CN112380992B - Method and device for evaluating and optimizing accuracy of monitoring data in machining process - Google Patents
Method and device for evaluating and optimizing accuracy of monitoring data in machining process Download PDFInfo
- Publication number
- CN112380992B CN112380992B CN202011270931.5A CN202011270931A CN112380992B CN 112380992 B CN112380992 B CN 112380992B CN 202011270931 A CN202011270931 A CN 202011270931A CN 112380992 B CN112380992 B CN 112380992B
- Authority
- CN
- China
- Prior art keywords
- data
- inaccurate data
- inaccurate
- acoustic emission
- optimizing
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention discloses a method and a device for evaluating and optimizing the accuracy of monitoring data in a machining process, wherein the method comprises the following steps: collecting an acoustic emission monitoring signal of the cutting process of the cutter; analyzing and extracting characteristics of the acoustic emission monitoring signals, and constructing a tool performance degradation index; constructing a reference sequence based on the tool performance decline index, and detecting inaccurate data based on the reference sequence; and constructing a K neighbor model based on dynamic time warping, finding out previous K historical sequences with the minimum distance as a candidate series, and optimizing inaccurate data by using the mean value of data at corresponding positions in the candidate series. According to the method and the device for evaluating and optimizing the accuracy of the monitoring data of the machining process, the priori knowledge is not needed, the identification and optimization of inaccurate data can be realized under the condition that the theoretical true value of the monitoring data of the process is unknown, and the data quality is improved.
Description
Technical Field
The invention relates to the technical field of machining, in particular to a method and a device for evaluating and optimizing accuracy of monitoring data in a machining process.
Background
With the rapid development of information technology, the degree of digitization and intellectualization of a workshop is higher and higher, the quantity of acquired data is also rapidly increased, and the data mining technology can find potential knowledge and rules behind the data and has important significance for guiding actual production decisions. High quality data is the premise and basis for the value of data. However, in practical applications, problems such as incompleteness and inaccuracy of process monitoring data are often caused by sensor faults, limitations of acquisition system capability, human factors and the like, so that the usability of the data is seriously affected, a data analysis conclusion is wrong, a decision fails, and serious economic loss is caused.
Data accuracy issues are an important aspect of data quality, which measures the degree of difference between measured or recorded data and theoretical truth. At present, research on the data accuracy is less, and the data accuracy is mainly analyzed and judged by depending on expert experience. The method depends on the prior knowledge of a specific field, however, the prior knowledge of some specific fields is difficult to obtain, and the conclusion obtained based on knowledge experience is not completely reliable, so that the method is difficult to be effectively applied to actual production.
Therefore, under the condition that the theoretical true value of the state monitoring data is unknown and no prior knowledge exists in the actual processing process, how to evaluate and optimize the accuracy of the data is a key problem to be solved urgently in the field.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a device for evaluating and optimizing the accuracy of monitoring data in a processing process, which can realize the identification and optimization of inaccurate data and improve the data quality under the condition that the theoretical true value of the monitoring data in the process is unknown without relying on prior knowledge.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention provides a method for evaluating and optimizing the accuracy of monitoring data in a machining process, which comprises the following steps:
s11: collecting an acoustic emission monitoring signal of the cutting process of the cutter;
s12: analyzing and extracting characteristics of the acoustic emission monitoring signals acquired in the step S11, and constructing a tool performance degradation index;
s13: constructing a reference sequence based on the tool performance decline index obtained in the S12, and detecting inaccurate data based on the reference sequence;
s14: and constructing a K neighbor model based on dynamic time warping, finding out previous K historical sequences with the minimum distance as a candidate series, and optimizing the inaccurate data obtained in the step S13 by using the mean value of the data at the corresponding positions in the candidate series.
Preferably, the S12 further includes:
s121: setting the length of signal processing, performing segmentation processing on the acoustic emission monitoring signals acquired in the step S11, and performing multi-dimensional signal feature extraction on the acoustic emission monitoring signals of each length unit by adopting a signal analysis method;
s122: performing feature reduction on the multi-dimensional signal features extracted in the step S121 by using a principal component analysis method, and calculating the contribution degree of each principal component;
s123: setting a contribution degree threshold value, and selecting a principal component with the contribution degree meeting the contribution degree threshold value as a tool performance decline index.
Preferably, the S13 further includes:
s131: based on the dynamic time regular distance, carrying out hierarchical clustering on the cutter performance decline indexes constructed in the step S12;
s132: calculating the mean vector of all samples in the class as the centroid vector of each class of samples after the S131 hierarchical clustering, setting the weight coefficient of each class of centroid vectors, and performing weighted calculation to obtain a reference sequence;
s133: calculating error values of the historical decline indexes and the position data corresponding to the reference sequence to obtain an error data set;
s134: performing distribution estimation on the error data set obtained in S133, and calculating an expected value μ and a standard deviation σ of the distribution;
s135: setting the error threshold as:
δ max ＝μ+λσ，
wherein λ is a weight coefficient, when the error value calculated in step S133 is greater than the set error threshold, the data point is regarded as an inaccurate data point, and the sequence in which the inaccurate data point is located is an abnormal sequence.
Preferably, the weighting factor for setting the centroid vector of each class in S132 increases as the number of samples in each class increases.
Preferably, the weighting factor λ in S135 is adjusted according to actual conditions, and the adjustment is performed by increasing or decreasing the value of λ according to actual production decision requirements until all inaccurate data satisfying the condition are detected.
Preferably, the S14 further includes:
s141: constructing a K nearest neighbor model based on dynamic time warping;
s142: finding out the previous K history sequences with the minimum distance as candidate sequences by using the K neighbor model constructed in the step S141;
s143: calculating a position coefficient of the inaccurate data in the S13;
ε＝l/M，
wherein l represents the position of inaccurate data in the time sequence, and M represents the length of the whole time sequence;
s144: multiplying the position coefficient obtained in the step S143 by the length of each historical sequence in the candidate sequence, and rounding according to a rounding method to obtain a candidate data point set of the corresponding position of each candidate sequence;
s145: calculating an average value of the candidate data sets of the positions corresponding to the candidate sequences obtained in the step S144 to obtain an optimized data set of the positions corresponding to the inaccurate data;
s146: and correcting the inaccurate data points in the abnormal sequence where the inaccurate data are located by using the optimized data set of the corresponding position of each inaccurate data obtained by the 145, so as to realize the optimization of the inaccurate data.
Preferably, the S141 further includes:
s1411: gathering the tool performance degradation indexes of each tool sample into a category;
s1412: calculating the mean vector of all samples in the class as the centroid of each class of samples;
s1413: calculating the dynamic time regular distance between various centroid vectors;
s1414: combining the two types with the minimum dynamic time warping distance into one type;
s1415: and repeating the steps S1412 to S1414 until the number of clusters reaches k.
The invention also provides a device for evaluating and optimizing the accuracy of the monitoring data of the machining process, which is used for realizing the method for evaluating and optimizing the accuracy of the monitoring data of the machining process and comprises the following steps: an acoustic emission monitoring signal acquisition unit, a cutter performance decline index construction unit, an inaccurate data detection unit and an inaccurate data optimization unit, wherein,
the acoustic emission monitoring signal acquisition unit is used for acquiring an acoustic emission monitoring signal of the cutting process of the cutter;
the cutter performance decline index construction unit is used for analyzing and extracting the characteristics of the acoustic emission monitoring signals collected by the acoustic emission detection signal collection unit to construct a cutter performance decline index;
the inaccurate data detection unit is used for constructing a reference sequence based on the cutter performance decline index obtained by the cutter performance decline index construction unit and detecting inaccurate data based on the reference sequence;
the inaccurate data optimization unit is used for constructing a K nearest neighbor model based on dynamic time warping, finding out previous K historical sequences with the minimum distance as candidate series, and optimizing the inaccurate data obtained by the inaccurate data detection unit by using the mean value of the corresponding position data in the candidate series.
The invention also provides a computer, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor is used for executing the method for evaluating and optimizing the accuracy of the monitoring data of the processing process when executing the program.
The present invention also provides a computer readable storage medium having stored thereon a computer program for executing the method of accuracy evaluation and optimization of process monitoring data described herein when executed by a processor.
Compared with the prior art, the embodiment of the invention has at least one of the following beneficial effects:
(1) According to the method and the device for evaluating and optimizing the accuracy of the monitoring data of the machining process, which are provided by the invention, the priori knowledge is not needed, the identification and optimization of inaccurate data can be realized under the condition that the theoretical true value of the monitoring data of the process is unknown, the data quality is improved, and the effectiveness of the state prediction and the actual production decision of the machining process is ensured;
(2) According to the method and the device for evaluating and optimizing the accuracy of the monitoring data of the machining process, the characteristics are extracted through the acoustic emission monitoring signals, and the real-time machining state can be effectively reflected;
(3) The method and the device for evaluating and optimizing the accuracy of the monitoring data of the machining process can adaptively adjust the error detection threshold value according to actual needs, and have universality under actual dynamic variable working conditions;
(4) The method and the device for evaluating and optimizing the accuracy of the monitoring data of the machining process can automatically evaluate and optimize abnormal data, effectively improve the data quality and have important significance for the prediction and intelligent decision of the data-driven machining state.
Drawings
Embodiments of the invention are further described below with reference to the accompanying drawings:
FIG. 1 is a flow chart of a method for evaluating and optimizing the accuracy of process monitoring data according to an embodiment of the present invention;
FIG. 2 is a hierarchical cluster diagram of a method for evaluating and optimizing the accuracy of process monitoring data according to a preferred embodiment of the present invention;
FIG. 3 is a schematic diagram of the tool performance degradation index and the reference sequence of the method for evaluating and optimizing the accuracy of the monitored data in the machining process according to the preferred embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating calculation of the inaccurate data position coefficients of the method for evaluating and optimizing the accuracy of the process monitoring data according to a preferred embodiment of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
Fig. 1 is a flowchart illustrating a method for evaluating and optimizing accuracy of process monitoring data according to an embodiment of the present invention.
Referring to fig. 1, the method for evaluating and optimizing the accuracy of the process monitoring data of the present embodiment includes:
s11: collecting an acoustic emission monitoring signal of the cutting process of the cutter;
s12: analyzing and extracting characteristics of the acoustic emission monitoring signals acquired in the step S11, and constructing a tool performance degradation index;
s13: constructing a reference sequence based on the tool performance degradation indexes obtained in the step S12, and detecting inaccurate data based on the reference sequence;
s14: and constructing a dynamic time warping-based K neighbor model, finding out the previous K historical sequences with the minimum distance as a candidate series, and optimizing the inaccurate data obtained in the step S13 by using the average value of the data of the corresponding positions in the candidate series.
In a preferred embodiment, S12 further comprises:
s121: setting the length of signal processing, for example, setting the length as 1000 data points, performing segmentation processing on the original signals to obtain 405 original signals, and performing feature extraction on the original data of each length unit by using a signal analysis method to obtain a multi-dimensional signal feature, where the 6-dimensional signal feature is taken as an example in this embodiment: energy (E), amplitude (a), root mean square value (RMS), average Signal Level (ASL), signal Strength (SS), and absolute energy (AbE);
s122: performing feature reduction on the extracted six-dimensional feature vector X = [ E, A, RMS, ASL, SS, abE ] by using a Principal Component Analysis (PCA) method, and calculating the contribution degrees of each principal component to be 0.9825,0.0148,0.0034,0.0011,1.0267e-4,7.1787e-12;
s123: setting a contribution threshold value, and selecting a main component with contribution degree meeting the contribution threshold value as a tool performance decline index. In the embodiment, the contribution threshold is 0.95 as an example, and it can be seen that the contribution rate of the first feature vector reaches 0.9825, which can effectively represent the original feature vector, and therefore, the first feature vector is selected as the tool performance degradation index.
In a preferred embodiment, S13 further comprises:
s131: based on a Dynamic Time Warping (DTW) distance, performing hierarchical clustering on the constructed tool performance decline indexes, wherein copolymerization is taken as class 2 in the embodiment, as shown in FIG. 2, wherein a tool 1 is a class, and tools 2-7 are another class;
s132: calculating the mean vector of all samples in the class as the centroid vector of each class of samples, respectively setting the weight coefficients of the two classes as b1=0.14 and b2=0.86 according to the principle that the weight coefficient is larger when the number of the samples in the class is larger, and performing weighting calculation to obtain a reference sequence, as shown by a thick solid line in fig. 3;
s133: calculating the error value of the position data corresponding to each historical decline index and the reference sequence to obtain an error data set;
s134: estimating the distribution of the error data set, and calculating to obtain expected mu =0.228 and standard deviation sigma =0.1891 of the distribution;
s135, setting an error threshold value:
δ max ＝μ+λσ，
wherein λ is a weight coefficient;
in this example delta max =0.251, when the error value calculated in step S133 is greater than the set error threshold, the data point is regarded as an inaccurate data point, and the sequence in which the inaccurate data point is located is an abnormal sequence.
In a preferred embodiment, S14 further comprises:
s141: constructing a K nearest neighbor model based on dynamic time warping;
s142: finding the previous K (taking 3 as an example in the embodiment) history sequences with the minimum distance as candidate sequences by using the K neighbor model constructed in the step S141;
s143: calculating the position coefficient of the inaccurate data in S13;
ε＝l/M，
wherein, l represents the position of the inaccurate data in the time series, and M represents the length of the whole time series, as shown in fig. 4, a schematic diagram of calculating the position coefficient of the inaccurate data is shown;
s144: multiplying the position coefficient obtained in the step S143 by the length of each historical sequence in the candidate sequence, and rounding according to a rounding method to obtain a candidate data point set of the corresponding position of each candidate sequence;
s145: calculating the average value of the candidate data sets of the corresponding positions of the candidate sequences obtained in the step S144 to obtain the optimized data sets of the corresponding positions of the inaccurate data;
s146: and correcting the inaccurate data points in the abnormal sequence where the inaccurate data are located by using the optimized data set of the corresponding position of each inaccurate data obtained by 145, so as to realize the optimization of the inaccurate data.
In a preferred embodiment, S141 further comprises:
s1411: tool performance decline indexes of each tool sample are gathered into one type;
s1412: calculating the mean vector of all samples in the class as the centroid of each class of samples;
s1413: calculating the dynamic time regular distance between various centroid vectors;
s1414: combining the two types with the minimum dynamic time regular distance into one type;
s1415: and repeating the steps of the S1412 to 1414 until the number of clusters reaches k.
In an embodiment, a device for evaluating and optimizing accuracy of monitoring data of a machining process is further provided, which is used for implementing the method for evaluating and optimizing accuracy of monitoring data of a machining process of the above embodiment, and includes: an acoustic emission monitoring signal acquisition unit, a cutter performance decline index construction unit, an inaccurate data detection unit and an inaccurate data optimization unit, wherein,
the acoustic emission monitoring signal acquisition unit is used for acquiring an acoustic emission monitoring signal of the cutting machining process of the cutter;
the cutter performance decline index construction unit is used for analyzing and extracting the characteristics of the acoustic emission monitoring signals collected by the acoustic emission detection signal collection unit to construct a cutter performance decline index;
the inaccurate data detection unit is used for constructing a reference sequence based on the cutter performance decline index obtained by the cutter performance decline index construction unit and detecting inaccurate data based on the reference sequence;
the inaccurate data optimization unit is used for constructing a K nearest neighbor model based on dynamic time warping, finding out previous K historical sequences with the minimum distance as candidate series, and optimizing the inaccurate data obtained by the inaccurate data detection unit by using the mean value of the corresponding position data in the candidate series.
In the device for evaluating and optimizing the accuracy of the processing procedure monitoring data according to the above embodiment of the present invention, the implementation technology of each unit may adopt a corresponding technology in the method for evaluating and optimizing the accuracy of the processing procedure monitoring data, and details are not repeated herein. In addition, the technical features of the preferred embodiments can be used in any combination or any combination without conflict with each other,
in another embodiment of the present invention, a computer is further provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to perform the method for accuracy evaluation and optimization of process monitoring data in any of the above embodiments.
In another embodiment of the present invention, a computer readable storage medium is further provided, on which a computer program is stored, the computer program being executed by a processor for performing the method for accuracy evaluation and optimization of process monitoring data according to any of the above embodiments.
The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, and not to limit the invention. Any modifications and variations within the scope of the description, which may occur to those skilled in the art, are intended to be within the scope of the invention.
Claims (9)
1. A method for evaluating and optimizing the accuracy of monitoring data in a machining process is characterized by comprising the following steps:
s11: collecting an acoustic emission monitoring signal of the cutting process of the cutter;
s12: analyzing and extracting characteristics of the acoustic emission monitoring signals acquired in the step S11, and constructing a tool performance degradation index;
s13: constructing a reference sequence based on the tool performance decline index obtained in the S12, and detecting inaccurate data based on the reference sequence;
s14: constructing a K neighbor model based on dynamic time warping, finding out previous K historical sequences with the minimum distance as candidate series, and optimizing the inaccurate data obtained in the S13 by using the mean value of the data of the corresponding positions in the candidate series;
the S13 further includes:
s131: based on the dynamic time warping distance, carrying out hierarchical clustering on the cutter performance degradation indexes constructed in the S12;
s132: calculating the mean vector of all samples in the class as the centroid vector of each class of samples after the S131 hierarchical clustering, setting the weight coefficient of each class of centroid vectors, and performing weighted calculation to obtain a reference sequence;
s133: calculating error values of the historical decline indexes and the position data corresponding to the reference sequence to obtain an error data set;
s134: performing distribution estimation on the error data set obtained in S133, and calculating an expected value μ and a standard deviation σ of the distribution;
s135: setting the error threshold as:
δ max ＝μ+λσ，
wherein λ is a weight coefficient, and when the error value calculated in step S133 is greater than the set error threshold, the data point is regarded as an inaccurate data point, and the sequence in which the inaccurate data point is located is an abnormal sequence.
2. The method for accuracy evaluation and optimization of process monitoring data according to claim 1, wherein the step S12 further comprises:
s121: setting the length of signal processing, performing segmentation processing on the acoustic emission monitoring signals acquired in the step S11, and performing multi-dimensional signal feature extraction on the acoustic emission monitoring signals of each length unit by adopting a signal analysis method;
s122: performing feature reduction on the multi-dimensional signal features extracted in the step S121 by using a principal component analysis method, and calculating the contribution degree of each principal component;
s123: setting a contribution threshold value, and selecting a main component with contribution degree meeting the contribution threshold value as a tool performance decline index.
3. The method as claimed in claim 1, wherein the weighting factor of the centroid vector of each class set in S132 increases as the number of samples in the class increases.
4. The method as claimed in claim 1, wherein the weighting factor λ in S135 is adjusted according to actual conditions by increasing or decreasing λ according to actual production decision requirements until all inaccurate data satisfying the condition is detected.
5. The method for accuracy evaluation and optimization of process monitoring data according to claim 1, wherein the step S14 further comprises:
s141: constructing a K nearest neighbor model based on dynamic time warping;
s142: finding out the previous K history sequences with the minimum distance as candidate sequences by using the K neighbor model constructed in the step S141;
s143: calculating a position coefficient of the inaccurate data in the S13;
ε＝l/M，
wherein l represents the position of inaccurate data in the time sequence, and M represents the length of the whole time sequence;
s144: multiplying the position coefficient obtained in the step S143 by the length of each historical sequence in the candidate sequence, and rounding according to a rounding method to obtain a candidate data point set of the corresponding position of each candidate sequence;
s145: calculating an average value of the candidate data sets of the positions corresponding to the candidate sequences obtained in the step S144 to obtain an optimized data set of the positions corresponding to the inaccurate data;
s146: and correcting the inaccurate data points in the abnormal sequence where the inaccurate data are located by using the optimized data set of the corresponding position of each inaccurate data obtained by the 145, so as to realize the optimization of the inaccurate data.
6. The method of claim 5, wherein the step S141 further comprises:
s1411: tool performance decline indexes of each tool sample are gathered into one type;
s1412: calculating the mean vector of all samples in the class as the centroid of each class of samples;
s1413: calculating the dynamic time regular distance between various centroid vectors;
s1414: combining the two types with the minimum dynamic time warping distance into one type;
s1415: and repeating the steps S1412 to S1414 until the number of clusters reaches k.
7. An apparatus for evaluating and optimizing accuracy of process monitoring data for realizing the apparatus for evaluating and optimizing accuracy of process monitoring data according to any one of claims 1 to 6, comprising: an acoustic emission monitoring signal acquisition unit, a cutter performance decline index construction unit, an inaccurate data detection unit and an inaccurate data optimization unit, wherein,
the acoustic emission monitoring signal acquisition unit is used for acquiring an acoustic emission monitoring signal of the cutting machining process of the cutter;
the cutter performance degradation index construction unit is used for analyzing and extracting characteristics of the acoustic emission monitoring signals acquired by the acoustic emission detection signal acquisition unit to construct a cutter performance degradation index;
the inaccurate data detection unit is used for constructing a reference sequence based on the tool performance degradation indexes obtained by the tool performance degradation index construction unit and detecting inaccurate data based on the reference sequence;
the inaccurate data optimization unit is used for constructing a K nearest neighbor model based on dynamic time warping, finding out previous K historical sequences with the minimum distance as candidate series, and optimizing the inaccurate data obtained by the inaccurate data detection unit by using the mean value of the corresponding position data in the candidate series.
8. A computer comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor is adapted to perform the method of any of claims 1-6 when executing the program.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, is adapted to carry out the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011270931.5A CN112380992B (en) | 2020-11-13 | 2020-11-13 | Method and device for evaluating and optimizing accuracy of monitoring data in machining process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011270931.5A CN112380992B (en) | 2020-11-13 | 2020-11-13 | Method and device for evaluating and optimizing accuracy of monitoring data in machining process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112380992A CN112380992A (en) | 2021-02-19 |
| CN112380992B true CN112380992B (en) | 2022-12-20 |
Family
ID=74582326
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011270931.5A Active CN112380992B (en) | 2020-11-13 | 2020-11-13 | Method and device for evaluating and optimizing accuracy of monitoring data in machining process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380992B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629706B (en) * | 2023-07-19 | 2023-09-22 | 山东新中鲁建设有限公司 | BIM-based green energy-saving building construction quality assessment method |
| CN116992297B (en) * | 2023-09-27 | 2023-12-15 | 广东石油化工学院 | Rotor monitoring method, device, terminal and medium based on segmented root mean square value ratio |
| CN117259960B (en) * | 2023-09-27 | 2024-02-09 | 韶山中新智能自动化科技有限公司 | Planning and cutting regulation method of metal plate planning and laser cutting compound machine |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915434A (en) * | 2015-06-24 | 2015-09-16 | 哈尔滨工业大学 | Multi-dimensional time sequence classification method based on mahalanobis distance DTW |
| CN104915568A (en) * | 2015-06-24 | 2015-09-16 | 哈尔滨工业大学 | Satellite telemetry data abnormity detection method based on DTW |
| CN108764577A (en) * | 2018-05-31 | 2018-11-06 | 山东师范大学 | Online time series prediction technique based on dynamic fuzzy Cognitive Map |
| CN109344962A (en) * | 2018-09-05 | 2019-02-15 | 山东师范大学 | Time Series Forecasting Methods based on intuitionistic fuzzy Cognitive Map |
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| CN110046585A (en) * | 2019-04-19 | 2019-07-23 | 西北工业大学 | A kind of gesture identification method based on environment light |
| CN110276125A (en) * | 2019-06-20 | 2019-09-24 | 中国航空发动机研究院 | Aero-engine overall performance slump evaluations and prediction technique based on data |
| CN110717379A (en) * | 2019-08-28 | 2020-01-21 | 南京康尼机电股份有限公司 | Health assessment method for subway car door key components based on feature fusion |
| CN110929743A (en) * | 2018-09-19 | 2020-03-27 | 上海仪电（集团）有限公司中央研究院 | Water quality pollutant change monitoring system based on time series association and cluster analysis |
| CN111368910A (en) * | 2020-03-03 | 2020-07-03 | 重庆邮电大学 | Internet of things equipment cooperative sensing method |
| CN111598129A (en) * | 2020-04-11 | 2020-08-28 | 中国地质大学（武汉） | Drilling process data abnormity discrimination and correction method based on dynamic time warping |
| CN111832624A (en) * | 2020-06-12 | 2020-10-27 | 上海交通大学 | Tool remaining life prediction method based on anti-migration learning |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3109801A1 (en) * | 2015-06-26 | 2016-12-28 | National University of Ireland, Galway | Data analysis and event detection method and system |
| CN109447164B (en) * | 2018-11-01 | 2019-07-19 | 厦门大学 | A kind of motor behavior method for classifying modes, system and device |
-
2020
- 2020-11-13 CN CN202011270931.5A patent/CN112380992B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104915434A (en) * | 2015-06-24 | 2015-09-16 | 哈尔滨工业大学 | Multi-dimensional time sequence classification method based on mahalanobis distance DTW |
| CN104915568A (en) * | 2015-06-24 | 2015-09-16 | 哈尔滨工业大学 | Satellite telemetry data abnormity detection method based on DTW |
| CN108764577A (en) * | 2018-05-31 | 2018-11-06 | 山东师范大学 | Online time series prediction technique based on dynamic fuzzy Cognitive Map |
| CN109344962A (en) * | 2018-09-05 | 2019-02-15 | 山东师范大学 | Time Series Forecasting Methods based on intuitionistic fuzzy Cognitive Map |
| CN110929743A (en) * | 2018-09-19 | 2020-03-27 | 上海仪电（集团）有限公司中央研究院 | Water quality pollutant change monitoring system based on time series association and cluster analysis |
| CN109740694A (en) * | 2019-01-24 | 2019-05-10 | 燕山大学 | A kind of smart grid inartful loss detection method based on unsupervised learning |
| CN110046585A (en) * | 2019-04-19 | 2019-07-23 | 西北工业大学 | A kind of gesture identification method based on environment light |
| CN110276125A (en) * | 2019-06-20 | 2019-09-24 | 中国航空发动机研究院 | Aero-engine overall performance slump evaluations and prediction technique based on data |
| CN110717379A (en) * | 2019-08-28 | 2020-01-21 | 南京康尼机电股份有限公司 | Health assessment method for subway car door key components based on feature fusion |
| CN111368910A (en) * | 2020-03-03 | 2020-07-03 | 重庆邮电大学 | Internet of things equipment cooperative sensing method |
| CN111598129A (en) * | 2020-04-11 | 2020-08-28 | 中国地质大学（武汉） | Drilling process data abnormity discrimination and correction method based on dynamic time warping |
| CN111832624A (en) * | 2020-06-12 | 2020-10-27 | 上海交通大学 | Tool remaining life prediction method based on anti-migration learning |
Non-Patent Citations (4)
| Title |
|---|
| An Automatic Procedure for Vehicle Tracking with a Roadside LiDAR Sensor;Jianqing Wu;《2018 DANIEL B. FAMBRO STUDENT PAPER AWARD WINNER》;20181130;论文全文 * |
| 加工监控数据准确性量化评价及优化研究;唐思游;《计算机集成制造系统》;20201009;论文第1-16页 * |
| 基于在线相关熵极限学习机的器件退化趋势实时流预测方法;梅文娟;《仪器仪表学报》;20191227;论文全文 * |
| 多工序下刀具磨损的不完备信息系统数据挖掘方法研究;刘颖超;《计算机集成制造系统》;20180810;论文全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112380992A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112380992B (en) | Method and device for evaluating and optimizing accuracy of monitoring data in machining process | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN112284440B (en) | Sensor data deviation self-adaptive correction method | |
| CN113838054B (en) | Mechanical part surface damage detection method based on artificial intelligence | |
| CN111538311B (en) | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining | |
| CN116237817B (en) | Five-axis linkage numerical control machine intelligent monitoring system based on Internet of things | |
| CN116756595B (en) | Conductive slip ring fault data acquisition and monitoring method | |
| CN113579851B (en) | Non-stationary drilling process monitoring method based on adaptive segmented PCA | |
| CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
| CN112207631B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| CN116522268B (en) | Line loss anomaly identification method for power distribution network | |
| CN115220396B (en) | Intelligent monitoring method and system for numerical control machine tool | |
| CN112518425B (en) | Intelligent machining cutter wear prediction method based on multi-source sample migration reinforcement learning | |
| CN114861788A (en) | Load abnormity detection method and system based on DBSCAN clustering | |
| CN114118219A (en) | Data-driven real-time abnormal detection method for health state of long-term power-on equipment | |
| CN113051092B (en) | Fault diagnosis method based on optimized kernel density estimation and JS divergence | |
| CN114266457A (en) | Method for detecting different loss inducement of distribution line | |
| CN108021725B (en) | Method for determining reversing point position of oil pumping unit in electric diagram data | |
| CN115310497A (en) | Abnormity identification method for bearing of numerical control machine tool | |
| CN113536955B (en) | Signal modulation type identification method capable of realizing continuous learning | |
| CN110376436B (en) | Multi-scale noise power spectral line spectrum detection method | |
| CN113312587A (en) | Sensor acquisition data missing value processing method based on ARIMA prediction and regression prediction | |
| CN113642801A (en) | Cutter suction dredger yield prediction method based on LSTM | |
| CN114637793B (en) | Equipment fault frequent region positioning method based on big data analysis | |
| CN117150244B (en) | Intelligent power distribution cabinet state monitoring method and system based on electrical parameter 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 |