CN107944491A - Mass property symbolism maps control figure construction method - Google Patents
Mass property symbolism maps control figure construction method Download PDFInfo
- Publication number
- CN107944491A CN107944491A CN201711188848.1A CN201711188848A CN107944491A CN 107944491 A CN107944491 A CN 107944491A CN 201711188848 A CN201711188848 A CN 201711188848A CN 107944491 A CN107944491 A CN 107944491A
- Authority
- CN
- China
- Prior art keywords
- msubsup
- mass property
- influence factor
- symbolism
- sequence
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9038—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Factory Administration (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a kind of mass property symbolism to map control figure construction method；It includes building quality characteristic value symbolism sequence, builds mass property influence factor symbolism sequence and establishes mapping relations, structure mass property symbolism mapping control figure.The mass property symbolism mapping control figure of the present invention is by establishing the mapping relations of quality characteristic value and its influence factor, establish the mapping relations between quality characteristics data fluctuation pattern and the influence factor for causing fluctuation, on the one hand the fluctuation pattern of quality characteristics data can be reflected, on the other hand the source of trouble can be found in advance by mapping relations, so as to error caused by artificial subjective judgement, realize and the influence factor of mass property is predicted and adjusted, so that mass property is in effective stable state, achieve the purpose that prevention and control.
Description
Technical field
The invention belongs to quality diagnosis and prevention technique field, more particularly to a kind of mass property symbolism mapping control figure
Construction method.
Background technology
In terms of mathematical angle, the process of quality diagnosis and pre-control is actually the DUAL PROBLEMS OF VECTOR MAPPING of symptom space to failure
Source space, that is, realize that space X (symptom space) arrives the mapping F (mapping relations) of space Y (source of trouble).Mapping relations F is unknown
, the essence of quality diagnosis namely integrates various knowledge and method, finds out this mapping relations F, and then apply this relation.
Occur that during quality problems question classification can be rapidly found out afterwards, to control in real time；
The situation that traditional control figure can only be changed with time by quality characteristics data, whether to judge generating process
In stable state, but can not complete production process occur the diagnosis of unusual fluctuations with tracing to the source；Charts can only describe matter
The fluctuation pattern of flow characteristic data, can not describe fluctuation pattern and the incidence relation of fluctuation sources., can only in actual application
There is the source of trouble of unusual fluctuations and reason by the Heuristics and subjective judgement of engineers and technicians.
The content of the invention
The present invention goal of the invention be：In order to solve problem above existing in the prior art, the present invention proposes one kind
Mass property symbolism maps control figure construction method, and error caused by avoiding artificial subjective judgement, is realized to mass property shadow
The prediction of the factor of sound.
The technical scheme is that：A kind of mass property symbolism maps control figure construction method, comprises the following steps：
S1, by Xiu Hate stationary zones and up and down control exlosure domain be divided into multiple regions, to the subregion such as each
It is indicated using multi-component system symbol sebolic addressing, builds quality characteristic value symbolism sequence, it is single-stranded forms gene order；
S2, carry out pivot point to observation of the mass property influence factor in each time-domain under each sampling instant
Analysis, and the mapping relations of quality characteristic value and its influence factor are established, according to the quality characteristic value symbolism built in step S1
Sequence obtains mass property influence factor sequence, then each mass property influence factor is normalized, and builds quality
Influential factors symbolism sequence, it is single-stranded to form gene order；
S3, by quality characteristic value symbolism sequence and mass property influence factor symbolism sequence using associating double-stranded gene
Pattern is combined, structure mass property symbolism mapping control figure.
Further, the step S1 controls exlosure domain to be divided into multiple regions by Xiu Hate stationary zones and up and down,
The subregion such as each is indicated using multi-component system symbol sebolic addressing, builds quality characteristic value symbolism sequence, forms gene
Sequence ss, specifically include it is following step by step：
S11, by Xiu Hate stationary zones and up and down control exlosure domain, using center line μ lines as starting point, be divided into eight areas
Domain, be expressed as (- ∞, μ -3 σ), [μ -3 σ,μ- 2 σ], (μ -2 σ, μ-σ], (μ-σ, μ], (μ, μ+σ], (μ+σ, μ+2 σ], (σ of μ+2,
The σ of μ+3], (μ+3 σ ,+∞) }, wherein Xiu Hate stationary zones are ± 3 σ of μ；
The subregions such as eight in step S11, is respectively adopted the progress of eight tuple of symbol { D, C, B, A, a, b, c, d } by S12
Represent；
S13, by the quality characteristics data point of different sampling instant in each time-domain be expressed as symbol sebolic addressing QD={ xi}=
... ..., A, B, C, a, b, c, D, d ... ... }, quality characteristic value symbolism sequence is obtained, it is single-stranded to form gene order.
Further, the step S2 is to sight of the mass property influence factor under each sampling instant in each time-domain
Measured value carries out pivot analysis, and establishes the mapping relations of quality characteristic value and its influence factor, according to the matter built in step S1
Flow characteristic value symbolism sequence obtains mass property influence factor sequence, then each mass property influence factor is normalized
Processing, build mass property influence factor symbolism sequence, formed gene order it is single-stranded, specifically include it is following step by step：
S21, according to observation of the mass property influence factor under each sampling instant in each time-domain, extraction influences
Factor pivot information, { V is expressed as by mass property influence factor pivot sequence1,V2,V3,…VB, wherein mass property influences
Factor is expressed as [V1,V2,V3,…VN], observation is expressed as [x1,…,xN]；
S22, establish a quality characteristic value and its influence factor one mapping
A mapping is established to a quality characteristic value and its influence factor pivot againAccording to step
The quality characteristic value symbolism sequence built in rapid S1 obtains mass property influence factor sequence：
Obtain mass property influence factor pivot sequence：
S23, by different quality influential factors in influence divided rank caused at different moments, it is special to each quality
Property influence factor be normalized and the score value after normalized be divided into 10 grades [0-9], it is steady by setting
Determine state grade threshold value, be 0 by the mass property influence factor state representation that score value is in stability region, score value is in shakiness
The mass property influence factor state representation for determining region is 1, so that by mass property influence factor state space SNFIt is expressed as：
By mass property influence factor state space SKFIt is expressed as：
Mass property influence factor symbolism sequence is obtained, it is single-stranded to form gene order.
Further, the step S3 is by quality characteristic value symbolism sequence and mass property influence factor symbolism sequence
It is combined using association double-stranded gene pattern, structure mass property symbolism mapping control figure, is specially：According in step S2
The quality characteristic value of foundation and the mapping relations of its influence factor, by the gene order formed in step S1 it is single-stranded with step S2
The gene order of formation is single-stranded, uses association double-stranded gene mode combinations as double-stranded gene sequence, so as to obtain mass property symbol
Number change mapping control figure.
The beneficial effects of the invention are as follows：The mass property symbolism of the present invention maps control figure by establishing quality characteristic value
With the mapping relations of its influence factor, that is, establish between quality characteristics data fluctuation pattern and the influence factor for causing fluctuation
Mapping relations, on the one hand can reflect the fluctuation pattern of quality characteristics data, on the other hand can find event in advance by mapping relations
Barrier source, so that error caused by artificial subjective judgement, realizes and the influence factor of mass property is predicted and is adjusted so that matter
Flow characteristic is in effective stable state, achievees the purpose that prevention and control.
Brief description of the drawings
Fig. 1 is the mass property symbolism mapping control figure construction method flow diagram of the present invention.
Fig. 2 is the quality characteristic value symbolism sequence construct schematic diagram of the present invention.
Fig. 3 is the extraction of mass property influence factor pivot and the mapping structure fundamental construction schematic diagram of the present invention.
Fig. 4 is the mass property influence factor symbolism sequence construct schematic diagram of the present invention.
Fig. 5 is the mass property symbolism control figure structure schematic representation of the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, map control figure construction method flow diagram for the mass property symbolism of the present invention.One germplasm
Flow characteristic symbolism maps control figure construction method, comprises the following steps：
S1, by Xiu Hate stationary zones and up and down control exlosure domain be divided into multiple regions, to the subregion such as each
It is indicated using multi-component system symbol sebolic addressing, builds quality characteristic value symbolism sequence, it is single-stranded forms gene order；
S2, carry out pivot point to observation of the mass property influence factor in each time-domain under each sampling instant
Analysis, and the mapping relations of quality characteristic value and its influence factor are established, according to the quality characteristic value symbolism built in step S1
Sequence obtains mass property influence factor sequence, then each mass property influence factor is normalized, and builds quality
Influential factors symbolism sequence, it is single-stranded to form gene order；
S3, by quality characteristic value symbolism sequence and mass property influence factor symbolism sequence using associating double-stranded gene
Pattern is combined, structure mass property symbolism mapping control figure.
In step sl, process stabilization slave mode quality characteristics data point is concentrated on ± 3 σ areas of μ by Shewhart control chart
Domain, if 99.73% data point fall into this region if declarative procedure it is controlled.Judge effectively according to whether data point falls into one's respective area
The criterion of control is fuzzy, but control figure can pass through any change during the change reflection of data point position.Control
Whether trend, chain, cycle and break bounds that the position distribution situation of data point occurs in drawing etc., can go out in declarative procedure
It is now abnormal.
Xiu Hate stationary zones and upper and lower control exlosure domain are divided into multiple regions, the subregion such as each is used
Multi-component system symbol sebolic addressing is indicated, and builds quality characteristic value symbolism sequence, formation gene order is single-stranded, specifically includes following
Step by step：
S11, by Xiu Hate stationary zones and up and down control exlosure domain, using center line μ lines as starting point, be divided into eight areas
Domain, be expressed as (- ∞, μ -3 σ), [μ -3 σ, μ -2 σ], (μ -2 σ, μ-σ], (μ-σ, μ], (μ, μ+σ], (μ+σ, μ+2 σ], (σ of μ+2,
The σ of μ+3], (μ+3 σ ,+∞) }, wherein Xiu Hate stationary zones are ± 3 σ of μ, and μ is the mathematic expectaion of quality characteristic value, and σ is special for quality
The variance of property value；
The subregions such as eight in step S11, is respectively adopted the progress of eight tuple of symbol { D, C, B, A, a, b, c, d } by S12
Represent；
S12, by the quality characteristics data point of different sampling instant in each time-domain be expressed as symbol sebolic addressing QD={ xi}=
... ..., A, B, C, a, b, c, D, d ... ... }, quality characteristic value symbolism sequence is obtained, it is single-stranded to form gene order.
Symbol sebolic addressing QDReflect the change procedure of the quality characteristics data point of different sampling instants in each time-domain.Example
Such as, when it is continuous there is character string { ..., c, b, a, A, B, C ... } when, then it represents that there is ascendant trend exception；When there is character
Sequence ..., A, A, B, B, C, C ... } when, then it represents that generative center side ascendant trend is abnormal；When occur character string ..., C,
B, A, a, b, c ... } when, then it represents that downward trend is abnormal；When there is character string { ..., a, a, b, b, c, c ... }, then it represents that
The downward trend of generative center side is abnormal；When occurring { ..., D ... } or { ..., d ... } in character string, then it represents that break bounds is different
Often；When continuously there is character string
When being spaced the identical repeat character (RPT) sequence risen or fallen within a certain period of time, then it represents that cycle disease occur
Shape；When continuous 12 character strings { ..., A, a, A, a, A, a ... } that occur more than are when center line is concentrated, then it represents that tightly center is different
Often.
The character string changing features of the present invention can reflect the change in process of data.The character string of different local features
Illustrate the presence of different abnormal patterns, this is far longer than traditional eight big abnormal patterns features, can be conducive to pass through information
Identification technology extends actual more specifically abnormal patterns.Eight traditional big abnormal patterns only give basic anomalous discrimination
Criterion, anomaly regularity but more need artificial judgement.The present invention is special by character string based on traditional abnormal patterns
Rule and combination failure information are levied, more abnormal patterns storehouses can be improved and supplement with the information discriminating technology of character,
It is more advantageous to diagnosis and the pre-control of mass property.
As shown in Fig. 2, the quality characteristic value symbolism sequence construct schematic diagram for the present invention.Wherein, 1,2...I distinguishes table
Show time-domain, First ray is mass property value sequence, and it is single-stranded to carry out quality characteristic value sequence symbolization formation gene order.Turn
The mass property character string changed has contained known and unknown quality characteristics data abnormal patterns, with the evolution of mass property
Operation, the quality characteristics data character string gathered in whole time-domain form mass property mass data information bank.
In step s 2, the key element for influencing quality characteristics data fluctuation pattern is exactly the qualitative factor in manufacturing process, this
A little factors compositions mass property fluctuation sources information aggregate.The result of mass property variation and the form of expression of influencing factors of quality
Between there is certain regularity.If influencing factors of quality is similar in manufacturing process (the i.e. operating personnel of same levels, inspection
Personnel；The device systems of same type and economic accuracy；The workpiece of identical difficulty of processing；The processing method of identical economic accuracy and
The qualitative character value of same type；The detection method of same detection error；Similar processing environment etc.), then the quality after processing is special
Property data should also meet the regularity of distribution of same type.This has established data fluctuations to the base of key element state change mapping relations
Plinth.
The step S2 carries out observation of the mass property influence factor in each time-domain under each sampling instant
Pivot analysis, and the mapping relations of quality characteristic value and its influence factor are established, according to the quality characteristic value built in step S1
Symbolism sequence obtains mass property influence factor sequence, then each mass property influence factor is normalized, structure
Build mass property influence factor symbolism sequence, it is single-stranded to form gene order, specifically include it is following step by step：
S21, according to observation of the mass property influence factor under each sampling instant in each time-domain, extract pivot
Information, { V is expressed as by mass property influence factor pivot sequence1,V2,V3,…VB, wherein mass property influence factor represents
For [V1,V2,V3,…VN], observation is expressed as [x1,…,xN], VBFor the B mass property influence factor pivot, VNFor n-th
Mass property factor, xNFor the observed value of n-th influence factor；
S22, establish a quality characteristic value and its influence factor one mapping
Wherein XNFor n-th quality characteristic value,For XNCorresponding n-th influence factor；A quality characteristic value is influenced with it again
Factor pivot establishes a mappingWherein XKFor k-th mass property after extraction pivot
Value,For X after extraction pivotKCorresponding the B influence factor；According to the quality characteristic value symbolism sequence built in step S1
Row obtain mass property influence factor sequence：
Obtain mass property influence factor sequence：
S23, by different quality influential factors in influence divided rank caused at different moments, it is special to each quality
Property influence factor be normalized and the score value after normalized be divided into 10 grades [0-9], it is steady by setting
Determine state grade threshold value, be 0 by the mass property influence factor state representation that score value is in stability region, score value is in shakiness
The mass property influence factor state representation for determining region is 1, so that by mass property influence factor state space SNFIt is expressed as：
By mass property influence factor pivot state space SKFIt is expressed as：
Mass property influence factor symbolism sequence is obtained, it is single-stranded to form gene order.
As shown in figure 3, the extraction of mass property influence factor pivot and mapping structure fundamental construction schematic diagram for the present invention.
In step S23, since mass property factor is related to the several aspects of 5M1E, some factors are measurable, and what is had can not
Measurement, have plenty of qualitative description, have can quantitative description, so want its state change of Unify legislation, it is necessary to necessarily knows
Knowledge method Unify legislation and analysis.There is no comparativity between the quantitative value of different affecting factors, it is impossible to compare and analyze, because
This, the quantitative values of each factor are normalized, in this way, similitude is just provided between all dimensionless elements,
It can be further analyzed.Product quality characteristics level is different combined factors effects as a result, so to each factor
Different factors of influence is assigned, the size of factor of influence represents influence degree of the factor to product quality, combined factors effect
Result finally embodied in the form of product quality data.
By different quality influential factors in the influence divided rank at different moments or caused by the period, to each quality
Influential factors VN∈ [0,1] is normalized and the score value after normalized is divided into 10 grades [0-9],
By setting stable state grade threshold [α, β], the mass property influence factor state representation that score value is in stability region is
0, it is 1 by the mass property influence factor state representation that score value is in unstable region, so that by mass property influence factor shape
State space SNFIt is expressed as：
By mass property influence factor pivot state space SKFIt is expressed as：
Mass property influence factor symbolism sequence is obtained, it is single-stranded to form gene order.Stable state grade threshold [α, β]
Represent the maximum magnitude of stable state grade, the grade in stable state of the influence factor of different product different quality characteristic
Scope is different, can rule of thumb draw.
As shown in figure 4, the mass property influence factor symbolism sequence construct schematic diagram for the present invention.If influence factor
Pivot number is B, then the assembled state of influence factor pivot symbol sebolic addressing has 2B.The mass property influence factor character of conversion
Sequence has contained the mass property influence factor of stable state and unstable state normally and exception information.
In step s3, mass property character string of the invention has contained known and unknown mass property exception mould
Formula, and quality characteristics data character string is established according to control figure on a timeline and is reflected with influence factor information character sequence
Relation is penetrated, passes through the character sequence that the character string space comprising different pieces of information fluctuation pattern is combined with comprising different faults factor
The mapping relations of column space and time series between the two, three compositions as mass property symbolism mapping control figure
Component, the basic structure of mass property symbolism mapping control figure is built using association double-stranded gene pattern jointly.Quality is special
Include the character string of normal mode and abnormal patterns in two sequence spaces of property, mass property sequence space is predictive diagnosis
The basis of abnormal quality, the main spy that abnormal patterns character string representation quality characteristics fluctuation included in sequence space makes a variation
Sign.Data exception fluctuation is combined with failure factor in the mass property character confidence storehouse established with time shaft in sequence space
There are fixed correspondence.
As shown in figure 5, control figure structure schematic representation for the mass property symbolism of the present invention.The mass property symbol of the present invention
Number change control figure using production process quality characteristics data and fault message for analysis object, using statistical method and control figure to aid in
Crossover tool, using database as carrier, a large amount of quality characteristics datas for being produced using computer as instrument to quality control procedure
Stored, retrieved, identified, handled and analyzed, and gained knowledge with quality control and result is explained, accumulate so as to finally disclose
Quality characteristics data is hidden with having practicality, empirical mass property fluctuation pattern in fault message sequence.
Those of ordinary skill in the art will understand that the embodiments described herein, which is to help reader, understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such special statement and embodiment.This area
Those of ordinary skill these disclosed technical inspirations can make according to the present invention and various not depart from the other each of essence of the invention
The specific deformation of kind and combination, these deform and combine still within the scope of the present invention.
Claims (4)
1. a kind of mass property symbolism maps control figure construction method, it is characterised in that comprises the following steps：
S1, by Xiu Hate stationary zones and up and down control exlosure domain be divided into multiple regions, to each etc.s subregion use
Multi-component system symbol sebolic addressing is indicated, and builds quality characteristic value symbolism sequence, and it is single-stranded to form gene order；
S2, carry out pivot analysis to observation of the mass property influence factor in each time-domain under each sampling instant, and
The mapping relations of quality characteristic value and its influence factor are established, are obtained according to the quality characteristic value symbolism sequence built in step S1
It is normalized to mass property influence factor sequence, then to each mass property influence factor, builds mass property shadow
The factor of sound symbolism sequence, it is single-stranded to form gene order；
S3, by quality characteristic value symbolism sequence and mass property influence factor symbolism sequence using associating double-stranded gene pattern
It is combined, structure mass property symbolism mapping control figure.
2. mass property symbolism as claimed in claim 1 maps control figure construction method, it is characterised in that the step S1
Xiu Hate stationary zones and upper and lower control exlosure domain are divided into multiple regions, the subregion such as each is accorded with using multi-component system
Number sequence is indicated, and builds quality characteristic value symbolism sequence, and it is single-stranded to form gene order, specifically include it is following step by step：
S11, by Xiu Hate stationary zones and up and down control exlosure domain, using center line μ lines as starting point, be divided into eight regions,
Be expressed as (- ∞, μ -3 σ), [μ -3 σ, μ -2 σ], (μ -2 σ, μ-σ], (μ-σ, μ], (μ, μ+σ], (μ+σ, μ+2 σ], (μ+2 σ, μ+3
σ], (μ+3 σ ,+∞) }, wherein Xiu Hate stationary zones are ± 3 σ of μ；
S12, be respectively adopted eight tuple of symbol { D, C, B, A, a, b, c, d } by the subregions such as eight in step S11 and be indicated；
S13, by the quality characteristics data point of different sampling instant in each time-domain be expressed as symbol sebolic addressing QD={ xi}=
... ..., A, B, C, a, b, c, D, d ... ... }, quality characteristic value symbolism sequence is obtained, it is single-stranded to form gene order.
3. mass property symbolism as claimed in claim 2 maps control figure construction method, it is characterised in that the step S2
Pivot analysis is carried out to observation of the mass property influence factor in each time-domain under each sampling instant, and establishes quality
Characteristic value and the mapping relations of its influence factor, quality spy is obtained according to the quality characteristic value symbolism sequence built in step S1
Property influence factor sequence, then each mass property influence factor is normalized, structure mass property influence factor symbol
Number change sequence, formed gene order it is single-stranded, specifically include it is following step by step：
S21, according to observation of the mass property influence factor under each sampling instant in each time-domain, extract influence factor
Pivot information, { V is expressed as by mass property influence factor pivot sequence1,V2,V3,…VB, wherein mass property influence factor
It is expressed as [V1,V2,V3,…VN], observation is expressed as [x1,…,xN]；
S22, establish a quality characteristic value and its influence factor one mappingAgain to one
A quality characteristic value establishes a mapping with its influence factor pivotAccording in step S1
The quality characteristic value symbolism sequence of structure obtains mass property influence factor sequence：
<mrow>
<mo>{</mo>
<msub>
<mi>X</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>X</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>X</mi>
<mi>N</mi>
</msub>
<mo>}</mo>
<mo>&RightArrow;</mo>
<mo>{</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>N</mi>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>N</mi>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<mn>......</mn>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mi>N</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mi>N</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mi>N</mi>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>N</mi>
<mi>N</mi>
</msubsup>
<mo>}</mo>
</mrow>
Obtain mass property influence factor pivot sequence：
<mrow>
<mo>{</mo>
<msub>
<mi>X</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>X</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<mn>...</mn>
<mo>,</mo>
<msub>
<mi>X</mi>
<mi>K</mi>
</msub>
<mo>}</mo>
<mo>&RightArrow;</mo>
<mo>{</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>B</mi>
<mn>1</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>B</mi>
<mn>2</mn>
</msubsup>
<mo>,</mo>
<mn>......</mn>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mi>K</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mi>K</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mi>K</mi>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>B</mi>
<mi>K</mi>
</msubsup>
<mo>}</mo>
<mo>;</mo>
</mrow>
S23, by different quality influential factors in influence divided rank caused at different moments, to each mass property shadow
The factor of sound is normalized and the score value after normalized is divided into 10 grades [0-9], stablizes shape by setting
State grade threshold, is 0 by the mass property influence factor state representation that score value is in stability region, score value is in range of instability
The mass property influence factor state representation in domain is 1, so that by mass property influence factor state space SNFIt is expressed as：
<mrow>
<msup>
<mi>S</mi>
<mrow>
<mi>N</mi>
<mi>F</mi>
</mrow>
</msup>
<mo>&RightArrow;</mo>
<mo>{</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mi>N</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mi>N</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mi>N</mi>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>N</mi>
<mi>N</mi>
</msubsup>
<mo>}</mo>
<mo>&RightArrow;</mo>
<mo>{</mo>
<mn>...</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>...</mn>
<mo>}</mo>
</mrow>
By mass property influence factor pivot state space SKFIt is expressed as：
<mrow>
<msup>
<mi>S</mi>
<mrow>
<mi>K</mi>
<mi>F</mi>
</mrow>
</msup>
<mo>&RightArrow;</mo>
<mo>{</mo>
<msubsup>
<mi>V</mi>
<mn>1</mn>
<mi>K</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>2</mn>
<mi>K</mi>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>V</mi>
<mn>3</mn>
<mi>K</mi>
</msubsup>
<mo>,</mo>
<mn>...</mn>
<msubsup>
<mi>V</mi>
<mi>B</mi>
<mi>K</mi>
</msubsup>
<mo>}</mo>
<mo>&RightArrow;</mo>
<mo>{</mo>
<mn>...</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>1</mn>
<mo>,</mo>
<mn>0</mn>
<mo>,</mo>
<mn>...</mn>
<mo>}</mo>
</mrow>
Mass property influence factor symbolism sequence is obtained, it is single-stranded to form gene order.
4. mass property symbolism as claimed in claim 3 maps control figure construction method, it is characterised in that the step S3
Quality characteristic value symbolism sequence is associated into double-stranded gene pattern with the use of mass property influence factor symbolism sequence and carries out group
Close, structure mass property symbolism mapping control figure, is specially：According to the quality characteristic value established in step S2 with its influence because
The mapping relations of element, the gene order formed in the single-stranded S2 with step of the gene order formed in step S1 is single-stranded, using pass
It is double-stranded gene sequence to join double-stranded gene mode combinations, so as to obtain mass property symbolism mapping control figure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711188848.1A CN107944491B (en) | 2017-11-24 | 2017-11-24 | Quality characteristic symbolization mapping control chart construction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711188848.1A CN107944491B (en) | 2017-11-24 | 2017-11-24 | Quality characteristic symbolization mapping control chart construction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107944491A true CN107944491A (en) | 2018-04-20 |
| CN107944491B CN107944491B (en) | 2021-01-05 |
Family
ID=61949567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711188848.1A Expired - Fee Related CN107944491B (en) | 2017-11-24 | 2017-11-24 | Quality characteristic symbolization mapping control chart construction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944491B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6811706B1 (en) * | 1999-05-05 | 2004-11-02 | Eric J. Wahlberg | Activated sludge process optimization |
| JP2005275766A (en) * | 2004-03-24 | 2005-10-06 | Seiko Epson Corp | Management diagram data processor, management diagram data processing method and program |
| KR20150034482A (en) * | 2013-09-26 | 2015-04-03 | 성균관대학교산학협력단 | Controling method of very small fraction of nonconforming |
| CN105653871A (en) * | 2016-01-06 | 2016-06-08 | 电子科技大学 | Symbolic multi-quality-characteristic analysis method based on relative entropy and grey relational degree |
| CN105678078A (en) * | 2016-01-06 | 2016-06-15 | 电子科技大学 | Symbolized quality characteristic grey prediction method of complicated electromechanical system |
| CN107122609A (en) * | 2017-04-28 | 2017-09-01 | 电子科技大学 | A kind of electromechanical product quality evaluation method based on mass property gene theory |
| CN107122907A (en) * | 2017-04-28 | 2017-09-01 | 电子科技大学 | A kind of analysis of electronic product symbolism mass property and failure cause retroactive method |
-
2017
- 2017-11-24 CN CN201711188848.1A patent/CN107944491B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6811706B1 (en) * | 1999-05-05 | 2004-11-02 | Eric J. Wahlberg | Activated sludge process optimization |
| JP2005275766A (en) * | 2004-03-24 | 2005-10-06 | Seiko Epson Corp | Management diagram data processor, management diagram data processing method and program |
| KR20150034482A (en) * | 2013-09-26 | 2015-04-03 | 성균관대학교산학협력단 | Controling method of very small fraction of nonconforming |
| CN105653871A (en) * | 2016-01-06 | 2016-06-08 | 电子科技大学 | Symbolic multi-quality-characteristic analysis method based on relative entropy and grey relational degree |
| CN105678078A (en) * | 2016-01-06 | 2016-06-15 | 电子科技大学 | Symbolized quality characteristic grey prediction method of complicated electromechanical system |
| CN107122609A (en) * | 2017-04-28 | 2017-09-01 | 电子科技大学 | A kind of electromechanical product quality evaluation method based on mass property gene theory |
| CN107122907A (en) * | 2017-04-28 | 2017-09-01 | 电子科技大学 | A kind of analysis of electronic product symbolism mass property and failure cause retroactive method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107944491B (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101903895B (en) | Method and apparatus for generating chemical toxicity prediction model | |
| JP4394728B2 (en) | Influence factor identification device | |
| CN107065842A (en) | A kind of fault detection method based on particle group optimizing core independent component analysis model | |
| Sallehuddin et al. | Application of grey relational analysis for multivariate time series | |
| Guh | Robustness of the neural network based control chart pattern recognition system to non‐normality | |
| CN107403196B (en) | Method for predicting concentration of butane at bottom of debutanizer by instant learning modeling based on spectral clustering analysis | |
| Yélamos et al. | Simultaneous fault diagnosis in chemical plants using a multilabel approach | |
| CN102663422B (en) | Floor layer classification method based on color characteristic | |
| CN103488874A (en) | Improved support vector machine-LIBS (laser-induced breakdown spectroscopy) combined sorting method for steel materials | |
| CN104106089A (en) | Social network analysis for use in a business | |
| JP2019101644A (en) | Data analysis system and data analysis device | |
| CN109409425A (en) | A kind of fault type recognition method based on neighbour's constituent analysis | |
| CN104915679A (en) | Large-scale high-dimensional data classification method based on random forest weighted distance | |
| CN110927478B (en) | Method and system for determining state of transformer equipment of power system | |
| Yu et al. | A framework to identify and respond to weak signals of disastrous process incidents based on FRAM and machine learning techniques | |
| CN107944491A (en) | Mass property symbolism maps control figure construction method | |
| CN110057588B (en) | Bearing early fault detection and diagnosis method and system based on fusion of singular value and graph theory characteristics | |
| Zhong et al. | SOM-based visualization monitoring and fault diagnosis for chemical process | |
| CN106485049A (en) | A kind of detection method of the NIRS exceptional sample based on Monte Carlo cross validation | |
| CN112183569A (en) | FDA and SOM based intermittent industrial process reaction phase clustering and fault classification visualization | |
| CN109389313A (en) | A kind of failure modes diagnostic method based on weighting neighbour's decision | |
| JPH09325890A (en) | Method and device for detecting pattern | |
| US20210117861A1 (en) | Machine learning variable selection and root cause discovery by cumulative prediction | |
| CN108053093A (en) | A kind of k- neighbour's method for diagnosing faults based on the conversion of average influence Value Data | |
| US6768972B1 (en) | Method and device for reducing a number of measured values of a technical system |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210105 Termination date: 20211124 |