CN112486096A - Machine tool operation state monitoring method - Google Patents
Machine tool operation state monitoring method Download PDFInfo
- Publication number
- CN112486096A CN112486096A CN202011427089.1A CN202011427089A CN112486096A CN 112486096 A CN112486096 A CN 112486096A CN 202011427089 A CN202011427089 A CN 202011427089A CN 112486096 A CN112486096 A CN 112486096A
- Authority
- CN
- China
- Prior art keywords
- machine tool
- signal
- data
- data set
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R23/00—Arrangements for measuring frequencies; Arrangements for analysing frequency spectra
- G01R23/16—Spectrum analysis; Fourier analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/31—From computer integrated manufacturing till monitoring
- G05B2219/31088—Network communication between supervisor and cell, machine group
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a monitoring method of machine tool running state, which collects current signal and voltage signal of machine tool and forms first signal after protocol analysis; carrying out missing value processing and denoising processing on the first signal to obtain a second signal; performing Hilbert transform on the second signal; extracting physical characteristic data in the second signal; taking the extracted data as a first data set; dividing the first data set into a training data set and a test data set by adopting a cross validation method, establishing a model by using a residual error network, and optimizing the training model by using the test data set; the optimization model is used for analyzing the data set to be tested and outputting a result for representing the running state of the machine tool; the invention has the advantages of realizing automatic real-time monitoring of the machine tool state in industrial production and simultaneously improving the generation efficiency and the utilization rate of the machine tool.
Description
Technical Field
The invention relates to the technical field of machine tool control in industrial production, in particular to a method for monitoring the running state of a machine tool.
Background
The semi-closed loop numerical control machine tool is one of the main forces of automatic production at present, and the state change of the machine tool in the production process is concerned at all times, so that the semi-closed loop numerical control machine tool plays an important role in production and machining of enterprises. The machine tool state is effectively acquired in time, and the production condition is mastered; the method has a good promotion effect on regulating resource allocation, improving production efficiency and increasing economic benefits of enterprises.
In the manufacturing monitoring process of the existing industrial production machine tool, manual inspection or monitoring at intervals is adopted. But not enough to prevent abnormalities from occurring during the manufacturing process. Real-time monitoring cannot be realized, and the real-time processing state and information of the numerical control machine cannot be acquired; various sensors sold in the current market can collect various signals such as current, sound, vibration and the like, process the collected signals and calculate various parameter changes possibly caused when the state of the machine tool changes. According to the changed parameters, the expert analyzes the machine tool and judges the current operating environment of the machine tool; collecting sound or vibration signals of a machine tool, extracting the characteristics of the signals, and establishing a characteristic project; and training the characteristic engineering by using a machine learning or deep learning algorithm, establishing a training model, and monitoring the running state of a certain machine tool or a certain type of machine tool.
However, under the coverage of informatization, the attention of enterprises to the machine tool state still has the following obvious problems: most enterprises still adopt a manual inspection mode, and in the mode, the enterprises need to spend a large amount of labor cost to inspect the state of the machine tool, which wastes time and labor; experience judges that many workers in the production activities in the same line evaluate and diagnose the operation state of the machine tool by virtue of production experiences for many years. However, such a front-line of experienced experts is too few to be owned by all enterprises; the machine tool is diversified, and the state parameters of the machine tool are different, so that a unified standard cannot be generated; it is difficult to establish a state monitoring system; the existing monitoring system is easy to receive the interference of external environmental factors and generate interference information; a machine tool state may be misjudged. Meanwhile, when the complex monitoring systems are deployed, the workshop layout of an enterprise can be changed, the workload is large, and the willingness of the enterprise is not high; artificial intelligence has developed, and many methods for monitoring the state of a machine tool by using machine learning or deep learning have appeared. However, the methods are basically aimed at specific conditions, and have strong unicity and weak generalization capability; and some models have long training time and higher cost for enterprises.
Disclosure of Invention
The invention aims to provide a method for monitoring the running state of a machine tool, which realizes automatic real-time monitoring of the machine tool state in industrial production and simultaneously improves the generation efficiency and the utilization rate of the machine tool.
The invention is realized by the following technical scheme:
the invention discloses a method for monitoring the running state of a machine tool, which comprises the following steps:
step A: collecting a current signal and a voltage signal of a machine tool, and forming a first signal after the collected current signal and the collected voltage signal are subjected to protocol analysis;
and B: carrying out missing value processing and denoising processing on the first signal to obtain a second signal;
and C: performing Hilbert transform on the second signal to obtain a Hilbert spectrum, and calculating characteristic indexes of the Hilbert spectrum to obtain frequency domain characteristic data;
step D: extracting physical characteristic data in the second signal to obtain time sequence characteristic data;
step E: taking the time-sequence characteristic data and the frequency-domain characteristic data as a first data set;
step F: dividing a first data set into a training data set and a test data set by adopting a cross validation method, establishing a model through a residual error network, using the training data set for training the model to obtain a training model, and performing optimization test on the training model through the test data set to obtain an optimized model;
step G: and the optimization model is used for analyzing the data set to be tested and outputting a result for representing the running state of the machine tool.
In the traditional method for detecting the state of the machine tool in industrial production, manual inspection or monitoring for each fixed time is usually adopted, when the machine tool is monitored by adopting the method, time and labor are wasted, the labor cost is particularly high, if the machine tool which is directly sold in the market is adopted for monitoring, a professional person with high literacy is required to monitor, and the number of the machine tools to be processed is limited; the invention provides a monitoring method of machine tool running state, which extracts characteristic data of signals collected from a machine tool, establishes a corresponding model for optimization, and applies the optimized model to a data set extracted next time for analysis, thereby realizing real-time monitoring of the machine tool state in industrial production and improving the generation efficiency and the utilization rate of the machine tool.
Preferably, the step a adopts a data acquisition instrument to acquire a current signal and a voltage signal of the machine tool.
Preferably, the missing value processing comprises the following specific steps: checking whether the first signal has missing values; if the missing value data is less than or equal to 5% of the total data, no processing is performed on the missing value; if the missing value data is larger than 5% of the total data, performing interpolation processing on the missing value by adopting an interpolation method; the interpolation method is used for filling missing data through mode of total data.
Preferably, the denoising process is to eliminate the noise of the first signal through adaptive filtering and wavelet threshold.
The cleaning noise data is mainly the noise data generated by the external environment, and the existing noise data is eliminated.
Preferably, the frequency domain characteristic data in step C includes kurtosis, margin, waveform index, pulse index, kurtosis factor.
Preferably, the time series characteristic data in step D are barycentric frequency, mean square frequency, root mean square frequency, frequency variance and frequency standard deviation.
Preferably, the hilbert transforming the second signal in the step C specifically includes: decomposing the input second signal into several inherent mode functions Cn(t), the second signal s (t) is decomposed into:
rn(t) is the residual signal of each subtraction of the first order natural mode function from the original signal.
Preferably, the data set to be tested is:
and C, acquiring current signals or voltage signals of the machine tool next time, and processing the acquired current signals and voltage signals through the data set obtained in the steps A to F.
Preferably, the result for characterizing the operating state of the machine tool is:
if the output result is 0, the machine tool is stopped; if the output result is 1, the machine tool is idle; if the output result is 3, the machine tool is represented to be machining; if the output result is 01, representing that the cutter of the machine tool is broken; if the output result is 02, it represents that the bearing of the machine tool is abnormal.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. by adopting the monitoring method of the machine tool running state provided by the invention, the running state of the machine tool in a workshop is intelligently monitored; the running state of the machine tool is monitored in real time, and the production efficiency and the utilization rate of the machine tool are improved;
2. by adopting the method for monitoring the running state of the machine tool, the intelligent bracelet data terminal is adopted, so that the machine tool is convenient and easy to carry; the running state of the machine tool and the utilization rate of the workshop machine tool can be checked at any time and any place, and reliable data support is provided for resource adjustment of the machine tool;
3. by adopting the monitoring method for the machine tool running state, provided by the invention, a set of complete data processing process is established, so that the acquired machine tool state data is directly and quickly converted into the characteristic data for analysis, a conclusion is obtained, and the effectiveness, the accuracy and the integrity of the data are guaranteed.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a schematic view of a method for monitoring the operating state of a machine tool
FIG. 2 is a flow chart of feature extraction for a signal
FIG. 3 is a schematic flow chart of modeling
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Example one
The embodiment discloses a monitoring method of a machine tool, as shown in fig. 1, comprising the following steps:
step A: collecting a current signal and a voltage signal of a machine tool, and forming a first signal after the collected current signal and the collected voltage signal are subjected to protocol analysis;
in the process of collecting the current signals and the voltage signals, the current signals and the voltage signals are collected by a data collector; and the collected data is sent to computer software after being analyzed by a protocol.
And B: carrying out missing value processing and denoising processing on the first signal to obtain a second signal;
the acquired first signal has noise interference influenced by external conditions or the acquired signal has data clustering, grouping, deleting or truncation conditions caused by lack of information, and the data with defects can cause inaccuracy or low data fitting degree to peculiar characteristic data, so as to basically process the defects of the first signal and eliminate inaccuracy of data characteristic value extraction caused by certain defects in the data as shown in fig. 3.
The missing value processing method comprises the following specific steps: checking whether the first signal has missing values; if the missing value data is less than or equal to 5% of the total data, no processing is performed on the missing value; if the missing value data is larger than 5% of the total data, performing interpolation processing on the missing value by adopting an interpolation method; the interpolation method is used for filling missing data through the mode of total data;
the denoising processing is to eliminate the noise of the first signal through adaptive filtering and wavelet threshold, the denoising processing is mainly to eliminate the interference brought to the acquired data by the external environment, and whether the data has the noise is detected through a hypothesis testing method.
And C: as shown in fig. 2, hilbert transform is performed on the second signal to obtain a hilbert spectrum, and a characteristic index of the hilbert spectrum is calculated to obtain frequency domain characteristic data; the frequency domain characteristic data comprise center of gravity frequency, mean square frequency, root mean square frequency, frequency variance and frequency standard deviation; the time sequence characteristic is that the physical characteristics of the model are calculated by collecting equal sample numbers in different states and carrying out physical modeling on the sample numbers, and the physical characteristics reflect the conditions of the machine tool in different states.
Decomposing the input second signal into several inherent mode functions Cn(t), the second signal s (t) is decomposed into:
rn(t) is the residual signal of each subtraction of the first order natural mode function from the original signal.
Step D: extracting physical characteristic data in the second signal to obtain time sequence characteristic data; the time sequence characteristic data comprises kurtosis, margin, waveform indexes, pulse indexes and kurtosis factors.
Step E: taking the time-sequence characteristic data and the frequency-domain characteristic data as a first data set;
step F: as shown in fig. 3, a first data set is divided into a training data set and a test data set by using a cross validation method, a model is established through a residual error network, the training data set is used for training the model to obtain a training model, and the training model is subjected to an optimization test through the test data set to obtain an optimization model;
the residual error network comprises a series of residual error blocks, and the residual error blocks are composed of a direct mapping part h (x)l) And residual part F (x)l，wl) And (4) forming. I.e. xl+1＝h(xl)+F(xl，wl). For a deeper residual block N, its relationship to l layers can be expressed as:
after the data set is input into a model, the aim is to approach the residual error part to 0 as much as possible, so that the predicted value approaches to an observed value after the data set finally passes through the N layers of residual error blocks; the output result can be closer to the real situation.
Step G: and the optimization model is used for analyzing the data set to be tested and outputting a result for representing the running state of the machine tool.
The final optimization model outputs a numerical data result, the numerical data result represents different operation states of the machine tool, the numerical data are finally presented in the terminal, the terminal can display a list of currently accessed machine tools, and each machine tool is clicked, for example, when the machine tool is processing a product at the current time, the terminal can output: currently the machine tool is in process. And the trend chart displays the state of the machine tool in the latest period of time in a line chart mode, data in the trend chart is the value change condition output by the machine tool at each moment model, the processing state of the machine tool is judged according to the final numerical data, and if the output result is 0, the machine tool is represented to be stopped; if the output result is 1, the machine tool is idle; if the output result is 3, the machine tool is represented to be processed; if the output result is 01, representing that the cutter of the machine tool is broken; if the output result is 02, it represents that the bearing of the machine tool is abnormal.
And C, current signals or voltage signals acquired by the machine tool next time by the data set to be detected are acquired, the acquired current signals and voltage signals are processed through the steps A to F to obtain a data set, namely, the platform acquires signals of the monitored machine tool in real time, the acquired signals are processed to obtain a new data set, the new data set is the data set to be detected, the data set is input into the optimization model, the new data set is analyzed through the optimization model, and the output numerical data represent the running state of the machine tool at the current moment.
The terminal can show on intelligent bracelet, computer or other mobile terminal, if show in intelligent bracelet, the current state of equipment and the rate of utilization of equipment can be known at any time to the light and easily carrying of intelligent bracelet, if show on the computer, can be more comprehensive show the concrete parameter data of every lathe, including the order of lathe range and the number or the processing condition of lathe.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A method for monitoring the operation state of a machine tool is characterized by comprising the following steps:
step A: collecting a current signal and a voltage signal of a machine tool, and forming a first signal after the collected current signal and the collected voltage signal are subjected to protocol analysis;
and B: carrying out missing value processing and denoising processing on the first signal to obtain a second signal;
and C: performing Hilbert transform on the second signal to obtain a Hilbert spectrum, and calculating characteristic indexes of the Hilbert spectrum to obtain frequency domain characteristic data;
step D: extracting physical characteristic data in the second signal to obtain time sequence characteristic data;
step E: taking the time-sequence characteristic data and the frequency-domain characteristic data as a first data set;
step F: dividing a first data set into a training data set and a test data set by adopting a cross validation method, establishing a model through a residual error network, using the training data set for training the model to obtain a training model, and performing optimization test on the training model through the test data set to obtain an optimized model;
step G: and the optimization model is used for analyzing the data set to be tested and outputting a result for representing the running state of the machine tool.
2. The method for monitoring the operating condition of the machine tool according to claim 1, wherein the step a adopts a data acquisition instrument to acquire a current signal and a voltage signal of the machine tool.
3. The method for monitoring the operation state of the machine tool according to claim 1, wherein the missing value processing comprises the following specific steps: checking whether the first signal has missing values; if the missing value data is less than or equal to 5% of the total data, no processing is performed on the missing value; if the missing value data is larger than 5% of the total data, performing interpolation processing on the missing value by adopting an interpolation method; the interpolation method is used for filling missing data through mode of total data.
4. The method of claim 1, wherein the denoising process is to eliminate the noise of the first signal by adaptive filtering and wavelet threshold.
5. The method of claim 1, wherein the frequency domain characteristic data in step C includes kurtosis, margin, waveform index, pulse index, kurtosis factor.
6. The method as claimed in claim 1, wherein the time series characteristic data in step D is barycentric frequency, mean square frequency, root mean square frequency, frequency variance and frequency standard deviation.
7. The method for monitoring the operating condition of the machine tool according to any one of claims 1 to 6, wherein the Hilbert transform performed on the second signal in the step C specifically comprises: decomposing the input second signal into several inherent mode functions Cn(t), the second signal s (t) is decomposed into:
rn(t) is the residual signal of each subtraction of the first order natural mode function from the original signal.
8. The method of claim 7, wherein the data set to be measured is:
and C, acquiring current signals or voltage signals of the machine tool next time, and processing the acquired current signals and voltage signals through the data set obtained in the steps A to F.
9. A method of monitoring the operating condition of a machine tool as claimed in claim 7, wherein the result of characterizing the operating condition of the machine tool is:
if the output result is 0, the machine tool is stopped; if the output result is 1, the machine tool is idle; if the output result is 3, the machine tool is represented to be machining; if the output result is 01, representing that the cutter of the machine tool is broken; if the output result is 02, it represents that the bearing of the machine tool is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011427089.1A CN112486096A (en) | 2020-12-09 | 2020-12-09 | Machine tool operation state monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011427089.1A CN112486096A (en) | 2020-12-09 | 2020-12-09 | Machine tool operation state monitoring method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112486096A true CN112486096A (en) | 2021-03-12 |
Family
ID=74940605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011427089.1A Pending CN112486096A (en) | 2020-12-09 | 2020-12-09 | Machine tool operation state monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112486096A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326590A (en) * | 2021-12-28 | 2022-04-12 | 苏州科腾软件开发有限公司 | Machine tool data acquisition and sharing device and acquisition method thereof |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103939325A (en) * | 2014-05-05 | 2014-07-23 | 重庆大学 | Fault diagnosis method for fire pump operating at low speed |
| CN104502103A (en) * | 2014-12-07 | 2015-04-08 | 北京工业大学 | Bearing fault diagnosis method based on fuzzy support vector machine |
| CN105718876A (en) * | 2016-01-18 | 2016-06-29 | 上海交通大学 | Evaluation method of health states of ball screw |
| CN106849069A (en) * | 2017-03-13 | 2017-06-13 | 东北电力大学 | A kind of transient stability evaluation in power system method based on Pin SVM |
| CN107168244A (en) * | 2017-07-10 | 2017-09-15 | 吉林工程技术师范学院 | A kind of Digit Control Machine Tool running status on-line monitoring and warning system |
| CN207408818U (en) * | 2017-08-10 | 2018-05-25 | 黄河交通学院 | A kind of numerically-controlled machine tool with failure predication and diagnostic function |
| CN207457811U (en) * | 2017-07-24 | 2018-06-05 | 黄河交通学院 | A kind of numerically-controlled machine tool intelligent trouble diagnosis device |
| CN110153801A (en) * | 2019-07-04 | 2019-08-23 | 西南交通大学 | A kind of cutting-tool wear state discrimination method based on multi-feature fusion |
| CN110346130A (en) * | 2019-07-19 | 2019-10-18 | 北京理工大学 | A kind of boring flutter detection method based on empirical mode decomposition and time-frequency multiple features |
| CN110434676A (en) * | 2019-07-29 | 2019-11-12 | 北京理工大学 | A kind of boring monitoring chatter method of multisensor time-frequency characteristics fusion |
| CN110503004A (en) * | 2019-07-29 | 2019-11-26 | 七彩安科智慧科技有限公司 | A kind of online method of discrimination of Switching Power Supply operating status |
| CN110595765A (en) * | 2019-08-26 | 2019-12-20 | 西安理工大学 | Wind turbine generator gearbox fault diagnosis method based on VMD and FA _ PNN |
| CN110647943A (en) * | 2019-09-26 | 2020-01-03 | 西北工业大学 | Cutting tool wear monitoring method based on evolutionary data cluster analysis |
| CN111208782A (en) * | 2019-12-26 | 2020-05-29 | 北京航天测控技术有限公司 | Data processing method and device for machine tool spindle state prediction |
| CN111259959A (en) * | 2020-01-16 | 2020-06-09 | 山东超越数控电子股份有限公司 | Method, device and readable storage medium for identifying fault state of aerospace flight controller |
| CN111289250A (en) * | 2020-02-24 | 2020-06-16 | 湖南大学 | Method for predicting residual service life of rolling bearing of servo motor |
| CN111507490A (en) * | 2020-05-09 | 2020-08-07 | 武汉数字化设计与制造创新中心有限公司 | Numerical control machine tool spindle predictive maintenance method and system based on multi-source data driving |
| CN111616701A (en) * | 2020-04-24 | 2020-09-04 | 杭州电子科技大学 | Electroencephalogram multi-domain feature extraction method based on multivariate variational modal decomposition |
| CN111650453A (en) * | 2020-05-25 | 2020-09-11 | 武汉大学 | Power equipment diagnosis method and system based on windowing characteristic Hilbert imaging |
| CN111884334A (en) * | 2020-07-01 | 2020-11-03 | 南京合纵电力设备有限公司 | Monitoring method and system suitable for unattended low-voltage cabinet |
| CN111914943A (en) * | 2020-08-14 | 2020-11-10 | 广西大学 | Information vector machine method and device for comprehensively judging stability of dumping type karst dangerous rock |
| CN112036547A (en) * | 2020-08-28 | 2020-12-04 | 江苏徐工信息技术股份有限公司 | Rolling bearing residual life prediction method combining automatic feature extraction with LSTM |
-
2020
- 2020-12-09 CN CN202011427089.1A patent/CN112486096A/en active Pending
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103939325A (en) * | 2014-05-05 | 2014-07-23 | 重庆大学 | Fault diagnosis method for fire pump operating at low speed |
| CN104502103A (en) * | 2014-12-07 | 2015-04-08 | 北京工业大学 | Bearing fault diagnosis method based on fuzzy support vector machine |
| CN105718876A (en) * | 2016-01-18 | 2016-06-29 | 上海交通大学 | Evaluation method of health states of ball screw |
| CN106849069A (en) * | 2017-03-13 | 2017-06-13 | 东北电力大学 | A kind of transient stability evaluation in power system method based on Pin SVM |
| CN107168244A (en) * | 2017-07-10 | 2017-09-15 | 吉林工程技术师范学院 | A kind of Digit Control Machine Tool running status on-line monitoring and warning system |
| CN207457811U (en) * | 2017-07-24 | 2018-06-05 | 黄河交通学院 | A kind of numerically-controlled machine tool intelligent trouble diagnosis device |
| CN207408818U (en) * | 2017-08-10 | 2018-05-25 | 黄河交通学院 | A kind of numerically-controlled machine tool with failure predication and diagnostic function |
| CN110153801A (en) * | 2019-07-04 | 2019-08-23 | 西南交通大学 | A kind of cutting-tool wear state discrimination method based on multi-feature fusion |
| CN110346130A (en) * | 2019-07-19 | 2019-10-18 | 北京理工大学 | A kind of boring flutter detection method based on empirical mode decomposition and time-frequency multiple features |
| CN110503004A (en) * | 2019-07-29 | 2019-11-26 | 七彩安科智慧科技有限公司 | A kind of online method of discrimination of Switching Power Supply operating status |
| CN110434676A (en) * | 2019-07-29 | 2019-11-12 | 北京理工大学 | A kind of boring monitoring chatter method of multisensor time-frequency characteristics fusion |
| CN110595765A (en) * | 2019-08-26 | 2019-12-20 | 西安理工大学 | Wind turbine generator gearbox fault diagnosis method based on VMD and FA _ PNN |
| CN110647943A (en) * | 2019-09-26 | 2020-01-03 | 西北工业大学 | Cutting tool wear monitoring method based on evolutionary data cluster analysis |
| CN111208782A (en) * | 2019-12-26 | 2020-05-29 | 北京航天测控技术有限公司 | Data processing method and device for machine tool spindle state prediction |
| CN111259959A (en) * | 2020-01-16 | 2020-06-09 | 山东超越数控电子股份有限公司 | Method, device and readable storage medium for identifying fault state of aerospace flight controller |
| CN111289250A (en) * | 2020-02-24 | 2020-06-16 | 湖南大学 | Method for predicting residual service life of rolling bearing of servo motor |
| CN111616701A (en) * | 2020-04-24 | 2020-09-04 | 杭州电子科技大学 | Electroencephalogram multi-domain feature extraction method based on multivariate variational modal decomposition |
| CN111507490A (en) * | 2020-05-09 | 2020-08-07 | 武汉数字化设计与制造创新中心有限公司 | Numerical control machine tool spindle predictive maintenance method and system based on multi-source data driving |
| CN111650453A (en) * | 2020-05-25 | 2020-09-11 | 武汉大学 | Power equipment diagnosis method and system based on windowing characteristic Hilbert imaging |
| CN111884334A (en) * | 2020-07-01 | 2020-11-03 | 南京合纵电力设备有限公司 | Monitoring method and system suitable for unattended low-voltage cabinet |
| CN111914943A (en) * | 2020-08-14 | 2020-11-10 | 广西大学 | Information vector machine method and device for comprehensively judging stability of dumping type karst dangerous rock |
| CN112036547A (en) * | 2020-08-28 | 2020-12-04 | 江苏徐工信息技术股份有限公司 | Rolling bearing residual life prediction method combining automatic feature extraction with LSTM |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114326590A (en) * | 2021-12-28 | 2022-04-12 | 苏州科腾软件开发有限公司 | Machine tool data acquisition and sharing device and acquisition method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112596495A (en) | Industrial equipment fault diagnosis method and system based on knowledge graph | |
| CN107742053B (en) | Wind turbine generator set abnormity identification method and device | |
| CN109034400B (en) | Transformer substation abnormal measurement data prediction platform system | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
| CN108491931B (en) | Method for improving nondestructive testing precision based on machine learning | |
| CN109063885A (en) | A kind of substation's exception metric data prediction technique | |
| US20220179393A1 (en) | Machine tool evaluation method, machine tool evaluation system and medium | |
| Branisavljević et al. | Automatic, semi-automatic and manual validation of urban drainage data | |
| CN117251812A (en) | High-voltage power line operation fault detection method based on big data analysis | |
| CN114386626A (en) | Equipment state evaluation and operation and maintenance strategy formulation realization system based on digital twinning | |
| CN115576284A (en) | Clothing workshop intelligent management method and system | |
| CN117270514B (en) | Production process whole-flow fault detection method based on industrial Internet of things | |
| CN113887749A (en) | Cloud edge cooperation-based multi-dimensional monitoring and disposal method, device and platform for power internet of things | |
| CN114611744A (en) | Machine tool management method, machine tool management system, and medium | |
| CN116611013A (en) | Anomaly detection and root cause analysis method and system for industrial time series data | |
| CN112580858A (en) | Equipment parameter prediction analysis method and system | |
| CN115660288A (en) | Analysis management system based on internet big data | |
| CN112486096A (en) | Machine tool operation state monitoring method | |
| CN107506832B (en) | Hidden danger mining method for assisting monitoring tour | |
| CN116566839A (en) | Communication resource quality evaluation system for power enterprises | |
| CN116108376A (en) | Monitoring system and method for preventing electricity stealing, electronic equipment and medium | |
| CN110008245B (en) | Method suitable for searching equipment fault early warning model time period | |
| CN114065651A (en) | Fault time prediction method for rotary equipment | |
| CN114442543A (en) | Computer monitoring method suitable for early warning of hydropower station fault |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210312 |