CN108844662B - Method for evaluating state of electrical cabinet of numerical control machine tool - Google Patents
Method for evaluating state of electrical cabinet of numerical control machine tool Download PDFInfo
- Publication number
- CN108844662B CN108844662B CN201810955492.8A CN201810955492A CN108844662B CN 108844662 B CN108844662 B CN 108844662B CN 201810955492 A CN201810955492 A CN 201810955492A CN 108844662 B CN108844662 B CN 108844662B
- Authority
- CN
- China
- Prior art keywords
- electrical cabinet
- value
- machine tool
- characteristic value
- layer
- 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 11
- 238000012423 maintenance Methods 0.000 claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000005070 sampling Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000011156 evaluation Methods 0.000 abstract description 13
- 230000000007 visual effect Effects 0.000 abstract description 9
- 230000032683 aging Effects 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 5
- 230000015556 catabolic process Effects 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004224 protection Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Fuzzy Systems (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Mathematics (AREA)
- Biomedical Technology (AREA)
- Mathematical Analysis (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a method for evaluating the state of an electrical cabinet of a numerical control machine tool, which is based on the real-time working condition of the machine tool, monitors the temperature data of the electrical cabinet on line, extracts sensitive characteristics, constructs a fuzzy neural network, and establishes a model for evaluating the state of the electrical cabinet of the numerical control machine tool on line, and has higher real-time performance and practicability. And reasonably evaluating the aging degree of components in the electrical cabinet according to the evaluation result of the working state of the electrical cabinet, finding out the visual maintenance of the performance-degraded components, and if an abnormal condition occurs, sending an alarm signal by the system, and stopping the machine for maintenance.
Description
Technical Field
The invention relates to the technical field of state evaluation of electrical cabinets, in particular to a state evaluation method for electrical cabinets of a numerical control machine tool.
Background
The electrical cabinet of the numerical control machine tool is provided with various electrical components for strong current control of the machine tool, and the electrical components not only provide a power supply for a weak current control system such as numerical control and servo, and various electrical protections such as short circuit, overload and undervoltage, but also play a role of a bridge between a PLC output interface and electrical execution elements of various auxiliary devices of the machine tool. At present, most machine tool electrical control cabinets are not provided with an online state evaluation system, components in the cabinet are replaced, fault maintenance and the like are mostly carried out after faults occur, and certain hysteresis exists.
Heat-generating faults of electrical equipment include faults external to the equipment (e.g., electrical joint faults) and various faults internal to the equipment housing. The external fault can obtain visual information from the outside of the equipment, and the internal fault obtains the temperature rule of the internal fault appearing outside the equipment by combining the statistical analysis of a field detection example according to the internal structure and the operation working condition of the equipment, so that the nature, the part and the severity of the internal fault of the equipment are judged. The method for evaluating the state of the electrical cabinet of the numerical control machine tool is provided, on the premise of the field working condition of the machine tool, the health state of the electrical cabinet is evaluated in real time based on temperature data measured at different parts in the electrical cabinet, and on the basis, the machine tool is maintained and shut down for maintenance according to the conditions, so that the method has great significance for improving the normal operation and production benefits of the machine tool.
Disclosure of Invention
The purpose of the invention is as follows: aiming at the prior art, a state evaluation method for an electrical cabinet of a numerical control machine tool is provided, and the state evaluation method is used for evaluating the working state of the electrical cabinet of the machine tool.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for evaluating the state of an electric cabinet of a numerical control machine tool comprises the following steps:
step 1: collecting data of each temperature sensor in the electrical cabinet, recording the data of each temperature sensor in the same moment as a sample, and recording the working state of the electrical cabinet corresponding to the sample to obtain a sample set;
step 2: extracting a temperature characteristic value from the sample set to obtain a characteristic value sequence X (k) consisting of the temperature characteristic values, wherein X (k) is (x)1(k),x2(k),...,xn(k) K is the temperature sampling sequence number of the whole sample data sequence, n is the dimension of a single sample, xi(k) Is a temperature characteristic value, i ═ 1, n];
And step 3: calculating a temperature characteristic value xi(k) Gray correlation coefficient gamma of working state of electric cabinet corresponding to gray correlation coefficient gammaiDistributing corresponding weight omega to the correlation coefficient of each sensor channel and the working state of the machine tooli;
And 4, step 4: according to the respective sampleThe working states of the electrical cabinet are divided into three types, the first type is as follows: the electrical cabinet works normally, and the components are not abnormal; the second type is: the electrical cabinet basically works normally, performance degradation of components and the like occurs, but the operation of the electrical cabinet is not influenced, and visual maintenance can be realized; in the third category: the regulator cubicle work is unusual, needs to shut down the maintenance. In the first kind of working stateMinimum value of (2)In the second type of operating stateMinimum value of (2)
And 5: calculating new samplesIf it is notJudging that the electrical cabinet works normally and the components are not abnormal; if it is notJudging that the electrical cabinet basically works normally, performance degradation of components and the like occurs, but the operation of the electrical cabinet is not influenced, and visual maintenance is realized; if it is notThe electrical cabinet is judged to be abnormal in work and needs to be shut down for maintenance.
Preferably, in step 2, a linear regression analysis method is used to extract the temperature data characteristic value:
establishing a unary linear regression model expressed as:
y=as+b
wherein y is a temperature value, s is a sampling time window sequence number, a is a linear characteristic value of a temperature sequence, b is a linear constant of the temperature sequence, i is a data sampling sequence number in a single sample, and n is a single sample dimension.
Preferably, in step 3, the grey correlation coefficient γ isiAnd weight omegaiThe calculation steps are as follows:
will be at temperatureCharacteristic value xi(k) Processed as reference data xo(k),Wherein, maxxi(k) Is the maximum value, x, of the sample data sequencemIs the target value of the target eye characteristic; calculating a gray correlation coefficientWherein, Deltaoi(k)=|xo(k)-xi(k) L, rho is a resolution coefficient, rho is more than or equal to 0 and less than or equal to 1,
distributing corresponding weight omega to the correlation coefficient of each sensor channel and the working state of the machine tooli,
The degree of association is then expressed as:k is a sample data sequence sampling serial number, i is a data sampling serial number in a single sample, and n is a single sample dimension.
putting the characteristic value sequence into a fuzzy neural network for network learning, wherein the fuzzy neural network comprises an input layer, a fuzzy layer, an input signal activation layer, a de-fuzzy layer and an output layer; the fuzzy layer is calculated by adopting a Gaussian membership function, and the calculation formula of the central value of the membership function is as follows:
the calculation formula of the width value of the membership function is as follows:
wherein t is 1, 2, 3; l is the number of iterations; eta is learning efficiency; x is a temperature characteristic value; the calculation formula of the blurring layer is:
the calculation formula of the input signal activation layer is as follows:
the calculation formula of the deblurring layer is as follows:
ft(x)=Nt(x)(λtx+μt),
wherein,
the calculation formula of the output layer is as follows:
the concrete network learning steps are as follows:
1) firstly, setting the central value and the width value of the membership function as random numbers tending to 0, and calculating the error between the actual output and the expected output of the networkWherein Z isqAnd Z is the expected output value and the actual output value of the output layer, respectively;
2) when the error E meets the precision requirement, the training is finished, otherwise, the learning efficiency and the iteration number are corrected to continue the training;
the corresponding fuzzy rule is as follows:
If(x is M1)then(f1=N1(x)(λ1x+μ1))
If(x is M2)then(f2=N2(x)(λ2x+μ2))
If(x is M3)then(f3=N3(x)(λ3x+μ3))
f1corresponding to the first type of working state of the electrical cabinet; f. of2Corresponding to the second working state of the electrical cabinet; f. of3Corresponding to the third working state of the electrical cabinet; will f istCorresponding temperature characteristic value as sample data to calculate correspondingf1、f2Corresponding toRespectively is
Preferably, the eigenvalue series is compressed and deburred before the eigenvalue series is subjected to fuzzy neural network training.
Has the advantages that: based on the real-time working condition of the machine tool, the temperature data of the electrical cabinet is monitored on line, the sensitive characteristics are extracted, the grey neural network is constructed, the state evaluation model of the electrical cabinet of the numerical control machine tool is established on line, and the real-time performance and the practicability are higher. And reasonably evaluating the aging degree of components in the electrical cabinet according to the evaluation result of the working state of the electrical cabinet, finding out the visual maintenance of the performance-degraded components, and if an abnormal condition occurs, sending an alarm signal by the system, and stopping the machine for maintenance.
Drawings
FIG. 1 is a schematic structural diagram of a numerically-controlled machine tool electrical cabinet state evaluation system;
fig. 2 is a schematic diagram of dividing the working state of the electrical cabinet into 3 stages, where point a is a visual maintenance critical point and point B is a shutdown maintenance critical point;
FIG. 3 is a schematic diagram of the evaluation of the working condition of the electrical cabinet;
fig. 4 is a schematic diagram of a fuzzy neural network structure.
Detailed Description
The invention is further explained below with reference to the drawings.
As shown in fig. 1, a method for evaluating the state of an electrical cabinet of a numerically-controlled machine tool includes the following steps: (1) collecting temperature data of an electrical cabinet of the numerical control machine tool. Temperature sensors are reasonably arranged in the machine tool electrical cabinet, and sensor signals are converted into temperature values after being processed by a data acquisition system, so that original parameters are provided for an electrical cabinet state evaluation system.
(2) And extracting a temperature characteristic value from the collected data. And establishing an unary linear regression model y as + b, selecting a primary term coefficient a as a temperature characteristic value, and selecting an optimal data sampling width, wherein the sampling width is too small to represent the change trend in a short time, and the calculation complexity is increased if the sampling width is too large.
(3) And carrying out compression and deburring processing on the characteristic value array. And partial points which frequently cause data density but do not influence the evaluation state are removed from the temperature characteristic value sequence, so that the sample capacity is reduced, and the calculation workload is reduced. In order to avoid false alarm caused by the phenomenon of 'burr', the square of the characteristic value is taken as a measurement standard, and if the square deviation of the characteristic value at a certain point is slightly larger, the point can be ignored.
(4) Collecting the processed temperature characteristic values a in a data sequence X (k), wherein X (k) is (x)1(k),x2(k),...,xn(k) K is the temperature sampling sequence number of the whole sample data sequence, and i is the temperature sampling sequence number in a single sample. x is the number ofi(k) Is a temperature characteristic value, i ═ 1, n]。
(5) And calculating grey correlation coefficients and correlation degrees of the temperature characteristic values of different positions in the electrical cabinet and the working state of the electrical cabinet. Sampling data x according to the characteristics of the targeti(k) Processed as reference data xo(k)。Wherein, maxxi(k) Is the maximum value, x, of the sample data sequencemFor the target value of the eye characteristic, for simplifying the calculation, x0(k)=[1 ... 1]. Calculating a gray correlation coefficient
Wherein, Deltaoi(k)=|xo(k)-xi(k) And | and rho are resolution coefficients, rho is more than or equal to 0 and less than or equal to 1, and is generally 0.5.
The gray correlation ∑ (ω) is obtained according to the gray correlation coefficientiγi) Where n is a single sample dimension, i ═ 1, n]. Distributing corresponding weight omega to the correlation coefficient of each sensor channel and the working state of the machine tooli,Whereinγave-γiIf > 0, get "-", otherwise get "+”。∑(ωiγi) The relationship with the machine tool operating state is shown in fig. 2. Fig. 2 divides the working state of the electrical cabinet into 3 stages, wherein point a is a visual maintenance critical point, and point B is a shutdown maintenance critical point. In stage 1, the electrical cabinet works normally, the components are not abnormal, and parameters are evaluatedIn stage 2, the electrical cabinet basically works normally, performance degradation of components and parts occurs, and the like, but operation is not influenced, visual maintenance is realized, and parameters are evaluatedIn stage 3, the electrical cabinet works abnormally and needs to be shut down for maintenance and parameters are evaluatedDifferent failure modes and failure degrees of the electrical cabinet have corresponding evaluation parametersThe evaluation diagram is shown in fig. 3.
Considering historical data and field working conditions, putting the temperature characteristic value sequence of the electrical cabinet during the operation of the machine tool into a fuzzy neural network for network learning, setting training times, learning rate and the like, fixing a network structure, and obtaining a critical value of visual maintenance and shutdown maintenance of the electrical cabinetA 5-layer fuzzy neural network of 1 input (temperature characteristic value array), 3 fuzzy rules and 1 output (denoted by Z) is established, and the structure is shown in fig. 4. The 1 st layer is an input layer, the 2 nd layer is a fuzzy layer, and a Gaussian membership function is adopted for calculation. Firstly, setting the central value and the width value of the membership function as random numbers tending to 0. Calculating an error between an actual output and a desired output of a networkWherein Z isqAnd Z is the desired output value of the output layer andthe actual output value. Center value of membership functionWidth value of membership functionWherein t is 1, 2, 3, l is iteration times, η is learning efficiency, training is finished when the error between the actual output and the ideal output of the network is in a small range, otherwise, the training is continued by correcting parameters, the network is fuzzified after calculating the central value and the width value of the membership function, and the following calculation formula is obtainedLayer 3 is the input signal active layer, level 4 is defuzzification, calculating the output of each rule, ft(x)=Nt(x)(λtx+μt). At layer 5, the sum of all rules,the corresponding fuzzy rule is as follows:
If(x is M1)then(f1=N1(x)(λ1x+μ1))
If(x is M2)then(f2=N2(x)(λ2x+μ2))
If(x is M3)then(f3=N3(x)(λ3x+μ3))
f1、f2、f3corresponding to stage 1, stage 2, stage 3, respectively, in fig. 2. Will f istCorresponding temperature characteristic value as sample data to calculate correspondingf1、f2Stage correspondenceIs the value at two critical points
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (4)
1. A method for evaluating the state of an electric cabinet of a numerical control machine tool is characterized by comprising the following steps:
step 1: collecting data of each temperature sensor in the electrical cabinet, recording the data of each temperature sensor in the same moment as a sample, and recording the working state of the electrical cabinet corresponding to the sample to obtain a sample set;
step 2: extracting a temperature characteristic value from the sample set to obtain a characteristic value sequence X (k) consisting of the temperature characteristic values, wherein X (k) is (x)1(k),x2(k),...,xn(k) K is the temperature sampling sequence number of the whole sample data sequence, n is the dimension of a single sample, xi(k) Is a temperature characteristic value, i ═ 1, n];
And step 3: calculating a temperature characteristic value xi(k) Gray correlation coefficient gamma of working state of electric cabinet corresponding to gray correlation coefficient gammaiAnd distributing corresponding weight omega to the correlation coefficient of each sensor channel and the working state of the machine tooli;
And 4, step 4: according to each sampleThe working states of the electrical cabinet are divided into three types, the first type is as follows: the electrical cabinet works normally, and the components are not abnormal; the second type is: the electrical cabinet basically works normally, and the performance of components is degraded without influencing the operation of the electrical cabinet; in the third category: the electrical cabinet works abnormally and needs to be shut down for maintenance; in the first kind of working stateMinimum value of (2)In the second type of operating stateMinimum value of (2)
And 5: calculating new samplesIf it is notJudging that the electrical cabinet works normally and the components are not abnormal; if it is notJudging that the electrical cabinet basically works normally, and the performance of the components is degraded without influencing the operation of the electrical cabinet; if it is notJudging the working abnormity of the electrical cabinet, and needing to be shut down for maintenance;
putting the characteristic value sequence into a fuzzy neural network for network learning, wherein the fuzzy neural network comprises an input layer, a fuzzy layer, an input signal activation layer, a de-fuzzy layer and an output layer; the fuzzy layer is calculated by adopting a Gaussian membership function, and the calculation formula of the central value of the membership function is as follows:
the calculation formula of the width value of the membership function is as follows:
wherein t is 1, 2, 3, l is iteration times, η is learning efficiency, and E is the error between the actual output and the expected output;to obtain a partial derivative about E for the central value of the membership function,calculating a partial derivative about E for the width value of the membership function; x is a temperature characteristic value; the calculation formula of the blurring layer is:
the calculation formula of the input signal activation layer is as follows:
the calculation formula of the deblurring layer is as follows:
ft(x)=Nt(x)(λtx+μt),
wherein,
t0as an initial value, the calculation formula of the output layer is:
the concrete network learning steps are as follows:
1) firstly, setting the central value and the width value of the membership function as random numbers tending to 0, and calculating the error between the actual output and the expected output of the networkWherein Z isqAnd Z is the expected output value and the actual output value of the output layer, respectively;
2) when the error E meets the precision requirement, the training is finished, otherwise, the learning efficiency and the iteration number are corrected to continue the training;
the corresponding fuzzy rule is as follows:
If(x is M1)then(f1=N1(x)(λ1x+μ1))
If(x is M2)then(f2=N2(x)(λ2x+μ2))
If(x is M3)then(f3=N3(x)(λ3x+μ3))
f1corresponding to the first type of working state of the electrical cabinet; f. of2Corresponding to the second working state of the electrical cabinet; f. of3Corresponding to the third working state of the electrical cabinet; will f istCorresponding temperature characteristic value as sample data to calculate correspondingf1、f2Corresponding toMinimum value of (2)I.e. each is
2. The method for evaluating the state of the electrical cabinet of the numerical control machine tool according to claim 1, wherein in the step 2, a linear regression analysis method is adopted to extract the temperature characteristic value:
establishing a unary linear regression model expressed as:
y=as+b
wherein y is a temperature value, s is a sampling time window sequence number, a is a linear characteristic value of a temperature sequence, b is a linear constant of the temperature sequence, i is a data sampling sequence number in a single sample, and n is a single sample dimension.
3. The method for evaluating the state of the electrical cabinet of the numerically-controlled machine tool according to claim 1, wherein in step 3, a grey correlation coefficient γiAnd weight omegaiThe calculation steps are as follows:
the temperature characteristic value xi(k) Processed as reference data xo(k),Wherein, maxxi(k) Is the maximum value, x, of the sample data sequencemIs the target value of the target eye characteristic; calculating a gray correlation coefficientWherein, Deltaoi(k)=|xo(k)-xi(k) Rho is a resolution coefficient, rho is more than or equal to 0 and less than or equal to 1,
distributing corresponding weight omega to the correlation coefficient of each sensor channel and the working state of the machine tooli,
4. The method for evaluating the state of the electrical cabinet of the numerical control machine tool according to claim 1, wherein before the fuzzy neural network training is performed on the characteristic value number series, the characteristic value number series is compressed and deburred.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810955492.8A CN108844662B (en) | 2018-08-21 | 2018-08-21 | Method for evaluating state of electrical cabinet of numerical control machine tool |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810955492.8A CN108844662B (en) | 2018-08-21 | 2018-08-21 | Method for evaluating state of electrical cabinet of numerical control machine tool |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108844662A CN108844662A (en) | 2018-11-20 |
CN108844662B true CN108844662B (en) | 2020-08-14 |
Family
ID=64189811
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810955492.8A Active CN108844662B (en) | 2018-08-21 | 2018-08-21 | Method for evaluating state of electrical cabinet of numerical control machine tool |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108844662B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111523660B (en) * | 2020-04-15 | 2024-06-21 | 南京清然能源科技有限公司 | Audio-visual heat integrated abnormality detection alarm method based on artificial intelligence |
CN114371658B (en) * | 2021-12-27 | 2024-06-07 | 上海滨捷机电有限公司 | Control method and system for numerical control machine integrated electric cabinet, electronic equipment and readable storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103678765B (en) * | 2013-10-31 | 2016-04-27 | 上海交通大学 | Based on the running state of transformer comprehensive estimation method of on-line monitoring |
CN104076233B (en) * | 2014-07-18 | 2017-03-15 | 彭浩明 | Degree of aging detection method and detection means |
CN107289998B (en) * | 2017-05-12 | 2019-08-23 | 淮阴工学院 | CAN bus based pig house environment temperature intelligent monitoring system |
-
2018
- 2018-08-21 CN CN201810955492.8A patent/CN108844662B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN108844662A (en) | 2018-11-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2021004154A1 (en) | Method for predicting remaining life of numerical control machine tool | |
Demetriou et al. | Incipient fault diagnosis of dynamical systems using online approximators | |
DE102017108169B4 (en) | Production system that defines a determination value of a variable in relation to a product deviation | |
CN107357275B (en) | Non-gaussian industrial process fault detection method and system | |
CN108363836B (en) | Multi-working-condition self-adaptive industrial robot health degree assessment method and system | |
Wang et al. | On line tool wear monitoring based on auto associative neural network | |
CN108280543B (en) | Working condition self-adaptive equipment health degree evaluation method based on classification regression mode | |
Lennox et al. | Application of multivariate statistical process control to batch operations | |
CN108844662B (en) | Method for evaluating state of electrical cabinet of numerical control machine tool | |
CN116086537B (en) | Equipment state monitoring method, device, equipment and storage medium | |
CN112989587B (en) | Online analysis method and system for degradation cause of capacitive voltage transformer | |
CN115828170B (en) | Fault detection method based on electronic control data of tunneling machine | |
CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
CN111506049A (en) | Multiple fault diagnosis method for aero-engine control system based on AANN network system | |
CN111368428A (en) | Sensor precision reduction fault detection method based on monitoring second-order statistics | |
CN112668105A (en) | Helicopter transmission shaft abnormity judgment method based on SAE and Mahalanobis distance | |
CN111340367B (en) | Oil-shortage equipment state evaluation method and system based on multi-dimensional relevance data analysis | |
Bejaoui et al. | A data-driven prognostics technique and rul prediction of rotating machines using an exponential degradation model | |
Wei et al. | Remaining useful life estimation based on gamma process considered with measurement error | |
CN108875276B (en) | A kind of closed-loop system stability monitoring method of data-driven | |
CN110751217A (en) | Equipment energy consumption ratio early warning analysis method based on principal component analysis | |
CN116627116B (en) | Process industry fault positioning method and system and electronic equipment | |
CN111618655B (en) | Quantitative evaluation method for health degree of ball screw of numerical control machine tool | |
CN115358294A (en) | Micro fault detection method for high-speed train traction system | |
CN115081798A (en) | PLS algorithm-based plate and strip hot finish rolling process sub-frame combined monitoring and diagnosis method |
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 |