CN111882188A - Process quality homogeneity level evaluation method and system based on Birch clustering algorithm - Google Patents
Process quality homogeneity level evaluation method and system based on Birch clustering algorithm Download PDFInfo
- Publication number
- CN111882188A CN111882188A CN202010682828.5A CN202010682828A CN111882188A CN 111882188 A CN111882188 A CN 111882188A CN 202010682828 A CN202010682828 A CN 202010682828A CN 111882188 A CN111882188 A CN 111882188A
- Authority
- CN
- China
- Prior art keywords
- data
- parameter
- steady
- state
- clustering algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 103
- 230000008569 process Effects 0.000 title claims abstract description 66
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 34
- 235000018185 Betula X alpestris Nutrition 0.000 title claims abstract description 32
- 235000018212 Betula X uliginosa Nutrition 0.000 title claims abstract description 32
- 238000011156 evaluation Methods 0.000 title claims description 32
- 238000004519 manufacturing process Methods 0.000 claims abstract description 34
- 241000208125 Nicotiana Species 0.000 claims abstract description 21
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000013210 evaluation model Methods 0.000 claims abstract description 18
- 238000012512 characterization method Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 238000011160 research Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 238000004148 unit process Methods 0.000 claims abstract description 4
- 239000000463 material Substances 0.000 claims description 28
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000004886 process control Methods 0.000 claims description 10
- 235000019504 cigarettes Nutrition 0.000 claims description 9
- 239000006185 dispersion Substances 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000009897 systematic effect Effects 0.000 claims description 4
- 238000013064 process characterization Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000004540 process dynamic Methods 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000010923 batch production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001960 triggered effect Effects 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Manufacturing & Machinery (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Fuzzy Systems (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- General Factory Administration (AREA)
Abstract
The invention relates to a method and a system for evaluating the process quality homogeneity level based on a Birch clustering algorithm, wherein the method comprises the following steps: collecting cut tobacco leaf making key parameter data; extracting historical batch data of the production process; preprocessing data, namely solving a characteristic value of the dimension of the batch by using a Birch clustering algorithm and a Kmeans algorithm; determining dynamic quality stability characterization of steady-state and non-steady-state processes; gradually constructing a quality stability evaluation model from a minimum research unit-process parameter scale, a process scale and a batch scale, and providing an effective method for analyzing and evaluating the quality of the wire-making processing from different scales; the clustered data set records characteristic parameters and time labels of the data, normal data sets and outlier data sets are distinguished according to the characteristic parameters of the data sets and are treated in a targeted and different mode, and abnormal time intervals of the data are traced according to the time labels of the data, so that a prerequisite is provided for batch quality abnormal tracing and intelligent equipment maintenance.
Description
Technical Field
The invention relates to an evaluation technology in the aspect of a tobacco shred making process, in particular to a method and a system for evaluating multi-scale correlation of the tobacco shred making process based on a Birch clustering algorithm.
Background
The cigarette process specification emphasizes the process control from control index to control parameter, and highlights the important role of process control in cigarette production. The inventor finds that the existing control and evaluation method for the cigarette production process mainly has the process capability index Cpk and sigma level, but the method has certain limitations (1) the evaluation covers incomplete production process objects, the existing control and evaluation only focuses on the steady-state processing process, and the unstable-state production process which obviously influences the processing quality of the working procedure such as the stub bar, the tail and the serious material breakage does not focus on the steady-state processing process; (2) the conventional evaluation method has certain limitations, and the statistical calculation of the conventional evaluation method is based on the assumption that data accords with normal distribution no matter the characteristics of Cpk, Sigma level and the like, however, the data in the cigarette production process cannot completely meet the normal distribution.
Disclosure of Invention
The invention aims to solve the problems and provides a method and a device for evaluating the multi-scale correlation of a tobacco shred making process based on a Birch clustering algorithm.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the invention provides a tobacco shred making process multi-scale correlation evaluation method based on a Birch clustering algorithm, which comprises the following steps:
1) collecting the key parameter data of the tobacco shred preparation. Combining the analysis of the characteristics of the cigarette products and the leaf shred process, respectively collecting the equipment state parameters and the process control parameters which influence and reflect the product quality from the production database according to the parameter types
2) And extracting historical production data. From the historical data, N lot process data of a certain grade are selected. The relevant data included in the evaluation parameter set is extracted. The extracted batch data is divided into steady-state data and unsteady-state data (including the conditions of a material head, a material tail, material breakage, material blockage and the like).
3) And (4) preprocessing data. Processing the extracted steady-state data of multiple batches respectively, and counting the count C of the data points of the parameter set P in each stepjAnd mean value M of the corresponding datajWith CjAs a parameter in the time dimension, multiplied by the mean value MjAnd the parameter is used as a parameter in the model matrix, and then the production data matrix corresponding to N batches is obtained.
4) And (3) solving the characteristic value of the dimension of the batch by adopting a Birch clustering algorithm and Kmeans, establishing a clustering characteristic tree by scanning a data set by the Birch method, clustering leaf nodes of the clustering characteristic tree, and correcting the clustered data by means of the Kmeans algorithm.
5) Determining dynamic quality stability characterization of steady-state and non-steady-state processes. This part contains two research works.
Firstly, characterization of dynamic quality stability in steady-state process
And establishing a parameter steady-state process characterization parameter with higher syntropy comprehensive sensitivity to the variation of the deviation degree and the dispersion degree.
② characterization of dynamic quality stability in unsteady state process
And determining the time domain of the unsteady processing process according to the change characteristics of each parameter in the unsteady process. And defining the sum of the base value of the material head period and the base value of the material tail time as the unqualified time T of the parameter unstable process. And (5) establishing a dynamic evaluation model of the parameter unsteady state process. And (5) establishing a parameter unsteady state process comprehensive evaluation model.
6) Gradually constructing a quality stability evaluation model from a minimum research unit-process parameter scale to a process scale and then to a batch scale, and providing a systematic and effective method for analyzing and evaluating the quality of the wire-making processing from different scales;
parameter control level
Steady state objective variable model: the target variable requires control of a central value and a standard deviation, namely, the deviation and the dispersion are required; unsteady extreme variable model: the extreme value control variable is expected to be large and small.
Processing level of working procedure
All variables in the process are parallel, and a quantitative process control index model is constructed by adopting an arithmetic weighting method
Third, batch comprehensive evaluation model
All processes before and after the batch are mutually influenced, and a quantitative batch comprehensive control index model is constructed by adopting a geometric weighting method.
7) The clustered data set records characteristic parameters and time labels of the data, normal data sets and outlier data sets can be distinguished according to the characteristic parameters of the data sets and can be treated in a targeted and differentiated mode, and abnormal time intervals of the data are traced according to the time labels of the data, so that convenience is brought to subsequent abnormal reason analysis.
In a second aspect, the invention further provides a server, which comprises a memory, a processor and a Birch clustering algorithm-based multi-scale correlation evaluation program stored on the memory and operable on the processor, wherein the evaluation program is configured to implement the steps of the foregoing evaluation method.
In a third aspect, the invention further provides a storage medium, wherein the storage medium is stored with a tobacco shred manufacturing process multi-scale correlation evaluation program based on the Birch clustering algorithm, and the tobacco shred manufacturing process multi-scale correlation evaluation program based on the Birch clustering algorithm realizes the steps of the evaluation method when being executed by a processor.
The invention has the following beneficial effects:
by adopting the technical scheme, the production data are collected, the key parameters are selected, the data are preprocessed, the process evaluation is carried out on the basis of a parameter-process-batch multi-scale evaluation model, the characteristic parameters and the time labels of the data are recorded in the clustered data group, the abnormal time period of the data is traced according to the time labels of the data, and convenience is brought to the subsequent abnormal reason analysis. Practice proves that key factors influencing the quality level of silk production are found by using data clustering and layering, a basis is provided for timely finding and tracing the problems needing attention in the production process, objective data support based on quality evaluation is provided for preventive maintenance, and a diagnosis basis for intelligent maintenance of equipment is provided. A systematic and effective method is provided for analyzing and evaluating the quality of the wire-making processing from different scales by gradually constructing a quality stability evaluation model of parameters, processes, batches and multiple scales.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and/or "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
as introduced in the background art, the control and evaluation method of the cigarette production process in the prior art mainly has the process capability index Cpk and sigma level, but the method has certain limitations (1) the evaluation covers incomplete production process objects, the control and evaluation only focuses on the steady-state processing process at present, and does not focus on the unsteady-state production process which obviously affects the processing quality of the working procedure, such as the stub bar, the material tail, the serious material breakage and the like; (2) the conventional evaluation method has certain limitations, and no matter the characteristics such as Cpk and sigma levels are represented, the statistical calculation is based on the assumption that data accords with normal distribution, however, the data in the cigarette production process cannot completely meet the normal distribution, and in order to solve the technical problems, the application provides a multi-scale correlation evaluation method for the tobacco shred manufacturing process based on the Birch clustering algorithm.
The Birch algorithm is a very effective and traditional hierarchical clustering algorithm and is one of the commonly used methods for big data analysis. Birch is based on hierarchical clustering of distances, a hierarchical clustering and iterative relocation method is integrated, a bottom-up hierarchical algorithm is used, iterative relocation is used for improving results, each object is used as an atomic cluster, and then the atomic clusters are combined according to the distances to form a larger cluster class.
The invention realizes the analysis research on the basis of the full data based on the big data thought, develops the dynamic quality evaluation method and the application research of the key working procedures and the key parameters of the cut tobacco aiming at the production process under the batch production mode, constructs the multi-scale analysis technology of the on-line quality stability evaluation of the cut tobacco making process of the key parameters, the working procedures and the batches on the basis of researching the quality stability characterization method of the steady-state data and the unsteady-state data of the production process of each key parameter batch, can better solve the limitations of SPC and sigma levels, realizes the evaluation and the guidance of the evaluation model in the production process, and specifically comprises the following steps:
as shown in fig. 1, a method for evaluating the multi-scale correlation of a tobacco shred making process based on a Birch clustering algorithm comprises the following steps:
1) collecting the key parameter data of the tobacco shred preparation. According to the technical standard of Chinese tobaccos, the analysis of the characteristics of cigarette products and the cut tobacco process is combined, and the technological ideas of quantitative analysis, statistical analysis and overall analysis are used as guidance to select parameters which influence and reflect the product quality from equipment state parameters and process control parameters respectively according to the parameter types. For example, in blade charging, equipment state parameters such as drum rotation speed, moisture discharge opening degree, charging pump motor frequency and motor current are selected, process parameters such as outlet moisture, outlet temperature, hot air temperature, material flow and charging flow are selected as evaluation parameters, and an evaluation parameter set P is formed as [ P1, P2, P3 … and Pq ].
2) And extracting historical production data. From the historical data, N lot process data of a certain grade are selected. The relevant data included in the evaluation parameter set is extracted. The extracted batch data is divided into steady-state data and unsteady-state data (including the conditions of a material head, a material tail, material breakage, material blockage and the like), and the steady-state data is triggered and collected to process parameters through a batch control signal and an electronic scale occupation signal. The data of the production process are collected in time after the material is put in, and meanwhile, the data of the equipment in idle running states such as a preheating stage, a shutdown material breaking stage and the like are automatically removed; for unsteady data, the data is extracted according to the following rules: the statistical rule of the stub bar time of low-moisture materials (less than or equal to 15 percent) is as follows: the timing was started with the outlet moisture meter reaching 8% and ended with the first data reaching the lower standard limit. Material tail time statistical rule: the timing is started with the first data that the outlet moisture meter is below the lower standard limit, and the timing is ended with the first data that is below 8%. ② high-moisture material (> 15% and less than or equal to 23%), material head time statistical rule: the timing was started with the outlet moisture meter reaching 12% and ended with the first data reaching the lower standard limit. Material tail time statistical rule: the timing is started with the first data that the outlet moisture meter is below the lower standard limit, and the timing is ended with the first data that is below 12%.
3) And (4) preprocessing data. Respectively processing the extracted steady-state data of a plurality of batches, and counting the count C of the data points of the parameter set P in each step according to the fact that the cumulative quantity of every five hundred kilograms is one stepjAnd mean value M of the corresponding datajWith CjAs a time dimensionParameter, multiplied by mean MjAnd the parameter is used as a parameter in the model matrix, and then the production data matrix corresponding to N batches is obtained.
4) And (3) solving the characteristic value of the dimension of the batch by adopting a Birch clustering algorithm and a Kmeans algorithm, establishing a clustering characteristic tree by scanning a data set by the Birch method, and then clustering the leaf nodes of the clustering characteristic tree. Its core is the cluster feature CF and the cluster feature tree. CF refers to the triplet CF ═ (N, LS, SS), where: n represents the number of data points in the cluster; LS represents the linear combination of each dimension of the N data points; SS represents the sum of the squares of the dimensions of the N data points. The CF summarizes the basic information of the cluster and is highly compressed, storing cluster information that is smaller than the actual data points. Meanwhile, the ternary structure arrangement of the CF makes it very easy to calculate the radius of the cluster, the diameter of the cluster and the distance between the clusters.
5) determining dynamic quality stability characterization of steady-state and non-steady-state processes. This part contains two research works.
Firstly, characterization of dynamic quality stability in steady-state process
And establishing a parameter steady-state process characterization parameter with higher syntropy comprehensive sensitivity to the variation of the deviation degree and the dispersion degree. The deviation is denoted by Z, the dispersion is denoted by ρ, and the parametric steady-state process quality index QI steady-state ═ f (Z, ρ).
② characterization of dynamic quality stability in unsteady state process
And determining the time domain of the unsteady processing process according to the change characteristics of each parameter in the unsteady process. Under the condition that the time domain is normal production (except abnormalities such as stub bars, no broken materials and the like), the stub bar period basic value Th and the stub bar time basic value Tt can be determined according to the running conditions of a plurality of normal batches; and defining the sum of the base value of the material head period and the base value of the material tail time as the unqualified time T of the parameter unstable process. And (5) establishing a dynamic evaluation model of the parameter unsteady state process. The method comprises the establishment of a dynamic quality state evaluation model in the period of a material head, the period of a material tail and other abnormal conditions. And (5) establishing a parameter unsteady state process comprehensive evaluation model. Tout is used for characterizing the actual time of the unsteady process, and a characterization parameter quality stability parameter QI unsteady state f (Tout, T unsteady state) is established in the time domain.
6) And (3) gradually constructing a quality stability evaluation model from a minimum research unit-process parameter scale, a process scale and a batch scale, and providing a systematic and effective method for analyzing and evaluating the silk-making processing quality from different scales.
Parameter control level
Steady state objective variable model: the objective variables require control center values and standard deviations, i.e., both deviation and dispersion, and the evaluation model should be a function of Z, P and be negatively correlated with Z, P. The control index Ic can be calculated by the formula (1), the value range is [0, 100], and the boundary value is taken after the overrun.
In the formula: ic-index variable control index
Unsteady extreme variable model: the extreme value control variable is expected to be large (not less than xpv) and small (not more than xpv), the control index Id can be calculated according to the following formula (2), the value range is [0, 100], and a boundary value is taken after the limit is exceeded.
In the formula:
id-extreme variable control index
Processing level of working procedure
All variables in the process are parallel, a quantitative process control index model is constructed by adopting an arithmetic weighting method, the value range is [0, 100], and a boundary value is taken after the process control index model is overrun as shown in a formula (3).
In the formula:
g, a process control index;
ii is the management and control index of the ith variable;
wi-the weight of the ith variable.
Third, batch comprehensive evaluation model
The front and rear working procedures in the batch are mutually influenced, a quantitative batch comprehensive control index model is constructed by adopting a geometric weighting method, as shown in the following formula (4), the value range is [0, 100], and a boundary value is obtained after the limit is exceeded.
In the formula: b, comprehensively managing and controlling indexes of batches;
gi is the management and control index of the ith procedure;
di-the weight of the ith process.
7) The clustered data set records characteristic parameters and time labels of the data, normal data sets and outlier data sets can be distinguished according to the characteristic parameters of the data sets and can be treated in a targeted and differentiated mode, and abnormal time intervals of the data are traced according to the time labels of the data, so that convenience is brought to subsequent abnormal reason analysis.
The embodiment also provides a server, which comprises a memory, a processor and a multi-scale correlation evaluation program based on a Birch clustering algorithm, wherein the multi-scale correlation evaluation program is stored in the memory and can run on the processor, and the evaluation program is configured to realize the steps of the previous evaluation method.
The embodiment also provides a storage medium, wherein the storage medium is stored with a tobacco shred manufacturing process multi-scale correlation evaluation program based on the Birch clustering algorithm, and the tobacco shred manufacturing process multi-scale correlation evaluation program based on the Birch clustering algorithm realizes the steps of the evaluation method when being executed by a processor.
The server may include a processor, such as a central processing unit, a communication bus, a user interface, a network interface, and a memory. Wherein the communication bus is used for realizing connection communication among the components. The user interface may include a display screen, an input module such as a keyboard, and the optional user interface may also include a standard wired interface, a wireless interface. The network interface may optionally include standard wired, wireless interfaces. The memory may be a high speed random access memory or may be a stable non-volatile memory such as a disk memory. The memory may alternatively be a storage device separate from the aforementioned processor.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (8)
1. A method for evaluating the process quality homogeneity level based on a Birch clustering algorithm is characterized by comprising the following steps:
1) collecting cut tobacco leaf making key parameter data;
2) extracting historical production data; extracting related data included in the evaluation parameter set from historical data, wherein the extracted batch data is divided into steady-state data and non-steady-state data;
3) preprocessing data to obtain production data matrixes corresponding to N batches;
4) obtaining the characteristic value of the dimension of the batch by adopting a Birch clustering algorithm and Kmeans, establishing a clustering characteristic tree by scanning a data set by the Birch method, clustering leaf nodes of the clustering characteristic tree, and correcting the clustered data by means of the Kmeans algorithm;
5) determining dynamic quality stability characterization of steady-state and non-steady-state processes;
6) gradually constructing a quality stability evaluation model from a minimum research unit-process parameter scale to a process scale and then to a batch scale, and providing a systematic and effective method for analyzing and evaluating the quality of the wire-making processing from different scales;
7) the clustered data set records characteristic parameters and time labels of the data, normal data sets and outlier data sets are distinguished according to the characteristic parameters of the data sets and are treated in a targeted and differentiated mode, and then abnormal time intervals of the data are traced according to the time labels of the data, so that convenience is brought to subsequent abnormal reason analysis.
2. The Birch clustering algorithm-based process quality homogeneity level evaluation method according to claim 1, characterized in that in step 1) in connection with the analysis of the cigarette product characteristics and the cut tobacco process, equipment status parameters and process control parameters affecting and reflecting the product quality are collected from the production database according to the parameter categories, respectively.
3. The method for evaluating the homogeneity level of process quality based on the Birch clustering algorithm as claimed in claim 1, wherein the characterization of the dynamic quality stability of the steady-state process in the step 5) is to establish a parametric steady-state process characterization parameter with higher syntropy comprehensive sensitivity to the variation of the deviation degree and the dispersion degree.
4. The Birch clustering algorithm-based process quality homogeneity level evaluation method according to claim 1, the data preprocessing method in step 3): processing the extracted steady-state data of multiple batches respectively, and counting the count C of the data points of the parameter set P in each stepjAnd mean value M of the corresponding datajWith CjAs a parameter in the time dimension, multiplied by the mean value MjAnd the parameter is used as a parameter in the model matrix, and then the production data matrix corresponding to N batches is obtained.
5. The Birch clustering algorithm-based process quality homogeneity level evaluation method according to claim 1, wherein the dynamic quality stability characterization of the non-steady-state process in the step 5) is to determine a time domain of the non-steady-state processing process according to the variation characteristics of each parameter in the non-steady-state process; and defining the sum of the base value of the material head period and the base value of the material tail time as the unqualified time T of the parameter unstable process. Establishing a parameter unsteady state process dynamic evaluation model; and (5) establishing a parameter unsteady state process comprehensive evaluation model.
6. The Birch clustering algorithm-based process quality homogeneity level evaluation method according to claim 1, wherein the step 6) comprises:
parameter control level
Steady state objective variable model: the target variable requires control of a central value and a standard deviation, namely, the deviation and the dispersion are required; unsteady extreme variable model: the extreme value control variable is expected to be large and small.
Processing level of working procedure
All variables in the process are parallel, and a quantitative process control index model is constructed by adopting an arithmetic weighting method
Third, batch comprehensive evaluation model
All processes before and after the batch are mutually influenced, and a quantitative batch comprehensive control index model is constructed by adopting a geometric weighting method.
7. A server, characterized in that the server comprises a memory, a processor and a multi-scale correlation evaluation program based on a Birch clustering algorithm stored on the memory and operable on the processor, the evaluation program being configured to implement the steps of the evaluation method according to any one of claims 1 to 6.
8. A storage medium, wherein a Birch clustering algorithm-based multi-scale correlation evaluation program of a tobacco shred manufacturing process is stored on the storage medium, and when the Birch clustering algorithm-based multi-scale correlation evaluation program of the tobacco shred manufacturing process is executed by a processor, the steps of the evaluation method according to any one of claims 1 to 6 are realized.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010682828.5A CN111882188A (en) | 2020-07-15 | 2020-07-15 | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010682828.5A CN111882188A (en) | 2020-07-15 | 2020-07-15 | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111882188A true CN111882188A (en) | 2020-11-03 |
Family
ID=73154501
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010682828.5A Pending CN111882188A (en) | 2020-07-15 | 2020-07-15 | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111882188A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113256102A (en) * | 2021-05-20 | 2021-08-13 | 中国安全生产科学研究院 | High-risk technological process risk control method and system |
CN113361661A (en) * | 2021-07-20 | 2021-09-07 | 红云红河烟草(集团)有限责任公司 | Modeling method and device for data cooperation capability evaluation |
CN113379278A (en) * | 2021-06-23 | 2021-09-10 | 红云红河烟草(集团)有限责任公司 | Method for evaluating quality of whole process of silk making batch |
CN113592314A (en) * | 2021-08-02 | 2021-11-02 | 红云红河烟草(集团)有限责任公司 | Silk making process quality evaluation method based on sigma level |
CN115669990A (en) * | 2022-11-23 | 2023-02-03 | 湖北中烟工业有限责任公司 | Intelligent electricity-saving method and device for tobacco shred production line |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103324089A (en) * | 2012-03-24 | 2013-09-25 | 厦门烟草工业有限责任公司 | Thread making technological parameter dynamic quality stability characterization method |
CN105707974A (en) * | 2015-12-30 | 2016-06-29 | 河南中烟工业有限责任公司 | Cigarette production process stability monitoring method |
CN106485422A (en) * | 2016-10-19 | 2017-03-08 | 河南中烟工业有限责任公司 | A kind of Cigarette quality stability of rolled evaluation methodology |
US20180189664A1 (en) * | 2015-06-26 | 2018-07-05 | National University Of Ireland, Galway | Data analysis and event detection method and system |
CN110866670A (en) * | 2019-04-29 | 2020-03-06 | 红云红河烟草(集团)有限责任公司 | Method and system for identifying stub bar and tail in cigarette production and manufacturing process |
CN111103854A (en) * | 2019-12-10 | 2020-05-05 | 云南昆船设计研究院有限公司 | System and method for improving production stability of tobacco cut-tobacco drier |
-
2020
- 2020-07-15 CN CN202010682828.5A patent/CN111882188A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103324089A (en) * | 2012-03-24 | 2013-09-25 | 厦门烟草工业有限责任公司 | Thread making technological parameter dynamic quality stability characterization method |
US20180189664A1 (en) * | 2015-06-26 | 2018-07-05 | National University Of Ireland, Galway | Data analysis and event detection method and system |
CN105707974A (en) * | 2015-12-30 | 2016-06-29 | 河南中烟工业有限责任公司 | Cigarette production process stability monitoring method |
CN106485422A (en) * | 2016-10-19 | 2017-03-08 | 河南中烟工业有限责任公司 | A kind of Cigarette quality stability of rolled evaluation methodology |
CN110866670A (en) * | 2019-04-29 | 2020-03-06 | 红云红河烟草(集团)有限责任公司 | Method and system for identifying stub bar and tail in cigarette production and manufacturing process |
CN111103854A (en) * | 2019-12-10 | 2020-05-05 | 云南昆船设计研究院有限公司 | System and method for improving production stability of tobacco cut-tobacco drier |
Non-Patent Citations (5)
Title |
---|
张朋等: "一种基于聚类算法的制丝生产过程实时追溯技术", 《山东工业技术》 * |
李山等: "制丝在线加工工艺批次间差异性评价", 《农产品加工》 * |
王梦遥等: "基于改进BIRCH聚类算法的评价对象挖掘", 《软件》 * |
王珺等: "基于BIRCH算法和K-MEANS算法相结合的数据挖掘聚类技术", 《山东科学》 * |
陈晓宇: "非稳态数据在制丝过程能力评价中的应用", 《现代工业经济和信息化》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113256102A (en) * | 2021-05-20 | 2021-08-13 | 中国安全生产科学研究院 | High-risk technological process risk control method and system |
CN113256102B (en) * | 2021-05-20 | 2021-12-17 | 中国安全生产科学研究院 | High-risk technological process risk control method and system |
CN113379278A (en) * | 2021-06-23 | 2021-09-10 | 红云红河烟草(集团)有限责任公司 | Method for evaluating quality of whole process of silk making batch |
CN113379278B (en) * | 2021-06-23 | 2022-05-10 | 红云红河烟草(集团)有限责任公司 | Method for evaluating quality of whole process of silk making batch |
CN113361661A (en) * | 2021-07-20 | 2021-09-07 | 红云红河烟草(集团)有限责任公司 | Modeling method and device for data cooperation capability evaluation |
CN113361661B (en) * | 2021-07-20 | 2023-04-07 | 红云红河烟草(集团)有限责任公司 | Modeling method and device for evaluating data cooperation capability |
CN113592314A (en) * | 2021-08-02 | 2021-11-02 | 红云红河烟草(集团)有限责任公司 | Silk making process quality evaluation method based on sigma level |
CN113592314B (en) * | 2021-08-02 | 2024-03-26 | 红云红河烟草(集团)有限责任公司 | Sigma level-based silk making process quality evaluation method |
CN115669990A (en) * | 2022-11-23 | 2023-02-03 | 湖北中烟工业有限责任公司 | Intelligent electricity-saving method and device for tobacco shred production line |
CN115669990B (en) * | 2022-11-23 | 2024-05-10 | 湖北中烟工业有限责任公司 | Intelligent electricity-saving method and device for tobacco leaf shredding production line |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111882188A (en) | Process quality homogeneity level evaluation method and system based on Birch clustering algorithm | |
CN112036701B (en) | Technological parameter optimization method for multi-process industrial production process | |
CN108256752B (en) | A kind of analysis method of gas user gas behavior | |
CN109343344A (en) | Cigarette machine operating parameter optimization method | |
CN115630839B (en) | Intelligent feedback production regulation and control system based on data mining | |
CN103844344A (en) | Method for regulating and controlling tobacco shred quality uniformity of different batches of cigarettes and application of method | |
CN111723367B (en) | Method and system for evaluating service scene treatment risk of power monitoring system | |
CN111160404B (en) | Analysis method and device for reasonable value of line loss marker post of power distribution network | |
CN113592314B (en) | Sigma level-based silk making process quality evaluation method | |
CN111553568A (en) | Line loss management method based on data mining technology | |
CN110264107A (en) | A kind of platform area line loss per unit abnormality diagnostic method based on big data technology | |
CN115577152A (en) | Online book borrowing management system based on data analysis | |
CN113159106A (en) | Load curve clustering method, medium and equipment based on morphological trend characteristics | |
CN116148753A (en) | Intelligent electric energy meter operation error monitoring system | |
CN117851908B (en) | Improved on-line low-voltage transformer area electric energy meter misalignment monitoring method and device | |
CN116307844A (en) | Low-voltage transformer area line loss evaluation analysis method | |
CN108519760A (en) | Filament making process steady-state identification method based on variable point detection theory | |
CN107274025B (en) | System and method for realizing intelligent identification and management of power consumption mode | |
CN114356900A (en) | Power data anomaly detection method, device, equipment and medium | |
CN114202179A (en) | Target enterprise identification method and device | |
CN117592656A (en) | Carbon footprint monitoring method and system based on carbon data accounting | |
CN116595102A (en) | Big data management method and system for improving clustering algorithm | |
CN113379278B (en) | Method for evaluating quality of whole process of silk making batch | |
CN114781847A (en) | TOPSIS-based method for evaluating comprehensive quality of wire making | |
Zhou et al. | Study on Optimization of Data-Driven Anomaly Detection |
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: 20201103 |
|
RJ01 | Rejection of invention patent application after publication |