CN117874687B - Data interaction method of industrial tablet personal computer - Google Patents
Data interaction method of industrial tablet personal computer Download PDFInfo
- Publication number
- CN117874687B CN117874687B CN202410275189.9A CN202410275189A CN117874687B CN 117874687 B CN117874687 B CN 117874687B CN 202410275189 A CN202410275189 A CN 202410275189A CN 117874687 B CN117874687 B CN 117874687B
- Authority
- CN
- China
- Prior art keywords
- monitoring data
- time sequence
- data time
- historical
- historical monitoring
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000003993 interaction Effects 0.000 title claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 409
- 230000002159 abnormal effect Effects 0.000 claims abstract description 48
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000013507 mapping Methods 0.000 claims description 10
- 239000006185 dispersion Substances 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 5
- 230000008569 process Effects 0.000 description 20
- 230000005856 abnormality Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000002411 adverse Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing for monitoring, in particular to a data interaction method of an industrial tablet computer, which is characterized by determining the abnormal importance possibility of each historical monitoring data time sequence by determining the similarity index of the current monitoring data time sequence and each historical monitoring data time sequence and the similarity index of each two historical monitoring data time sequences and combining the time interval of the current monitoring data time sequence and the historical monitoring data time sequence; according to the abnormal importance possibility and the similarity index corresponding to the current monitoring data time sequence, determining the importance degree of each historical monitoring data time sequence, and determining the fault degree of the current monitoring data time sequence by combining the difference of the monitoring data discrete degrees of the current monitoring data time sequence and each historical monitoring data time sequence, so as to determine the working state of equipment to be monitored. According to the invention, through data processing, the monitoring accuracy of the working state of the equipment is effectively improved.
Description
Technical Field
The invention relates to the technical field of data processing for monitoring, in particular to a data interaction method of an industrial tablet computer.
Background
Industrial tablet computers have various uses in terms of data interaction, depending on the application scenario and requirements of the industrial tablet computer. In general, main uses of industrial tablet computers in data interaction include: sensor data acquisition and analysis, remote monitoring and control, internet of things (IoT) connectivity, data display and visualization, data storage and management, and the like.
Industrial tablet computers can collect data from various sensors, instruments and devices through data interaction, the data can be used for analysis and decision making, and through cloud services or remote connection, the industrial tablet computers can realize remote access to industrial devices and data, which is extremely useful for remote maintenance, monitoring and fault elimination. The industrial tablet personal computer is beneficial to timely detecting and solving the problems through data interaction, and improves the industrial production efficiency and the product quality.
When the industrial tablet personal computer is used for monitoring the working state of the mechanical equipment of the factory through data interaction, the working state of the mechanical equipment of the factory changes, and accordingly the temperature data of the mechanical motor can be changed, so that the preliminary judgment of the working state of the mechanical equipment can be realized through analyzing the temperature data change. The existing method generally compares the collected temperature data with a set threshold value, and determines the working state of the mechanical equipment according to the comparison result. However, for the temperature data change caused by special situations, for example, when the environmental temperature changes or when the working strength of the mechanical equipment changes for a short time, the temperature data change, at this time, the temperature data is similar to abnormal data, so that the misjudgment phenomenon is easily caused by simple threshold comparison, and the monitoring accuracy of the working state of the mechanical equipment is lower.
Disclosure of Invention
The invention aims to provide a data interaction method of an industrial tablet personal computer, which is used for solving the problem of low monitoring accuracy of the working state of the existing mechanical equipment.
In order to solve the technical problems, the invention provides a data interaction method of an industrial tablet computer, which comprises the following steps:
acquiring a current monitoring data time sequence and each historical monitoring data time sequence of equipment to be monitored, and a time interval between the current monitoring data time sequence and each historical monitoring data time sequence;
Determining the degree of the discrete monitoring data of the current monitoring data time sequence and the degree of the discrete monitoring data of each historical monitoring data time sequence according to the current monitoring data time sequence and the distribution situation of the monitoring data in each historical monitoring data time sequence, and determining the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence and the similarity index between any two historical monitoring data time sequences;
Determining abnormal importance possibility corresponding to each historical monitoring data time sequence according to the difference between the similarity indexes corresponding to the current monitoring data time sequence, the size of the similarity index between any two historical monitoring data time sequence and the time interval between the current monitoring data time sequence and each historical monitoring data time sequence;
Determining the importance degree corresponding to each historical monitoring data time sequence according to the abnormal importance possibility corresponding to each historical monitoring data time sequence and the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence;
determining the fault degree of the current monitoring data time sequence according to the difference of the discrete degree of the monitoring data between the current monitoring data time sequence and each historical monitoring data time sequence and the importance degree corresponding to each historical monitoring data time sequence, and determining the working state of the equipment to be monitored according to the fault degree.
Further, determining an abnormally important likelihood for each historical monitoring data timing sequence includes:
determining the average value of the similarity indexes between the current monitoring data time sequence and each historical monitoring data time sequence to obtain a similarity index average value;
Determining the accumulated value of the similarity index between each historical monitoring data time sequence and other historical monitoring data time sequences to obtain the total value of the similarity index corresponding to each historical monitoring data time sequence;
and determining the abnormal importance possibility corresponding to each historical monitoring data time sequence according to the difference between the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence and the average value of the similarity index and the total value and the time interval of the similarity index corresponding to each historical monitoring data time sequence.
Further, determining the abnormal importance possibility corresponding to each historical monitoring data time sequence, wherein the corresponding calculation formula is as follows:
; wherein/> Representing the abnormal important possibility corresponding to the ith historical monitoring data time sequence; /(I)Representing a similarity index between the ith historical monitoring data time sequence and the current monitoring data time sequence b; /(I)Representing the average value of the similar indexes; /(I)Representing the total value of similar indexes corresponding to the ith historical monitoring data time sequence; /(I)A similarity index between the ith historical monitoring data time sequence and other kth historical monitoring data time sequences is represented; /(I)Representing a total number of historical monitoring data timing sequences; /(I)Representing a normalization function; /(I)Representing a time interval between a current monitoring data timing sequence and an ith historical monitoring data timing sequence; the symbol of absolute value is taken.
Further, determining the fault level of the current monitoring data time sequence includes:
calculating the absolute value of the difference between the discrete degree of the monitoring data of the current monitoring data time sequence and the discrete degree of the monitoring data of each historical monitoring data time sequence, thereby obtaining the discrete degree difference value of the monitoring data corresponding to each historical monitoring data time sequence;
And determining the fault degree of the current monitoring data time sequence according to the importance degree corresponding to each historical monitoring data time sequence and the difference value of the discrete degree of the monitoring data.
Further, determining the fault degree of the current monitoring data time sequence, wherein the corresponding calculation formula is as follows:
; wherein/> Representing the fault degree of the current monitoring data time sequence; A monitor data discrete degree difference value representing an ith historical monitor data time sequence; /(I) Representing the discrete degree of the monitoring data of the current monitoring data time sequence b; /(I)Representing the degree of dispersion of the monitoring data of the ith historical monitoring data time sequence; /(I)Representing a total number of historical monitoring data timing sequences; the symbol of absolute value is taken.
Further, determining the importance degree corresponding to each historical monitoring data time sequence, wherein the corresponding calculation formula is as follows:
; wherein/> Representing the importance degree corresponding to the ith historical monitoring data time sequence; /(I)Representing the abnormal important possibility corresponding to the ith historical monitoring data time sequence; /(I)Representing a similarity indicator between the ith historical monitoring data timing sequence and the current monitoring data timing sequence b.
Further, the step of determining the degree of dispersion of the monitored data includes:
Determining the variance of each monitoring data in the current monitoring data time sequence, thereby obtaining the discrete degree of the monitoring data of the current monitoring data time sequence;
and determining the variance of each monitoring data in each historical monitoring data time sequence, thereby obtaining the degree of dispersion of the monitoring data of each historical monitoring data time sequence.
Further, the step of determining the similarity index includes:
Determining a DTW distance between the current monitoring data time sequence and each historical monitoring data time sequence by using a DTW algorithm, and performing negative correlation mapping on the DTW distance so as to obtain a similarity index between the current monitoring data time sequence and each historical monitoring data time sequence;
And determining the DTW distance between any two historical monitoring data time sequence by using a DTW algorithm, and performing negative correlation mapping on the DTW distance so as to obtain a similarity index between any two historical monitoring data time sequence.
Further, determining the working state of the device to be monitored includes:
Judging whether the fault degree of the current monitoring data time sequence is larger than a set fault degree threshold value, if so, judging that the equipment to be monitored is in an abnormal working state, otherwise, judging that the equipment to be monitored is in a normal working state.
Further, the method further comprises:
And when the equipment to be monitored is judged to be in an abnormal working state, carrying out early warning prompt on equipment management personnel.
The invention has the following beneficial effects: the method comprises the steps of obtaining a current monitoring data time sequence corresponding to the current use process of equipment to be monitored and a historical monitoring data time sequence corresponding to each historical use process, and determining a similarity index between the current monitoring data time sequence and each historical monitoring data time sequence so as to quantify the trend similarity degree of the current monitoring data and each set of historical monitoring data. And then analyzing the deviation trend of the similar indexes corresponding to each historical monitoring data time sequence by combining the time interval between the current monitoring data and each set of historical monitoring data and the similar indexes between any two historical monitoring data time sequence so as to eliminate the influence of monitoring data change caused by time factors and the adverse influence caused by abnormality of a single historical monitoring data time sequence, thereby accurately determining the abnormal important possibility corresponding to each historical monitoring data time sequence. Comprehensively considering the similarity index and the abnormal importance possibility corresponding to each historical monitoring data time sequence, accurately measuring the reference value condition of judging whether the current monitoring data is abnormal or not by the historical monitoring data time sequence, and finally obtaining the importance degree corresponding to each historical monitoring data time sequence. According to the difference of the discrete degree of the monitoring data between the current monitoring data time sequence and each historical monitoring data time sequence, the abnormal fluctuation difference of the current monitoring data time sequence relative to each historical monitoring data time sequence can be determined, the importance degree corresponding to each historical monitoring data time sequence is utilized to measure the reference value of the fluctuation difference, and finally the fault degree of the current monitoring data time sequence is accurately determined, so that the monitoring of the working state of the equipment to be monitored is finally realized. The invention analyzes the overall fluctuation condition of the current monitoring data and each group of historical monitoring data to accurately determine the fault degree of the time sequence of the current monitoring data, and finally can accurately identify the working state of the equipment, thereby avoiding the misjudgment phenomenon of monitoring the working state of the equipment by judging only single monitoring data and effectively improving the monitoring accuracy of the working state of the equipment.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a data interaction method of an industrial tablet computer according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention to achieve the preset purpose, the following detailed description is given below of the specific implementation, structure, features and effects of the technical solution according to the present invention with reference to the accompanying drawings and 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 one or more embodiments 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. In addition, all parameters or indices in the formulas referred to herein are values after normalization that eliminate the dimensional effects.
In order to solve the problem of low monitoring accuracy of the working state of the existing mechanical equipment, the embodiment provides a data interaction method of an industrial tablet computer, and a flow chart corresponding to the method is shown in fig. 1, and the method comprises the following steps:
Step S1: the method comprises the steps of obtaining a current monitoring data time sequence and each historical monitoring data time sequence of equipment to be monitored, and obtaining a time interval between the current monitoring data time sequence and each historical monitoring data time sequence.
When the working state of the mechanical equipment of the factory is monitored by adopting the data interaction of the industrial tablet computer, the temperature data of the equipment motor of the mechanical equipment of the factory is acquired by monitoring the temperature sensor through the industrial tablet computer. The mechanical equipment in this embodiment refers to a machine tool, and the temperature data of the machine tool motor is the monitoring data of the machine tool. The collected temperature data comprises current temperature data and historical temperature data, wherein the current temperature data refers to temperature data collected by the machine tool in the current use process, and the historical temperature data refers to temperature data collected by the machine tool before the current use process and in each historical use process.
The collected temperature data of the machine tool in each historical use process not only comprises all temperature data in the temperature rising process, but also comprises all temperature data in the temperature falling process, and the analysis is not needed in the process of detecting the working state of the machine tool, and the temperature begins to fall back after the equipment is finished, so that all temperature data in the temperature falling process in the collected temperature data in each historical use process can be deleted, and the calculated amount is reduced. When deleting all temperature data in the temperature falling process, curve fitting can be performed according to the temperature data acquired in each historical use process and the acquisition time corresponding to the temperature data, and all temperature data which are in the whole falling trend in the fitted curve are deleted, so that the residual temperature data in each historical use process are obtained. Meanwhile, the acquired current temperature data only comprise the temperature data corresponding to the machine tool in the running process, and the temperature data are in an ascending state as a whole.
The acquired current temperature data are arranged according to the sequence from front to back at the acquisition time, so that a current temperature data sequence is obtained, and the current temperature data sequence is recorded as a current monitoring data time sequence. The residual temperature data in each historical use process is also arranged according to the sequence from front to back of the acquisition time, so that a temperature data sequence of each historical use process is obtained, and the temperature data sequence of each historical use process is called a historical monitoring data time sequence. Wherein the current temperature data sequence，/>Representing the current temperature data sequence/>The p-th temperature data in (a), m represents the current temperature data sequence/>The total number of temperature data in the database; each historical monitoring data timing sequence/>，/>Representing historical monitoring data timing sequence/>P-th temperature data of/(Representing historical monitoring data timing sequence/>The total number of temperature data in the database.
And meanwhile, determining a time interval between the current monitoring data time sequence and each historical monitoring data time sequence, wherein the time interval refers to the size of a time period between the sampling time corresponding to the first temperature data in the current monitoring data time sequence and the sampling time corresponding to the first temperature data in each historical monitoring data time sequence.
Step S2: determining the degree of the discrete monitoring data of the current monitoring data time sequence and the degree of the discrete monitoring data of each historical monitoring data time sequence according to the current monitoring data time sequence and the distribution situation of the monitoring data in each historical monitoring data time sequence, and determining the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence and the similarity index between any two historical monitoring data time sequences.
The time series of the history monitoring data obtained through the above steps may be regarded as periodic, and although the temperature data of each time series of the history monitoring data is not exactly the same, the trend of change in the temperature data is similar. The similarity between the current data and the historical data can thus be determined by comparing the historical data for each time period with the current data, i.e., comparing each historical monitoring data timing sequence with the current monitoring data timing sequence. And meanwhile, comparing any two historical monitoring data time sequence, and determining the similarity between any two historical monitoring data time sequence.
When the similarity between the current data and the historical data and the similarity between any two historical monitoring data time sequence are determined, determining the DTW distance between the current monitoring data time sequence and each historical monitoring data time sequence by using a DTW algorithm, and performing negative correlation mapping on the DTW distance so as to obtain a similarity index between the current monitoring data time sequence and each historical monitoring data time sequence; and determining the DTW distance between any two historical monitoring data time sequence by using a DTW algorithm, and performing negative correlation mapping on the DTW distance so as to obtain a similarity index between any two historical monitoring data time sequence. The DTW algorithm refers to a dynamic time adjustment (DYNAMIC TIME WARPING) algorithm. In performing the negative correlation mapping on the DTW distance, the present embodiment takes the inverse of the sum of the setting coefficient and the DTW distance as the negative correlation mapping result of the DTW distance, and takes the negative correlation mapping result as the similarity index. The setting coefficient is to prevent the inverse of the DTW distance from being directly used as the negative correlation mapping result of the DTW distance, and the phenomenon that the denominator is zero may occur, and the value of the setting coefficient is set to be 1 in this embodiment. When the similarity index between two time series is smaller, it is indicated that the larger the difference in temperature data in the two time series is, the more inconsistent the variation tends to be.
Meanwhile, in order to facilitate subsequent data analysis, the working state of the machine tool is finally and accurately determined, and the degree of dispersion of the monitoring data of the current monitoring data time sequence and the degree of dispersion of the monitoring data of each historical monitoring data time sequence are determined according to the current monitoring data time sequence and the monitoring data distribution condition in each historical monitoring data time sequence. When the discrete degree of the monitoring data is determined, determining the variance of each monitoring data in the current monitoring data time sequence, so as to obtain the discrete degree of the monitoring data of the current monitoring data time sequence; and determining the variance of each monitoring data in each historical monitoring data time sequence, thereby obtaining the degree of dispersion of the monitoring data of each historical monitoring data time sequence.
Step S3: and determining the abnormal importance possibility corresponding to each historical monitoring data time sequence according to the difference between the similarity indexes corresponding to the current monitoring data time sequence, the size of the similarity index between any two historical monitoring data time sequences and the time interval between the current monitoring data time sequence and each historical monitoring data time sequence.
The similarity between the current data and the historical data and the similarity between any two historical monitoring data time sequences can be determined through the steps, but the similarity is not enough to judge the current temperature abnormality according to the similarity, because not all the historical data are completely matched with the current data due to the influence of factors such as the use time of the processing materials and the machine tool equipment, namely, when the time interval corresponding to different monitoring data time sequences is shorter, the degree of the corresponding processing materials and the mechanical ageing is likely to be similar, the degree of the correlation between the corresponding sequences is higher, and the degree of the similarity between the corresponding sequences has reference value; on the contrary, when the time intervals corresponding to different monitoring data time sequence are longer, the association degree between the corresponding sequences is lower, and the similarity degree between the corresponding sequences is less valuable as a reference.
Based on the above analysis, in order to judge the current temperature abnormality, the abnormal important possibility corresponding to the historical data needs to be determined according to the similarity between the current data and the historical data and the similarity between any two time sequences of the historical monitoring data by combining the time interval between the current data and the historical data, and the implementation steps comprise: determining the average value of the similarity indexes between the current monitoring data time sequence and each historical monitoring data time sequence to obtain a similarity index average value; determining the accumulated value of the similarity index between each historical monitoring data time sequence and other historical monitoring data time sequences to obtain the total value of the similarity index corresponding to each historical monitoring data time sequence; and determining the abnormal importance possibility corresponding to each historical monitoring data time sequence according to the difference between the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence and the average value of the similarity index and the total value and the time interval of the similarity index corresponding to each historical monitoring data time sequence.
Optionally, in this embodiment, the abnormal importance probability corresponding to each historical monitoring data time sequence is determined, and the corresponding calculation formula is:
; wherein/> Representing the abnormal important possibility corresponding to the ith historical monitoring data time sequence; /(I)Representing a similarity index between the ith historical monitoring data time sequence and the current monitoring data time sequence b; /(I)Representing the average value of the similar indexes; /(I)Representing the total value of similar indexes corresponding to the ith historical monitoring data time sequence; /(I)A similarity index between the ith historical monitoring data time sequence and other kth historical monitoring data time sequences is represented; /(I)Representing a total number of historical monitoring data timing sequences; /(I)Representing a normalization function; /(I)Representing a time interval between a current monitoring data timing sequence and an ith historical monitoring data timing sequence; the symbol of absolute value is taken.
In the above calculation formula of the abnormal importance probability, when the i-th historical monitoring data time sequence and the current monitoring data time sequence are similar to each otherThe larger the difference between the average value of the similarity indexes between all the historical monitoring data time sequence and the current monitoring data time sequence is, namely/>When the value of the (i) is larger, the deviation trend corresponding to the ith historical monitoring data time sequence is larger, the value of the abnormal importance possibility corresponding to the ith historical monitoring data time sequence is larger, and the value of the abnormal importance possibility is larger, so that the relevant importance of the ith historical monitoring data time sequence is higher. When the time interval between the ith historical monitoring data time sequence and the current monitoring data time sequence is longer, the method shows that the relativity between the ith historical monitoring data time sequence and the current monitoring data time sequence is lower, and the similarity index/>, between the ith historical monitoring data time sequence and the current monitoring data time sequence is higherThe less valuable the reference is, and thus the inverse of the time interval is taken as the weight of the bias trend, thereby achieving the correction of the bias trend. At the same time, the method comprises the steps of,The comprehensive similarity between the ith historical monitoring data time sequence and other historical monitoring data time sequences is reflected, and in order to prevent the condition that the ith historical monitoring data time sequence is abnormal and thus influences the accuracy of current judgment, the comprehensive similarity/>The larger the value of (c), the larger the value of the final likelihood of abnormal importance should be.
Step S4: and determining the importance degree corresponding to each historical monitoring data time sequence according to the abnormal importance possibility corresponding to each historical monitoring data time sequence and the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence.
According to the abnormal importance possibility corresponding to each historical monitoring data time sequence, and combining the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence, the importance degree corresponding to each historical monitoring data time sequence can be determined. When the probability of abnormal importance corresponding to a certain historical monitoring data time sequence is larger and the similarity index between the historical monitoring data time sequence and the current monitoring data time sequence is higher, the corresponding importance degree is larger.
Optionally, in this embodiment, the importance degree corresponding to each historical monitoring data time sequence is determined, and the corresponding calculation formula is:
; wherein/> Representing the importance degree corresponding to the ith historical monitoring data time sequence; /(I)Representing the abnormal important possibility corresponding to the ith historical monitoring data time sequence; /(I)Representing a similarity indicator between the ith historical monitoring data timing sequence and the current monitoring data timing sequence b.
In the above calculation formula of the importance degree, when the probability of abnormal importance and the similarity index corresponding to a certain historical monitoring data time sequence are larger, the historical monitoring data time sequence is more important for judging the current monitoring data, and the historical monitoring data time sequence is more valuable for judging whether the current monitoring data is abnormal or not, and the corresponding importance degree is larger.
Step S5: determining the fault degree of the current monitoring data time sequence according to the difference of the discrete degree of the monitoring data between the current monitoring data time sequence and each historical monitoring data time sequence and the importance degree corresponding to each historical monitoring data time sequence, and determining the working state of the equipment to be monitored according to the fault degree.
Based on the current monitoring data time sequence and the monitoring data discrete degree of each historical monitoring data time sequence determined in the steps, and comprehensively considering the importance degree corresponding to each historical monitoring data time sequence, measuring the abnormal degree of the current monitoring data, namely the possibility of abnormality, so as to determine the fault degree of the current monitoring data time sequence, wherein the implementation steps comprise: calculating the absolute value of the difference between the discrete degree of the monitoring data of the current monitoring data time sequence and the discrete degree of the monitoring data of each historical monitoring data time sequence, thereby obtaining the discrete degree difference value of the monitoring data corresponding to each historical monitoring data time sequence; and determining the fault degree of the current monitoring data time sequence according to the importance degree corresponding to each historical monitoring data time sequence and the difference value of the discrete degree of the monitoring data.
Optionally, in this embodiment, the fault degree of the current monitoring data timing sequence is determined, and the corresponding calculation formula is:
; wherein/> Representing the fault degree of the current monitoring data time sequence; A monitor data discrete degree difference value representing an ith historical monitor data time sequence; /(I) Representing the discrete degree of the monitoring data of the current monitoring data time sequence b; /(I)Representing the degree of dispersion of the monitoring data of the ith historical monitoring data time sequence; /(I)Representing a total number of historical monitoring data timing sequences; the symbol of absolute value is taken.
In the above calculation formula of the fault degree, the difference value of the discrete degree of the monitoring data of the current monitoring data time sequence and the absolute value of the difference value of the discrete degree of the monitoring data of each historical monitoring data time sequence are calculated to obtain the difference value of the discrete degree of the monitoring data, the difference value of the discrete degree of the monitoring data is utilized to represent the abnormal fluctuation difference between the current monitoring data time sequence and each historical monitoring data time sequence, and when the abnormal fluctuation difference is larger, the higher the degree of the data abnormality of the current monitoring data time sequence is, that is, the higher the possibility of the data fault is, the larger the value of the corresponding fault degree is. Meanwhile, the abnormal fluctuation difference is weighted by utilizing the importance degree corresponding to each historical monitoring data time sequence, so that the reference value of each historical monitoring data time sequence is measured, and finally, the accurate fault degree is obtained.
Because the fault degree of the current monitoring data time sequence reflects the possibility of data abnormality of the current monitoring data time sequence, the working state of the equipment to be monitored can be determined according to the fault degree, and the method comprises the following steps: judging whether the fault degree of the current monitoring data time sequence is larger than a set fault degree threshold value, if so, judging that the equipment to be monitored is in an abnormal working state, otherwise, judging that the equipment to be monitored is in a normal working state. The set fault degree threshold value can be reasonably set according to actual conditions, and the value of the set fault degree threshold value is set to be 0.9 in the embodiment. When the equipment to be monitored is judged to be in an abnormal working state, early warning prompt is carried out on equipment management personnel through the industrial tablet personal computer, so that potential safety hazards are prevented.
According to the method, the current monitoring data time sequence corresponding to the current use process of the equipment to be monitored and the historical monitoring data time sequence corresponding to each historical use process are obtained, and the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence is determined, so that the trend similarity degree of the current monitoring data and each set of historical monitoring data is quantified. And then analyzing the deviation trend of the similar indexes corresponding to each historical monitoring data time sequence by combining the time interval between the current monitoring data and each set of historical monitoring data and the similar indexes between any two historical monitoring data time sequence so as to eliminate the influence of monitoring data change caused by time factors and the adverse influence caused by abnormality of a single historical monitoring data time sequence, thereby accurately determining the abnormal important possibility corresponding to each historical monitoring data time sequence. Comprehensively considering the similarity index and the abnormal importance possibility corresponding to each historical monitoring data time sequence, accurately measuring the reference value condition of judging whether the current monitoring data is abnormal or not by the historical monitoring data time sequence, and finally obtaining the importance degree corresponding to each historical monitoring data time sequence. According to the difference of the discrete degree of the monitoring data between the current monitoring data time sequence and each historical monitoring data time sequence, the abnormal fluctuation difference of the current monitoring data time sequence relative to each historical monitoring data time sequence can be determined, the importance degree corresponding to each historical monitoring data time sequence is utilized to measure the reference value of the fluctuation difference, and finally the fault degree of the current monitoring data time sequence is accurately determined, so that the monitoring of the working state of the equipment to be monitored is finally realized. The invention analyzes the overall fluctuation condition of the current monitoring data and each group of historical monitoring data to accurately determine the fault degree of the time sequence of the current monitoring data, and finally can accurately identify the working state of the equipment, thereby avoiding the misjudgment phenomenon of monitoring the working state of the equipment by judging only single monitoring data and effectively improving the monitoring accuracy of the working state of the equipment.
It should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.
Claims (5)
1. The data interaction method of the industrial tablet personal computer is characterized by comprising the following steps of:
acquiring a current monitoring data time sequence and each historical monitoring data time sequence of equipment to be monitored, and a time interval between the current monitoring data time sequence and each historical monitoring data time sequence;
Determining the degree of the discrete monitoring data of the current monitoring data time sequence and the degree of the discrete monitoring data of each historical monitoring data time sequence according to the current monitoring data time sequence and the distribution situation of the monitoring data in each historical monitoring data time sequence, and determining the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence and the similarity index between any two historical monitoring data time sequences;
Determining abnormal importance possibility corresponding to each historical monitoring data time sequence according to the difference between the similarity indexes corresponding to the current monitoring data time sequence, the size of the similarity index between any two historical monitoring data time sequence and the time interval between the current monitoring data time sequence and each historical monitoring data time sequence;
Determining the importance degree corresponding to each historical monitoring data time sequence according to the abnormal importance possibility corresponding to each historical monitoring data time sequence and the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence;
Determining the fault degree of the current monitoring data time sequence according to the difference of the discrete degree of the monitoring data between the current monitoring data time sequence and each historical monitoring data time sequence and the importance degree corresponding to each historical monitoring data time sequence, and determining the working state of equipment to be monitored according to the fault degree;
determining an abnormally important likelihood for each historical monitoring data timing sequence, including:
determining the average value of the similarity indexes between the current monitoring data time sequence and each historical monitoring data time sequence to obtain a similarity index average value;
Determining the accumulated value of the similarity index between each historical monitoring data time sequence and other historical monitoring data time sequences to obtain the total value of the similarity index corresponding to each historical monitoring data time sequence;
Determining abnormal importance possibility corresponding to each historical monitoring data time sequence according to the difference between the similarity index between the current monitoring data time sequence and each historical monitoring data time sequence and the average value of the similarity index and the total value and the time interval of the similarity index corresponding to each historical monitoring data time sequence;
determining the abnormal important possibility corresponding to each historical monitoring data time sequence, wherein the corresponding calculation formula is as follows:
; wherein/> Representing the abnormal important possibility corresponding to the ith historical monitoring data time sequence; /(I)Representing a similarity index between the ith historical monitoring data time sequence and the current monitoring data time sequence b; /(I)Representing the average value of the similar indexes; /(I)Representing the total value of similar indexes corresponding to the ith historical monitoring data time sequence; A similarity index between the ith historical monitoring data time sequence and other kth historical monitoring data time sequences is represented; /(I) Representing a total number of historical monitoring data timing sequences; /(I)Representing a normalization function; /(I)Representing a time interval between a current monitoring data timing sequence and an ith historical monitoring data timing sequence; the absolute value sign is taken;
Determining the degree of failure of the current monitoring data timing sequence comprises:
calculating the absolute value of the difference between the discrete degree of the monitoring data of the current monitoring data time sequence and the discrete degree of the monitoring data of each historical monitoring data time sequence, thereby obtaining the discrete degree difference value of the monitoring data corresponding to each historical monitoring data time sequence;
according to the importance degree corresponding to each historical monitoring data time sequence and the discrete degree difference value of the monitoring data,
Determining the fault degree of the current monitoring data time sequence; determining the fault degree of the current monitoring data time sequence, wherein the corresponding calculation formula is as follows:
; wherein/> Representing the fault degree of the current monitoring data time sequence; /(I)A monitor data discrete degree difference value representing an ith historical monitor data time sequence; /(I)Representing the discrete degree of the monitoring data of the current monitoring data time sequence b; /(I)Representing the degree of dispersion of the monitoring data of the ith historical monitoring data time sequence;
determining the importance degree corresponding to each historical monitoring data time sequence, wherein the corresponding calculation formula is as follows:
; wherein/> And representing the importance degree corresponding to the ith historical monitoring data time sequence.
2. The method for data interaction of an industrial tablet computer according to claim 1 wherein the step of determining the degree of discreteness of the monitored data comprises:
Determining the variance of each monitoring data in the current monitoring data time sequence, thereby obtaining the discrete degree of the monitoring data of the current monitoring data time sequence;
and determining the variance of each monitoring data in each historical monitoring data time sequence, thereby obtaining the degree of dispersion of the monitoring data of each historical monitoring data time sequence.
3. The method for data interaction of an industrial tablet computer according to claim 1, wherein the step of determining the similarity index comprises:
Determining a DTW distance between the current monitoring data time sequence and each historical monitoring data time sequence by using a DTW algorithm, and performing negative correlation mapping on the DTW distance so as to obtain a similarity index between the current monitoring data time sequence and each historical monitoring data time sequence;
And determining the DTW distance between any two historical monitoring data time sequence by using a DTW algorithm, and performing negative correlation mapping on the DTW distance so as to obtain a similarity index between any two historical monitoring data time sequence.
4. The method for data interaction of an industrial tablet computer of claim 1 wherein determining the operational status of the device to be monitored comprises:
Judging whether the fault degree of the current monitoring data time sequence is larger than a set fault degree threshold value, if so, judging that the equipment to be monitored is in an abnormal working state, otherwise, judging that the equipment to be monitored is in a normal working state.
5. The method of claim 4, further comprising:
And when the equipment to be monitored is judged to be in an abnormal working state, carrying out early warning prompt on equipment management personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410275189.9A CN117874687B (en) | 2024-03-12 | 2024-03-12 | Data interaction method of industrial tablet personal computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410275189.9A CN117874687B (en) | 2024-03-12 | 2024-03-12 | Data interaction method of industrial tablet personal computer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117874687A CN117874687A (en) | 2024-04-12 |
| CN117874687B true CN117874687B (en) | 2024-05-31 |
Family
ID=90581601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410275189.9A Active CN117874687B (en) | 2024-03-12 | 2024-03-12 | Data interaction method of industrial tablet personal computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874687B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118940197B (en) * | 2024-10-12 | 2025-01-21 | 江苏威拉里新材料科技有限公司 | A fault warning method and system for metal powder production equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009245228A (en) * | 2008-03-31 | 2009-10-22 | Yamatake Corp | Abnormality detecting method and abnormality detection device |
| CN110515781A (en) * | 2019-07-03 | 2019-11-29 | 北京交通大学 | A complex system state monitoring and fault diagnosis method |
| CN112766429A (en) * | 2021-04-09 | 2021-05-07 | 北京瑞莱智慧科技有限公司 | Method, device, computer equipment and medium for anomaly detection |
| CN114358540A (en) * | 2021-12-23 | 2022-04-15 | 京东科技信息技术有限公司 | Anomaly detection method, device, device and storage medium for index time series data |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116117827A (en) * | 2023-04-13 | 2023-05-16 | 北京奔驰汽车有限公司 | Industrial robot state monitoring method and device |
| CN117193164A (en) * | 2023-11-08 | 2023-12-08 | 东莞市博思特数控机械有限公司 | Fault monitoring method and system of numerical control machine tool |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109239265B (en) * | 2018-09-11 | 2021-01-22 | 清华大学合肥公共安全研究院 | Fault detection method and device for monitoring equipment |
-
2024
- 2024-03-12 CN CN202410275189.9A patent/CN117874687B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009245228A (en) * | 2008-03-31 | 2009-10-22 | Yamatake Corp | Abnormality detecting method and abnormality detection device |
| CN110515781A (en) * | 2019-07-03 | 2019-11-29 | 北京交通大学 | A complex system state monitoring and fault diagnosis method |
| CN112766429A (en) * | 2021-04-09 | 2021-05-07 | 北京瑞莱智慧科技有限公司 | Method, device, computer equipment and medium for anomaly detection |
| CN114358540A (en) * | 2021-12-23 | 2022-04-15 | 京东科技信息技术有限公司 | Anomaly detection method, device, device and storage medium for index time series data |
| CN115840897A (en) * | 2023-02-09 | 2023-03-24 | 广东吉器电子有限公司 | Temperature sensor data exception handling method |
| CN116117827A (en) * | 2023-04-13 | 2023-05-16 | 北京奔驰汽车有限公司 | Industrial robot state monitoring method and device |
| CN117193164A (en) * | 2023-11-08 | 2023-12-08 | 东莞市博思特数控机械有限公司 | Fault monitoring method and system of numerical control machine tool |
Non-Patent Citations (1)
| Title |
|---|
| 基于大数据分析的热镀锌机组关键设备故障诊断技术;王鲁;冶金设备;20231231(第285期);第92-153页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117874687A (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116879662B (en) | Transformer fault detection method based on data analysis | |
| CN112348237B (en) | Abnormal trend detection method for dynamic drilling data | |
| US10852357B2 (en) | System and method for UPS battery monitoring and data analysis | |
| CN111368428B (en) | Sensor precision degradation fault detection method based on monitoring second-order statistics | |
| CN117932501B (en) | Electric energy meter running state management method and system | |
| CN117874687B (en) | Data interaction method of industrial tablet personal computer | |
| WO2016208315A1 (en) | Plant diagnosis device and plant diagnosis method | |
| CN114664063B (en) | A device classification alarm method based on general indicator trend analysis | |
| CN117972600A (en) | Wind turbine generator set key component abnormality detection method based on multidimensional fault feature learning | |
| CN118391249B (en) | Method and device for processing running state monitoring data of large water pump | |
| CN118277924B (en) | Desktop power supply intelligent detection method based on data driving | |
| CN118211082B (en) | Oil filter element residual life prediction method and system based on data analysis | |
| CN119198086B (en) | A bearing temperature early warning method and system based on the Internet of Things | |
| CN119179042B (en) | A method for monitoring safe electricity consumption of electric energy meters based on the Internet of Things | |
| CN114429308A (en) | Enterprise security risk assessment method and system based on big data | |
| CN119067386A (en) | A device operation and maintenance management system and method based on IOT technology | |
| CN117928655B (en) | Material reaction instant acid value data on-line monitoring system | |
| CN117951633B (en) | Photovoltaic power generation equipment fault diagnosis method and system | |
| CN118962362A (en) | A method for detecting insulation of high voltage power capacitor | |
| CN119026761B (en) | Loom operation efficiency assessment method | |
| CN119271968B (en) | Component reliability assessment method and system based on big data analysis | |
| CN119622528B (en) | Fault early warning method for tailing paste filling system | |
| CN119880298B (en) | Oil leakage diagnosis and gas concentration compensation method and system for oil gas monitoring equipment | |
| CN119803641B (en) | Electronic scale transaction misalignment monitoring method and system and electronic equipment | |
| CN120145277A (en) | Method and system for monitoring running state of connector production machine |
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 |