CN117148784A - Operation fault analysis method for multi-axis multi-channel numerical control system - Google Patents
Operation fault analysis method for multi-axis multi-channel numerical control system Download PDFInfo
- Publication number
- CN117148784A CN117148784A CN202311404785.4A CN202311404785A CN117148784A CN 117148784 A CN117148784 A CN 117148784A CN 202311404785 A CN202311404785 A CN 202311404785A CN 117148784 A CN117148784 A CN 117148784A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- item
- incomplete
- acquisition
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 claims abstract description 616
- 238000012937 correction Methods 0.000 claims abstract description 38
- 230000008859 change Effects 0.000 claims abstract description 33
- 238000000034 method Methods 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 230000003321 amplification Effects 0.000 description 4
- 238000003199 nucleic acid amplification method Methods 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
- G05B19/4065—Monitoring tool breakage, life or condition
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/37—Measurements
- G05B2219/37616—Use same monitoring tools to monitor tool and workpiece
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an operation fault analysis method of a multi-axis multi-channel numerical control system, which comprises the following steps: acquiring monitoring data and incomplete data points of a plurality of monitoring items, acquiring standardized multidimensional data, acquiring a slope sequence of each monitoring item to obtain a covariant data set, and acquiring initial fitting data of each monitoring item according to the monitoring data; obtaining the influence weight of each monitoring item according to the covariant data set, and obtaining the neighborhood trend change degree of each incomplete data point of each monitoring item; obtaining correction coefficients of incomplete data points of each monitoring item according to the influence weight of each monitoring item and the neighborhood trend change degree; obtaining a correction fitting value according to the initial fitting data and the correction coefficient; and (3) completing the operation state monitoring of the multi-axis multi-channel numerical control system by using the corrected fitting value and an anomaly analysis algorithm. The invention aims to solve the problem of error in linear fitting by correcting and fitting incomplete running state monitoring data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an operation fault analysis method of a multi-axis multi-channel numerical control system.
Background
The multi-axis multi-channel numerical control system is an automatic control system for controlling a plurality of motion axes and channels, and is commonly used in the field of automatic production, and complex motion control is realized by programming the plurality of motion axes, distributing single-channel control or multi-channel control to simultaneously execute a plurality of motion tasks. Because the motion control of a plurality of shafts and channels is involved, fault analysis becomes more complex, and therefore, fault positioning and fault cause determination are required to be carried out on the real-time monitoring of the running state of the numerical control system, so that fault repair and fault prevention are realized.
In a multi-axis multi-channel numerical control system, the shaft position, the speed, the force applied by a servo motor and the like need to be cooperated with each other through NC programming, so that the running state needs to be monitored in real time, abnormal data are extracted for fault positioning and fault cause determination, and fault repair and fault prevention are realized. Thus, abnormality detection algorithms such as LOF outlier detection are used to extract abnormalities from the state monitoring data, and therefore the accuracy requirements for the state monitoring data are high. However, the state monitoring of the existing multi-axis multi-channel numerical control system is that because of the fact that the sensors are more and the acquisition time is inconsistent when each sensor acquires data, some sensors acquire data at certain time, but other sensors do not acquire data, and therefore the acquired data at certain time are incomplete, when the data are preprocessed and repaired, the interpolation is mainly repaired by using a least square method according to the adjacent value of time sequence, and the interpolation repaired data are easy to cause to be abnormal compared with other monitoring.
Disclosure of Invention
The invention provides an operation fault analysis method of a multi-axis multi-channel numerical control system, which aims to solve the problem that interpolation repaired data are easy to cause compared with other monitoring and displaying abnormality when the state data of the multi-axis multi-channel numerical control system are preprocessed and repaired in the prior art.
The invention relates to a multi-axis multi-channel numerical control system operation fault analysis method which adopts the following technical scheme:
the embodiment of the invention provides a method for analyzing the operation faults of a multi-axis multi-channel numerical control system, which comprises the following steps:
collecting monitoring data of a plurality of monitoring items and forming multi-dimensional monitoring data, acquiring the acquisition incomplete time of each monitoring item according to the acquisition time corresponding to the monitoring data, and recording the monitoring data corresponding to the acquisition incomplete time as incomplete data points;
recording any one monitoring item in the multi-dimensional monitoring data as a target monitoring item; normalizing the target monitoring data to obtain normalized monitoring data of the target monitoring data, and obtaining the slope of each incomplete data point in the target monitoring item according to the slope of the normalized monitoring data of the target monitoring item, wherein the slope of the normalized monitoring data of the target monitoring item and the slopes of all the incomplete data points in the target monitoring item form a slope sequence of the target monitoring item; obtaining a covariant data set of the target monitoring item according to the correlation between the slope sequence of the target monitoring item and the slope sequences of other monitoring items in the standardized multidimensional data; interpolation is carried out on incomplete data points of all monitoring items in the target monitoring items and the covariant data sets of the target monitoring items, and initial fitting data of each incomplete data point of the target monitoring items are obtained; recording any one monitoring item in the covariate data set of the target monitoring item as a reference monitoring item, and obtaining the influence weight of the reference monitoring item on the target monitoring item according to the target monitoring item and the slope sequence of the reference monitoring item; obtaining the neighborhood trend change degree of the reference monitoring item at the acquisition incomplete moment of the target monitoring item according to the neighborhood relation of the target monitoring item and the reference monitoring item at the acquisition incomplete moment; obtaining a correction coefficient of each incomplete data point of the target monitoring item according to the influence weight of the reference monitoring item and the neighborhood trend change degree of the acquisition incomplete time; obtaining a corrected fitting value of the target monitoring item according to the correction coefficient of the incomplete data point of the target monitoring item and the initial fitting data;
and obtaining complete monitoring data by using the corrected fitting value and the monitoring data, and detecting faults by using the complete monitoring data.
Further, the obtaining the acquisition incomplete time of each monitoring item includes:
in the monitoring data of the target monitoring item, the first item in the target monitoring item is selectedThe acquisition time of each monitoring data is recorded asItem number one of the target monitoring itemsThe collection time of each monitoring item is recorded asThe method comprises the steps of carrying out a first treatment on the surface of the Then in the acquisition time intervalAll the acquisition moments in between are recorded as acquisition incomplete moments of the target monitoring project.
Further, the obtaining the slope of each incomplete data point in the target monitoring item according to the slope of the standardized monitoring data of the target monitoring item includes:
item No. of target monitoringThe standardized monitoring data are recorded asItem of target monitoringIndividual standardized monitoring dataSlope of (2)The calculation method of (1) is as follows:
wherein,item number representing target monitoring itemThe data of the monitoring is normalized by the data of the monitoring,item number representing target monitoring itemThe time of acquisition of the individual monitoring data,item number representing target monitoring itemThe collection time of each monitoring data;
using standardised monitoring dataSlope of (2)Representing the acquisition time intervalSlope of all incomplete data points in (a).
Further, the obtaining the covariate data set of the target monitoring item includes:
recording any one of the monitoring items other than the target monitoring item as the monitoring itemCalculating slope sequence of target monitoring item and monitoring itemPearson correlation coefficient of slope sequence of (c)Presetting covariate thresholdWhen the object is monitored and the monitored item is monitoredPearson correlation coefficient of slope sequences of (c) satisfyTime, record and monitor the projectCovariate monitoring items for the target monitoring items; all covariate monitoring items of the target monitoring item constitute a covariate data set of the target monitoring item.
Further, the obtaining initial fit data for each incomplete data point of the target monitoring item includes:
item number one of the target monitoring itemsThe individual monitoring data are recorded asItem of target monitoringThe acquisition time of each monitoring data is recorded asItem number one of the target monitoring itemsThe individual monitoring data are recorded asItem of target monitoringThe acquisition time of each monitoring data is recorded asFor the acquisition time intervalA plurality of incomplete data points contained in the data processing system according to the monitoring dataAnd monitoring dataPerforming least square fitting interpolation on the incomplete data points to obtain interpolation results of the incomplete data points, and marking the interpolation results as acquisition time intervalsInitial fit data for each incomplete data point within.
Further, the obtaining the influence weight of the reference monitoring item on the target monitoring item includes:
marking the reference monitoring item asCovariate data set representing target monitoring itemA plurality of monitoring items, the monitoring items being referencedThe calculation mode of the influence weight on the target monitoring item is as follows:
in the middle ofFor reference monitoring itemsThe impact weight on the target monitoring item,for reference monitoring itemsPearson correlation coefficients with the slope sequence of the target monitored item,the total number of monitored items in the covariate data set for the target monitored item,to extract a sign function.
Further, the obtaining the neighborhood trend change degree of the reference monitoring item at the acquisition incomplete time of the target monitoring item includes:
marking the reference monitoring item asCovariate data set representing target monitoring itemA number of monitoring items, a number of target monitoring itemsThe acquisition time of each monitoring data is recorded asItem of target monitoringThe acquisition time of each monitoring data is recorded asAcquisition time interval of target monitoring itemBetween the first twoThe acquisition incomplete time of each incomplete data point is recorded asThen refer to the monitoring itemItem number in the target monitoring projectThe calculation mode of the neighborhood trend change degree at the acquisition incomplete time of each incomplete data point is as follows:
in the middle ofFor reference monitoring itemsItem number in the target monitoring projectThe extent of neighborhood trend change at the time of acquisition of the incomplete data points,for reference monitoring itemsIs used for the monitoring of the average value of the data,representing a reference data point;representing the time interval of acquisitionInner firstAcquisition of incomplete data points the first in the analysis neighborhood at the moment of incomplete acquisitionThe number of data to be monitored is determined,andrespectively represent target monitoring items and reference monitoring itemsIs a collection period of (a);
at the reference monitoring projectSelecting and collecting malpractice timeThe nearest monitoring data is recorded as reference data point；
Selecting items including reference monitoring itemsReference data points of (2)Left side of the insideIndividual monitoring data and reference monitoring itemsReference data points of (2)Right sideThe monitoring data is used as an analysis neighborhood of the incomplete data points.
Further, the obtaining the correction coefficient of each incomplete data point of the target monitoring item includes:
marking the reference monitoring item asCovariate data set representing target monitoring itemA number of monitoring items, a number of target monitoring itemsThe acquisition time of each monitoring data is recorded asItem of target monitoringThe acquisition time of each monitoring data is recorded as；
In the middle ofAcquisition time interval representing target monitoring itemIn (1)Acquisition of incomplete data pointsIs used to determine the correction coefficients of the initial fitting data,representation purposeTarget monitoring item is in target monitoring itemThe extent of neighborhood trend change at the time of acquisition of the incomplete data points,for reference monitoring itemsItem number in the target monitoring projectThe extent of neighborhood trend change at the time of acquisition of the incomplete data points,reference monitoring items in covariate data setsThe impact weight on the target monitoring item,the total number of items in the covariate data set for the target monitored item.
Further, the obtaining the corrected fitting value of the target monitoring item includes:
item number one of the target monitoring itemsThe acquisition time of each monitoring data is recorded asItem of target monitoringThe acquisition time of each monitoring data is recorded asAcquisition time interval of target monitoring itemBetween the first twoAcquisition of the amount of incomplete data pointsThe calculation mode of the correction fitting value is as follows:
in the middle ofAcquisition time interval for target monitoring itemBetween the first twoMoment of acquisition incompleteIs used to correct the fitting value of the (c),acquisition time interval for target monitoring itemBetween the first twoMoment of acquisition incompleteIs used to determine the initial fit data of the (c),acquisition time interval for target monitoring itemIn (1)Acquisition of incomplete data pointsIs used to determine the correction factors for the initial fit data.
Further, the obtaining the complete monitoring data by using the corrected fitting value and the monitoring data, and the fault detection by using the complete monitoring data includes:
the corrected fitting value of each acquisition incomplete time of the target monitoring item and all monitoring data are arranged according to time sequence to obtain the complete monitoring data of the target monitoring item, the complete monitoring data of all monitoring items are obtained, the complete monitoring data of all monitoring items are input into an LOF algorithm to obtain abnormal data points, and the acquisition time corresponding to the abnormal data points is recorded as the time of the operation fault.
The technical scheme of the invention has the beneficial effects that: according to the invention, the monitoring data and incomplete data points are obtained by collecting a plurality of monitoring items in the running process of the multi-axis multi-channel numerical control system, multi-dimensional monitoring data are obtained, standardized multi-dimensional data are obtained by standardizing the multi-dimensional data, and error problems caused by different accuracy of the monitoring data are eliminated; the slope sequence of each monitoring data is obtained by analyzing slope assignment of each monitoring data slope to incomplete data points, a covariant data set of each monitoring item is obtained, and the problem that monitoring data of different monitoring items cannot be in one-to-one correspondence due to different acquisition periods of different monitoring items is solved; the influence weight of each monitoring item is obtained by analyzing the covariant data set of each monitoring item, the neighborhood trend change degree of each monitoring item at each acquisition incomplete moment is obtained, the correction coefficient of each monitoring item is obtained according to the neighborhood trend change degree, the initial fitting data of each incomplete data point is obtained by using a least square method, the initial fitting data is corrected according to the correction coefficient, the correction fitting value of each monitoring item is obtained, the running state of the multi-axis multi-channel numerical control system is monitored according to the correction fitting value, and the problem that the data obtained by traditional interpolation fitting is abnormal compared with other monitoring is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for analyzing operation faults of a multi-axis multi-channel numerical control system.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a multi-axis multi-channel numerical control system operation fault analysis method according to the invention, which is specific to the implementation, structure, characteristics and effects thereof, with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of an embodiment may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the operation fault analysis method of the multi-axis multi-channel numerical control system provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart illustrating a method for analyzing an operation fault of a multi-axis multi-channel numerical control system according to an embodiment of the present invention is shown, the method includes the following steps:
and S001, collecting monitoring data of a plurality of monitoring items, obtaining monitoring data of each monitoring item at the collection time and collecting incomplete data points at the incomplete time, and obtaining multidimensional monitoring data of the plurality of monitoring items.
The purpose of the embodiment is to correct the defect data in the operation monitoring data of the multi-axis multi-channel numerical control system, and to be used for analyzing the operation faults of the numerical control system, so that the monitoring data of the operation state of the multi-axis multi-channel numerical control system is required to be collected firstly; the method comprises the steps of monitoring running data of a numerical control system by using sensors comprising monitoring items such as positions, speeds, accelerations and temperatures of a transmission shaft, acquiring a collection period of each sensor, recording running state data of the numerical control system acquired by the monitoring items at every other collection period as monitoring data of the monitoring items at the collection moment, and acquiring time sequence data of each monitoring item at each collection moment to form one-dimensional monitoring data.
It should be noted that, because the acquisition period of the sensor is inconsistent when each monitoring item acquires data, some monitoring items acquire monitoring data at some acquisition moments, and other monitoring items do not acquire monitoring data at the acquisition moments, so that the monitoring data at the acquisition moments are missing, interpolation and complementation are required to be performed on the missing monitoring data, and the method is used for operation fault analysis of the multi-axis multi-channel numerical control system.
Specifically, acquiring the acquisition time of all the monitoring data of all the monitoring items, and arranging all the acquisition time of all the monitoring data according to a time sequence to obtain an acquisition sequence, wherein the acquisition sequence is a sequence subjected to de-duplication. In monitoring projectsIs to monitor the item in the one-dimensional monitoring data of (1)Middle (f)The acquisition time of each monitoring data is recorded asItems are to be monitoredThe first of (3)The collection time of each monitoring item is recorded asThe method comprises the steps of carrying out a first treatment on the surface of the Then in interval in the acquisition sequenceAll the acquisition moments in between are recorded as monitoring itemsIs the time of acquisition of malpractice of (1)WhereinRepresenting that is in the intervalBetween the first twoThe moment of the incomplete collection is that,，representing a monitored itemThe number and the length of the data are monitored.
It should be noted that, since the items are monitoredAt the position ofNo monitoring data is collected at all times in between, so the project is monitoredIs missing, and the missing monitoring data is recorded as a monitoring itemIs a incomplete data point of (c).
And similarly, acquiring all the collection incomplete moments and incomplete data points of each monitoring item, wherein the monitoring data and the incomplete data points of all the monitoring items form multi-dimensional monitoring data, each dimension of the multi-dimensional monitoring data is one monitoring item, a plurality of monitoring data and incomplete data points are arranged in each dimension, and the monitoring data and the incomplete data are distributed on the collection sequence.
Thus, the multidimensional monitoring data of all the monitoring items are obtained.
Step S002, standardized multidimensional data is obtained by standardization of the multidimensional monitoring data, the slope of incomplete data points of each monitoring item is obtained according to the monitoring data of each monitoring item in the standardized multidimensional data, and the covariant data set of each monitoring item is obtained according to the slope of each incomplete data point of each monitoring item.
It should be noted that, after the multidimensional monitoring data is obtained, because the numerical control system is operated cooperatively, that is, there is a certain covariance in the monitoring data of different projects, the interpolation fitting of the incomplete data points by linear fitting is easy to cause the fitted data points to be normal compared with the current monitoring project, but abnormal to other monitoring projects, so the embodiment interpolates the multidimensional monitoring data by the covariance relation of the data of different monitoring projects to obtain the corrected interpolation deficiency value; however, because the monitoring frequencies of different monitoring items are different, the collection time of the monitoring data of each monitoring item is not necessarily aligned, so that after the multi-dimensional monitoring data is standardized, the amplification degree of the monitoring data of each monitoring item is analyzed, and the covariant data set of each monitoring item is obtained and used for correcting interpolation fitting of incomplete data points.
In the operation monitoring process of the multi-axis multi-channel numerical control system, the accuracy of each monitoring item is different so that the data distribution of the multi-dimensional monitoring data is different, therefore, the monitoring data of each monitoring item needs to be standardized to obtain standardized multi-dimensional data.
In particular, to monitor itemsIs the first of (2)Individual monitoring dataFor example, then monitor the projectIs the first of (2)Individual monitoring dataIs a standardized monitoring data of (a)The calculation method of (1) is as follows:
wherein,to monitor itemsIs the first of (2)Individual monitoring dataIs provided with a standardized monitoring data of the (c),represents the maximum and minimum normalization functions, the normalization range is. By normalizing the monitoring data, each monitoring item is inspectedThe measured data are distributed inAnd the distribution range of the monitoring data of each monitoring item is limited. And similarly, normalizing each monitoring data of each monitoring item in the multi-dimensional monitoring data to obtain all the normalized monitoring data, wherein all the normalized monitoring data form the normalized multi-dimensional data.
It should be further noted that the objective of the present embodiment is to correct interpolation and deficiency for incomplete data points in monitoring items by analyzing different monitoring items with covariances, so that it is first necessary to obtain covariate data sets of each monitoring item for monitoring operation faults of the multi-axis multi-channel numerical control system. Since the collection period of each monitoring item is different, so that the monitoring data does not necessarily exist at each collection time of one monitoring item in the standardized multidimensional data, the embodiment indicates the amplification in the adjacent collection time through the slope of each monitoring item, and assigns a value to each incomplete data point by using the amplification, so that all the incomplete data points of different monitoring items have physical significance when analyzing the covariances of different monitoring items.
Further, for the amplification of the monitored data, if a covariant relationship is presented between the data, then when the monitored itemWhen the monitoring data of (a) trend changes, the monitoring data and the monitoring projectThe trend of the monitoring data of the monitoring items with covariances shows positive correlation change or negative correlation change. The present embodiment thus uses the slope of each monitor data to represent trend changes, and obtains covariate data sets for each monitor item from the slope of each monitor data and incomplete data points.
In particular, to monitor itemsIs the first of (2)Individual standardized monitoring dataFor example, monitor itemsIs the first of (2)Individual standardized monitoring dataSlope of (2)The calculation method of (1) is as follows:
wherein,representing a monitored itemIs the first of (2)Individual standardized monitoring dataIs used to determine the slope of the (c) for the (c),representing a monitored itemIs the first of (2)The data of the monitoring is normalized by the data of the monitoring,representing a monitored itemIs the first of (2)The data of the monitoring is normalized by the data of the monitoring,representing a monitored itemIs the first of (2)The time of acquisition of the individual monitoring data,representing a monitored itemIs the first of (2)The acquisition time of each monitoring data.
Due to the monitoring of itemsAdjacent standardized monitoring dataAndbetween which are incomplete data points, trend of which and standardized monitoring dataAndthe trend of (2) is the same, and thus for the acquisition time intervalSlope of incomplete data points at all acquisition incomplete moments in using standardized monitoring dataAndslope betweenAnd (3) representing. Similarly, the monitoring item is obtainedThe slope of all the incomplete data points at the time of acquisition of the incomplete data points and the slope of the incomplete data points at the time of acquisition of the incomplete data points form a monitoring itemIs a slope sequence of (a).
Similarly, calculating the slope of each piece of standardized monitoring data and adjacent pieces of monitoring data in the standardized multidimensional data, and using the slope to assign a value to the slope of each incomplete data point at the moment of acquisition of the incomplete, so as to obtain the slope of all monitoring items in the standardized multidimensional data, and obtain a slope sequence of each monitoring item.
Further, a monitoring item is obtainedAfter the slope values of the acquisition sequences of (2), calculating the monitoring item according to the slopes of all the acquisition sequences in the standardized multidimensional dataIn addition to monitoring items in the slope sequence and normalized multidimensional data of (1)Monitoring items other thanPearson correlation coefficient of slope sequence of (c)The value range of the pearson correlation coefficient isWhen monitoring itemsMonitoring itemsPearson correlation coefficient of slope sequence of (c)The monitoring item is described when the value approaches 1Monitoring itemsThe more likely it is that the change trend of (a) is the same; when monitoring itemsMonitoring itemsPearson correlation coefficient of slope sequence of (c)The value approaches to-1, the monitoring item is describedMonitoring itemsThe larger the variation trend difference of (2) is, the more likely it is that the negative correlation is; when monitoring itemsMonitoring itemsPearson correlation coefficient of slope sequence of (c)The more the value isApproaching 0, the monitoring item is describedMonitoring itemsThe more likely it is uncorrelated.
Further, preset covariate thresholdThe present embodiment takes covariate thresholdTo describe, when monitoring itemsMonitoring itemsPearson correlation coefficient of slope sequences of (c) satisfyAt the time, the monitoring item is describedMonitoring itemsPresenting greater positive or negative covariances, then recording the monitored itemTo monitor itemsIs a covariate monitoring project; when monitoring itemsMonitoring itemsPearson correlation coefficient of slope sequences of (c) satisfyAt the time, the monitoring item is describedMonitoring itemsNo covariances exist, no monitoring items are aimed atProcessing; computing a monitoring itemAnd normalizing the divide monitor project in the multidimensional dataThe pearson correlation coefficient of the slope sequence of all other monitoring items is judged by the covariant threshold value to obtain the monitoring itemsAll covariate monitoring items of (1), all covariate monitoring items constitute monitoring itemsCovariate data sets of (1). Similarly, a covariate data set is obtained for each monitored item.
Thus, a covariate data set for each monitored item is obtained.
And S003, fitting interpolation is carried out on each monitoring item and the incomplete data points in the covariant data set of the monitoring item by using a least square method, and initial fitting data of each incomplete data point are obtained.
After the covariant data set of each monitoring item is obtained, the monitoring item and the variation trend of the monitoring data of each monitoring item in the covariant data set are the same or opposite, and the incomplete data points in each monitoring item of the multidimensional monitoring data and the monitoring items in the covariant data set of the monitoring item are subjected to fitting interpolation by a least square method to obtain all initial fitting data of each monitoring item and each monitoring item in the covariant data set of the monitoring item.
In particular, to monitor itemsIs the first of (2)Individual monitoring dataFor example, monitor itemsIs the first of (2)The individual monitoring data areThen (1)Individual monitoring dataAnd (d)Individual monitoring dataAcquisition time interval of (a)Is shared byThe incomplete data points are the data to be interpolated, and then to the firstIndividual monitoring dataAnd (d)Individual monitoring dataAll the data to be interpolated are interpolated by using a least square method, and then the time interval is acquiredInner firstInterpolation results of incomplete data points at the time of acquisition of incomplete are recorded as the firstMoment of acquisition incompleteInitial fitting data of (a). Similarly, for the monitoring itemsMonitoring itemsFitting interpolation is carried out on the incomplete data points of each acquisition incomplete moment in the covariate data set, and initial fitting data of all acquisition incomplete moments are obtained.
And similarly, fitting interpolation is carried out on incomplete data points at the acquisition incomplete time of all the monitoring items through a least square method, so as to obtain initial fitting data of all the monitoring items.
To this end, the initial fitting data of all the incomplete data points are obtained by fitting interpolation of the incomplete data points in the multidimensional monitoring data by a least square method.
S004, obtaining influence weights of each monitoring item in the covariant data set according to the Pearson correlation coefficient of each monitoring item and each monitoring item in the covariant data set, obtaining the neighborhood trend change degree of the collection incomplete moment of each monitoring item according to the neighborhood change of the monitoring data of each monitoring item and each monitoring item in the covariant data set, and obtaining the correction coefficient of the collection incomplete moment of each monitoring item according to the neighborhood trend change degree and the influence weights.
The monitoring items are obtained through the stepsCovariate data sets of (1)Later, due to each monitoring item and each monitoring item in the covariate data setSuch that each monitored item in the covariate data set is different from monitored item to monitored item when the initial fit data is modifiedThe reference degree of (2) is different, so that the embodiment is based on each monitoring item in the covariate data setThe pearson correlation coefficient of the slope sequence of (2) to obtain each monitoring item to monitoring item in the covariant data setIs used to influence the weight.
Specifically, by covariating data setsMiddle (f)Individual monitoring itemsFor example, then covariate data setsMiddle (f)Individual monitoring itemsFor monitoring itemsThe calculation mode of the influence weight of (a) is as follows:
in the middle ofFor covariate data setsMiddle (f)Individual monitoring itemsFor monitoring itemsIs used for the influence weight of the (c) in the (c),to monitor itemsAnd monitor itemsPearson correlation coefficients of the slope sequence of (c),to monitor itemsCovariate data sets of (1)Medium monitoring itemThe total number of the orders is set,to extract the sign function, the representationIs the sign of (c). Calculation and monitoring items according to pearson correlation coefficient of slope sequenceFirst of existence of covariancesIndividual monitoring itemsFor monitoring itemsIs used for the influence weight of the (c) in the (c),the larger the instruction of the monitoring itemAnd monitor itemsThe greater the intensity of the covariances of (a) then the more the item is monitoredIs the first in the covariate data set during the initial fit data correctionIndividual monitoring itemsFor monitoring itemsThe greater the reference level of (2);representing a monitored itemFor monitoring itemsPositive and negative correlation is exhibited.
Monitoring itemsIs the first of (2)Individual monitoring dataFor example, monitor itemsIs the first of (2)The individual monitoring data areThen (1)Individual monitoring dataAnd (d)Individual monitoring dataAcquisition time interval of (a)Is shared byThe individual incomplete data points are the data to be interpolated,
further, the monitoring itemIs the first of (2)Individual monitoring dataAnd (d)Individual monitoring dataAcquisition time interval of (a)Among them are incomplete data points, and the use of the monitoring itemWhen the covariate data set of (a) obtains the correction coefficients of all the initial fitting data in the acquisition time interval, the embodiment uses the monitoring items because the monitoring data does not necessarily exist at each acquisition time of the plurality of monitoring items, that is, the data which can be used for analyzing the covariate relationship does not existCovariate data sets of (1)The difference of analysis neighborhood of each incomplete data point of each monitoring item to obtain covariate data setNeighborhood trend change for each incomplete data point of the item.
In particular, to monitor itemsAcquisition time interval of (a)Between the first twoMoment of acquisition incompleteFor example, then covariate data setsIs the first of (2)Individual monitoring itemsIn monitoring projectsThe first of (3)The calculation mode of the neighborhood trend change degree at the acquisition incomplete time of each incomplete data point is as follows:
in the middle ofIs the firstIndividual monitoring itemsIn monitoring projectsThe first of (3)The extent of neighborhood trend change at the time of acquisition of the incomplete data points,to monitor itemsCovariates of (1)Data collectionMiddle (f)Individual monitoring itemsIs used for the monitoring of the average value of the data,representing reference data pointsThe acquisition mode of (a) is as follows: in the first placeIndividual monitoring itemsSelecting and collecting malpractice timeIs recorded as a reference data point。
Andrespectively represent monitoring itemsAnd monitor itemsIs a collection period of (a); first, theIndividual monitoring dataIs the time of acquisition of malpractice of (1)The analysis neighborhood of the incomplete data point is obtained by the following steps: acquisition of the firstIndividual monitoring dataIs the time of acquisition of malpractice of (1)After the reference data points of (1) are selected to includeIndividual monitoring itemsReference data points of (2)Left side of the insidePersonal monitoring data, the firstIndividual monitoring itemsReference data points of (2)Right sideMonitoring data as an analysis neighborhood of incomplete data points; if the reference data point isThen the left or right side is deficientAnd (3) monitoring data, and calculating the number of the monitoring data by the number of the monitoring data.Representing the time interval of acquisitionInner firstThe first in the analysis neighborhood of the moment of acquisition defectAnd monitoring data.
Represent the firstIndividual monitoring itemsReference data points of (2)The degree of difference between the method and the analysis of the monitoring data in the adjacent area is larger to indicate the datum pointThe greater the degree of difference from the monitored data in the acquisition cycle interval, then the more the item is monitoredIs the first of (2)Acquisition of incomplete data pointsData correction fitting, the firstIndividual monitoring itemsThe greater the reference of (2);to the first pairIndividual monitoring itemsIs a value specification coefficient of (a).
Similarly, the monitoring items are obtainedEach monitoring item in the covariate data set of (1) is associated with a monitoring itemThe neighborhood trend change degree at the same time as all the acquisition incomplete time.
Further, according to the neighborhood trend change degree of all the collection incomplete moments of each monitoring item, combining the monitoring itemsEach monitoring item in the covariate data set is to a monitoring itemIs used for obtaining the influence weight of the monitoring itemIs used to determine the correction coefficients for all initial fit data.
Specifically, a neighborhood trend change degree calculation method is used for obtaining monitoring itemsIn monitoring projectsThe first of (3)Extent of neighborhood trend change at acquisition incomplete time of each incomplete data pointMonitoring itemsAcquisition time interval of (a)In (1)Acquisition of incomplete data pointsThe calculation mode of the correction coefficient of the initial fitting data is as follows:
in the middle ofMonitoring itemsAcquisition time interval of (a)In (1)Acquisition of incomplete data pointsIs used to determine the correction coefficients of the initial fitting data,representing a monitored itemIn monitoring projectsThe first of (3)The extent of neighborhood trend change at the time of acquisition of the incomplete data points,is the firstIndividual monitoring itemsIn monitoring projectsThe first of (3)The extent of neighborhood trend change at the time of acquisition of the incomplete data points,andthe calculation method of (a) is the same,monitoring items in covariate data setsFor monitoring itemsIs used for the influence weight of the (c) in the (c),to monitor itemsCovariate data sets of (1)The total number of items is monitored. When correcting coefficientAt the time, the monitoring item is describedThe variation of (2) is smaller than the variation of other monitoring items with covariate relation, so the fitting data should be increased for correction; when correcting coefficientMonitoring itemsThe variation of (2) is larger than the variation of other monitoring items with covariate relation, so the fitting data should be reduced for correction; when correcting coefficientMonitoring itemsThe initial fit data is unchanged as compared to the other monitored items with covariances.
Similarly, correction coefficients for all initial fit data for all monitored items are obtained.
So far, the correction coefficients of the initial fitting data of all the monitoring items are obtained.
S005, correcting the initial fitting data by using the correction coefficient to obtain a corrected fitting value of each monitoring item.
After the correction coefficient and the initial fitting data of each monitoring item in the initial fitting data of each monitoring item are obtained, the initial fitting data is corrected by using the correction coefficient, and a corrected fitting value of each monitoring item in the acquisition incomplete moment of each incomplete data point is obtained.
Specifically, the project is monitoredAcquisition time interval of (a)Between (a) and (b)First, theMoment of acquisition incompleteThe calculation mode of the correction fitting value is as follows:
in the middle ofTo monitor itemsAcquisition time interval of (a)Between the first twoAcquisition of incomplete data pointsIs used to correct the fitting value of the (c),to monitor itemsAcquisition time interval of (a)In (1)Acquisition of incomplete data pointsIs used to determine the initial fit data of the (c),to monitor itemsAcquisition time interval of (a)Between the first twoAcquisition of incomplete data pointsIs used to determine the correction factors for the initial fit data. Usage monitoring projectIs the first of (2)Acquisition of incomplete data pointsTo initial fit dataCorrection to obtain monitoring itemsIs the first of (2)Acquisition of incomplete data pointsIs a modified fit value of (2)When correcting coefficientWhen the corrected fitting value is larger than the initial fitting data; when correcting coefficientWhen the corrected fitting value is smaller than the initial fitting data; when correcting coefficientThe corrected fitting value is unchanged from the initial fitting data.
Similarly, use the monitoring projectThe correction coefficients and the initial fitting data of the acquisition incomplete time of all incomplete data points of each monitoring item obtain all correction fitting values of each monitoring item.
So far, all corrected fitting values of all monitoring items are obtained.
S006, obtaining complete monitoring data by using the corrected fitting value and the monitoring data, and performing fault analysis by using the complete monitoring data.
Specifically, the corrected fitting value of each acquisition incomplete time of each monitoring item and all monitoring data are arranged according to time sequence to obtain the complete monitoring data of each monitoring item, the complete monitoring data of all monitoring items are obtained in a similar way, the complete monitoring data of all monitoring items are input into an LOF algorithm to obtain abnormal data points, the acquisition time corresponding to the abnormal data points is the time of operation faults, and the monitoring data of the time of all operation faults are used for fault analysis. Wherein the method comprises the steps ofThe algorithm is a known technology, and this embodiment is not described herein.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The operation fault analysis method of the multi-axis multi-channel numerical control system is characterized by comprising the following steps of:
collecting monitoring data of a plurality of monitoring items and forming multi-dimensional monitoring data, acquiring the acquisition incomplete time of each monitoring item according to the acquisition time corresponding to the monitoring data, and recording the monitoring data corresponding to the acquisition incomplete time as incomplete data points;
recording any one monitoring item in the multi-dimensional monitoring data as a target monitoring item; normalizing the target monitoring data to obtain normalized monitoring data of the target monitoring data, and obtaining the slope of each incomplete data point in the target monitoring item according to the slope of the normalized monitoring data of the target monitoring item, wherein the slope of the normalized monitoring data of the target monitoring item and the slopes of all the incomplete data points in the target monitoring item form a slope sequence of the target monitoring item; obtaining a covariant data set of the target monitoring item according to the correlation between the slope sequence of the target monitoring item and the slope sequences of other monitoring items in the standardized multidimensional data; interpolation is carried out on incomplete data points of all monitoring items in the target monitoring items and the covariant data sets of the target monitoring items, and initial fitting data of each incomplete data point of the target monitoring items are obtained; recording any one monitoring item in the covariate data set of the target monitoring item as a reference monitoring item, and obtaining the influence weight of the reference monitoring item on the target monitoring item according to the target monitoring item and the slope sequence of the reference monitoring item; obtaining the neighborhood trend change degree of the reference monitoring item at the acquisition incomplete moment of the target monitoring item according to the neighborhood relation of the target monitoring item and the reference monitoring item at the acquisition incomplete moment; obtaining a correction coefficient of each incomplete data point of the target monitoring item according to the influence weight of the reference monitoring item and the neighborhood trend change degree of the acquisition incomplete time; obtaining a corrected fitting value of the target monitoring item according to the correction coefficient of the incomplete data point of the target monitoring item and the initial fitting data;
and obtaining complete monitoring data by using the corrected fitting value and the monitoring data, and detecting faults by using the complete monitoring data.
2. The method for analyzing the operation fault of the multi-axis multi-channel numerical control system according to claim 1, wherein the obtaining the collection incomplete time of each monitoring item comprises:
in the monitoring data of the target monitoring item, the first item in the target monitoring item is selectedThe acquisition time of each monitoring data is marked as +.>The +.>The acquisition time of each monitoring item is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the Then +.>All the acquisition moments in between are recorded as acquisition incomplete moments of the target monitoring project.
3. The method for analyzing the operation fault of the multi-axis and multi-channel numerical control system according to claim 1, wherein the step of obtaining the slope of each incomplete data point in the target monitoring item according to the slope of the standardized monitoring data of the target monitoring item comprises the steps of:
item No. of target monitoringThe normalized monitoring data is recorded as +.>Then the target monitors item +.>Normalized monitoring data->Slope of +.>The calculation method of (1) is as follows:
wherein,represents the +.>Normalized monitoring data->Represents the +.>Time of acquisition of individual monitoring data,/->Represents the +.>The collection time of each monitoring data;
using standardised monitoring dataSlope of +.>Representing the acquisition time interval +.>Slope of all incomplete data points in (a).
4. The method for analyzing the operation fault of the multi-axis multi-channel numerical control system according to claim 1, wherein the obtaining the covariate data set of the target monitoring item comprises:
any one of the monitoring items except the target monitoring itemRecorded as a monitoring itemCalculating the slope sequence of the target monitoring item and the monitoring item +.>Pearson correlation coefficient of slope sequence +.>Preset covariate threshold +.>When the target monitoring item and the monitoring item +.>The pearson correlation coefficient of the slope sequence of (2) satisfies +.>Recording the monitoring item->Covariate monitoring items for the target monitoring items; all covariate monitoring items of the target monitoring item constitute a covariate data set of the target monitoring item.
5. The method of claim 1, wherein obtaining initial fit data for each incomplete data point of a target monitoring item comprises:
item number one of the target monitoring itemsThe individual monitoring data are recorded as->Item>The acquisition time of each monitoring data is marked as +.>The +.>The individual monitoring data are recorded as->Item>The acquisition time of each monitoring data is marked as +.>For the acquisition time interval +.>The number of incomplete data points included in the data are +.>And monitoring data->Performing least square fitting interpolation on the incomplete data points to obtain interpolation results of the incomplete data points, and marking the interpolation results as acquisition time intervals +.>Initial fit data for each incomplete data point within.
6. The method for analyzing the operation fault of the multi-axis multi-channel numerical control system according to claim 1, wherein the step of obtaining the influence weight of the reference monitoring item on the target monitoring item comprises the steps of:
marking the reference monitoring item asFirst +.in covariate data set representing target monitoring item>A monitoring item, reference monitoring item->The calculation mode of the influence weight on the target monitoring item is as follows:
in the middle ofFor reference monitoring items->Influence weight on target monitoring item, +.>For reference monitoring items->Pearson correlation coefficient with slope sequence of target monitoring item, +.>Total number of monitoring items in covariate data set for target monitoring item, +.>To extract a sign function.
7. The method for analyzing the operation fault of the multi-axis multi-channel numerical control system according to claim 1, wherein the step of obtaining the neighborhood trend change degree of the reference monitoring item at the acquisition incomplete time of the target monitoring item comprises the steps of:
marking the reference monitoring item asFirst +.in covariate data set representing target monitoring item>The monitoring item>The acquisition time of each monitoring data is marked as +.>Item>The acquisition time of each monitoring data is marked as +.>Acquisition time interval of target monitoring item +.>The%>Acquisition of the incomplete data points the time of the acquisition of the incomplete data points is marked as +.>Reference to the monitoring item->The +.>The calculation mode of the neighborhood trend change degree at the acquisition incomplete time of each incomplete data point is as follows:
in the middle ofFor reference monitoring items->The +.>Neighborhood trend change degree at acquisition incomplete time of each incomplete data point, < ->For reference monitoring items->Mean value of the monitored data of>Representing a reference data point; />Indicating +.>Interior (I)>The analysis neighborhood of the moment of acquisition of the malformed data points +.>Personal monitoring data,/->And->Respectively representing the target monitoring item and the reference monitoring item +.>Is a collection period of (a);
at the reference monitoring projectSelecting and collecting malposition moment->The nearest monitoring data is recorded as reference data point；
Selecting items including reference monitoring itemsReference data point->Left side of the inner part->Individual monitoring data, reference monitoring item->Reference data point->Right side->The monitoring data is used as an analysis neighborhood of the incomplete data points.
8. The method for analyzing the operation fault of the multi-axis multi-channel numerical control system according to claim 1, wherein the obtaining the correction coefficient of each incomplete data point of the target monitoring item comprises:
marking the reference monitoring item asFirst +.in covariate data set representing target monitoring item>A monitoring item, the +.>The acquisition time of each monitoring data is marked as +.>Item>The acquisition time of each monitoring data is marked as +.>；
In the middle ofAcquisition time interval representing target monitoring item +.>In->Acquisition of individual malformed data points malformed time +.>Correction coefficients of the initial fitting data of +.>Indicating the +.f of the target monitoring item in the target monitoring item>Neighborhood trend change degree at acquisition incomplete time of each incomplete data point, < ->For reference monitoring items->The +.>Neighborhood trend change degree at acquisition incomplete time of each incomplete data point, < ->Reference monitoring item in covariate data set>Influence weight on target monitoring item, +.>The total number of items in the covariate data set for the target monitored item.
9. The method for analyzing the operation fault of the multi-axis and multi-channel numerical control system according to claim 1, wherein the obtaining the corrected fitting value of the target monitoring item comprises:
item number one of the target monitoring itemsThe acquisition time of each monitoring data is marked as +.>Order ofTarget monitor item->The acquisition time of each monitoring data is marked as +.>Acquisition time interval of target monitoring item +.>The%>Acquisition of the individual malformed data points +.>The calculation mode of the correction fitting value is as follows:
in the middle ofAcquisition time interval for target monitoring item +.>The%>Acquisition malpractice +.>Is a modified fit value of>Acquisition time interval for target monitoring item +.>The%>Acquisition malpractice +.>Is>Acquisition time interval for target monitoring item +.>In->Acquisition of individual malformed data points malformed time +.>Is used to determine the correction factors for the initial fit data.
10. The method for analyzing the operation fault of the multi-axis multi-channel numerical control system according to claim 1, wherein the obtaining the complete monitoring data by using the corrected fitting value and the monitoring data, and the fault detection by using the complete monitoring data comprises:
the corrected fitting value of each acquisition incomplete time of the target monitoring item and all monitoring data are arranged according to time sequence to obtain the complete monitoring data of the target monitoring item, the complete monitoring data of all monitoring items are obtained, the complete monitoring data of all monitoring items are input into an LOF algorithm to obtain abnormal data points, and the acquisition time corresponding to the abnormal data points is recorded as the time of the operation fault.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311404785.4A CN117148784B (en) | 2023-10-27 | 2023-10-27 | Operation fault analysis method for multi-axis multi-channel numerical control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311404785.4A CN117148784B (en) | 2023-10-27 | 2023-10-27 | Operation fault analysis method for multi-axis multi-channel numerical control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117148784A true CN117148784A (en) | 2023-12-01 |
| CN117148784B CN117148784B (en) | 2024-01-26 |
Family
ID=88884644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311404785.4A Active CN117148784B (en) | 2023-10-27 | 2023-10-27 | Operation fault analysis method for multi-axis multi-channel numerical control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117148784B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574305A (en) * | 2024-01-17 | 2024-02-20 | 阿尔卑斯***集成(大连)有限公司 | Real-time monitoring method and system for running state of equipment |
| CN117786584A (en) * | 2024-02-27 | 2024-03-29 | 西安中创博远网络科技有限公司 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
| CN117892248A (en) * | 2024-03-15 | 2024-04-16 | 山东鲁新国合节能环保科技有限公司 | Abnormal data monitoring method in sintering flue gas internal circulation process |
| CN117909908A (en) * | 2024-03-15 | 2024-04-19 | 头等舱互联科技(深圳)有限公司 | Intelligent monitoring method for running state of shared massage chair |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649579A (en) * | 2016-11-17 | 2017-05-10 | 苏州航天***工程有限公司 | Time-series data cleaning method for pipe net modeling |
| CN109086804A (en) * | 2018-07-12 | 2018-12-25 | 中石化石油机械股份有限公司 | A kind of hydraulic device fault forecast method merged based on multi source status monitoring information and reliability characteristic |
| CN115987295A (en) * | 2023-03-20 | 2023-04-18 | 河北省农林科学院 | Crop monitoring data efficient processing method based on Internet of things |
-
2023
- 2023-10-27 CN CN202311404785.4A patent/CN117148784B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649579A (en) * | 2016-11-17 | 2017-05-10 | 苏州航天***工程有限公司 | Time-series data cleaning method for pipe net modeling |
| CN109086804A (en) * | 2018-07-12 | 2018-12-25 | 中石化石油机械股份有限公司 | A kind of hydraulic device fault forecast method merged based on multi source status monitoring information and reliability characteristic |
| CN115987295A (en) * | 2023-03-20 | 2023-04-18 | 河北省农林科学院 | Crop monitoring data efficient processing method based on Internet of things |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574305A (en) * | 2024-01-17 | 2024-02-20 | 阿尔卑斯***集成(大连)有限公司 | Real-time monitoring method and system for running state of equipment |
| CN117574305B (en) * | 2024-01-17 | 2024-04-05 | 阿尔卑斯***集成(大连)有限公司 | Real-time monitoring method and system for running state of equipment |
| CN117786584A (en) * | 2024-02-27 | 2024-03-29 | 西安中创博远网络科技有限公司 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
| CN117786584B (en) * | 2024-02-27 | 2024-04-30 | 西安中创博远网络科技有限公司 | Big data analysis-based method and system for monitoring and early warning of water source pollution in animal husbandry |
| CN117892248A (en) * | 2024-03-15 | 2024-04-16 | 山东鲁新国合节能环保科技有限公司 | Abnormal data monitoring method in sintering flue gas internal circulation process |
| CN117909908A (en) * | 2024-03-15 | 2024-04-19 | 头等舱互联科技(深圳)有限公司 | Intelligent monitoring method for running state of shared massage chair |
| CN117892248B (en) * | 2024-03-15 | 2024-05-28 | 山东鲁新国合节能环保科技有限公司 | Abnormal data monitoring method in sintering flue gas internal circulation process |
| CN117909908B (en) * | 2024-03-15 | 2024-05-28 | 头等舱互联科技(深圳)有限公司 | Intelligent monitoring method for running state of shared massage chair |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117148784B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117148784B (en) | Operation fault analysis method for multi-axis multi-channel numerical control system | |
| CN110889091B (en) | Machine tool thermal error prediction method and system based on temperature sensitive interval segmentation | |
| WO2020194534A1 (en) | Abnormality determination assistance device | |
| JP6792746B2 (en) | State identification method by segment feature analysis of frequency domain | |
| CN111353482A (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| JP2003506786A (en) | A method for statistically determining process control loop parameter estimates. | |
| CN117196353B (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN109615121B (en) | High-speed train axle temperature prediction method based on data driving support vector machine | |
| US11630028B2 (en) | Method and controller for deciding whether a bearing is faulty or not | |
| CN117708748B (en) | Operation monitoring system and method for centrifugal fan | |
| JP7012888B2 (en) | Abnormal factor estimation device, abnormal factor estimation method, and program | |
| US20190163163A1 (en) | Numerical controller | |
| CN112414694A (en) | Equipment multistage abnormal state identification method and device based on multivariate state estimation technology | |
| CN117807551B (en) | Heart rate abnormality capturing method and system based on intelligent ring | |
| CN116400639B (en) | PLC (programmable logic controller) collected data intelligent cleaning method and system | |
| CN114020598A (en) | Method, device and equipment for detecting abnormity of time series data | |
| CN117313020A (en) | Data processing method of bearing type tension sensor | |
| WO2020230422A1 (en) | Abnormality diagnosis device and method | |
| CN105629959A (en) | Industrial process fault detection method | |
| CN108182306B (en) | Method for determining degradation failure threshold of abrasive particle characteristic parameters of vehicle power transmission device | |
| CN108427375B (en) | Method for monitoring cutter state based on band-pass filtering processing multi-sensor | |
| WO2020204043A1 (en) | Blast furnace abnormality assessment device, blast furnace abnormality assessment method, and blast furnace operation method | |
| KR102668033B1 (en) | Valve integrity diagnostic system and method | |
| CN116226239B (en) | Data-driven-based state monitoring method for spindle system of machining center | |
| CN117874445B (en) | Enzyme preparation production monitoring method for real-time online monitoring data analysis |
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 |