CN108510180B - Method for calculating performance interval of production equipment - Google Patents
Method for calculating performance interval of production equipment Download PDFInfo
- Publication number
- CN108510180B CN108510180B CN201810264936.3A CN201810264936A CN108510180B CN 108510180 B CN108510180 B CN 108510180B CN 201810264936 A CN201810264936 A CN 201810264936A CN 108510180 B CN108510180 B CN 108510180B
- Authority
- CN
- China
- Prior art keywords
- index
- data
- clustering
- equipment
- calculating
- 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
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 33
- 238000012423 maintenance Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 6
- 239000002994 raw material Substances 0.000 claims description 6
- 238000005265 energy consumption Methods 0.000 claims description 5
- 238000012797 qualification Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 5
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000011160 research Methods 0.000 abstract description 4
- 239000011159 matrix material Substances 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000010924 continuous production Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000012706 support-vector machine Methods 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
-
- 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)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for calculating a performance interval of production equipment, and relates to research on an evaluation method for calculating and judging the performance interval condition of the equipment according to the interval and running real-time monitoring data. Compared with the traditional clustering algorithm, the method has the advantages of more accurate clustering result and higher precision, the influence of each index on the performance of the equipment in the actual production is considered, the weight of the index with larger influence is highlighted, and the final performance clustering center is more in line with the actual operation condition of the equipment; the method comprises the steps that the maximum clustering radius is defined on a mathematical level, and is different from fuzzy division of other types, so that accurate performance interval division is obtained; the size of the acquisition window on a specific mathematical level is defined, and when data in the acquisition window are all divided into the same interval, the evaluation of the performance condition of the equipment can be obtained, so that the evaluation accuracy is determined, and the influence of individual interference data on the evaluation result is also avoided.
Description
Technical Field
The invention relates to an evaluation method research for modeling performance interval division of equipment based on historical data of equipment operation and calculating and judging the performance interval condition of the equipment according to the interval and operation real-time monitoring data.
Background
With the development of industrial technology and the expansion of scale of manufacturing enterprises, the manufacturing technology gradually develops from the past semi-manual semi-mechanization to the direction of comprehensive mechanical intelligence, and highly complex, precise and expensive equipment is more and more widely applied to enterprise production lines. The manufacturing equipment of the 'flow production type' enterprise has the characteristics of high safety requirement, continuous production and the like, once the equipment performance is reduced or fails, not only can the maintenance cost of the enterprise be increased, but also the influence on the production efficiency of the enterprise is very great, so that the performance condition of each equipment can be known in time, the production line can be kept with good production efficiency by adopting targeted maintenance measures, and the method plays a significant role in keeping competitive advantage of the enterprise in fierce market competition.
However, currently, division of the device performance interval is mostly expressed in a simple and general manner conceptually, a standard and quantitative model is lacked for selection of the device performance index and division of the performance interval, and in mainstream method research for division and performance evaluation of the performance interval, a simple analytic hierarchy process or a simple data fusion method is used, so that precision in the aspects of interval division and evaluation accuracy is low, subjective influence on index weight is large, and representativeness is lacked, so that objective weighting methods for calculating weight coefficients based on decision matrix information are mostly used for weighting multiple indexes. The information entropy is a measure of uncertainty, the lower the entropy, the smaller the uncertainty, the larger the index information quantity, the larger the weight, and vice versa, but the correlation among indexes is ignored. The CRITIC is comprehensive weighting according to the contrast strength and the conflict among indexes, mainly depends on the correlation coefficient among the indexes to be used for weighting calculation, and the two methods can well utilize the correlation degree between actual information data and the indexes to obtain more reasonable objective weight of each index by combining. The K-means algorithm considers that all indexes of the analyzed samples have the same effect in clustering, the support vector machine has higher training difficulty for the samples with large data volume and mainly supports the algorithm of two-class classification, and the practical application of the equipment performance classification which is more than the two-class classification needs multiple training to finish the classification. Aiming at the defects of the methods, a K-means clustering algorithm is improved by performing combined weighting based on CRITIC and an information entropy method, and clustering division is performed on historical data of equipment to obtain relatively accurate equipment performance partitions.
Disclosure of Invention
The invention provides an evaluation method for modeling the division of the performance intervals of equipment based on historical data monitored during the operation of the equipment and judging the performance intervals of the equipment according to the intervals and real-time monitoring data, aiming at the conditions that the division of the performance intervals of the equipment is less researched, the standardization is lacked and the equipment performance evaluation method with high precision is provided. Aiming at the defects that the clustering of each index attribute of the analysis equipment in the performance interval division clustering is the same by using a K-means algorithm, the interval clustering accuracy is not high, and the information entropy method only ignores the correlation among indexes according to data information, and the like, the method combines the CRITIC and the information entropy method to obtain the comprehensive weight of each index, and then clusters out an aggregation focus through multiple indexes to obtain the equipment performance interval division;
the technical scheme of the invention is a method for calculating a performance interval of production equipment and further calculating and judging the performance interval of the equipment according to real-time monitoring data, wherein the method comprises the following steps:
step 1: selecting key performance indexes in the production activities of target equipment;
further, the method for selecting the key performance index in the step 1 comprises the following steps:
indicators in terms of quality capability level include: the standard qualification rate of the product, the quality score of the product and the quality loss influence of the product;
the indicators of the performance status include: equipment operation production efficiency, average fault-free operation time and equipment large halt fault rate;
the indicators in terms of production consumption status include: raw material loss rate, auxiliary material loss rate and energy consumption level;
indicators in terms of equipment maintenance feedback include: average maintenance times, average maintenance duration and average maintenance loss;
respectively selecting one or more indexes from the one or more aspects as key performance indexes in the production activity of the target equipment;
step 2: determining the weight of each attribute according to the CRITIC and the information entropy method respectively, and determining a combination coefficient by using a variation coefficient method to optimize index attribute comprehensive weight;
step 2.1: calculating the associated weight of each index by adopting a CRITIC method;
1) acquiring data of indexes, normalizing the data of the indexes, and grouping the data of the indexes acquired in the same time period;
2) the correlation of the jth index with other indexes in each group is calculated as:
wherein r isijThe correlation coefficient between the ith index and the jth index is obtained;
calculating the information content C contained in the j indexj:
Wherein: sigmajThe contrast intensity of the j index is represented; cjThe larger the information content contained in the jth evaluation index is, the greater the relative importance of the index is;
calculating the associated weight theta of the jth indexj:
Step 2.2: entropy weight of each index by using an information entropy method;
1) normalizing the obtained indexes, wherein all data of one index are divided into one group;
2) calculating the information entropy H of the jth evaluation factorj：
Wherein: f. ofijAnd (3) representing a probability function of ith data in the jth index, wherein the calculation formula is as follows:
the ith data of the jth index after normalization is represented, and m represents the total number of data in each index;
3) calculating the entropy weight W of each indexj：
Wherein:
n represents the total number of indexes;
step 2.3: calculating the combination weight w of the jth index by using a coefficient of variation methodj；
wj＝aθj+βWj
Wherein:
and also
p1,p2,…，pnRepresenting the corresponding numerical value obtained by rearranging the entropy weight of each index obtained by calculation from small to large;
and step 3: after attaching corresponding weights to the indexes, clustering the index data into k classes by adopting a k-means clustering method, wherein different classes represent different performance intervals where the target equipment is located;
further, the k-means clustering method in the step 3 is as follows:
step 3.1: randomly selecting k data from all data as initial clustering centers c1,c2,…,ck；
Step 3.2: with c1,c2,…,ckAs an initial clustering center, calculating the distance between each data and each clustering center, dividing each data into clustering clusters to which the clustering centers with the minimum distances belong, and traversing all data to obtain k clustering clusters;
step 3.3: after the combination weight obtained in the step 2 is attached to each data in the k clustering clusters obtained in the step 3.2, the clustering center c of each cluster is recalculated1',c'2,…,c'k；
Step 3.4: calculating by adopting the same method as the step 3.2 and the step 3.4 to obtain a new generation of clustering centers until a clustering end condition is met, and obtaining k clustering centers and k clustering clusters;
step 3.5: and eliminating data with a distance greater than R from the cluster of the cluster in each cluster, wherein R is a threshold set according to actual conditions, and obtaining a final clustering result.
Further, R/R in the step 3.5max0.95, wherein RmaxRepresenting the maximum distance of the data point in the cluster to the cluster center.
And 4, step 4: and (3) acquiring the index data of the target equipment in real time, calculating which cluster the acquired index data belongs to, and determining that the target equipment belongs to the equipment performance interval corresponding to the cluster.
Furthermore, after M pieces of continuously obtained data belong to the same cluster, it is determined that the target device at the current moment belongs to the device performance interval corresponding to the cluster.
Compared with the traditional clustering algorithm, the method has the advantages of more accurate clustering result and higher precision, the influence of each index on the performance of the equipment in the actual production is considered, the weight of the index with larger influence is highlighted, and the final performance clustering center is more in line with the actual operation condition of the equipment; the method comprises the steps that the maximum clustering radius is defined on a mathematical level, and is different from fuzzy division of other types, so that accurate performance interval division is obtained; the size of the acquisition window on a specific mathematical level is defined, and when data in the acquisition window are all divided into the same interval, the evaluation of the performance condition of the equipment can be obtained, so that the evaluation accuracy is determined, and the influence of individual interference data on the evaluation result is also avoided.
Drawings
FIG. 1 is a flow chart of an embodiment of the method of the present invention;
FIG. 2 is a diagram of an analysis model of key performance evaluation indexes of the equipment;
FIG. 3 is a diagram of an equipment performance evaluation index layer model;
fig. 4 shows a device performance interval division and performance evaluation procedure.
Detailed Description
The following describes in detail an implementation routine of the present invention (see fig. 1), and the present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation and a specific operation procedure are given, but the scope of the present invention is not limited to the implementation routine described below.
The implementation routine can be mainly divided into the following steps:
step 1: an S-I-P-O-C-F model (as shown in figure 2) is used for formulating the key performance indexes of the equipment production activities and constructing a performance evaluation key index analysis model.
The key dimensionality of the overall performance of the equipment has four aspects:
first, quality level. The core of the equipment performance evaluation is the quality of the product produced by the equipment. And quantitatively evaluating the internal and external quality of the product aiming at the key quality parameters.
Secondly, operating efficiency. The basic evaluation dimension for measuring the performance is whether the normal operation state can be kept under the use environment. And the operation characteristics such as process capability, machining precision, reliability and the like are mainly evaluated.
And thirdly, material consumption. From the perspective of input and output, consumption levels of raw materials and auxiliary materials are also important references for performance evaluation.
And fourthly, maintaining feedback. The maintenance process means that the cost is increased, the production is slowed down, and the maintenance times and the maintenance time are important feedback indexes for performance evaluation.
The overall index design model takes quality, efficiency, loss and maintenance as longitudinal dimensions, key related parties such as customers, production managers and equipment maintainers relate to different longitudinal dimensions, overall evaluation indexes need to be fully identified, key requirements of key related different longitudinal dimensions are reflected, and the science and reliability of final evaluation results are guaranteed. And (3) comprehensively evaluating key performance indexes of the model of the equipment performance, as shown in figure 3.
Step 2: determining the weight of each attribute according to the CRITIC and the information entropy method respectively, and determining a combination coefficient by using a variation coefficient method to optimize index attribute comprehensive weight;
step 2.1: CRITIC method for determining attribute weight
1) From the index matrix A ═ aij)m×nThe normalized index matrix B is calculated from the formula (1) and the formula (2) ═ Bij)m×n(ii) a For the benefit index, it is general to order：
For cost-type indicators, let:
in the formula
Namely, it is
Are respectively the jth index ajMaximum and minimum values of. The normalized partial experimental data are shown in table 1:
table 1 example of normalizing each performance evaluation index data
2) And calculating the weight of each index according to CRITIC equations (3) and (4). The conflict quantization index of the jth index and other indexes is as follows:
wherein r isijThe correlation coefficient between the indices i and j is evaluated.
The objective weight of each index is comprehensively measured by the contrast intensity and the conflict. Is provided with CjC represents the amount of information contained in the jth evaluation indexjCan be expressed as:
Cjthe greater the amount of information contained in the jth evaluation index, the greater the relative importance of that index, so the objective weight of the jth index:
the CRITIC weight values of the indexes calculated by the above formula and experimental data are shown in table 2:
TABLE 2 CRITIC method for calculating weight value of each index
| Index (I) | Weighted value |
| Standard qualification rate of products | 0.27 |
| Product quality score | 0.15 |
| Product quality loss effect | 0.08 |
| Production efficiency of equipment operation | 0.12 |
| Mean time to failure | 0.16 |
| Large rate of equipment shutdown | 0.04 |
| Rate of loss of raw material | 0.08 |
| Energy consumption level | 0.02 |
| Loss of auxiliary material | 0.02 |
| Average number of maintenance | 0.02 |
| Average maintenance duration | 0.01 |
| Average maintenance loss | 0.03 |
Step 2.2: information entropy obtaining attribute objective weight
Let the normalized matrix be T ═ Tij}m×nFor the evaluation factors of larger and more excellent types, there are
For smaller and more optimal evaluation factors, there are
Wherein, for the larger and more excellent type factor, cmaxRepresenting the most qualified of all the information data of the factor, cminIt represents the least qualified; conversely, for smaller and more preferred factors, cmaxIndicates the factorThe most unsatisfactory one in the informative data, cminIt indicates the most satisfactory one.
Taking the normalized matrix T as an object, and according to a calculation formula of the information entropy, the information entropy of the jth evaluation factor is as follows:
fijand representing the probability function of each information data of the factor j, wherein the calculation formula is as follows:
when t isijWhen 0, f in formula (6)ijWhen 0, equation (7) is not valid. Therefore, it is necessary to correct (8):
and finally, calculating the information entropy weight of each factor:
wherein:
i.e. the normalization condition of the weights is fulfilled.
The entropy weight values of the indexes calculated by the above formula and experimental data are shown in table 3:
TABLE 3 calculation of weight values of indexes by information entropy method
| Index (I) | Weighted value |
| Standard qualification rate of products | 0.12 |
| Product quality score | 0.10 |
| Product quality loss effect | 0.06 |
| Production efficiency of equipment operation | 0.14 |
| Mean time to failure | 0.08 |
| Large rate of equipment shutdown | 0.10 |
| Rate of loss of raw material | 0.06 |
| Energy consumption level | 0.04 |
| Loss of auxiliary material | 0.08 |
| Average number of maintenance | 0.07 |
| Average maintenance duration | 0.09 |
| Mean dimensionProtection of loss | 0.06 |
Step 2.3: determining combining weights using coefficient of variation
The combined weight values of the indicators calculated by the formulas of the coefficient of variation method are shown in table 4:
TABLE 4 Combined weighted values of indexes
| Index (I) | Weighted value |
| Standard qualification rate of products | 0.20 |
| Product quality score | 0.13 |
| Product quality loss effect | 0.07 |
| Equipment operation deviceEfficiency of production | 0.13 |
| Mean time to failure | 0.12 |
| Large rate of equipment shutdown | 0.07 |
| Rate of loss of raw material | 0.07 |
| Energy consumption level | 0.03 |
| Loss of auxiliary material | 0.05 |
| Average number of maintenance | 0.04 |
| Average maintenance duration | 0.03 |
| Average maintenance loss | 0.06 |
And step 3: clustering each weight and index attribute value to obtain the division of the equipment performance interval, and setting the maximum cluster center radius Rmax. Inputting a data set X to be clustered and the clustering number K; and outputting K clusters.
The k-means algorithm firstly sets k initial clustering centers, divides a data sample into k clustering clusters according to the k clustering centers during each iteration, calculates the center of each cluster (namely the flat value of the distances between all objects in the cluster) after the division is finished, and takes the center as a clustering center reference point of the next round, and through multiple iterations, the obtained clustering centers are closer and closer to the real clustering cluster centers, the target function is smaller and smaller, and the clustering quality is better and better.
The specific processing process based on the k-means clustering algorithm is as follows:
(1) randomly selecting k data from n normal data objects as initial clustering center c1,c2,…,ck。
(2) With c1,c2,…,ckAs an initial clustering center, dividing clustering clusters of the data sample set according to the following principle: if d isij(xi,cj)＜dim(xi,cm) Wherein m is 1,2, …, k; j is not equal to m; i 1,2, …, n, and data sample xiDivision into clusters cjAnd the inside.
(3) According to the formula
Recalculating cluster center c1',c'2,…,c'k。
(4) If j ∈ (1,2, …, k), c'j＝cjThen is over, and c1',c'2,…,c'kRepresents the last cluster center, otherwise let cj＝c'jAnd (2) is executed again until the maximum iteration number is met.
(5) And outputting the clustering result and the final normal data clustering center.
(6) Taking the data point X to be measured, let ri＝|x-ciI is the data point X to be measured to the ith cluster center ciDistance of (d), if max (r)i) And if R is greater than R, the R is a reasonable threshold set by an experiment, and the data point is considered not to belong to any normal cluster.
Defining a maximum cluster radius R:
using non-standard numerical methods, define RmaxThe size of the cluster is related to the clustering result of the historical data, and the distance cluster of the historical data is selected according to different clustering centersThe 95% coverage of the lattice nearest to the center is approximated by a circle, and the actual size is determined.
u/n is 0.95, u is ∈ (0, n) and Rmax＝|xu-ci|
Wherein xuIs the u-th smallest from the i-th cluster center ciSampled data points of distance.
According to the previous research, the division of the interval related to the performance evaluation of the production equipment is finished, the function of the interval is mainly used for guiding that in the actual production application scene, the performance interval of the equipment at present is evaluated according to the monitored production data in the operation process of the similar equipment, because the spheroid characteristic of the clustering interval always has some abnormal points falling outside all the intervals, a data acquisition window with the size of M needs to be set, because the variation data belong to a few, the performance of the equipment is in a relatively stable state for a long time in the operation period, only when the data with the size of the window continuously acquired belongs to the maximum radius range of the clustering center of a certain class, the real performance condition of the equipment can be judged, so the conventional data is not considered, and the conventional data is only considered, and the variation data is neglected in the calculation process.
The device performance interval division and performance evaluation steps are shown in fig. 4;
clustering points (X) in different performance intervals of the equipment are analyzed according to historical data clustering1,X2,X3,...,Xk) Respectively represent performance intervals (V)1,V2,V3,...,Vk) The number of points in the clustering radius, wherein k is the category number, firstly, according to the confidence coefficient, 5 percent of the clustering points of each interval of the historical data is taken as an acquisition window N of each intervalxX 1, 2.. k, for the setting of the new device online monitoring data acquisition window size N, N max { N } may be definedxAnd f, determining that the device is in a certain performance interval when the data exceeding the acquisition window N belong to a certain interval.
Claims (3)
1. A method for calculating a performance interval of production equipment comprises the following steps:
step 1: selecting an index which is regarded as key performance in the production activity of the target equipment;
step 2: determining the weight of each attribute according to the CRITIC and the information entropy method respectively, and determining a combination coefficient by using a variation coefficient method to optimize index attribute comprehensive weight;
step 2.1: calculating the associated weight of each index by adopting a CRITIC method;
1) acquiring data of indexes, normalizing the data of the indexes, and grouping the data of the indexes acquired in the same time period;
2) the correlation of the jth index with other indexes in each group is calculated as:
wherein r isijThe correlation coefficient between the ith index and the jth index is obtained;
calculating the information content C contained in the j indexj:
Wherein: sigmajThe contrast intensity of the j index is represented;
calculating the associated weight theta of the jth indexj:
Step 2.2: calculating the entropy weight of each index by adopting an information entropy method;
1) normalizing the obtained indexes, wherein all data of one index are divided into one group;
2) calculating the information entropy H of the jth evaluation factorj：
Wherein: f. ofijAnd (3) representing a probability function of ith data in the jth index, wherein the calculation formula is as follows:
the ith data of the jth index after normalization is represented, and m represents the total number of data in each index;
3) calculating the entropy weight W of each indexj：
Wherein:
n represents the total number of indexes;
step 2.3: calculating the combination weight w of the jth index by using a coefficient of variation methodj；
wj＝aθj+βWj
Wherein:
and also
p1,p2,…,pnRepresenting the corresponding numerical value obtained by rearranging the entropy weight of each index obtained by calculation from small to large;
and step 3: after attaching corresponding weights to the indexes, clustering the index data into k classes by adopting a k-means clustering method, wherein different classes represent different performance intervals where the target equipment is located;
the k-means clustering method in the step 3 comprises the following steps:
step 3.1: randomly selecting k data from all data as initial clustering centers c1,c2,…,ck；
Step 3.2: with c1,c2,…,ckAs an initial clustering center, calculating the distance between each data and each clustering center, dividing each data into clustering clusters to which the clustering centers with the minimum distances belong, and traversing all data to obtain k clustering clusters;
step 3.3: and 6, after the combined weight obtained in the step 2 is attached to each data in the k clustering clusters obtained in the step 3.2, recalculating the clustering center c 'of each cluster'1,c’2,…,c'k；
Step 3.4: calculating by adopting the same method as the step 3.2 and the step 3.4 to obtain a new generation of clustering centers until a clustering end condition is met, and obtaining k clustering centers and k clustering clusters;
step 3.5: eliminating data with a distance greater than R from the cluster of the cluster in each cluster, wherein R is a threshold set according to actual conditions, and obtaining a final clustering result;
when M continuously obtained data belong to the same cluster, determining that the target equipment at the current moment belongs to an equipment performance interval corresponding to the cluster;
and 4, step 4: and (3) acquiring the index data of the target equipment in real time, calculating which cluster the acquired index data belongs to, and determining that the target equipment belongs to the equipment performance interval corresponding to the cluster.
2. The method for calculating the performance interval of the production equipment according to claim 1, wherein the method for selecting the key performance index in the step 1 comprises the following steps:
indicators in terms of quality capability level include: the standard qualification rate of the product, the quality score of the product and the quality loss influence of the product;
the indicators of the performance status include: equipment operation production efficiency, average fault-free operation time and equipment large halt fault rate;
the indicators in terms of production consumption status include: raw material loss rate, auxiliary material loss rate and energy consumption level;
indicators in terms of equipment maintenance feedback include: average maintenance times, average maintenance duration and average maintenance loss;
and respectively selecting one or more indexes from the one or more aspects as key performance indexes in the production activity of the target equipment.
3. The method for calculating the performance interval of the production equipment according to claim 1, wherein R/R in the step 3.5max0.95, wherein RmaxRepresenting the maximum distance of the data point in the cluster to the cluster center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810264936.3A CN108510180B (en) | 2018-03-28 | 2018-03-28 | Method for calculating performance interval of production equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810264936.3A CN108510180B (en) | 2018-03-28 | 2018-03-28 | Method for calculating performance interval of production equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108510180A CN108510180A (en) | 2018-09-07 |
| CN108510180B true CN108510180B (en) | 2021-08-06 |
Family
ID=63379085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810264936.3A Active CN108510180B (en) | 2018-03-28 | 2018-03-28 | Method for calculating performance interval of production equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108510180B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109144839A (en) * | 2018-10-09 | 2019-01-04 | 郑州云海信息技术有限公司 | The acquisition methods and device of equipment state |
| CN110889468A (en) * | 2019-12-23 | 2020-03-17 | 长沙理工大学 | Multi-model uncertain reproduction result analysis method capable of eliminating error information |
| CN112446509B (en) * | 2020-11-10 | 2023-05-26 | 中国电子科技集团公司第三十八研究所 | Prediction maintenance method for complex electronic equipment |
| CN112668862A (en) * | 2020-12-23 | 2021-04-16 | 华中科技大学 | Adaptability quantitative evaluation method of production line |
| CN115757076B (en) * | 2022-12-09 | 2023-10-27 | 国网湖北省电力有限公司信息通信公司 | Cluster management fitness computing method based on equipment operation characteristics and performance indexes |
| CN116227754B (en) * | 2023-05-09 | 2023-07-25 | 张家港大裕橡胶制品有限公司 | Production self-adaptive optimization control method and system for rubber gloves |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1684082A (en) * | 2005-02-18 | 2005-10-19 | 北京大学深圳医院 | Evaluation management system and its method for modern hospital performance |
| CN105512448A (en) * | 2014-09-22 | 2016-04-20 | 国家电网公司 | Power distribution network health index assessment method |
| CN105654229A (en) * | 2015-11-26 | 2016-06-08 | 国家电网公司 | Power grid automation system and equipment running state risk assessment algorithm |
| CN106372952A (en) * | 2016-11-14 | 2017-02-01 | 北京创业公社征信服务有限公司 | Objective and subjective weight determining multi-model compositional verification-based enterprise credit assessment method and system |
| CN106709654A (en) * | 2016-12-28 | 2017-05-24 | 中南大学 | Global operating condition evaluating and quality tracing method for hydrocracking process |
| CN107038460A (en) * | 2017-04-10 | 2017-08-11 | 南京航空航天大学 | A kind of ship monitor shortage of data value complementing method based on improvement KNN |
| CN107330458A (en) * | 2017-06-27 | 2017-11-07 | 常州信息职业技术学院 | A kind of fuzzy C-means clustering method of minimum variance clustering of optimizing initial centers |
| CN107679677A (en) * | 2017-10-30 | 2018-02-09 | 华南农业大学 | A kind of drought changes the preferential area's system of selection of water |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110060603A1 (en) * | 2009-09-09 | 2011-03-10 | Capelli Christopher C | Population Adjusted Indexes |
-
2018
- 2018-03-28 CN CN201810264936.3A patent/CN108510180B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1684082A (en) * | 2005-02-18 | 2005-10-19 | 北京大学深圳医院 | Evaluation management system and its method for modern hospital performance |
| CN105512448A (en) * | 2014-09-22 | 2016-04-20 | 国家电网公司 | Power distribution network health index assessment method |
| CN105654229A (en) * | 2015-11-26 | 2016-06-08 | 国家电网公司 | Power grid automation system and equipment running state risk assessment algorithm |
| CN106372952A (en) * | 2016-11-14 | 2017-02-01 | 北京创业公社征信服务有限公司 | Objective and subjective weight determining multi-model compositional verification-based enterprise credit assessment method and system |
| CN106709654A (en) * | 2016-12-28 | 2017-05-24 | 中南大学 | Global operating condition evaluating and quality tracing method for hydrocracking process |
| CN107038460A (en) * | 2017-04-10 | 2017-08-11 | 南京航空航天大学 | A kind of ship monitor shortage of data value complementing method based on improvement KNN |
| CN107330458A (en) * | 2017-06-27 | 2017-11-07 | 常州信息职业技术学院 | A kind of fuzzy C-means clustering method of minimum variance clustering of optimizing initial centers |
| CN107679677A (en) * | 2017-10-30 | 2018-02-09 | 华南农业大学 | A kind of drought changes the preferential area's system of selection of water |
Non-Patent Citations (3)
| Title |
|---|
| 基于 AHP 和 CRITIC 综合赋权的 K-means 算法;丁晓琴 等;《计算机系统应用》;20161231;第182-186页 * |
| 基于性能退化的车身焊装生产线动态预防性维护方法研究;刘恒宇;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;20181015;第J152-336页 * |
| 基于改进GRA法构建P2P网贷平台风险评价体系;梁寒冰;《财会月刊》;20171231;第55-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108510180A (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108510180B (en) | Method for calculating performance interval of production equipment | |
| CN105117602B (en) | A kind of metering device running status method for early warning | |
| CN113255848B (en) | Water turbine cavitation sound signal identification method based on big data learning | |
| Olson | Comparison of weights in TOPSIS models | |
| CN111369070B (en) | Multimode fusion photovoltaic power prediction method based on envelope clustering | |
| CN111062508B (en) | Method for evaluating real-time running state of wind turbine generator based on big data technology | |
| CN110956273A (en) | Credit scoring method and system integrating multiple machine learning models | |
| CN104239712B (en) | Real-time evaluation method for anti-interference performance of radar | |
| CN111401785A (en) | Power system equipment fault early warning method based on fuzzy association rule | |
| CN110766320A (en) | Method and device for evaluating operation safety of airport intelligent power grid | |
| CN106896219A (en) | The identification of transformer sub-health state and average remaining lifetime method of estimation based on Gases Dissolved in Transformer Oil data | |
| CN110705859A (en) | PCA-self-organizing neural network-based method for evaluating running state of medium and low voltage distribution network | |
| CN112884590A (en) | Power grid enterprise financing decision method based on machine learning algorithm | |
| CN113627735A (en) | Early warning method and system for safety risk of engineering construction project | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| CN114548494B (en) | Visual cost data prediction intelligent analysis system | |
| CN115375026A (en) | Method for predicting service life of aircraft engine in multiple fault modes | |
| CN110533109A (en) | A kind of storage spraying production monitoring data and characteristic analysis method and its device | |
| CN112966449B (en) | Manufacturing process quality defect root cause diagnosis method based on variable selection and probabilistic neural network | |
| CN117371861B (en) | Digital-based household service quality intelligent analysis method and system | |
| CN110991743B (en) | Wind power short-term combination prediction method based on cluster analysis and neural network optimization | |
| CN110210154B (en) | Method for judging similarity of measuring points representing dam performance state by using dam measuring point data | |
| CN112149870A (en) | Pig house ammonia concentration combined prediction method based on ISODATA clustering and Elman neural network | |
| CN113642834B (en) | Task importance evaluation method and system based on task attribute priority mapping | |
| CN115496264A (en) | Method for predicting generated power of wind turbine generator |
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 |