CN115345430A - Health degree evaluation method and system of chip mounter - Google Patents
Health degree evaluation method and system of chip mounter Download PDFInfo
- Publication number
- CN115345430A CN115345430A CN202210815683.0A CN202210815683A CN115345430A CN 115345430 A CN115345430 A CN 115345430A CN 202210815683 A CN202210815683 A CN 202210815683A CN 115345430 A CN115345430 A CN 115345430A
- Authority
- CN
- China
- Prior art keywords
- health
- chip mounter
- health monitoring
- historical
- matrix
- 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
- 230000036541 health Effects 0.000 title claims abstract description 338
- 238000011156 evaluation Methods 0.000 title claims abstract description 20
- 238000012544 monitoring process Methods 0.000 claims abstract description 141
- 239000013598 vector Substances 0.000 claims abstract description 73
- 238000000034 method Methods 0.000 claims abstract description 69
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 12
- 239000011159 matrix material Substances 0.000 claims description 67
- 238000012423 maintenance Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 4
- 230000017105 transposition Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 19
- 230000008569 process Effects 0.000 abstract description 13
- 230000006870 function Effects 0.000 description 24
- 238000000513 principal component analysis Methods 0.000 description 13
- 230000008859 change Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 6
- 230000006866 deterioration Effects 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (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 health degree assessment method and system of a chip mounter, belonging to the technical field of industrial manufacturing equipment and comprising the following steps: acquiring current running state data of the chip mounter; performing feature extraction on the current operation state data by adopting a principal component analysis method to obtain i health monitoring indexes; calculating the distance between the vector of each health monitoring index and the ideal health vector according to the health weight of the health monitoring index in the overall health condition of the chip mounter by adopting a standardized Euclidean distance method; and converting the distance into a health value of the chip mounter by adopting a negative function. The whole prediction process is simple and easy to operate, has strong interpretability, does not need to be configured complicatedly, fits an industrial environment, does not need to occupy excessive computing resources, and realizes the health degree evaluation of the chip mounter.
Description
Technical Field
The invention relates to the technical field of industrial manufacturing equipment, in particular to a health degree evaluation method and system of a chip mounter.
Background
With the rapid development of electronic technology and the great demand of people for electronic products, the electronic product manufacturing accounts for higher and higher proportion in the manufacturing industry, and the maintenance problem of electronic product manufacturing equipment becomes more and more critical. The chip mounter is key equipment in an electronic product production line, and is used for sucking and mounting electronic parts on a PCB (printed Circuit Board), and the mounting quality directly determines the quality of a produced mainboard. The chip mounter has the advantages of critical function, numerous quantity, fine structure and easy failure in the production line, so that the maintenance work is very difficult. The health state of the chip mounter in the present and future period of time is judged and predicted, the running state of the equipment can be known in advance, reasonable maintenance is planned by combining the health state of the chip mounter, normal production is guaranteed, and the manufacturing efficiency and product quality of electronic products are effectively improved.
In the related art, chinese patent application with publication No. CN112988843A discloses an SMT chip mounter fault management and diagnosis system based on SQL Server database, which mainly includes the following implementation steps: (1) fault data storage; (2) analyzing fault data; (3) inputting a fault category; and (4) predicting the running state. The chip mounter fault diagnosis and fault data management are realized, the fault data are referred to, the fault diagnosis and maintenance are guided, and the equipment fault occurrence rate is reduced.
However, the prediction result is only whether the operation state is abnormal or not, and the maintenance plan cannot be effectively guided, so that excessive maintenance or insufficient maintenance force can be caused; moreover, the data are subjected to fault prediction through a deep neural network model, the data calculation amount is large, and higher calculation resources are required to be occupied; and due to the inexplicability of the neural network, the prediction result is difficult to have reasonable physical meaning interpretation.
Disclosure of Invention
The invention aims to solve the technical problem of how to realize the evaluation of the health degree of the chip mounter so as to effectively guide the maintenance plan of the chip mounter.
The invention solves the technical problems through the following technical means:
in one aspect, the invention provides a health degree evaluation method for a chip mounter, which includes:
acquiring current operation state data of the chip mounter;
extracting the characteristics of the current operation state data by adopting a principal component analysis method to obtain i health monitoring indexes;
calculating the distance between the vector of each health monitoring index and an ideal health vector according to the health weight of each health monitoring index in the overall health condition of the chip mounter by adopting a standardized Euclidean distance method;
and converting the distance into a health value of the chip mounter by adopting a negative function.
The method extracts the health monitoring indexes for evaluating the health degree of the chip mounter from the operation state data of the chip mounter by adopting a principal component analysis method, is simple and easy to use, calculates the distance between the vector of the health monitoring indexes and an ideal health vector by using a standardized Euclidean distance method, and converts the health value of each health monitoring index into an integral health value through a negative function; the whole prediction process is simple and easy to operate, has strong interpretability, does not need to be configured complicatedly, fits an industrial environment, does not need to occupy excessive computing resources, and can realize the health degree evaluation of the chip mounter.
Further, before the feature extraction is performed on the current operating state data by using a principal component analysis method to obtain i health monitoring indicators, the method further includes:
performing data cleaning processing on the current running state data to obtain cleaned running state data;
and carrying out noise filtration on the cleaned running state data to obtain smooth running state data.
Further, the performing feature extraction on the current operation state data by using a principal component analysis method to obtain i health monitoring indexes includes:
arranging the current operation state data into an original matrix X with n rows and m columns, wherein m represents the number of chip mounters, and each chip mounter comprises n groups of monitoring data;
zero-averaging each row of the original matrix X and calculating a covariance matrix
X' represents a matrix of the original matrix X after zero equalization, and T represents matrix transposition;
solving the eigenvalue and the eigenvector of the covariance matrix C by using an eigenvalue decomposition method;
sorting the eigenvalues from large to small, and forming an eigenvector matrix S by using the corresponding eigenvectors as row vectors in sequence;
constructing a matrix P for the first i rows of eigenvectors of the eigenvector matrix S;
and converting the current running state data into a space constructed by the i rows of feature vectors to obtain i health monitoring indexes.
Further, the constructing a matrix P for the first i rows of eigenvectors of the eigenvector matrix S includes:
and calculating a reconstruction error e based on the characteristic vector matrix S, wherein the calculation formula is as follows:
in the formula, S f I =1,2, \ 8230for the f-th row of the eigenvector matrix S;
and taking the minimum row number value i from all the rows meeting the condition that the reconstruction error e is smaller than the error threshold value, and constructing a matrix P according to the characteristic vectors of the first i rows.
Further, the dynamic determination process of the health weight is as follows:
extracting the characteristics of the historical operating state data of the chip mounter by adopting a principal component analysis method to obtain i historical health monitoring indexes;
scoring the i historical health monitoring indexes according to the reference working range of the chip mounter to obtain health scores of the i historical health monitoring indexes, wherein a formula is represented as follows:
in the formula: s lk A health score representing the ith of the historical health monitoring indicators for the kth sample,
the upper boundary of the reference operating range is indicated,x l lower boundary, x, representing a reference working range lk A first historical health monitoring indicator, l =1,2, \8230;, i, of the kth sample;
and weighting the i historical health monitoring indexes by adopting a CRITIC weighting method to obtain the health weights of the i historical health monitoring indexes in the integral health condition of the chip mounter.
Further, the weighting i historical health monitoring indicators by using the CRITIC weighting method to obtain the health weights of the i historical health monitoring indicators in the overall health condition of the chip mounter includes:
carrying out standardization processing on the i historical health monitoring indexes to obtain a standardization matrix;
calculating the standard deviation of each row vector in the standardized matrix;
calculating linear correlation coefficients among different historical health monitoring indexes;
calculating the information quantity of each historical health monitoring index according to the standard deviation and the linear correlation coefficient, wherein the formula is as follows:
in the formula: sigma l Is the standard deviation, r lj Is the linear correlation coefficient;
normalizing the information of the historical health monitoring indexes to obtain weights, and adjusting the weights of the indexes deviating from ideal values by adopting an index function to obtain adjusted weights, wherein a formula is expressed as follows:
in the formula: omega cl Is the weight, δ l Represents the deviation of the actual monitored value from the ideal value in the ith historical health monitoring index, mu l Representing the base of an exponential function;
and normalizing the adjusted weight to obtain the health weight of the historical health monitoring index in the overall health condition of the chip mounter.
Further, the distance between the vector of each health monitoring index and the ideal health vector is calculated as follows:
in the formula: d k Representing the difference between the health monitoring index of the kth chip mounter and an ideal health vector; v. of kl The health monitoring index of the kth chip mounter is represented; ε represents the ideal health vector; omega kl The health weight of the ith historical health monitoring index of the kth chip mounter in the overall health condition of the chip mounter is k =1,2, \ 8230;, m;
is the variance of the ith said health monitoring indicator.
Further, the distance is converted into a health value of the chip mounter by using a negative function, and the formula is as follows:
in the formula: h k Representing the health value of the kth chip mounter; a represents a health range coefficient; d max Represents the measured maximum distance; b representsA shape parameter.
Further, the method further comprises:
based on the health value of the chip mounter, determining the health grade of the chip mounter according to a health value interval-health grade comparison table;
and guiding a predictive maintenance decision of the chip mounter based on the health level of the chip mounter.
In addition, the invention also provides a health degree evaluation system of the chip mounter, and the system comprises:
the acquisition module is used for acquiring current running state data of the chip mounter;
the characteristic extraction module is used for extracting the characteristics of the current operation state data by adopting a principal component analysis method to obtain i health monitoring indexes;
the distance calculation module is used for calculating the distance between the vector of each health monitoring index and the ideal health vector according to the health weight of the health monitoring index in the overall health condition of the chip mounter by adopting a standardized Euclidean distance method;
and the health value calculation module is used for converting the distance into the health value of the chip mounter by adopting a negative function.
The invention has the advantages that:
(1) The health monitoring index for evaluating the health degree of the chip mounter is extracted from the operation state data of the chip mounter by adopting a Principal Component Analysis (PCA), the method is simple and easy to use, the distance between the vector of the health monitoring index and an ideal health vector is calculated by using a standardized Euclidean distance method, and the health value of each health monitoring index is converted into an integral health value through a negative function; the whole prediction process is simple and easy to operate, has strong interpretability, does not need to be configured complicatedly, fits an industrial environment, does not need to occupy excessive computing resources, and realizes the health degree evaluation of the chip mounter.
(2) In the method, data are converted into health scores in a linear relation in the scoring of health monitoring indexes, so that the method is simple, intuitive and easy to operate; objective weighting (CRITIC) is adopted to assign values in consideration of objective information inside data, rather than subjective assignment without basis.
(3) The index deviating from the ideal value is adjusted by adopting the exponential function, and the influence of the deterioration degree of a single index on the whole health degree is described by using a dynamic weight value adjusting mechanism, so that the inaccuracy is avoided.
(4) The invention guides planned reasonable maintenance action based on the health degree change trend of the chip mounter, avoids the problems of excessive maintenance or insufficient maintenance and the like, improves the reliability of equipment, and improves the efficiency and the product quality in the manufacturing process of electronic products.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a schematic flow chart of a first embodiment of a health degree evaluation method of a chip mounter according to the present invention;
fig. 2 is a schematic flow chart of a health degree evaluation method of a chip mounter according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a health degree evaluation system of a chip mounter according to a first embodiment of the present invention;
fig. 4 is a schematic structural diagram of a health degree evaluation system of a chip mounter according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a first embodiment of the present invention provides a method for evaluating health of a chip mounter, where the method includes the following steps:
and S10, acquiring current operation state data of the chip mounter.
Further, the operation state data of the chip mounter includes, but is not limited to, current and voltage data of each component, data related to the head portion drawn by the chip mounter, position deviation data of each sensor, load data (stress) of moving components, vibration data of transmission components and the head portion, and the like. Wherein, the chip mounter absorbs relevant data of head and includes: air pressure, response speed of the blowing valve and the vacuum valve, and the like.
It should be noted that the operation state data of the chip mounter may be obtained through various sensors installed on the chip mounter, and it is required that each monitoring index may reflect the health degree of the chip mounter to a certain extent.
Particularly, when the existing data are judged to be insufficient to comprehensively reflect the health degree of the equipment, a sensor can be additionally arranged to acquire the running state data of the chip mounter.
And S20, performing feature extraction on the current operation state data by adopting a principal component analysis method to obtain i health monitoring indexes.
It should be noted that the principal component analysis PCA is a method for reducing high-dimensional data into low-dimensional linearly independent data, and is commonly used for feature extraction. Due to the fact that health monitoring parameters of the chip mounter are various, scoring is conducted on all monitoring data, weight distribution is complex, efficiency is poor, principal components can be obtained by using PCA, and data needing to be processed are reduced.
And S30, calculating the distance between the vector of each health monitoring index and an ideal health vector according to the health weight of each health monitoring index in the overall health condition of the chip mounter by adopting a standardized Euclidean distance method.
And S40, converting the distance into a health value of the chip mounter by adopting a negative function.
The method comprises the steps of extracting health monitoring indexes for evaluating the health degree of the chip mounter from chip mounter running state data by adopting a Principal Component Analysis (PCA), calculating the distance between a vector of the health monitoring indexes and an ideal health vector by using a standardized Euclidean distance method, and converting the health value of each health monitoring index into an integral health value through a negative function; the whole prediction process is simple and easy to operate, has strong interpretability, does not need to be configured complicatedly, fits an industrial environment, does not need to occupy excessive computing resources, and realizes the health degree evaluation of the chip mounter.
In an embodiment, before the step S10, the method further includes the steps of:
and carrying out data cleaning processing on the current running state data to obtain cleaned running state data.
Further, the data cleaning refers to reasonably performing consistency check and invalid value and missing value processing on the collected chip mounter running state data. The consistency index data is in a range which should be physically meaningful, and sample mean, median and mode estimation is adopted to replace or directly delete data which does not accord with consistency or is invalid or missing.
And carrying out noise filtration on the cleaned running state data to obtain smooth running state data.
Further, in this embodiment, noise filtering refers to filtering and smoothing noise of each monitored data by using an exponential weighted average method, where the formula of the exponential weighted average method is as follows:
v t ＝βv t-1 +(1-β)θ t
wherein, theta t Is the actual monitored value at time t; v. of t The weighted average value at the time t is used for replacing an actual monitoring value; β is a weight, typically between 0 and 1.
It should be noted that, the larger β is, the smaller the noise is, the smoother the data is, but the fact that the parameter changes may not be reflected, and in the practical use, β =0.9 is taken in the present embodiment.
It should be noted that, in consideration of the complexity of data acquisition in an actual scene, the embodiment performs data cleaning and noise filtering on the acquired real operating state data, so that the requirement of calculating the health value of the device is met.
In an embodiment, the step S20 includes the following steps:
and S21, arranging the current operation state data into an original matrix X with n rows and m columns, wherein m represents the number of chip mounters, and each chip mounter comprises n groups of monitoring data.
S22, carrying out zero mean value treatment on each line of the original matrix X and calculating a covariance matrix
X' represents a matrix of the original matrix X after zero equalization, and T represents matrix transposition;
it should be noted that, in this embodiment, zero equalization is performed on each row of X, that is, the average value of the row where each element is located is subtracted from each element to obtain a matrix X'.
And S23, solving the eigenvalue and the eigenvector of the covariance matrix C by using an eigenvalue solution.
And S24, sequencing the eigenvalues from large to small, and forming a eigenvector matrix S by taking the corresponding eigenvectors as row vectors in sequence.
And S25, constructing a matrix P for the first i rows of feature vectors of the feature vector matrix S.
And S26, converting the current running state data into a space constructed by the i rows of feature vectors to obtain i health monitoring indexes.
Further, the step S25 specifically includes:
and calculating a reconstruction error e based on the characteristic vector matrix S, wherein the calculation formula is as follows:
in the formula, S f I =1,2, \ 8230for the f-th row of the eigenvector matrix S;
and taking the minimum row numerical value i from all the rows which meet the condition that the reconstruction error e is smaller than the error threshold value, and constructing a matrix P according to the characteristic vectors of the previous i rows.
It should be noted that, the selection of i generally calculates a "reconstruction error", that is, calculates the information lost by the PCA dimension reduction, and generally makes the lost information be 1%, 5%, 10%, or even 20%, which depends on the trade-off between the calculation cost and the information loss. Such as: that is, if i is required to make the reconstruction error of PCA not exceed 5%, i with the minimum reconstruction error e less than or equal to 0.05 is required.
In an embodiment, in the step S30, the health weight of the health monitoring index in the overall health condition of the chip mounter is obtained by analyzing historical operating state data of the chip mounter, and the specific process includes:
s1, extracting characteristics of historical operating state data of the chip mounter by adopting a principal component analysis method to obtain i historical health monitoring indexes.
It should be understood that the obtaining process of the historical operating state data of the chip mounter may adopt the obtaining method of the current operating state data of the chip mounter in the step S10, and details are not described here.
It should be noted that the collected historical operating state data of the chip mounter may reflect the health condition of the chip mounter to a certain extent, and may be known by consulting expert opinions, or may collect monitoring data of each index at a completely healthy (brand new) moment of the chip mounter and data of a period of time before the failure of the chip mounter. And judging the difference of the monitoring data of each index in the two periods of time by a data statistical analysis method or a machine learning method, wherein if the difference is not large, the correlation between the index and the health degree is small, otherwise, the correlation is strong.
S2, scoring the i historical health monitoring indexes according to the reference working range of the chip mounter to obtain health scores of the i historical health monitoring indexes, wherein a formula is as follows:
in the formula: s is lk A health score representing the ith of the historical health monitoring indicators for the kth sample,
the upper boundary of the reference operating range is indicated,x l lower boundary, x, representing the reference working range lk The ith historical health monitoring indicator, l =1,2, \8230;, i, of the kth sample is indicated.
It should be noted that, since the operating state data is zero-averaged by using the principal component analysis PCA in the previous step, the ideal value of each index is 0, and the health value is 0 when the index is at the ideal value
For the health value at the boundary value of the normal working rangesWhen the parameters are in other values, the parameters are obtained according to the linear functions determined by the two values, and the data are converted into the health score in a linear relation, so that the method is simple, visual and easy to operate.
In practice, it is often taken
s=60, it is needless to say that other values may be selected as needed, and this embodiment is not particularly limited.
And S3, weighting the i historical health monitoring indexes by adopting a CRITIC weighting method to obtain the health weights of the i historical health monitoring indexes in the overall health condition of the chip mounter.
It should be noted that, the CRITIC method considers the assignment of objective information inside data, the CRITIC analysis method considers not only the difference between data inside indexes but also the correlation between different indexes, and the larger the difference between values in the same index is, the larger the information amount represented by the difference is, the larger the weight is; the larger the correlation coefficient between different indexes is, the higher the correlation between the indexes is, and the smaller the weight is.
Suppose that the first monitoring index (l =1,2, \8230;, i) of the kth station (k =1,2, \8230;, m) in the m chip mounter is scored as s lk Then, the CRITIC method is specifically implemented as follows:
in an embodiment, the step S3 specifically includes the following steps:
(1) And carrying out standardization processing on the i historical health monitoring indexes to obtain a standardization matrix.
It should be noted that, in the present embodiment, the data range is changed to be between 0 and 1 through the normalization process, and the formula is:
wherein s is lmin And s lmax Respectively representing the minimum and maximum scores under the l < th > health monitoring index to obtain a standardized matrix A = (a) lk ) i×m 。
(2) And calculating the standard deviation of each row vector in the standardized matrix.
It should be noted that the standard deviation is calculated to describe the difference of data in each index.
(3) And calculating linear correlation coefficients among different historical health monitoring indexes.
Further, a linear correlation coefficient r between each health monitoring index l and the index j (l, j =1,2, \8230;, i) is calculated lj The formula is as follows:
where Cov [ a, b ] represents the covariance of the vectors a, b, var [ a ] represents the variance of the vector a,
(4) Calculating the information quantity of each historical health monitoring index according to the standard deviation and the linear correlation coefficient, wherein the formula is as follows:
in the formula: sigma l Is the standard deviation, r lj Is the linear correlation coefficient.
(5) Normalizing the information of the historical health monitoring index to obtain a weight omega ci And adjusting the weight of the index deviating from the ideal value by using an exponential function to obtain an adjustmentThe weight after the adjustment is expressed by the following formula:
in the formula: omega cl As the weight, δ l Represents the deviation of the actual monitoring value from the ideal value in the ith historical health monitoring index, mu l The base number of the exponential function is expressed and given by expert opinion.
(6) And normalizing the adjusted weight to obtain the health weight of the historical health monitoring index in the overall health condition of the chip mounter.
It should be noted that, because the suction head part of the chip mounter is the most important working component in the whole machine, the weight of the related index is necessarily large. In addition, in order to describe the influence of single index deterioration on the whole health condition, the index function is adopted to adjust the weight of the index deviating from the ideal value, the inaccuracy is avoided, the weight determination process is simple, the interpretability is strong, and the indexes which are important can be seen, and the indexes represent the health condition of part of the machine
In an embodiment, in the step S30, a distance between the vector of each health monitoring indicator and the ideal health vector is calculated as follows:
in the formula: d is a radical of k Representing the difference between the health monitoring index of the kth chip mounter and an ideal health vector; v. of kl The health monitoring index of the kth chip mounter is represented; ε represents the ideal health vector; omega kl The health weight of the ith historical health monitoring index of the kth chip mounter in the overall health condition of the chip mounter;
is the variance of the ith said health monitoring indicator.
In an embodiment, in step S40, the distance is converted into a health value of the chip mounter by using a negative function, and the formula is as follows:
in the formula: h k Representing the health value of the kth chip mounter; a represents a health range coefficient; d max Represents the maximum distance measured; b represents a shape parameter.
It should be noted that a =100 in the present embodiment, but those skilled in the art may set the health range coefficient to other values according to actual needs, and the present embodiment is not particularly limited.
It should be noted that, the difference d between the monitoring data vector and the health vector of the chip mounter k The larger the distance is, the unhealthy the chip mounter is, so that the distance needs to be converted into a healthy value by adopting a negative function, and a healthy value between 0 and 100 can be obtained for judging the working condition of the chip mounter.
As shown in fig. 2, based on the disclosure of the first embodiment, a second embodiment of the health degree evaluation method of the chip mounter according to the present invention is provided, and the method further includes the following steps:
and S50, based on the health value of the chip mounter, determining the health grade of the chip mounter according to a health value interval-health grade comparison table.
Specifically, according to practical experience, the health state of the chip mounter may be divided into five health levels according to the health values, and the corresponding relationship between the meaning of each health level and the health value interval is shown in table 1 below:
TABLE 1 correspondence between each health grade meaning and health value interval
And S60, guiding a predictive maintenance decision of the chip mounter based on the health grade of the chip mounter.
It should be noted that, in this embodiment, a maintenance decision of the chip mounter is performed according to the obtained health value of the chip mounter and the corresponding health level. For a chip mounter, a historical health degree change curve can be obtained by monitoring the historical state of the chip mounter and calculating the health degree. The historical health degree change curve is fitted, the future change trend of the health degree of the chip mounter can be predicted, the expected maintenance time and maintenance action are selected according to the trend, the production plan can be adjusted according to the expected maintenance time, the benefit of a production line is improved, and the decision process is rolling along with the time.
In addition, maintenance actions can be properly arranged according to the production situation and the current health value, for example, the health value of a chip mounter is 72, the chip mounter is in a state of being about to enter sub-health state, and has no production task temporarily, and some simple maintenance can be carried out on the chip mounter to change the trend of slowing down the deterioration of the health state. Of course, if the pick & place machine health value is found to have fallen below 60 during the monitoring, then maintenance should be scheduled for shutdown as soon as possible.
Further, corresponding maintenance strategies, including different actions such as lubrication, cleaning, repair, replacement, etc., are executed according to the maintenance time determined in the table.
In fact, according to the method, the health evaluation and the predictive maintenance can be respectively carried out on each part in the chip mounter, even other machines on an SMT production line or other various types of machines. Moreover, the method has wide applicability, and can be used on chip mounters and other similar machines.
Further, as shown in fig. 3, a third embodiment of the present invention provides a health degree evaluation system for a chip mounter, including:
the obtaining module 10 is configured to obtain current operation state data of the chip mounter.
And the feature extraction module 20 is configured to perform feature extraction on the current operation state data by using a principal component analysis method to obtain i health monitoring indexes.
The distance calculation module 30 is configured to calculate, by using a standardized euclidean distance method, a distance between a vector of each health monitoring index and an ideal health vector according to a health weight of the health monitoring index in the overall health condition of the chip mounter.
And the health value calculation module 40 is configured to convert the distance into a health value of the chip mounter by using a negative function.
In the embodiment, the health monitoring indexes for evaluating the health degree of the chip mounter are extracted from the chip mounter running state data by adopting a Principal Component Analysis (PCA) method, the operation is simple and easy to use, the distance between the vector of the health monitoring indexes and an ideal health vector is calculated by using a standardized Euclidean distance method, and the health values of the health monitoring indexes are converted into an integral health value through a negative function; the whole prediction process is simple and easy to operate, has strong interpretability, does not need to be configured complicatedly, fits an industrial environment, does not need to occupy excessive computing resources, and realizes the health degree evaluation of the chip mounter.
In one embodiment, the system further comprises a data preprocessing module for:
performing data cleaning processing on the current running state data to obtain cleaned running state data;
and carrying out noise filtration on the cleaned running state data to obtain smooth running state data.
In one embodiment, the feature extraction module 20 includes:
and the original matrix construction unit is used for arranging the current operation state data into an original matrix X with n rows and m columns, wherein m represents the number of chip mounters, and each chip mounter comprises n groups of monitoring data.
A zero-averaging processing unit for zero-averaging each line of the original matrix X and calculating a covariance matrix
X' represents a matrix of the original matrix X after zero equalization;
it should be noted that, in this embodiment, zero equalization is performed on each row of X, that is, the average value of the row where each element is located is subtracted from each element to obtain a matrix X'.
And the characteristic solving unit is used for solving the characteristic value and the characteristic vector of the covariance matrix C by using a characteristic value solving method.
And the characteristic vector matrix construction unit is used for sequencing the characteristic values from large to small and forming a characteristic vector matrix S by taking the corresponding characteristic vectors as row vectors in sequence.
And the matrix constructing unit is used for constructing a matrix P for the characteristic vectors of the first i rows of the characteristic vector matrix S.
And the conversion unit is used for converting the current running state data into a space constructed by the i rows of feature vectors to obtain i health monitoring indexes.
In one embodiment, the distance between each of the vectors of the health monitoring indicators and the ideal health vector of the distance calculation module 30 is calculated as follows:
in the formula: d k Representing the difference between the health monitoring index of the kth chip mounter and an ideal health vector; v. of kl The health monitoring index of the kth chip mounter is represented; ε represents the ideal health vector; omega kl The health weight of the ith historical health monitoring index of the kth chip mounter in the overall health condition of the chip mounter is set;
is the variance of the ith said health monitoring indicator.
In an embodiment, the health value calculating module 40 is configured to convert the distance into a health value of the chip mounter by using a negative function, where the formula is as follows:
in the formula: h k Indicating kth chip mounterA health value of; a represents a health range coefficient; d max Represents the measured maximum distance; b represents a shape parameter.
In one embodiment, the system further comprises a weight determination module comprising:
and the characteristic extraction unit is used for extracting the characteristics of the historical operating state data of the chip mounter by adopting a principal component analysis method to obtain i historical health monitoring indexes.
A health score determining unit, configured to score the i historical health monitoring indicators according to a reference working range of the chip mounter, to obtain health scores of the i historical health monitoring indicators, where a formula is as follows:
in the formula: s lk A health score representing the ith of the historical health monitoring indicator for the kth sample,
the upper boundary of the reference operating range is indicated,x l lower boundary, x, representing a reference working range lk The ith historical health monitoring indicator, l =1,2, \8230;, i, of the kth sample.
And the weighting unit is used for weighting the i historical health monitoring indexes by adopting a CRITIC weighting method to obtain the health weights of the i historical health monitoring indexes in the overall health condition of the chip mounter.
Wherein, the empowerment unit is specifically configured to:
(1) And carrying out standardization processing on the i historical health monitoring indexes to obtain a standardization matrix.
It should be noted that, in the present embodiment, the data range is changed to be between 0 and 1 through the normalization process, and the formula is:
wherein s is lmin And s lmax Respectively representing the minimum and maximum scores under the l < th > health monitoring index to obtain a standardized matrix A = (a) lk ) i×m 。
(2) And calculating the standard deviation of each row vector in the standardized matrix.
It should be noted that the standard deviation is calculated to describe the difference of data in each index.
(3) And calculating linear correlation coefficients among different historical health monitoring indexes.
Further, a linear correlation coefficient r between each health monitoring index l and the index j (l, j =1,2, \8230;, i) is calculated lj The formula is as follows:
where Cov [ a, b ] represents the covariance of the vector a, b, var [ a ] represents the variance of the vector a,
(4) Calculating the information quantity of each historical health monitoring index according to the standard deviation and the linear correlation coefficient, wherein the formula is as follows:
in the formula: sigma l Is the standard deviation, r lj Is the linear correlation coefficient.
(5) Normalizing the information of the historical health monitoring index to obtain a weight omega cl And adjusting the weight of the index deviating from the ideal value by adopting an exponential function to obtain the adjusted weight, wherein the formula is as follows:
in the formula: omega cl Is the weight, δ l Denotes the first placeDeviation mu between actual monitoring value and ideal value in historical health monitoring index l The base number of the exponential function is expressed and given by expert opinion.
(6) And normalizing the adjusted weight to obtain the health weight of the historical health monitoring index in the integral health condition of the chip mounter.
By adopting the index function to adjust the index deviating from the ideal value and using a dynamic weight value adjusting mechanism, the influence of the deterioration degree of a single index on the whole health degree is described, and the inaccuracy is avoided.
Further, as shown in fig. 4, on the basis of the disclosure of the third embodiment, a health degree evaluation system of a chip mounter according to a fourth embodiment of the present invention is provided, and the system further includes:
and the health grade determining module 50 is configured to determine a health grade of the chip mounter according to a health value interval-health grade comparison table based on the health value of the chip mounter.
Specifically, according to practical experience, the health state of the chip mounter can be divided into five health levels according to the health values, and the corresponding relationship between the meaning of each health level and the health value interval is shown in table 1 below:
TABLE 1 correspondence between each health grade meaning and health value interval
A maintenance decision guidance module 60 for guiding a predictive maintenance decision of the chip mounter based on the health level of the chip mounter.
It should be noted that, in this embodiment, a maintenance decision of the chip mounter is performed according to the obtained health value of the chip mounter and the corresponding health level. For a chip mounter, a historical health degree change curve can be obtained by monitoring the historical state of the chip mounter and calculating the health degree. The historical health degree change curve is fitted, the future change trend of the health degree of the chip mounter can be predicted, then the expected maintenance time and maintenance action are selected according to the trend, the production plan can be adjusted according to the expected maintenance time, the benefit of a production line is improved, and the decision process is rolling all the time.
In addition, maintenance actions can be properly arranged according to the production condition and the current health value, for example, the health value of a chip mounter is 72, the chip mounter is in a state of being about to enter sub-health state, and has no production task temporarily, and some simple maintenance can be performed on the chip mounter to change the trend of slowing down the health state deterioration. Of course, if the chip mounter health value is found to be below 60 in the monitoring, then shutdown maintenance should be scheduled as soon as possible.
It should be noted that other embodiments or implementation methods of the health assessment system of a chip mounter according to the present invention may refer to the above method embodiments, and no redundancy is required here.
It should be noted that the logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (10)
1. A health degree evaluation method of a chip mounter is characterized by comprising the following steps:
acquiring current running state data of the chip mounter;
extracting the characteristics of the current operation state data by adopting a principal component analysis method to obtain i health monitoring indexes;
calculating the distance between the vector of each health monitoring index and an ideal health vector by adopting a standardized Euclidean distance method according to the health weight of each health monitoring index in the overall health condition of the chip mounter;
and converting the distance into a health value of the chip mounter by adopting a negative function.
2. The method for assessing the health of a chip mounter according to claim 1, wherein before the extracting the features of the current operating state data by using a principal component analysis method to obtain i health monitoring indicators, the method further comprises:
performing data cleaning processing on the current running state data to obtain cleaned running state data;
and carrying out noise filtration on the cleaned running state data to obtain smooth running state data.
3. The method for assessing the health degree of the mounter according to claim 1, wherein the obtaining i health monitoring indicators by performing feature extraction on the current operating state data by using a principal component analysis method includes:
arranging the current operation state data into an original matrix X with n rows and m columns, wherein m represents the number of chip mounters, and each chip mounter comprises n groups of monitoring data;
zero-averaging each row of the original matrix X and calculating a covariance matrix
X' represents a matrix of the original matrix X after zero equalization, and T represents matrix transposition;
solving eigenvalues and eigenvectors of the covariance matrix C by using an eigenvalue solution;
sorting the eigenvalues from large to small, and forming an eigenvector matrix S by using the corresponding eigenvectors as row vectors in sequence;
constructing a matrix P for the first i rows of eigenvectors of the eigenvector matrix S;
and converting the current running state data into a space constructed by the i rows of feature vectors to obtain i health monitoring indexes.
4. The method for evaluating the health degree of the chip mounter according to claim 3, wherein the constructing a matrix P for the feature vectors in the first i rows of the feature vector matrix S includes:
based on the feature vector matrix S, a reconstruction error e is calculated, and the calculation formula is as follows:
in the formula, S f For the f-th row of the eigenvector matrix S, i =1,2, \8230;, n;
and taking the minimum row number value i from all the rows meeting the condition that the reconstruction error e is smaller than the error threshold value, and constructing a matrix P according to the characteristic vectors of the first i rows.
5. The method for health assessment of a placement machine according to claim 1, wherein the dynamic determination of the health weight is:
extracting the characteristics of the historical operating state data of the chip mounter by adopting a principal component analysis method to obtain i historical health monitoring indexes;
scoring the i historical health monitoring indexes according to the reference working range of the chip mounter to obtain health scores of the i historical health monitoring indexes, wherein a formula is as follows:
in the formula: s lk A health score representing the ith of the historical health monitoring indicators for the kth sample,
the upper boundary of the reference operating range is indicated,x l lower boundary, x, representing a reference working range lk A first historical health monitoring indicator, l =1,2, \8230;, i, of the kth sample;
and weighting the i historical health monitoring indexes by adopting a CRITIC weighting method to obtain the health weights of the i historical health monitoring indexes in the overall health condition of the chip mounter.
6. The method for assessing the health of a chip mounter according to claim 5, wherein the weighting i historical health monitoring indicators by a CRITIC weighting method to obtain the health weights of the i historical health monitoring indicators in the overall health condition of the chip mounter comprises:
carrying out standardization processing on the i historical health monitoring indexes to obtain a standardization matrix;
calculating the standard deviation of each row vector in the standardized matrix to obtain a standard deviation vector;
calculating linear correlation coefficients among different historical health monitoring indexes;
calculating the information quantity of each historical health monitoring index according to the standard deviation and the linear correlation coefficient, wherein the formula is as follows:
in the formula: sigma l Is the standard deviation, r lj Is the linear correlation coefficient;
normalizing the information of the historical health monitoring indexes to obtain weights, and adjusting the weights of the indexes deviating from ideal values by adopting an index function to obtain adjusted weights, wherein a formula is expressed as follows:
in the formula: omega cl Is the weight, δ l Represents the deviation of the actual monitored value from the ideal value in the ith historical health monitoring index, mu l Representing the base number of an exponential function;
and normalizing the adjusted weight to obtain the health weight of the historical health monitoring index in the overall health condition of the chip mounter.
7. The method for evaluating the health degree of the mounter according to claim 1, wherein a calculation formula of a distance between the vector of each health monitoring index and an ideal health vector is as follows:
in the formula: d is a radical of k Representing the difference between the health monitoring index of the kth chip mounter and an ideal health vector; v. of kl The health monitoring index of the kth chip mounter is represented; ε represents the ideal health vector; omega kl The health weight value of the ith historical health monitoring index of the kth chip mounter in the overall health condition of the chip mounter;
is the variance of the ith said health monitoring indicator.
8. The method for evaluating the health degree of the chip mounter according to claim 1, wherein the distance is converted into a health value of the chip mounter by using a negative function, and a formula is expressed as follows:
in the formula: h k The health value of the kth chip mounter is represented; a represents a health range coefficient; d max Represents the maximum distance measured; b represents a shape parameter.
9. The method of health assessment of a placement machine according to any of claims 1-8, wherein the method further comprises:
based on the health value of the chip mounter, determining the health grade of the chip mounter according to a health value interval-health grade comparison table;
and guiding a predictive maintenance decision of the chip mounter based on the health level of the chip mounter.
10. A health assessment system for a placement machine, the system comprising:
the acquisition module is used for acquiring current running state data of the chip mounter;
the characteristic extraction module is used for extracting the characteristics of the current operation state data by adopting a principal component analysis method to obtain i health monitoring indexes;
the distance calculation module is used for calculating the distance between the vector of each health monitoring index and the ideal health vector according to the health weight of the health monitoring index in the overall health condition of the chip mounter by adopting a standardized Euclidean distance method;
and the health value calculation module is used for converting the distance into the health value of the chip mounter by adopting a negative function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210815683.0A CN115345430A (en) | 2022-07-12 | 2022-07-12 | Health degree evaluation method and system of chip mounter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210815683.0A CN115345430A (en) | 2022-07-12 | 2022-07-12 | Health degree evaluation method and system of chip mounter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345430A true CN115345430A (en) | 2022-11-15 |
Family
ID=83947435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210815683.0A Pending CN115345430A (en) | 2022-07-12 | 2022-07-12 | Health degree evaluation method and system of chip mounter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345430A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115689397A (en) * | 2022-12-30 | 2023-02-03 | 北京和利时系统集成有限公司 | Water pump health degree determination method and device |
-
2022
- 2022-07-12 CN CN202210815683.0A patent/CN115345430A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115689397A (en) * | 2022-12-30 | 2023-02-03 | 北京和利时系统集成有限公司 | Water pump health degree determination method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110410282B (en) | SOM-MQE and SFCM (Small form-factor pluggable) based wind turbine generator health state online monitoring and fault diagnosis method | |
| CN111222290B (en) | Multi-parameter feature fusion-based method for predicting residual service life of large-scale equipment | |
| US6088658A (en) | Statistical pattern analysis methods of partial discharge measurements in high voltage insulation | |
| Subrahmanyam et al. | Using neural networks for the diagnosis of localized defects in ball bearings | |
| KR101948604B1 (en) | Method and device for equipment health monitoring based on sensor clustering | |
| CN108069308A (en) | A kind of electric staircase failure diagnosis method based on sequential probability | |
| CN113579851B (en) | Non-stationary drilling process monitoring method based on adaptive segmented PCA | |
| CN112393906B (en) | Method for diagnosing, classifying and evaluating health of weak signal fault of bogie bearing of metro vehicle | |
| CN111723850A (en) | Automatic verification equipment state evaluation method based on intelligent inspection system | |
| CN115345430A (en) | Health degree evaluation method and system of chip mounter | |
| JPWO2018146768A1 (en) | Defect factor estimation device and defect factor estimation method | |
| CN112116198A (en) | Data-driven process industrial state perception network key node screening method | |
| CN115828170B (en) | Fault detection method based on electronic control data of tunneling machine | |
| CN116380445A (en) | Equipment state diagnosis method and related device based on vibration waveform | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| CN114036656A (en) | Fault diagnosis method and device for wind turbine generator gearbox | |
| CN117706943B (en) | Self-adaptive control method and system for converter transformer valve side sleeve end screen voltage divider | |
| CN112016800B (en) | Feature selection method and system based on effectiveness index | |
| CN116910680B (en) | Remote fault detection method and system for fitness equipment | |
| CN117786461A (en) | Water pump fault diagnosis method, control device and storage medium thereof | |
| CN112859741A (en) | Method and system for evaluating operation reliability of sequential action units of machine tool | |
| CN116644348A (en) | Cross-mechanical part fault diagnosis method and device based on transfer type countermeasure migration | |
| CN111938594B (en) | Epilepsia electroencephalogram signal anomaly monitoring system and equipment based on hierarchical graph model | |
| Baruah et al. | An autonomous diagnostics and prognostics framework for condition-based maintenance | |
| CN114492636A (en) | Transformer winding state signal acquisition 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 |