CN109724785A - A kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion - Google Patents
A kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion Download PDFInfo
- Publication number
- CN109724785A CN109724785A CN201811636302.2A CN201811636302A CN109724785A CN 109724785 A CN109724785 A CN 109724785A CN 201811636302 A CN201811636302 A CN 201811636302A CN 109724785 A CN109724785 A CN 109724785A
- Authority
- CN
- China
- Prior art keywords
- parameter
- hobboing cutter
- module
- life prediction
- cutter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 54
- 230000004927 fusion Effects 0.000 title claims abstract description 15
- 238000005299 abrasion Methods 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000004891 communication Methods 0.000 claims abstract description 6
- 238000012806 monitoring device Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 36
- 238000000034 method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 14
- 230000007423 decrease Effects 0.000 claims description 13
- 208000024891 symptom Diseases 0.000 claims description 12
- 230000001133 acceleration Effects 0.000 claims description 9
- 230000007850 degeneration Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 239000000203 mixture Substances 0.000 claims description 6
- 230000002123 temporal effect Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 230000001788 irregular Effects 0.000 claims description 4
- 230000003321 amplification Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims 1
- 238000005096 rolling process Methods 0.000 claims 1
- 230000001427 coherent effect Effects 0.000 abstract description 3
- 241000208340 Araliaceae Species 0.000 description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 description 3
- 235000008434 ginseng Nutrition 0.000 description 3
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 230000037431 insertion Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000005641 tunneling Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a kind of tool condition monitoring based on Multi-source Information Fusion and life prediction systems, including information acquisition module, signal pre-processing module, state monitoring module, life prediction module and long-range monitoring modular；The parameter information of information acquisition module acquisition hobboing cutter, state monitoring module and/or life prediction module are sent to after pre-processing by signal pre-processing module, state monitoring module exports hobboing cutter state, the remaining life of life prediction module output hobboing cutter, state monitoring module, the output result of life prediction module can be directly viewable at the scene, can also remotely be checked.The present invention realizes visualized management by key parameters such as hobboing cutter monitoring device real-time monitoring hobboing cutter stress, abrasion loss, revolving speed, shapes, by handling hobboing cutter coherent signal analysis, real-time monitoring hobboing cutter state simultaneously predicts hobboing cutter remaining life, and it can check whether humanized auxiliary judgment replaces cutter by mobile phone, long-range end PC etc. for correlation engineering administrative staff with the communication of long-range monitoring modular.
Description
Technical field
The invention belongs to tool monitoring technical fields, and in particular to a kind of tool condition monitoring based on Multi-source Information Fusion
And life prediction system.
Background technique
Complete-section tunnel boring machine is in the construction process to the inspection of knife disc tool at present it may first have to shut down, Wu Fa
Tool wear situation is observed in tunneling process, has seriously affected project progress.The region of knife disc tool is unsupported area domain,
And Tu Cang is closed hyperbaric environment, more demanding to service personnel's self diathesis, exchanging knives process is time-consuming and laborious, and is easy to appear
Safety accident.Itself to equipment, it can be just repaired or replaced after tool damage, construction personnel can not know in tunneling process
The working condition of road hobboing cutter, only cutter occur it is badly damaged driving progress is affected greatly when, carry out inspection knife, tool changing
Work, impacts construction efficiency and construction economy.Relevant enterprise has carried out hobboing cutter study on monitoring both at home and abroad at present, but
It is still at an early stage but lower to the utilization rate of information, the remaining life of hobboing cutter can not be predicted in advance.
Summary of the invention
For above-mentioned deficiency described in the prior, the present invention provides a kind of hobboing cutter monitoring system based on multi-source information
System is handled by the analysis to hobboing cutter coherent signal, knows the working condition of hobboing cutter, judge whether to break down, and predict to roll
Knife remaining life, humanized auxiliary shield driver judge whether to replace cutter.
In order to solve the above technical problems, the technical solution adopted in the present invention is as follows: a kind of based on Multi-source Information Fusion
Tool condition monitoring and life prediction system, including information acquisition module, signal pre-processing module, state monitoring module, service life
Prediction module and long-range monitoring modular；The parameter information of the information acquisition module acquisition hobboing cutter, passes through signal pre-processing module
State monitoring module and/or life prediction module are sent to after pretreatment, state monitoring module receives hobboing cutter parameter information and locates
Hobboing cutter state is exported after reason, life prediction module receives hobboing cutter parameter and exports the remaining life of hobboing cutter, status monitoring after handling
The direct scene of the output result of module and life prediction module is checked and is delivered to long-range monitoring modular.
Specifically, state monitoring module, the output result of life prediction module both can directly scene check, can also pass through
Wireless communication module is sent to remote port, can be checked by mobile phone, long-range end PC etc. for long-range correlation engineering administrative staff.
The hobboing cutter parameter information, including running parameter and technological parameter；The running parameter include revolving speed, hobboing cutter power,
Torque, cutter shaft vibration；Revolving speed is obtained by speed probe, for example Hall sensor, encoder or angular transducer；Hobboing cutter
Power and torque, are obtained by six-dimension force sensor；Cutter shaft vibration, is passed by acceleration transducer (such as gravity sensor) or speed
Sensor obtains.
The technological parameter includes cutter ring appearance profile, temperature, cutter ring abrasion loss；Cutter ring appearance profile, is passed by ranging
Sensor collects to obtain；Temperature is obtained by temperature sensor；Cutter ring abrasion loss, is obtained by current vortex sensor.
The signal pre-processing module is to revolving speed, hobboing cutter power, torque, cutter shaft vibration, cutter ring appearance profile, temperature, knife
Circle abrasion loss carries out the pretreatment such as signal amplification and filtering respectively.
The state monitoring module handles the parameter information of acquisition to obtain the working condition of hobboing cutter, status monitoring
The processing step of module are as follows:
S1 extracts the signal key feature of pretreated operating parameter information；
Extracting applicable method is support vector machines, deep neural network algorithm, BP neural network algorithm, wavelet analysis calculation
The combination of one or more of method, Principal Component Analysis Algorithm etc..
S2, binding signal key feature and hobboing cutter technological parameter establish symptom set.
S2.1 vibrates width to the temperature in hobboing cutter technological parameter information and the power in operating parameter information, torque, cutter shaft
Value calculates sign degree of membership μ (x), sign degree of membership μ (x) general formula are as follows:
When parameter increases:
When parameter reduces:
Wherein, the value interval that parameter allows is [min, max], and normal value is fallen within section [a, b], and
Judgement according to the value of sign degree of membership μ (x) for hobboing cutter working condition provides foundation.
S2.2, the sign degree of membership obtained according to step S2.1 simultaneously combine the parameter information obtained to establish symptom set.
The symptom set, including parameter type, parameter name and parameter attribute；The parameter type, including working condition,
Frequency domain character, temporal signatures, related process parameters and fundamental surveillance information.
The working condition includes four parameters, respectively the relationship of rotary regimes, load condition, amplitude and revolving speed, vibration
The relationship of width and load；The parameter attribute of the rotary regimes, including the decline of speed stabilizing, speed change, speed, stalling；The load shape
The parameter attribute of state, including constant, up and down；The parameter attribute of the relationship of the amplitude and revolving speed, including with rotation speed change
Obviously, unobvious with rotation speed change；The parameter attribute of the relationship of the amplitude and load, including it is obvious with load variations, with negative
Lotus variation is unobvious.
The frequency domain character includes two parameters, respectively amplitude and amplitude variation；The parameter attribute of the amplitude, including
It is larger；The parameter attribute of the amplitude variation, including be basically unchanged, slowly rise, slowly decline, fly up, declining suddenly,
Cyclically-varying, irregular variation.
The temporal signatures include two parameters, respectively amplitude variation tendency and waveform state；The amplitude variation becomes
The parameter attribute of gesture, including be basically unchanged, slowly rise, slowly decline, fly up, decline suddenly, cyclically-varying, not advising
Then change；The parameter attribute of the waveform variation, including simple harmonic quantity waveform, aperiodic waveform, deformity.
The related process parameters include three parameters, respectively temperature, abrasion loss, conduit profile；The ginseng of the temperature
Number attribute, including it is excessively high, too low；The parameter attribute of the abrasion loss, including excessively high, eccentric wear；The parameter category of the conduit profile
Property, including normal, deformation.
The parameter of the fundamental surveillance information is hobboing cutter channel information, and the parameter attribute of hobboing cutter channel information is hobboing cutter volume
Number.
Knowledge base, the knowledge base of hobboing cutter relevant parameter threshold value of S3, the symptom set that will acquire and hobboing cutter historical data carry out
Comparison.
The result that step S3 is obtained is obtained hobboing cutter failure by forward reasoning and assumes collection by S4.
S5, backward inference validation fault assume collection, and the reasoning results are carried out Fuzzy processing if verifying is correct, will be obscured
Quantifier and numerical intervals correspond.
The fuzzy quantifier include affirm, be likely to, may, a little may, possibility it is small, it is not possible that；With fuzzy quantifier
One-to-one numerical intervals are 1,0.8,0.6,0.4,0.2,0.
S6 selects Threshold Alerts or man-machine interaction mode display parameter information and the reasoning results on industrial personal computer, according to work
The display result of control machine judges the working condition of hobboing cutter, to judge whether to tool changing operation.
The life prediction module handles the parameter information received to obtain the remaining life of hobboing cutter；It is received
To parameter information include hobboing cutter power, torque, temperature, abrasion loss and cutter shaft vibration.
The processing step of life prediction module are as follows: S1, it is mutually empty using multivariable to obtained pretreated parameter information
Between restructing algorithm carry out phase space reconfiguration, as mode input end data:
X (t)=(X1(t),X2(t),…,Xi(t),…,XK(t))；
Wherein: Xi(t) the different types of information value of i-th of parameter index of hobboing cutter, m are indicatediFor the insertion dimension of i-th of variable
Number, τiFor the delay time of i-th of variable, K is the number of parameter index.
S2 obtains hobboing cutter degeneration index Ab, and using hobboing cutter degeneration index as model fan-out evidence.
S2.1, construction feature space vector matrix X.
S2.1.1 obtains the time domain index of each parameter index waveform.
The time domain index includes maximum value, minimum value, average amplitude, peak value, root-mean-square value gradient and kurtosis.
S2.1.2 obtains the frequency-domain index of each parameter index.
The frequency-domain index, the characteristic frequency amplitude including vibration values.
S2.1.3, the time domain index and frequency-domain index constitutive characteristic space vector matrix X of acquisition:
Wherein, the row of feature space vector matrix X indicates the feature vector of synchronization different parameters index composition；Feature
The column of space vector matrix X indicate the feature vector of the index composition of different moments；N is constitutive characteristic space vector matrix X's
Parameter index number, and n≤K.
Feature space vector matrix X is standardized and is obtained covariance matrix S by S2.2.
S2.3 obtains eigenvalue λ according to covariance matrix S1,λ2,…,λnAnd feature vector v corresponding with characteristic value1,
v2,…,vn。
The descending sequence of characteristic value is obtained diagonal matrix A by S2.4:
S2.5 calculates the principal component matrix Y of feature space vector matrix X according to feature vector:
Y=XV；
V=[v1,v2,…,vn]。
S2.6, using the first principal component of principal component matrix Y as hobboing cutter degeneration index Ab.
S3 constructs Life Prediction Model in conjunction with step S1 and step S2 with extreme learning machine algorithm:
β=[βi1,βi2,…βiK]T；
ω=[ωi1,ωi2,…ωiN]T；
In formula: β indicates i-th of hidden node in the weight of k-th output node；ω indicates i-th of hidden node and N
The weight of a input node；biIndicate the biasing on i-th of hidden node.
S4, online real time collecting hobboing cutter operating state data information update mode input end data and model fan-out
According to, and correction model is updated, the output valve of Life Prediction Model and actual comparison are finally obtained into the essence of Life Prediction Model
Degree and evaluation result.
A kind of hobboing cutter information monitoring device, including hob holder are equipped with Laser Measuring on the inside of the sliding block end cap of hob holder
Away from sensor, temperature sensor and Hall sensor are equipped on the hobboing cutter outer end face of hob holder, in the hobboing cutter of hob holder
Lateral wall be equipped with current vortex sensor；Six-dimension force sensor and acceleration transducer are equipped on the C-shaped block of hob holder；?
It is equipped with battery on the driving sliding block of hob holder, is equipped with wireless signal transmitter on screw rod on driving sliding block；Laser ranging passes
Sensor, temperature sensor, Hall sensor, six-dimension force sensor, acceleration transducer, current vortex sensor pass through wireless communication
Number transmitter is sent to the intracorporal signal receiver of shield, and signal receiver is transferred to data preprocessing module, data through signal wire
Preprocessing module is transmitted in industrial personal computer, and industrial personal computer can directly display processing result and result is sent to remote port by treated
It is checked, long-range related management personnel can directly be checked by mobile phone, the end PC etc. of oneself.
Beneficial effects of the present invention: the present invention by hobboing cutter monitoring device real-time monitoring hobboing cutter stress, abrasion loss, revolving speed,
The key parameters such as shape realize its visualized management, are handled by the analysis to hobboing cutter coherent signal, real-time monitoring hobboing cutter state
And predict hobboing cutter remaining life, and can check by mobile phone, long-range end PC etc. for correlation engineering administrative staff with long-range end communication,
Whether the auxiliary judgment of hommization replaces cutter.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is the system flow chart of embodiment 1.
Fig. 2 is limit learning network structure chart in 1 Life Prediction Model of embodiment.
Fig. 3 is the structural schematic diagram of embodiment 2.
Fig. 4 is the assembling schematic diagram of embodiment 2 each sensor and hob holder.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under that premise of not paying creative labor
Embodiment shall fall within the protection scope of the present invention.
Embodiment 1: a kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion, including information collection
Module, signal pre-processing module, state monitoring module, life prediction module and long-range monitoring modular；The information acquisition module
The parameter information for acquiring hobboing cutter, is sent to state monitoring module and/or life prediction after pre-processing by signal pre-processing module
Module, state monitoring module receive hobboing cutter parameter information and export hobboing cutter state after handling, and life prediction module receives hobboing cutter ginseng
The remaining life of hobboing cutter is exported after counting and handling, state monitoring module, the output result of life prediction module can at the scene directly
Check, long-range monitoring modular can be also sent to by wireless communication module, for long-range correlation engineering administrative staff can by mobile phone,
Long-range end PC etc. is checked.
Specifically, the hobboing cutter parameter information, including running parameter and technological parameter；The running parameter include revolving speed,
Hobboing cutter power, torque, cutter shaft vibration；Revolving speed is obtained by speed probe, for example Hall sensor, encoder or angle sensor
Device；Hobboing cutter power and torque, are obtained by six-dimension force sensor；Cutter shaft vibration, passes through acceleration transducer (such as gravity sensor)
Or velocity sensor obtains.
The technological parameter includes cutter ring appearance profile, temperature, cutter ring abrasion loss；Cutter ring appearance profile, is passed by ranging
Sensor collects to obtain；Temperature is obtained by temperature sensor；Cutter ring abrasion loss, is obtained by current vortex sensor.
Before carrying out data analysis, the signal pre-processing module is to revolving speed, hobboing cutter power, torque, cutter shaft vibration, cutter ring
Appearance profile, temperature, cutter ring abrasion loss carry out the pretreatment such as signal amplification and filtering respectively.
When carrying out status monitoring, the state monitoring module is handled to obtain hobboing cutter to the parameter information of acquisition
The processing step of working condition, state monitoring module is, as shown in Figure 1:
S1 extracts the signal key feature of operating parameter information；
Extracting applicable method is support vector machines, deep neural network algorithm, BP neural network algorithm, wavelet analysis calculation
One of method, Principal Component Analysis Algorithm.
S2, binding signal key feature and hobboing cutter technological parameter establish symptom set.
S2.1 vibrates width to the temperature in hobboing cutter technological parameter information and the power in operating parameter information, torque, cutter shaft
Value calculates sign degree of membership μ (x), sign degree of membership μ (x) general formula are as follows:
When parameter increases:
When parameter reduces:
Wherein, the value interval that parameter allows is [min, max], and normal value is fallen within section [a, b], and
Judgement according to the value of sign degree of membership μ (x) for hobboing cutter working condition provides foundation.
S2.2, the sign degree of membership obtained according to step S2.1 simultaneously combine the parameter information obtained to establish symptom set.
The symptom set, including parameter type, parameter name and parameter attribute；The parameter type, including working condition,
Frequency domain character, temporal signatures, related process parameters and fundamental surveillance information.
The working condition includes four parameters, respectively the relationship of rotary regimes, load condition, amplitude and revolving speed, vibration
The relationship of width and load；The parameter attribute of the rotary regimes, including the decline of speed stabilizing, speed change, speed, stalling；The load shape
The parameter attribute of state, including constant, up and down；The parameter attribute of the relationship of the amplitude and revolving speed, including with rotation speed change
Obviously, unobvious with rotation speed change；The parameter attribute of the relationship of the amplitude and load, including it is obvious with load variations, with negative
Lotus variation is unobvious.
The frequency domain character includes two parameters, respectively amplitude and amplitude variation；The parameter attribute of the amplitude, including
It is larger；The parameter attribute of the amplitude variation, including be basically unchanged, slowly rise, slowly decline, fly up, declining suddenly,
Cyclically-varying, irregular variation.
The temporal signatures include two parameters, respectively amplitude variation tendency and waveform state；The amplitude variation becomes
The parameter attribute of gesture, including be basically unchanged, slowly rise, slowly decline, fly up, decline suddenly, cyclically-varying, not advising
Then change；The parameter attribute of the waveform variation, including simple harmonic quantity waveform, aperiodic waveform, deformity.
The related process parameters include three parameters, respectively temperature, abrasion loss, conduit profile；The ginseng of the temperature
Number attribute, including it is excessively high, too low；The parameter attribute of the abrasion loss, including excessively high, eccentric wear；The parameter category of the conduit profile
Property, including normal, deformation.
The parameter of the fundamental surveillance information is hobboing cutter channel information, and the parameter attribute of hobboing cutter channel information is hobboing cutter volume
Number.
It is specific as shown in table 1.
Table 1
Knowledge base, the knowledge base of hobboing cutter relevant parameter threshold value of S3, the symptom set that will acquire and hobboing cutter historical data carry out
Comparison.
The result that step S3 is obtained is obtained hobboing cutter failure by forward reasoning and assumes collection by S4.
S5, backward inference validation fault assume collection, and the reasoning results are carried out Fuzzy processing if verifying is correct, will be obscured
Quantifier and numerical intervals correspond.
The fuzzy quantifier include affirm, be likely to, may, a little may, possibility it is small, it is not possible that；With fuzzy quantifier
One-to-one numerical intervals are 1,0.8,0.6,0.4,0.2,0.Fuzzy corresponding relationship is as shown in table 2.
Table 2
| Fuzzy quantifier | Certainly | It is likely to | It may | A little may | Possibility is small | It can not |
| Numerical intervals | 1 | 0.8 | 0.6 | 0.4 | 0.2 | 0 |
S6 selects Threshold Alerts or man-machine interaction mode display parameter information and the reasoning results on industrial personal computer, according to work
The display result of control machine judges the working condition of hobboing cutter, to judge whether to tool changing operation.
And when carrying out life prediction, the life prediction module is handled to obtain hobboing cutter to the parameter information received
Remaining life；Received parameter information includes hobboing cutter power, torque, temperature, abrasion loss and cutter shaft vibration.
The processing step of life prediction module is that S1, mutually empty using multivariable to obtained parameter information as shown in Figure 1:
Between restructing algorithm carry out phase space reconfiguration, as mode input end data:
X (t)=(X1(t),X2(t),…,Xi(t),…,XK(t))；
Wherein: Xi(t) the different types of information value of i-th of parameter index of hobboing cutter, m are indicatediFor the insertion dimension of i-th of variable
Number, τiFor the delay time of i-th of variable, K is the number of parameter index.
S2 obtains hobboing cutter degeneration index Ab, and using hobboing cutter degeneration index as model fan-out evidence.
S2.1, construction feature space vector matrix X.
S2.1.1 obtains the time domain index of each parameter index waveform.
The time domain index includes maximum value, minimum value, average amplitude, peak value, root-mean-square value gradient and kurtosis.
S2.1.2 obtains the frequency-domain index of each parameter index.
The frequency-domain index, the characteristic frequency amplitude including vibration values.
S2.1.3, the time domain index and frequency-domain index constitutive characteristic space vector matrix X of acquisition:
Wherein, the row of feature space vector matrix X indicates the feature vector of synchronization different parameters index composition；Feature
The column of space vector matrix X indicate the feature vector of the index composition of different moments；N is constitutive characteristic space vector matrix X's
Parameter index number, and n≤K.
Feature space vector matrix X is standardized and is obtained covariance matrix S by S2.2.
S2.3 obtains eigenvalue λ according to covariance matrix S1,λ2,…,λnAnd feature vector v corresponding with characteristic value1,
v2,…,vn。
The descending sequence of characteristic value is obtained diagonal matrix A by S2.4:
S2.5 calculates the principal component matrix Y of feature space vector matrix X according to feature vector:
Y=XV；
V=[v1,v2,…,vn]。
S2.6, using the first principal component of principal component matrix Y as hobboing cutter degeneration index Ab.
S3 constructs Life Prediction Model in conjunction with step S1 and step S2 with extreme learning machine algorithm, as shown in Figure 2:
β=[βi1,βi2,…βiK]T；
ω=[ωi1,ωi2,…ωiN]T；
In formula: β indicates i-th of hidden node in the weight of k-th output node；ω indicates i-th of hidden node and N
The weight of a input node；biIndicate the biasing on i-th of hidden node.
S4, online real time collecting hobboing cutter operating state data information update mode input end data and model fan-out
According to, and correction model is updated, the output valve of Life Prediction Model and actual comparison are finally obtained into the essence of Life Prediction Model
Degree and evaluation result.
Embodiment 2: a kind of hobboing cutter information monitoring device, as shown in Figure 3-4, including hob holder 100, in hob holder
It is equipped with laser range sensor 1 on the inside of 100 sliding block end cap 101, is passed on 102 outer end face of hobboing cutter of hob holder equipped with temperature
Sensor 2 and Hall sensor 3 are equipped with current vortex sensor 6 in the lateral wall of the hobboing cutter 102 of hob holder；In the C of hob holder
Six-dimension force sensor 4 and acceleration transducer 5 are equipped on shape block 103；Battery 8 is equipped on the driving sliding block 104 of hob holder,
Wireless signal transmitter 7 is equipped on screw rod 105 on driving sliding block 104；Laser range sensor 1, temperature sensor 2, Hall
Sensor 3, six-dimension force sensor 4, acceleration transducer 5, current vortex sensor 6 are sent to by wireless signal transmitter 7
The intracorporal signal receiver 200 of shield, signal receiver 200 are transferred to data preprocessing module 300, data prediction through signal wire
Module 300 is transmitted in industrial personal computer 400, and industrial personal computer 400 can directly display processing result and result is sent to far by treated
Cheng Duan 500 is checked that long-range related management personnel can directly be checked by mobile phone, the end PC etc. of oneself.
Embodiment of above is only used for the description of this invention, rather than limitation of the present invention.To those skilled in the art
It carrying out variation or modification appropriate is without departing from the scope of the invention it will be apparent that therefore all equivalent skills for member
Art scheme also belongs to scope of the invention, and scope of patent protection of the invention is defined by the following claims.
Claims (10)
1. a kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion, it is characterised in that: adopted including information
Collect module, signal pre-processing module, state monitoring module, life prediction module and long-range monitoring modular；The information collection mould
Block acquires the parameter information of hobboing cutter, and state monitoring module is sent to after pre-processing by signal pre-processing module and/or the service life is pre-
Module is surveyed, state monitoring module receives hobboing cutter parameter information and exports hobboing cutter state after handling, and life prediction module receives hobboing cutter
The remaining life of hobboing cutter is exported after parameter and processing, the direct scene of the output result of state monitoring module and life prediction module is looked into
It sees and is delivered to long-range monitoring modular.
2. the tool condition monitoring and life prediction system according to claim 1 based on Multi-source Information Fusion, feature
It is: the hobboing cutter parameter information, including running parameter and technological parameter；The running parameter includes revolving speed, hobboing cutter power, power
Square, cutter shaft vibration；Revolving speed is obtained by speed probe；Hobboing cutter power and torque, are obtained by six-dimension force sensor；Cutter shaft vibration
It is dynamic, it is obtained by acceleration transducer or velocity sensor；
The technological parameter includes cutter ring appearance profile, temperature, cutter ring abrasion loss；Cutter ring appearance profile, passes through distance measuring sensor
It collects to obtain；Temperature is obtained by temperature sensor；Cutter ring abrasion loss, is obtained by current vortex sensor.
3. the tool condition monitoring and life prediction system according to claim 1 or 2 based on Multi-source Information Fusion, special
Sign is: the signal pre-processing module is to revolving speed, hobboing cutter power, torque, cutter shaft vibration, cutter ring appearance profile, temperature, cutter ring
Abrasion loss carries out signal amplification and filtering processing respectively.
4. the tool condition monitoring and life prediction system according to claim 3 based on Multi-source Information Fusion, feature
Be: the state monitoring module handles the parameter information of acquisition to obtain the working condition of hobboing cutter.
5. the tool condition monitoring and life prediction system according to claim 4 based on Multi-source Information Fusion, feature
It is: the processing step of state monitoring module are as follows:
S1 extracts the signal key feature of pretreated operating parameter information；
Extract applicable method be support vector machines, deep neural network algorithm, BP neural network algorithm, Algorithms of Wavelet Analysis,
At least one of Principal Component Analysis Algorithm；
S2, binding signal key feature and hobboing cutter technological parameter establish symptom set；
S3, the symptom set that will acquire are compared with the knowledge base of hobboing cutter historical data, the knowledge base of hobboing cutter relevant parameter threshold value；
The result that step S3 is obtained is obtained hobboing cutter failure by forward reasoning and assumes collection by S4；
S5, backward inference validation fault assume collection, the reasoning results are carried out Fuzzy processing if verifying is correct, by fuzzy quantifier
It is corresponded with numerical intervals；
The fuzzy quantifier include affirm, be likely to, may, a little may, possibility it is small, it is not possible that；One by one with fuzzy quantifier
Corresponding numerical intervals are 1,0.8,0.6,0.4,0.2,0；
S6 selects Threshold Alerts or man-machine interaction mode display parameter information and the reasoning results on industrial personal computer, according to industrial personal computer
Display result judge the working condition of hobboing cutter, to judge whether to tool changing operation.
6. the tool condition monitoring and life prediction system according to claim 5 based on Multi-source Information Fusion, feature
Be: in step s 2, specific steps are as follows: S2.1, in hobboing cutter technological parameter information temperature and operating parameter information in
Power, torque, cutter shaft vibration amplitude calculate sign degree of membership μ (x), sign degree of membership μ (x) general formula are as follows:
When parameter increases:
When parameter reduces:
Wherein, the value interval that parameter allows is [min, max], and normal value is fallen within section [a, b], and
Judgement according to the value of sign degree of membership μ (x) for hobboing cutter working condition provides foundation；
S2.2, the sign degree of membership obtained according to step S2.1 simultaneously combine the parameter information obtained to establish symptom set；
The symptom set, including parameter type, parameter name and parameter attribute；The parameter type, including working condition, frequency domain
Feature, temporal signatures, related process parameters and fundamental surveillance information；
The working condition include four parameters, respectively the relationship of rotary regimes, load condition, amplitude and revolving speed, amplitude with
The relationship of load；The parameter attribute of the rotary regimes, including the decline of speed stabilizing, speed change, speed, stalling；The load condition
Parameter attribute, including constant, up and down；The parameter attribute of the relationship of the amplitude and revolving speed, including it is bright with rotation speed change
It is aobvious, unobvious with rotation speed change；The parameter attribute of the relationship of the amplitude and load, including it is obvious with load variations, with load
Change unobvious；
The frequency domain character includes two parameters, respectively amplitude and amplitude variation；The parameter attribute of the amplitude, including compared with
Greatly；The parameter attribute of the amplitude variation, including be basically unchanged, slowly rise, slowly decline, fly up, decline suddenly, week
The variation of phase property, irregular variation；
The temporal signatures include two parameters, respectively amplitude variation tendency and waveform state；The amplitude variation tendency
Parameter attribute, including be basically unchanged, slowly rise, slowly decline, fly up, decline suddenly, cyclically-varying, irregular change
Change；The parameter attribute of the waveform variation, including simple harmonic quantity waveform, aperiodic waveform, deformity；
The related process parameters include three parameters, respectively temperature, abrasion loss, conduit profile；The parameter category of the temperature
Property, including it is excessively high, too low；The parameter attribute of the abrasion loss, including excessively high, eccentric wear；The parameter attribute of the conduit profile, packet
Include normal, deformation；
The parameter of the fundamental surveillance information is hobboing cutter channel information, and the parameter attribute of hobboing cutter channel information is hobboing cutter number.
7. the tool condition monitoring and life prediction system according to claim 1 based on Multi-source Information Fusion, feature
Be: the life prediction module handles the parameter information received to obtain the remaining life of hobboing cutter；Received
Parameter information includes hobboing cutter power, torque, temperature, abrasion loss and cutter shaft vibration.
8. the tool condition monitoring and life prediction system according to claim 7 based on Multi-source Information Fusion, feature
It is: the processing step of the life prediction module are as follows:
S1 carries out phase space reconfiguration using multivariate phase space reconstruction algorithm to obtained parameter information, as mode input end
Data:
X (t)=(X1(t),X2(t),…,Xi(t),…,XK(t))；
Wherein: Xi(t) the different types of information value of i-th of parameter index of hobboing cutter, m are indicatediFor the Embedded dimensions of i-th of variable, τi
For the delay time of i-th of variable, K is the number of parameter index；
S2 obtains hobboing cutter degeneration index Ab, and using hobboing cutter degeneration index Ab as model fan-out evidence；
S3 constructs Life Prediction Model in conjunction with step S1 and step S2 with extreme learning machine algorithm:
β=[βi1,βi2,…βiK]T；
ω=[ωi1,ωi2,…ωiN]T；
In formula: β indicates i-th of hidden node in the weight of k-th output node；ω indicates that i-th of hidden node and n-th are defeated
The weight of ingress；biIndicate the biasing on i-th of hidden node；
S4, online real time collecting hobboing cutter operating state data information update mode input end data and model fan-out evidence, and
Correction model is updated, the output valve of Life Prediction Model and actual comparison are finally obtained to the precision of Life Prediction Model and commented
Valence result.
9. the tool condition monitoring and life prediction system according to claim 8 based on Multi-source Information Fusion, feature
It is, in step s 2, specific steps are as follows: S2.1, construction feature space vector matrix X；
S2.1.1 obtains the time domain index of each parameter index waveform；
The time domain index includes maximum value, minimum value, average amplitude, peak value, root-mean-square value gradient and kurtosis；
S2.1.2 obtains the frequency-domain index of each parameter index；
The frequency-domain index, the characteristic frequency amplitude including vibration values；
S2.1.3, the time domain index and frequency-domain index constitutive characteristic space vector matrix X of acquisition:
Wherein, the row of feature space vector matrix X indicates the feature vector of synchronization different parameters index composition；Feature space
The column of vector matrix X indicate the feature vector of the index composition of different moments；N is the parameter of constitutive characteristic space vector matrix X
Index number, and n≤K；
Feature space vector matrix X is standardized and is obtained covariance matrix S by S2.2；
S2.3 obtains eigenvalue λ according to covariance matrix S1,λ2,…,λnAnd feature vector v corresponding with characteristic value1,
v2,…,vn；
The descending sequence of characteristic value is obtained diagonal matrix A by S2.4:
S2.5 calculates the principal component matrix Y of feature space vector matrix X according to feature vector:
Y=XV；
V=[v1,v2,…,vn]；
S2.6, using the first principal component of principal component matrix Y as hobboing cutter degeneration index Ab.
10. a kind of hobboing cutter information monitoring device, including hob holder (100), it is characterised in that: the cunning in hob holder (100)
It is equipped with laser range sensor (1) on the inside of block end cap (101), is passed on hobboing cutter (102) outer end face of hob holder equipped with temperature
Sensor (2) and Hall sensor (3) are equipped with current vortex sensor (6) in the lateral wall of the hobboing cutter (102) of hob holder；It is rolling
Six-dimension force sensor (4) and acceleration transducer (5) are equipped on the C-shaped block (103) of knife tool apron；In the driving sliding block of hob holder
(104) battery (8) are equipped on, are equipped with wireless signal transmitter (7) on screw rod (105) in driving sliding block (104)；Laser ranging
Sensor (1), temperature sensor (2), Hall sensor (3), six-dimension force sensor (4), acceleration transducer (5), current vortex
Sensor (6) is sent to the intracorporal signal receiver of shield (200), signal receiver (200) by wireless signal transmitter (7)
It is transferred to data preprocessing module (300) through signal wire, data preprocessing module (300) is transmitted in industrial personal computer (400), industry control
Machine (400) shows processing result and is communicated by wireless communication module and remote port (500).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811636302.2A CN109724785B (en) | 2018-12-29 | 2018-12-29 | Cutter state monitoring and life predicting system based on multisource information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811636302.2A CN109724785B (en) | 2018-12-29 | 2018-12-29 | Cutter state monitoring and life predicting system based on multisource information fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109724785A true CN109724785A (en) | 2019-05-07 |
| CN109724785B CN109724785B (en) | 2024-08-06 |
Family
ID=66296092
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811636302.2A Active CN109724785B (en) | 2018-12-29 | 2018-12-29 | Cutter state monitoring and life predicting system based on multisource information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109724785B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110370080A (en) * | 2019-07-19 | 2019-10-25 | 广东寰球智能科技有限公司 | A kind of monitoring method and monitoring system of trimmer cutter |
| CN110687450A (en) * | 2019-08-28 | 2020-01-14 | 武汉科技大学 | Lithium battery residual life prediction method based on phase space reconstruction and particle filtering |
| CN110779988A (en) * | 2019-10-30 | 2020-02-11 | 同济大学 | Bolt life prediction method based on deep learning |
| CN110987155A (en) * | 2019-12-17 | 2020-04-10 | 山东大学 | TBM hob loss state real-time monitoring device and method |
| CN111152069A (en) * | 2020-01-21 | 2020-05-15 | 徐州工业职业技术学院 | Tool life monitoring system for machine tool machining |
| CN111236956A (en) * | 2020-01-16 | 2020-06-05 | 中铁工程装备集团有限公司 | Shield tunneling machine hob load real-time monitoring system and method |
| CN111337234A (en) * | 2020-03-09 | 2020-06-26 | 西南交通大学 | TBM scraper service life prediction system and method based on real-time monitoring |
| CN111577313A (en) * | 2020-05-13 | 2020-08-25 | 中铁隧道局集团有限公司 | Data acquisition terminal for real-time monitoring of hob load and rotating speed and acquisition method thereof |
| CN111915178A (en) * | 2020-07-26 | 2020-11-10 | 同济大学 | Signal equipment service life cause analysis method |
| CN111931798A (en) * | 2019-05-13 | 2020-11-13 | 北京绪水互联科技有限公司 | Method for carrying out classification detection and service life prediction of cold head state |
| CN112418450A (en) * | 2020-10-30 | 2021-02-26 | 济南浪潮高新科技投资发展有限公司 | Equipment predictive maintenance method based on multi-mode machine learning |
| CN113505911A (en) * | 2021-06-08 | 2021-10-15 | 北京建工土木工程有限公司 | Cutter life prediction system based on automatic cruise and prediction method thereof |
| CN113723016A (en) * | 2021-11-01 | 2021-11-30 | 深圳市信润富联数字科技有限公司 | Punch residual life prediction method, device and system and readable storage medium |
| CN113843305A (en) * | 2021-09-02 | 2021-12-28 | 上汽通用五菱汽车股份有限公司 | Mold monitoring and early warning method, system, equipment and computer readable storage medium |
| CN114011903A (en) * | 2021-11-01 | 2022-02-08 | 深圳市信润富联数字科技有限公司 | Stamping production abnormity monitoring method, device and system and readable storage medium |
| CN114136570A (en) * | 2021-11-19 | 2022-03-04 | 四川启睿克科技有限公司 | Raw material quality identification method based on predictive maintenance data |
| CN114595779A (en) * | 2022-03-15 | 2022-06-07 | 中铁十四局集团大盾构工程有限公司 | Shield machine cutter fault analysis and diagnosis method |
| CN115167276A (en) * | 2022-06-22 | 2022-10-11 | 武汉益模科技股份有限公司 | Tool life prediction method based on tool path running track |
| CN116187047A (en) * | 2023-02-16 | 2023-05-30 | 北京思维实创科技有限公司 | Equipment life prediction method and related device |
| CN116976148A (en) * | 2023-09-22 | 2023-10-31 | 常州润来科技有限公司 | Method and system for monitoring ion content change in copper electrolysis process |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH041395A (en) * | 1990-04-18 | 1992-01-06 | Ohbayashi Corp | Self-diagnosing method for tunnel excavating machine |
| US20070088550A1 (en) * | 2005-10-13 | 2007-04-19 | Dimitar Filev | Method for predictive maintenance of a machine |
| CN104111346A (en) * | 2014-07-17 | 2014-10-22 | 石家庄铁道大学 | Working and abrasion state on-line detection method for shield hob |
| CN104361242A (en) * | 2014-11-20 | 2015-02-18 | 青岛理工大学 | Bearing fault diagnosis method based on data driving and random intuition fuzzy strategy |
| CN106126906A (en) * | 2016-06-22 | 2016-11-16 | 重庆科技学院 | Short-term wind speed forecasting method based on C C Yu ELM |
| CN107655393A (en) * | 2017-11-06 | 2018-02-02 | 中铁工程装备集团有限公司 | A kind of TBM hob total state real time on-line monitoring system and its measuring method |
| CN108181484A (en) * | 2017-12-25 | 2018-06-19 | 中铁工程装备集团有限公司 | A kind of normal pressure cutterhead hobboing cutter rotating speed and temperature measuring equipment and abrasion amount measuring method |
| CN108536938A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | A kind of machine tool life prediction system and prediction technique |
| CN109015111A (en) * | 2018-07-06 | 2018-12-18 | 华中科技大学 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
| CN209485669U (en) * | 2018-12-29 | 2019-10-11 | 中铁工程装备集团有限公司 | A kind of hobboing cutter information monitoring device |
-
2018
- 2018-12-29 CN CN201811636302.2A patent/CN109724785B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH041395A (en) * | 1990-04-18 | 1992-01-06 | Ohbayashi Corp | Self-diagnosing method for tunnel excavating machine |
| US20070088550A1 (en) * | 2005-10-13 | 2007-04-19 | Dimitar Filev | Method for predictive maintenance of a machine |
| CN104111346A (en) * | 2014-07-17 | 2014-10-22 | 石家庄铁道大学 | Working and abrasion state on-line detection method for shield hob |
| CN104361242A (en) * | 2014-11-20 | 2015-02-18 | 青岛理工大学 | Bearing fault diagnosis method based on data driving and random intuition fuzzy strategy |
| CN106126906A (en) * | 2016-06-22 | 2016-11-16 | 重庆科技学院 | Short-term wind speed forecasting method based on C C Yu ELM |
| CN107655393A (en) * | 2017-11-06 | 2018-02-02 | 中铁工程装备集团有限公司 | A kind of TBM hob total state real time on-line monitoring system and its measuring method |
| CN108181484A (en) * | 2017-12-25 | 2018-06-19 | 中铁工程装备集团有限公司 | A kind of normal pressure cutterhead hobboing cutter rotating speed and temperature measuring equipment and abrasion amount measuring method |
| CN108536938A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | A kind of machine tool life prediction system and prediction technique |
| CN109015111A (en) * | 2018-07-06 | 2018-12-18 | 华中科技大学 | A kind of cutting tool state on-line monitoring method based on information fusion and support vector machines |
| CN209485669U (en) * | 2018-12-29 | 2019-10-11 | 中铁工程装备集团有限公司 | A kind of hobboing cutter information monitoring device |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111931798A (en) * | 2019-05-13 | 2020-11-13 | 北京绪水互联科技有限公司 | Method for carrying out classification detection and service life prediction of cold head state |
| CN110370080A (en) * | 2019-07-19 | 2019-10-25 | 广东寰球智能科技有限公司 | A kind of monitoring method and monitoring system of trimmer cutter |
| CN110687450A (en) * | 2019-08-28 | 2020-01-14 | 武汉科技大学 | Lithium battery residual life prediction method based on phase space reconstruction and particle filtering |
| CN110779988A (en) * | 2019-10-30 | 2020-02-11 | 同济大学 | Bolt life prediction method based on deep learning |
| CN110987155A (en) * | 2019-12-17 | 2020-04-10 | 山东大学 | TBM hob loss state real-time monitoring device and method |
| CN111236956A (en) * | 2020-01-16 | 2020-06-05 | 中铁工程装备集团有限公司 | Shield tunneling machine hob load real-time monitoring system and method |
| CN111236956B (en) * | 2020-01-16 | 2021-07-16 | 中铁工程装备集团有限公司 | Shield tunneling machine hob load real-time monitoring system and method |
| CN111152069A (en) * | 2020-01-21 | 2020-05-15 | 徐州工业职业技术学院 | Tool life monitoring system for machine tool machining |
| CN111337234A (en) * | 2020-03-09 | 2020-06-26 | 西南交通大学 | TBM scraper service life prediction system and method based on real-time monitoring |
| CN111577313A (en) * | 2020-05-13 | 2020-08-25 | 中铁隧道局集团有限公司 | Data acquisition terminal for real-time monitoring of hob load and rotating speed and acquisition method thereof |
| CN111915178A (en) * | 2020-07-26 | 2020-11-10 | 同济大学 | Signal equipment service life cause analysis method |
| CN111915178B (en) * | 2020-07-26 | 2024-02-27 | 同济大学 | Signal equipment service life cause analysis method |
| CN112418450A (en) * | 2020-10-30 | 2021-02-26 | 济南浪潮高新科技投资发展有限公司 | Equipment predictive maintenance method based on multi-mode machine learning |
| CN113505911A (en) * | 2021-06-08 | 2021-10-15 | 北京建工土木工程有限公司 | Cutter life prediction system based on automatic cruise and prediction method thereof |
| CN113843305A (en) * | 2021-09-02 | 2021-12-28 | 上汽通用五菱汽车股份有限公司 | Mold monitoring and early warning method, system, equipment and computer readable storage medium |
| CN113843305B (en) * | 2021-09-02 | 2024-02-06 | 上汽通用五菱汽车股份有限公司 | Die monitoring and early warning method, system, equipment and computer readable storage medium |
| CN114011903A (en) * | 2021-11-01 | 2022-02-08 | 深圳市信润富联数字科技有限公司 | Stamping production abnormity monitoring method, device and system and readable storage medium |
| CN113723016A (en) * | 2021-11-01 | 2021-11-30 | 深圳市信润富联数字科技有限公司 | Punch residual life prediction method, device and system and readable storage medium |
| CN114136570A (en) * | 2021-11-19 | 2022-03-04 | 四川启睿克科技有限公司 | Raw material quality identification method based on predictive maintenance data |
| CN114595779A (en) * | 2022-03-15 | 2022-06-07 | 中铁十四局集团大盾构工程有限公司 | Shield machine cutter fault analysis and diagnosis method |
| CN115167276A (en) * | 2022-06-22 | 2022-10-11 | 武汉益模科技股份有限公司 | Tool life prediction method based on tool path running track |
| CN116187047A (en) * | 2023-02-16 | 2023-05-30 | 北京思维实创科技有限公司 | Equipment life prediction method and related device |
| CN116976148A (en) * | 2023-09-22 | 2023-10-31 | 常州润来科技有限公司 | Method and system for monitoring ion content change in copper electrolysis process |
| CN116976148B (en) * | 2023-09-22 | 2023-12-08 | 常州润来科技有限公司 | Method and system for monitoring ion content change in copper electrolysis process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109724785B (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109724785A (en) | A kind of tool condition monitoring and life prediction system based on Multi-source Information Fusion | |
| CN209485669U (en) | A kind of hobboing cutter information monitoring device | |
| CN103033359B (en) | A kind of main transmission in wind generating set method for diagnosing faults of multiple features Multilateral Comprehensive Judge | |
| CN108038553B (en) | Rolling mill equipment state on-line monitoring and diagnosing system and monitoring and diagnosing method | |
| CN102270271B (en) | Equipment failure early warning and optimizing method and system based on similarity curve | |
| CN104808585B (en) | A kind of quick inspection method of lathe health status | |
| CN105067209B (en) | The method of bridge structure stiffness variation is judged based on bridge health monitoring deformation data | |
| CN101718634B (en) | Equipment state comprehensive dynamic alarming method based on multivariate probability model | |
| CN103198147B (en) | The differentiation of automatic monitoring abnormal data and processing method | |
| CN103331310A (en) | Magnesium alloy plate rolling parameter monitoring and fault diagnosing system and method | |
| CN104573850A (en) | Method for evaluating state of thermal power plant equipment | |
| CN102848266B (en) | Machine tool spindle accuracy prediction method | |
| CN105003453A (en) | Online monitoring and fault diagnosis system of mine fan | |
| CN204113701U (en) | A kind of mine fan on-line monitoring and fault diagnosis system | |
| CN103530818B (en) | A kind of water supply network modeling method based on BRB system | |
| CN115499473B (en) | Shield construction early warning method and early warning system based on edge computing architecture | |
| CN106199174A (en) | Extruder energy consumption predicting abnormality method based on transfer learning | |
| CN104299169B (en) | A kind of sewage disposal system information security online risk analysis method and system | |
| CN107291830A (en) | A kind of creation method of equipment knowledge base | |
| CN105243393A (en) | Characteristic-based fault forecasting method for complex electromechanical system | |
| CN113902288A (en) | Management system and method for water resource regulation and control and operation | |
| CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
| CN107967521A (en) | A kind of equipment complex method of evaluating performance | |
| CN117541717A (en) | Modeling method of digital twin body of ball mill | |
| CN117105098A (en) | Door machine grab bucket control system and method based on multi-sensor fusion |
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 |