this embodiment, the spinning process case library is composed of specific information of various different spinning process cases, and the specific information includes basic information of yarns, raw material data, spinning process parameters of each process, and finished product quality data.
The basic information of the yarn comprises a batch number, a product name (named by raw materials and content, namely containing a blending ratio and a raw material name), a spinning mode, a yarn count, single twist, strand twist, a ply number and a yarn application.
The raw material data comprises three types: the wool fiber information comprises content, average fineness, average length, short fiber rate, oil content and moisture regain; cotton fiber information includes content, linear density, average length, micronaire value, flock rate and moisture regain; other fiber information includes content, linear density, average length, and moisture regain.
The technological parameters of the procedures comprise specific parameters of dyeing, wool blending, carding, spinning, spooling, doubling and two-for-one twisting.
The finished product quality data comprises a finished product count (NM), a single yarn twist (T/m), a double yarn twist (T/m), a single yarn strength (CN), a double yarn strength (CN), a single yarn elongation (%), a double yarn elongation (%), a single yarn moisture regain (%), a finished product moisture regain (%), a linear density deviation (%), a single yarn twist deviation (%), and a strand twist deviation (%).
The spinning process recommending module comprises a new product characteristic attribute value input unit, a characteristic attribute similarity calculating unit, a case similarity calculating unit and a similar case selecting unit.
The spinning process case comprises various attributes, and can be divided into 3 types according to the attribute characteristics:
precise matching, such as spinning mode, yarn use, and the like;
numerical types, such as yarn count, single twist, strand twist, and the like;
character string type, such as brand name, etc.
And (3) calculating the similarity of each characteristic attribute by adopting the most common nearest neighbor algorithm in case inference, and then obtaining the similarity between cases according to the weight of each characteristic attribute, wherein the similarity of the cases is divided into two parts.
New product feature attribute value and weight input unit: the factors mainly considered in the design of the spinning process in the embodiment are yarn number, twist, blending ratio, raw material type and used raw material data; the spinning mode directly influences the selection of a machine table and a spinning process; the yarn usage also determines the process settings to some extent. Therefore, the spinning mode, the yarn application, the name, the yarn count, the single twist, the strand twist, the ply number and the raw material data are selected as the characteristic attributes for measuring the similarity among the spinning process cases, and a user can input the characteristic attribute value and the weight of part of the characteristic attributes in the new product characteristic attribute value and weight input interface.

Claims (9)

1. A double spinning process recommendation system based on case reasoning is characterized in that: the spinning process case library comprises a spinning process case library (1), wherein the spinning process case library (1) is connected with a spinning process recommending module (2), the spinning process recommending module (2) is connected with a similar process reusing module (3), and the similar process reusing module (3) is connected with a case learning module (4); the case learning module (4) is also connected with the spinning process case library (1).
2. The case-based reasoning double spinning process recommendation system as claimed in claim 1, characterized in that: the spinning process case library (1) comprises a yarn basic information unit (101), a raw material data unit (102), a spinning process parameter unit (103) of each process and a finished product quality data unit (104).
3. The case-based reasoning double spinning process recommendation system as claimed in claim 1, characterized in that: the spinning process recommending module (2) comprises a new product feature attribute value and weight input unit (201), feature attribute similarity calculating units (202), case similarity calculating units (203) and a similar case selecting unit (204).
4. The case-based reasoning double spinning process recommendation system as claimed in claim 3, characterized in that: each feature attribute similarity calculation unit (202) calculates according to the feature attribute data type by using a corresponding similarity calculation formula, wherein the similarity calculation formula is as follows:
accurate matching formula:
Figure FDA0002958005370000011
numerical matching formula:
Figure FDA0002958005370000012
string type matching formula:
Figure FDA0002958005370000021
in the formula, sim (x)i，yi) Similarity of feature attributes for 2 cases; x is the number ofi,yiThe values of the ith characteristic attribute of the two cases respectively; k has a value range of [0,1 ]](ii) a Distance represents a character string xi,yiThe edit distance between; length (x)i) As a string xiLength of (d); length (y)i) As a character string yiLength of (d).
5. The case-based reasoning double spinning process recommendation system as claimed in claim 3, characterized in that: the case similarity calculation unit (203) divides the characteristic attributes into a first part of characteristic attributes and a second part of characteristic attributes according to the characteristics of the characteristic attributes, such as the spinning mode, the yarn specification, the yarn application and indexes of all fibers forming the yarn, and respectively calculates the similarity of the cases to obtain corresponding first repeated similarity and second repeated similarity;
the calculation formula of the first re-similarity is as follows:
Figure FDA0002958005370000022
the second similarity is calculated by the following formula:
Figure FDA0002958005370000023
in the formula, sim1、sim2Respectively shows the similarity between the first and second cases, wiRepresenting the weight of the ith characteristic attribute.
6. The case-based reasoning double spinning process recommendation system as claimed in claim 5, characterized in that: the first re-similarity adopts an analytic hierarchy process and an expert scoring system, professionals of enterprises and schools are selected to score the first part of characteristic attributes, and the weight of each characteristic attribute in the first part of characteristic attributes is determined;
and determining the weight of each characteristic attribute in the second part of characteristic attributes by the second weight similarity in a mode of giving weight by the user independently.
7. The case-based reasoning double spinning process recommendation system as claimed in claim 5, characterized in that: the similar case selecting unit (204) sorts the similarity of the new product and each process case in the spinning process case library from big to small according to the first re-similarity, and selects the process cases with the sequence in the first ten places to form a similar process case sequence.
8. The case-based reasoning double spinning process recommendation system as claimed in claim 1, characterized in that: and the similar process reusing module (3) selects the process case which is most suitable for the spinning process of the new product from the similar process case sequence, modifies the process in the selected process case according to the requirements of the new product, selects a suitable spinning machine table, and adjusts the process parameters to obtain the final spinning process of the new product.
9. The case-based reasoning double spinning process recommendation system as claimed in claim 8, characterized in that: the case learning module (4) can store the final new product spinning process obtained in the similar process reusing module (3) into a spinning process case library as a standard spinning process case of the new product.
CN202110230961.1A 2021-03-02 2021-03-02 Dual spinning process recommendation system based on case reasoning Pending CN112926938A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110230961.1A CN112926938A (en) 2021-03-02 2021-03-02 Dual spinning process recommendation system based on case reasoning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110230961.1A CN112926938A (en) 2021-03-02 2021-03-02 Dual spinning process recommendation system based on case reasoning

Publications (1)

Publication Number Publication Date
CN112926938A true CN112926938A (en) 2021-06-08

Family

ID=76173042

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110230961.1A Pending CN112926938A (en) 2021-03-02 2021-03-02 Dual spinning process recommendation system based on case reasoning

Country Status (1)

Country Link
CN (1) CN112926938A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113689113A (en) * 2021-08-20 2021-11-23 北京数码大方科技股份有限公司 Method and device for recommending process information, storage medium and processor

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104536408A (en) * 2014-12-18 2015-04-22 江苏工程职业技术学院 Handheld type yarn technology optimizing device and work process thereof

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104536408A (en) * 2014-12-18 2015-04-22 江苏工程职业技术学院 Handheld type yarn technology optimizing device and work process thereof

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
刘利军等: "基于多Agent案例推理的个性化智能推荐服务", 《武汉理工大学学报(信息与管理工程版)》 *
刘海江等: "基于案例推理的航天大型薄壁件加工过程质量追溯", 《制造业自动化》 *
吕志军等: "知识表达及其在毛纺织工艺设计中的应用", 《纺织学报》 *
文尧奇等: "基于案例推理的纺纱工艺智能设计", 《控制工程》 *
韩江洪等: "基于案例推理的纺纱质量预测模型研究", 《系统仿真学报》 *
马维国: "纺纱生产BP神经网络模型", 《计算机辅助工程》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113689113A (en) * 2021-08-20 2021-11-23 北京数码大方科技股份有限公司 Method and device for recommending process information, storage medium and processor

Similar Documents

Publication Publication Date Title
Chakraborty et al. An integrated DEMATEL–VIKOR method-based approach for cotton fibre selection and evaluation
CN112926938A (en) Dual spinning process recommendation system based on case reasoning
CN110607586A (en) Continuous intelligent spinning system
Kotb Predicting yarn quality performance based on fibers types and yarn structure
CN110516978A (en) A kind of electronic product commissioning production line mixed flow scheduled production method
CN204138845U (en) A kind of spinning apparatus of novel colour-spun yarns
Majumdar Selection of raw materials in textile spinning industry using fuzzy multi-criteria decision making approach
Chakraborty et al. Cotton fibre selection and grading–a PROMETHEE-GAIA-based approach
CN109754164B (en) Dynamic yield model for calculating input amount in cashmere textile production
CN101587545B (en) Method and system for selecting feature of cotton heterosexual fiber target image
Kaplan et al. A multicriteria decision aid approach on navel selection problem for rotor spinning
CN103388208B (en) Slub spandex stocking yarn and manufacture craft thereof
Alam et al. Assessing the impact of speed change on energy consumption and productivity: Investigating ring frame process parameters
WO2023165979A1 (en) Method and data-based assistance system for an optimal adjustment of a textile machine
CN102567920B (en) Method for generating sewing smoothness based on structural parameters of fabric
Kabir et al. Customer perceived quality improvement of synthetic fiber using fuzzy QFD: a case study
CN101724945B (en) Manufacturing method of Modundai mink knitted velour
CN207646363U (en) A kind of slub production-process systems based on PLC
Moghassem et al. Processing parameters optimization of draw frame for rotor spun yarn strength using gene expression programming (GEP)
Huang et al. Combining Taguchi Method with fuzzy inference on process optimization for fiber manufacturing
Shao et al. A new quality control method for cotton spinning
CN113313430B (en) Integrated BOM system for whole process of manufacturing steel wire rope and construction method
CN115933564B (en) Textile yarn production process monitoring regulation and control system
Hunter Gendering the Labor Market: Evidence from the Interwar Textile Industry
Jeyakkannan et al. Modified improved genetic algorithm to minimise tri-objective functions in a textile mill

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: 20210608

RJ01 Rejection of invention patent application after publication