CN109559059B - Regression decision tree-based optical fiber production rule making method - Google Patents
Regression decision tree-based optical fiber production rule making method Download PDFInfo
- Publication number
- CN109559059B CN109559059B CN201811542570.8A CN201811542570A CN109559059B CN 109559059 B CN109559059 B CN 109559059B CN 201811542570 A CN201811542570 A CN 201811542570A CN 109559059 B CN109559059 B CN 109559059B
- Authority
- CN
- China
- Prior art keywords
- data
- optical fiber
- model
- optical
- decision tree
- 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.)
- Active
Links
- 239000013307 optical fiber Substances 0.000 title claims abstract description 85
- 238000003066 decision tree Methods 0.000 title claims abstract description 44
- 238000007380 fibre production Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000003287 optical effect Effects 0.000 claims abstract description 44
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000002790 cross-validation Methods 0.000 claims abstract description 6
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims description 26
- 238000005259 measurement Methods 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 2
- 230000001502 supplementing effect Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000010200 validation analysis Methods 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 description 14
- 239000000047 product Substances 0.000 description 14
- 238000004519 manufacturing process Methods 0.000 description 13
- 239000000835 fiber Substances 0.000 description 10
- 230000008021 deposition Effects 0.000 description 7
- 238000005452 bending Methods 0.000 description 6
- 238000005520 cutting process Methods 0.000 description 6
- 239000006185 dispersion Substances 0.000 description 6
- 230000003595 spectral effect Effects 0.000 description 5
- 238000005253 cladding Methods 0.000 description 3
- 238000005245 sintering Methods 0.000 description 3
- 239000004071 soot Substances 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Light Guides In General And Applications Therefor (AREA)
- Optical Fibers, Optical Fiber Cores, And Optical Fiber Bundles (AREA)
Abstract
The invention discloses an optical fiber production rule making method based on a regression decision tree, which belongs to the technical field of machine learning and big data processing and specifically comprises the following steps: 101, collecting optical rod data and optical fiber data in the optical fiber production process and carrying out preprocessing operation on the optical rod data and the optical fiber data; 102, performing characteristic engineering construction operation on the optical wand data; 103, establishing a decision tree regression model; 104, optimizing the model through cross validation; 105 obtaining the fiber production rules from the paths split by the decision tree. The method is mainly characterized in that optical rod data and optical fiber data in the optical fiber production process are preprocessed, analyzed and characterized, a decision tree regression model is established, the model is optimized, and the optical fiber production rule is obtained through a split path of the decision tree.
Description
Technical Field
The invention belongs to the technical field of machine learning and big data processing, and particularly relates to an optical fiber production rule making method based on a regression decision tree.
Background
The optical fiber industry is an important support for national economy in China. In recent years, with the rapid development of communication and mobile internet, the domestic optical fiber demand is increasing, the production capacity and technical strength of the optical fiber industry are rapidly improved, and the optical fiber industry is developing towards industrial informatization, intellectualization and datamation. During the production of optical fibers, optical fiber production experts determine certain parameters of the predicted optical fiber according to the measured parameters of the optical rod, and these parameters directly affect the quality of the optical fiber. However, the judgment standards of each production expert are inconsistent, and the production volume becomes large, the manufacturing process has differences and other factors, so that the expert rules are difficult to solidify, and a set of finished production rule system is difficult to form. According to the optical fiber production rule making method based on the regression decision tree, based on the traditional optical fiber production process, redundant information in data can be effectively eliminated through data preprocessing operation, effective information in characteristics can be extracted through characteristic selection, the efficiency of an algorithm can be improved, and the accuracy of the algorithm can be improved. The invention adopts a machine learning method of the regression decision tree, continuously optimizes the regression decision tree model through a cross verification method, and obtains accurate optical fiber production rules according to the split paths of the decision tree.
Disclosure of Invention
The present invention is directed to solving the above problems of the prior art. The optical fiber production rule making method based on the regression decision tree is provided, wherein the rules in optical fiber production are accurately obtained and are solidified, and therefore the optical fiber production level is effectively improved. The technical scheme of the invention is as follows:
an optical fiber production rule making method based on a regression decision tree comprises the following steps:
101. collecting measurement data of an optical rod in the optical fiber production process to form an optical rod characteristic table, collecting the measurement data of the optical fiber to form an optical fiber table, and carrying out noise processing and missing value processing pre-operation on the optical rod characteristic data and the optical fiber data;
102.102. linking the optical wand characteristic data and the optical fiber data, and performing characteristic engineering operation on the optical wand characteristic data;
103. establishing a decision regression tree model; using optical rod characteristic data as the characteristic of the model, using certain label data of the optical fiber label data as the label of the model, establishing a regression decision tree model,
104. optimizing the regression decision tree model through parameter adjustment and cross validation, and selecting a model with a low average absolute error value in the model as a final model;
105. and obtaining a plurality of optical fiber production rules consisting of optical rod characteristics and optical fiber labels according to the split paths of the regression decision tree model.
Further, the step 101 collects the measurement data of the optical rod in the optical fiber production process to form an optical rod characteristic table, collects the measurement data of the optical fiber to form an optical fiber table, and performs a preprocessing operation on the optical rod data and the optical fiber data: according to the description of the optical rod feature table and the optical fiber table and the physical understanding, the following processing is carried out:
(1) the optical rod data and the optical fiber data have abnormal values, wherein the screening length of the small optical fiber discs is a negative value, the proportion value is greater than 1, and the data of the data are removed from the abnormal values;
(2) if some characteristic values are missing, the hot card filling method is used to search the most similar data value to the characteristic values for supplement.
Furthermore, the hot card filling method is that for a row of data containing an missing value, the hot card filling method finds the row of data with the highest cosine similarity in the complete data, and then fills the missing value with a value corresponding to the row of data.
Further, the step 102 performs a feature engineering construction operation on the optical wand data, specifically including: and filtering data of the small disc number and date field in the light bar data, and taking the rest data as the characteristics of the model.
Further, the step 103 of establishing a decision regression tree model specifically includes: and establishing a regression decision tree model by using the optical wand characteristic data as the characteristic of the model and using certain label data of the optical fiber label data as the label of the model.
Further, in the step 104, a ten-fold cross-validation method is adopted to validate the regression decision tree model, and the validation step includes: and (3) randomly dividing the data set into 10 parts, taking 9 parts as training data and 1 part as verification data in turn, and performing verification on the model. Each verification results in a corresponding average absolute error value. The average of the 10 mean absolute error values is used as the output of the model from which the model is validated and the model parameters adjusted.
Further, the step 105 obtains a plurality of optical fiber production rules composed of optical rod features and optical fiber labels according to the splitting paths of the regression decision tree model, and specifically includes: a regression decision tree includes a root node, a plurality of internal nodes, and a plurality of leaf nodes. The leaf nodes correspond to decision results, and each of the other nodes corresponds to an attribute test. The data set contained by each node is divided into sub-nodes according to the result of the attribute test. The split path from the root node to the leaf node corresponds to a decision path. According to the established regression decision tree model, each split path of the model is a rule for optical fiber production.
The invention has the following advantages and beneficial effects:
the invention combines the traditional optical fiber production and machine learning, big data and other technologies, has auxiliary effect on optical fiber production personnel to find new production rules and solidify old rules, further optimizes the optical fiber production process and improves the light production efficiency.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the present invention providing a regression decision tree based optical fiber production rule making method;
FIG. 2 is a graph showing a split view of a regression decision tree model in a method for formulating a regression decision tree based optical fiber production rules according to an embodiment of the present invention;
Detailed Description
The technical solutions in the embodiments of the present invention will be described in detail and clearly with reference to the accompanying drawings. The described embodiments are only some of the embodiments of the present invention.
The technical scheme for solving the technical problems is as follows:
referring to fig. 1, fig. 1 is a flowchart of a method for making an optical fiber production rule providing a regression decision tree according to an embodiment of the present invention, which specifically includes:
101. collecting data in the production process of the optical rod and the optical fiber and carrying out pretreatment operation on the production data: collecting the measurement data of the optical rod in the optical fiber production process to form an optical rod characteristic table, and collecting the measurement data of the optical fiber to form an optical fiber table.
The light bar feature list has the following specific features: date, core rod number, small disc number, measuring person, total fiber length, fiber _ step _ lens _ ratio, predicted Soot _ VAD deposition, actual Soot _ VAD deposition, cladding diameter up _ VAD deposition, cladding diameter in _ VAD deposition, cladding diameter down _ VAD deposition, deposition actual length _ VAD sintering, sintering Core rod length _ VAD sintering, length _ PK2600 Core rod, position _ PK2600 Core rod, deltaplus test value _ PK2600 Core rod, deltaMinus test value _ PK2600 Core rod Delta Total test value _ PK2600 Core rod, OD _ Core test value _ PK2600 Core rod, OD _ Clad test value _ PK2600 Core rod, coreLope test value _ PK2600 Core rod, D _ D test value _ PK2600 Core rod, non _ Core test value _ PK2600 Core rod, non _ Clad test value _ PK2600 Core rod, A _ esi test value _ PK2600 Core rod, index1 test value _ PK2600 Core rod, index2 test value _ PK2600 Core rod, actual effective length _ stretch, target diameter _ draw, target diameter _ Stroke stretching length _ stretching, diameter _ stretching at D1, diameter _ stretching at D2, diameter _ stretching at D3, diameter _ stretching at D4, diameter _ stretching at D5, length _ rough cutting after slitting, length _ rough cutting of original Core rod, length _ fine cutting before fine cutting, length _ fine cutting after fine cutting, maximum run-out value _ OVD run-out test, total length _ OVD finished product inspection, length _ OVD finished product inspection of false Core rod, effective length _ OVD finished product inspection, net weight _ OVD finished product inspection, effective length _ OVD test, net weight _ OVD test, and the like effective prestretching length _ OVD finished product inspection, charging weight _ OVD finished product inspection, charging prestretching length _ OVD finished product inspection, bottom _ B _ OVD finished product inspection, top _ A _ OVD finished product inspection, cut _ Off _ OVD finished product inspection, maximum diameter _ OVD finished product inspection, minimum diameter _ OVD finished product inspection, average diameter _ OVD finished product inspection, density _ density test, weight _ density test, deposition rate _ density test, soot diameter _ density test, and the like, effective length density test, weight error density test.
The measured data of the optical fiber are specifically: date, small disc number, small disc screening length, clamping dia, clamping cir, fiber dia, OCE, fiber cir, ECC, core out-of-roundness, primary coating dia, PCE, core dia, test length, att.1310 nm, 1310nmA end attenuation, 1310nmB end attenuation, att.1550 nm, 1550nmA end attenuation, 1550nmB end attenuation, 1310 end difference, 1550 end difference, 1310nm attenuation discontinuity, 1550nm attenuation discontinuity, 1310nm attenuation nonuniformity, 1550nm attenuation nonuniformity, att.1383 nm, att.1625 nm, 1310MFD, 1550MFD, λ c, 1383 spectral attenuation, 1625 spectral attenuation, and the maximum attenuation in the 1285-1330nm range is compared to 1310nm comparing the maximum attenuation in the 1525-1575nm range with 1550nm, 1310 spectral attenuation, 1550 spectral attenuation, 1460 spectral attenuation, 7.5mm turn-number 1 (1550 nm) of macrobend attenuation/bending radius, 7.5mm turn-number 1 (1625 nm) of macrobend attenuation/bending radius, 10mm turn-number 1 (1550 nm) of macrobend attenuation/bending radius, 10mm turn-number 1 (1625 nm) of macrobend attenuation/bending radius, 15mm turn-number 10 (1550 nm) of macrobend attenuation/bending radius, 15mm turn-number 10 (1625 nm) of macrobend attenuation/bending radius, curl, zero DML, slope Zero DML, 1285-9 nm Dispersion, 1271-1360nm Dispersion, dispersion 1550nm, dispersion 1625nm, 1530-1565nm Dispersion, 1565-1625nm Dispersion, PMD, optical Fiber grade, and optical Fiber grade
The data preprocessing comprises the processing of the optical rod characteristic data and the optical fiber data, and the following processing is carried out according to the description of two data tables and the physical understanding:
(1) because some abnormal values exist in the optical wand data and the optical fiber data, for example, the screening length of the small disc is negative, the fiber _ step _ lens _ ratio is larger than 1, and the like, the abnormal values are cleaned, namely, the data of the line is removed;
(2) because some characteristics in the optical wand data and the optical fiber data have a missing phenomenon, different processing is respectively carried out on the numerical characteristic and the enumeration characteristic, and if some numerical characteristics are missing, for example, a null value can appear in 1310MFD, the current median is used for supplementing; fiber level and other enumerated features are filled with enumerated values that are distinguished from existing enumerated values in the dataset, such as "unknown";
102. and (3) carrying out characteristic engineering construction operation on the light bar data: the invalid features in the wand data mean that the wand feature data and the fiber label data need to be connected together through certain fields in the wand feature table and the fiber label table, but the corresponding features of the fields are meaningless for the regression decision tree described below and need to be removed.
103. Establishing a decision tree regression model: the step of establishing the regression decision tree model is to establish the regression decision tree model by using optical rod feature data as features of the model and certain label data of optical fiber label data as labels of the model, and set the maximum depth of the tree to be 4.
104. And (3) optimizing the model through cross validation: and (4) sending a verification regression decision tree model by using ten-fold cross verification, and selecting the model with a low MAE value in the model as a final model.
105. Obtaining an optical fiber production rule according to a path split by a regression decision tree: according to the splitting path of the regression decision tree model, a plurality of optical fiber production rules consisting of optical rod characteristics and optical fiber labels can be obtained.
Referring to fig. 2, fig. 2 is a split view of a regression decision tree. When the rule condition before the fiber index cutoff wavelength (lambada c) and the optical rod characteristic is analyzed, a regression decision tree is used for establishing a model to form a plurality of split paths, and each path can be regarded as a production rule related to lambada c. For example, the rightmost split path, a production rule can be obtained as follows:
{ billing length _ OVD finished product inspection >1430and fiber _steplens ratio > -0.052 } = > λ c mean value 1238.1949/variance 644.409. In this way, a plurality of production rules for optical fibers can be obtained.
The above examples are to be construed as merely illustrative and not limitative of the remainder of the disclosure. After reading the description of the invention, the skilled person can make various changes or modifications to the invention, and these equivalent changes and modifications also fall into the scope of the invention defined by the claims.
Claims (1)
1. An optical fiber production rule making method based on a regression decision tree is characterized by comprising the following steps:
101. collecting measurement data of an optical rod in the optical fiber production process to form optical rod characteristic data, collecting the measurement data of the optical fiber to form optical fiber characteristic data, and carrying out noise processing and missing value processing pre-operation on the optical rod characteristic data and the optical fiber characteristic data;
102. linking the optical wand characteristic data and the optical fiber characteristic data, and performing characteristic engineering construction operation on the optical wand characteristic data;
103. establishing a decision regression tree model; establishing a regression decision tree model by using optical rod characteristic data as the characteristics of the model and using certain label data of the optical fiber characteristic data as the label of the model;
104. optimizing the regression decision tree model through parameter adjustment and cross validation, and selecting a model with a low average absolute error value in the model as a final model;
105. obtaining a plurality of optical fiber production rules consisting of optical rod characteristics and optical fiber labels according to the splitting path of the regression decision tree model;
step 101, collecting measurement data of an optical rod in an optical fiber production process to form optical rod characteristic data, collecting measurement data of an optical fiber to form optical fiber characteristic data, and performing preprocessing operation on the optical rod characteristic data and the optical fiber characteristic data: according to the description of the optical rod characteristic data and the optical fiber characteristic data and the physical understanding, the following processing is carried out:
abnormal values with the optical fiber small disc screening length being a negative value and the duty ratio being greater than 1 exist in the optical rod characteristic data and the optical fiber characteristic data, and the operation of removing the data of the abnormal values is carried out;
if the characteristic value is missing, searching the most similar data value to the characteristic value by using a hot card filling method for supplementing;
the hot card filling method is that for a row of data containing a missing value, the hot card filling method finds the row of data with the highest cosine similarity in the complete data, and then fills the missing value by using a value corresponding to the row of data;
the step 102 of performing feature engineering construction operation on the optical wand feature data specifically includes: filtering data of a small disc number and a date field in the light bar characteristic data, and taking the rest data as the characteristics of the model;
the step 103 of establishing a decision regression tree model specifically includes: establishing a regression decision tree model by using optical wand feature data as the features of the model and certain label data of the optical fiber label data as the labels of the model;
the step 104 is to adopt a ten-fold cross-validation method to validate the regression decision tree model, and the validation step comprises the following steps: randomly dividing the data set into 10 parts, taking 9 parts as training data and 1 part as verification data in turn, verifying the model, obtaining a corresponding average absolute error value in each verification, taking the average value of the 10 average absolute error values as the output of the model, and verifying the model and adjusting the parameters of the model through the output;
and 105, obtaining a plurality of optical fiber production rules composed of optical wand features and optical fiber labels according to the split path of the regression decision tree model, wherein the method specifically comprises the following steps: a regression decision tree comprises a root node, a plurality of internal nodes and a plurality of leaf nodes, wherein the leaf nodes correspond to decision results, other nodes correspond to attribute tests, a data set contained in each node is divided into sub-nodes according to the results of the attribute tests, a split path from the root node to the leaf node corresponds to a judgment path, and each split path of the model is a rule for optical fiber production according to an established regression decision tree model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542570.8A CN109559059B (en) | 2018-12-17 | 2018-12-17 | Regression decision tree-based optical fiber production rule making method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811542570.8A CN109559059B (en) | 2018-12-17 | 2018-12-17 | Regression decision tree-based optical fiber production rule making method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109559059A CN109559059A (en) | 2019-04-02 |
| CN109559059B true CN109559059B (en) | 2022-12-27 |
Family
ID=65870224
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811542570.8A Active CN109559059B (en) | 2018-12-17 | 2018-12-17 | Regression decision tree-based optical fiber production rule making method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109559059B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112053019B (en) * | 2019-06-06 | 2022-10-25 | 湖南师范大学 | Method for realizing intellectualization of optical fiber preform deposition process |
| CN117392467B (en) * | 2023-12-08 | 2024-02-13 | 南京烽火星空通信发展有限公司 | Light bar grade division method based on bar graph characteristics |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214213A (en) * | 2011-05-31 | 2011-10-12 | 中国科学院计算技术研究所 | Method and system for classifying data by adopting decision tree |
| CN104364664A (en) * | 2012-04-11 | 2015-02-18 | 爱德万测试公司 | An algorithm and structure for creation, definition, and execution of an SPC rule decision tree |
| CN107923898A (en) * | 2015-05-29 | 2018-04-17 | 欧金尼奥·曼维埃尔 | Nutrient-based food system and method |
| CN108072596A (en) * | 2016-11-11 | 2018-05-25 | 基德科技公司 | Detection based on high sensitivity optical fiber |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108932480B (en) * | 2018-06-08 | 2022-03-15 | 电子科技大学 | Distributed optical fiber sensing signal feature learning and classifying method based on 1D-CNN |
-
2018
- 2018-12-17 CN CN201811542570.8A patent/CN109559059B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102214213A (en) * | 2011-05-31 | 2011-10-12 | 中国科学院计算技术研究所 | Method and system for classifying data by adopting decision tree |
| CN104364664A (en) * | 2012-04-11 | 2015-02-18 | 爱德万测试公司 | An algorithm and structure for creation, definition, and execution of an SPC rule decision tree |
| CN107923898A (en) * | 2015-05-29 | 2018-04-17 | 欧金尼奥·曼维埃尔 | Nutrient-based food system and method |
| CN108072596A (en) * | 2016-11-11 | 2018-05-25 | 基德科技公司 | Detection based on high sensitivity optical fiber |
Non-Patent Citations (5)
| Title |
|---|
| A novel optical fiber doped with semiconductor nano-particles;Wang JIn等;《Chinese Journal of Lasers》;20081001;第35卷(第10期);第1528-31页，全文 * |
| Assessing Wireless Network Dependability through Knowledge Extraction via Decision Trees;G. Weckman等;《Third International Conference on Systems (icons 2008)》;20080425;第1-4页，全文 * |
| 传输技术在信息通信工程中的应用;邵帅;《数字技术与应用》;20160531(第5期);第27-29页，全文 * |
| 基于决策树算法的工业光纤网络通信故障检测系统;黄勇等;《现代电子技术》;20141015;第37卷(第20期);第134-136、140页，全文 * |
| 铸坯质量的多元统计分析及决策树规则研究;曹俊;《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅰ辑》;20090615(第6期);第B022-94页，全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109559059A (en) | 2019-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245802B (en) | Cigarette empty-head rate prediction method and system based on improved gradient lifting decision tree | |
| CN109559059B (en) | Regression decision tree-based optical fiber production rule making method | |
| CN106650807B (en) | A kind of concrete in marine environment strength deterioration prediction and evaluation method | |
| CN104750496B (en) | A kind of model changes disturbance degree automatic check method | |
| CN104756106A (en) | Characterizing data sources in a data storage system | |
| CN113590396B (en) | Defect diagnosis method and system for primary equipment, electronic equipment and storage medium | |
| CN113127339B (en) | Method for acquiring Github open source platform data and source code defect repair system | |
| CN105550189A (en) | Ontology-based intelligent retrieval system for information security event | |
| CN110555058A (en) | Power communication equipment state prediction method based on improved decision tree | |
| CN116881834B (en) | Stage load monitoring and early warning method based on stage deformation analysis | |
| CN112547807A (en) | Decision tree algorithm-based hot rolled strip quality accurate judgment method | |
| CN111639850A (en) | Quality evaluation method and system for multi-source heterogeneous data | |
| CN113259388A (en) | Network flow abnormity detection method, electronic equipment and readable storage medium | |
| CN107798137B (en) | A kind of multi-source heterogeneous data fusion architecture system based on additive models | |
| CN116306923A (en) | Evaluation weight calculation method based on knowledge graph | |
| CN115470994A (en) | Information popularity prediction method and system based on explicit time and cascade attention | |
| CN112527769B (en) | Automatic quality assurance framework for software change log generation method | |
| Nguyen et al. | Grammatical evolution to mine OWL disjointness axioms involving complex concept expressions | |
| CN109543712B (en) | Method for identifying entities on temporal data set | |
| Bo | Research on the classification of high dimensional imbalanced data based on the optimizational random forest algorithm | |
| CN108536796A (en) | A kind of isomery Ontology Matching method and system based on figure | |
| CN115641599A (en) | Entity alignment method for customhouse import and export commodity knowledge map | |
| CN110196912B (en) | Power grid archive parallel model construction method based on trust rule network | |
| CN117392467B (en) | Light bar grade division method based on bar graph characteristics | |
| Langer et al. | Fame. q-a formal approach to master quality in enterprise linked data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230828 Address after: 230000 B-1015, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui. Patentee after: HEFEI MINGLONG ELECTRONIC TECHNOLOGY Co.,Ltd. Address before: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee before: Dragon totem Technology (Hefei) Co.,Ltd. Effective date of registration: 20230828 Address after: 230000 floor 1, building 2, phase I, e-commerce Park, Jinggang Road, Shushan Economic Development Zone, Hefei City, Anhui Province Patentee after: Dragon totem Technology (Hefei) Co.,Ltd. Address before: 400065 Chongwen Road, Nanshan Street, Nanan District, Chongqing Patentee before: CHONGQING University OF POSTS AND TELECOMMUNICATIONS |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240617 Address after: 442000, No. 38 Shuidu Avenue, Danjiangkou City, Shiyan City, Hubei Province Patentee after: Huayuan (Danjiangkou City) Material Technology Co.,Ltd. Country or region after: China Address before: 230000 B-1015, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui. Patentee before: HEFEI MINGLONG ELECTRONIC TECHNOLOGY Co.,Ltd. Country or region before: China |
|
| TR01 | Transfer of patent right | ||
| CP03 | Change of name, title or address |
Address after: 442000, No. 38 Shuidu Avenue, Danjiangkou City, Shiyan City, Hubei Province Patentee after: Huayuan Electric (Hubei) Co.,Ltd. Country or region after: China Address before: 442000, No. 38 Shuidu Avenue, Danjiangkou City, Shiyan City, Hubei Province Patentee before: Huayuan (Danjiangkou City) Material Technology Co.,Ltd. Country or region before: China |
|
| CP03 | Change of name, title or address |