CN109933004A - The machine failure diagnosis and prediction method and system cooperateed with based on edge calculations and cloud - Google Patents
The machine failure diagnosis and prediction method and system cooperateed with based on edge calculations and cloud Download PDFInfo
- Publication number
- CN109933004A CN109933004A CN201910235933.1A CN201910235933A CN109933004A CN 109933004 A CN109933004 A CN 109933004A CN 201910235933 A CN201910235933 A CN 201910235933A CN 109933004 A CN109933004 A CN 109933004A
- Authority
- CN
- China
- Prior art keywords
- cloud
- prediction
- data
- numerical control
- fault diagnosis
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses the machine failure diagnosis and prediction method and system based on edge calculations and cloud collaboration, method includes: 1) status data of sensing node collection machinery system and to extract feature, obtains mechanical features data；The status data of gateway node acquisition digital control system simultaneously extracts feature, obtains numerical control characteristic, and send mechanical characteristic and numerical control characteristic to cloud；2) cloud carries out fault diagnosis and prediction to mechanical features data and numerical control characteristic using preset fault diagnosis and prediction model, and fault diagnosis and prediction result are sent to client；3) client receiver bed expert is to the feedback result of fault diagnosis and prediction result, and feedback result is sent to cloud；4) cloud marks mechanical characteristic and numerical control characteristic according to feedback result, and training simultaneously updates fault diagnosis and prediction model, and returns to step 2).Using the embodiment of the present invention, machine failure diagnosis and prediction accuracy are improved.
Description
Technical field
The present invention relates to machine failure diagnosis and prediction method and system, it is more particularly to based on edge calculations and Yun Xietong
Machine failure diagnosis and prediction method and system.
Background technique
With the sustainable development of modern industry and the continuous improvement of scientific and technological level, electromechanical equipment also increasingly to high speed,
Serialization, centralization, automation and precise treatment direction develop, and then cause the Nomenclature Composition and Structure of Complexes of electromechanical equipment also more and more multiple
Miscellaneous, this failure rate for directly resulting in electromechanical equipment increases and the increasing of diagnosis difficulty.For example, the key components and parts in lathe are (such as
Rolling bearing, gear, ball-screw etc.) subtle nuisance fault or exception, if detecting and excluding not in time, it is possible to cause
Failure, the paralysis of whole system, even result in catastrophic effect.Therefore, it is to the analysis and prediction of electromechanical equipment progress failure
Very necessary.By predictive fault diagnosis, it can reduce or avoid to varying degrees workpiece to scrap and be damaged with lathe
Generation.Lathe can integrally be divided into three subsystems: digital control system, electricity as a kind of typical electromechanical integrated product
Gas system and it is easiest to the mechanical system for irreversible damage occur.In the process of production and processing, Mechanical System Trouble is one
The phenomenon that kind certainly exists.Traditional prevention and processing method is to inspect the workpiece that the lathe is processed by random samples by operator
Quality condition, or the healthy shape of lathe is periodically or non-periodically judged by technical staff according to vibration and noise of lathe etc.
Condition.Aforementioned two ways is easy to be influenced by subjective factors such as professional abilities, not can guarantee accuracy, poor reliability and efficiency
It is low.Lathe HEALTH ONLINE detection method mainly has diagram method and indirect method at present.Chart detection method is made to collected data
It is handled with some algorithms, then generates time domain or frequency domain chart, by manually or using machine learning contrast images being sentenced
It is disconnected.Indirect detection method be to stress, spindle motor current, torque, vibration, sound, temperature and it is hydraulic etc. detect, to infer machine
Bed health degree.Chart detection method needs contrast images to be judged, brings very big pressure, efficiency to network flow and server
Also not high, and tend not to find the problem in time；The factor that indirect detection method is related to is too many, and interference is also more, and accuracy can not
Guarantee.
Digital control system data or only collection machinery system data are used only in the prior art, and are carried out according to these data
Fault diagnosis and fault prediction, but the data of the digital control system of lathe and the mechanical system reciprocal causation in machine failure generating process
Connection, and the two is not combined in the prior art, therefore, the accuracy that diagnosis and prediction exists in the prior art is not high
The technical issues of.
Summary of the invention
Technical problem to be solved by the present invention lies in provide the machine failure diagnosis based on edge calculations and cloud collaboration
With prediction technique and system, with improve the online test method based on industry internet platform detection accuracy.
The present invention is to solve above-mentioned technical problem by the following technical programs:
The present invention provides a kind of machine failure diagnosis and prediction method cooperateed with based on edge calculations and cloud, the methods
Include:
1), sensing node acquires the machine performance data of machine tool component according to default first acquisition strategies and extracts feature,
Mechanical features data are obtained, and the mechanical features data are uploaded into gateway node；The gateway node is according to default second
The operating state data of acquisition strategies acquisition digital control system simultaneously extracts feature, obtains numerical control characteristic, and will be described mechanical special
Sign data and numerical control characteristic are sent to cloud；
2), the cloud receives the mechanical features data and numerical control characteristic, using preset fault diagnosis and in advance
It surveys model and carries out fault diagnosis and prediction, and fault diagnosis and prediction result are sent to client；
3), the client shows the fault diagnosis and prediction result to lathe expert, receives lathe expert to described
The feedback result of fault diagnosis and prediction result, and the feedback result is sent to the cloud；
4), the cloud receives the feedback result, marks the mechanical features data and numerical control characteristic, obtains sample
Notebook data；According to the sample data training fault diagnosis and prediction model, and returns and execute the step 2).
Optionally, using gateway node as root node, sensing node is based on wireless sensor network network and is completed by FTSP
Time synchronization；It is synchronous by the fieldbus NCUC-bus deadline that digital control system is based on cable network.
Optionally, the method also includes:
The gateway node receives the instruction that the client is sent, and described instruction includes but is not limited to adjust characteristic
According to frequency acquisition, the acquisition duration of adjustment characteristic, the type for adjusting characteristic, update feature extraction algorithm library, restart
Or close sensing node or gateway node.
The present invention provides a kind of machine failure diagnosis and prediction system cooperateed with based on edge calculations and cloud, the systems
Including marginal end and cloud, wherein
The marginal end, including gateway node and sensing node, the sensing node is arranged on the component of lathe, and presses
Machine performance data according to preset first acquisition strategies acquisition component simultaneously extract feature, obtain mechanical features data；
The gateway node is used for, and is acquired the operating state data of digital control system according to preset second strategy and is extracted spy
Sign obtains numerical control characteristic, and the mechanical features data and numerical control characteristic is sent to the cloud；
The gateway node is sent in the data in the cloud, and the mechanical features data include but is not limited to, temperature,
One of humidity, revolving speed, torque, amplitude, form factor, crest factor and kurtosis coefficient combine；The numerical control feature
Data include but is not limited to, instruction code, alarm code, the speed of mainshaft, the direction of motion, a kind of or combination in coordinate；
The cloud, including communication unit, computing unit, storage unit, business unit, training unit, wherein described logical
Unit is interrogated, the storage is written in the mechanical features data and numerical control characteristic uploaded for receiving the gateway node
Unit is simultaneously transmitted to the computing unit；
The computing unit, for carrying out fault diagnosis and prediction to the mechanical features data and numerical control characteristic,
And the storage unit is written into fault diagnosis and prediction result；
The storage unit, for storing the feedback knot of the mechanical features data and numerical control characteristic, lathe expert
Fruit, various businesses data；
The business unit receives lathe expert couple for showing the fault diagnosis and prediction result to lathe expert
The feedback result of the fault diagnosis and prediction result；
The training unit, for according to the training of the feedback result, the mechanical features data and numerical control characteristic
Fault diagnosis and prediction model, so that the fault diagnosis and the result of prediction model and the feedback result, and model is joined
Number feeds back to the computing unit.
Optionally, the business unit is used for, to marginal end under send instructions, wherein described instruction includes but is not limited to, and adjusts
The sensing section is restarted or closed to the frequency acquisition or duration of entire data, update feature extraction algorithm library, at the data type of acquisition
Point or gateway node.
Optionally, the client is also used to, and receives the operational order of user, and the client include Web apply and
Mobile phone A pp.
Optionally, the gateway node is used for, and the time synchronization of gateway node is completed by NTP network, as marginal end
Time synchronization basis.
Optionally, the gateway node is used for, and is judged whether lathe is in and is not shut down and non-standby mode, if then by institute
It states mechanical features data and numerical control characteristic is sent to the cloud.
Optionally, the system also includes clients, for showing the fault diagnosis and prediction knot to lathe expert
Fruit, and lathe expert is received to the feedback result of diagnosis and prediction result.
The present invention has the advantage that compared with prior art
Using the embodiment of the present invention, the present invention is based on cooperateing with for edge calculations and cloud, utilize sensing node in marginal end
It acquires the machine performance data of lathe mechanical system and extracts feature, obtain mechanical features data, acquire lathe in gateway node
The operating state data of digital control system simultaneously extracts feature, obtains numerical control characteristic, then beyond the clouds to mechanical features data and
Numerical control characteristic carries out fault diagnosis and prediction, then marks mechanical characteristic and numerical control characteristic using expert feedback
Sample data is obtained, the update of fault diagnosis and prediction model is then carried out using sample data, is then carried out at multiple circulation
Reason, and then most accurate fault diagnosis and prediction model are obtained, and then improve the precision of fault diagnosis and prediction.
Detailed description of the invention
Fig. 1 is the machine failure diagnosis and prediction method provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
Flow diagram；
Fig. 2 is the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
Structural schematic diagram；
Fig. 3 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The data processing schematic diagram of marginal end；
Fig. 4 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
Instruct the process schematic issued；
Fig. 5 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The first process schematic of time synchronization；
Fig. 6 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The second process schematic diagram of time synchronization；
Fig. 7 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The third process schematic of time synchronization.
Specific embodiment
It elaborates below to the embodiment of the present invention, the present embodiment carries out under the premise of the technical scheme of the present invention
Implement, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to following implementation
Example.
The embodiment of the invention provides based on edge calculations and cloud collaboration machine failure diagnosis and prediction method and system,
The machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud is carried out first below
It introduces.
Embodiment 1
Fig. 1 is the machine failure diagnosis and prediction method provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
Flow diagram, as shown in Figure 1, the embodiment of the present invention 1 includes:
S101: sensing node acquires the machine performance data of machine tool component according to default first acquisition strategies and extracts spy
Sign obtains mechanical features data, and mechanical features data is uploaded to gateway node；Gateway node is according to default second acquisition plan
It slightly acquires the operating state data of digital control system and extracts feature, receive numerical control characteristic, and by mechanical features data sum number
Control characteristic is sent to cloud.
Illustratively,
Ball-screw is actuated element most-often used on machine tool and precision machinery, and major function is will to rotate fortune
Turn changes linear movement into, or torque is converted into axial repeated action power, while having both high-precision, invertibity and efficient
Feature.Due to the frictional resistance with very little, ball-screw is widely used in various industrial equipments and precision instrument.It is whole next
It says, ball screw arrangement is complicated, precision is higher, sport efficiency is high but shock resistance is poor, and maintenance cost is higher.Ball-screw is in numerical control
Actual motion is the most frequent in lathe, and each component often generates mechanical wear and insufficient lubrication, usually occur positioning accuracy decline,
The failures such as backlass is excessive, mechanical creep, lead screw serious wear, noise are excessive.
In the present embodiment, the data of combining with digital control system and the sensing node being mounted on ball-screw critical component are adopted
The data of collection carry out fault diagnosis and prediction to the ball-screw in lathe.
In the practical application of ball-screw fault diagnosis, the vibration velocity of critical component and the time domain data tool of acceleration
Have the characteristics that intuitive, real-time is good, some failures can directly react in temperature, and the status code of digital control system is to a part of event
Barrier has certain direction directive function.Vibration temporal signatures data in machine performance data involved in the present embodiment are as follows:
1. amplitude
What the peak value in amplitude reflected is the maximum value of certain moment amplitude, suitable for having for surface pitting damage etc
The fault diagnosis of temporary impact.The diagnostic effect of the mean value of amplitude and peak value are essentially the same, its advantage is that detected value compared with
Peak steady.The root-mean-square value of amplitude was averaged to the time, suitable for wearing, the amplitude of alligatoring etc at any time
Slowly varying fault diagnosis.
2. form factor
Form factor is defined as the ratio between peak value and mean value.When form factor value is excessive, illustrate that lead screw or ball may be a little
Erosion；And form factor value it is too small when, illustrate that lead screw or ball are worn.The time of form factor variation is shorter, illustrates to roll
Pearl is more likely to faulty；And the time of form factor variation is longer, illustrates that lead screw or ball are faulty.
3. crest factor
Crest factor is defined as the ratio between peak value and root-mean-square value.Diagnosis suitable for spot corrosion class failure.By to wave crest because
Numerical value changes over time the monitoring of trend, and early prediction, and the development tendency of energy faults can be effectively performed.When
It is lesser stationary value when ball-screw fault-free；Once damage occurs in lead screw, then impact signal, vibration peak can be generated
It significantly increases, but root-mean-square value there is no apparent increase at this time, so crest factor value increases；When failure constantly extends, peak value
After progressively reaching limiting value, root-mean-square value then starts to increase, and crest factor value gradually reduces, until big when being restored to fault-free
It is small.
4. kurtosis coefficient
Calculation formula are as follows:Wherein,
β2For kurtosis coefficient；|Xi| it is the instantaneous amplitude at the i-th moment；For amplitude mean value；σ is standard deviation；N is the moment
Quantity.
When amplitude meets the fault-free lead screw or ball of normal distribution law, kurtosis coefficient value is about 3.With failure
Emergence and development, kurtosis coefficient value have the variation tendency similar with form factor.There is scar suitable for lead screw or ball surface
Diagnosis, the especially diagnosis of initial failure.
Due to big more of the stroke of the stroke ratio ball of lead screw, then the health status needs of diagnosis and prediction ball-screw
Data it is also more, therefore first to diagnose the health status of ball.
Workshop where the numerically-controlled machine tool that the present embodiment is related to is not laid with network, and gateway section is disposed near digital control system
Point, gateway node and digital control system are connected by cable network, in ball screw assembly, each one biography of upper installation of lead screw both ends pedestal
Feel node.It mainly comprises the steps that
It is synchronous by the NTP deadline that gateway node is based on wireless network；Gateway node is as root node, sensing node base
It is synchronous by the FTSP deadline in wireless sensor network network；Digital control system passes through fieldbus by main website of gateway node
The NCUC-bus deadline is synchronous.
Digital control system, sensing node, gateway node respectively acquire data simultaneously according to set acquisition strategies first, when continuing
Between length it is identical；Then operating state data is uploaded to gateway node by digital control system, and sensing node extracts mechanical characteristic
And gateway node is uploaded to, gateway node extracts numerical control characteristic；Last gateway node uses numerical control characteristic, judges machine
Whether bed is in not shutting down and non-standby mode, if mechanical features data and numerical control characteristic are then sent to cloud.
The frequency acquisition of vibration acceleration is often beyond 10kHz, so transmitting initial data can be with serious consumption network stream
Amount, and pass through two layers of feature extraction of sensing node and gateway node, network flow is not only substantially reduced, but also effectively reduce cloud
Hold centralized computing load.Based on above method, with high precision based on time synchronization, machine tool numerical control system data are realized for the first time
It is excavated with coordination data of the mechanical system data in machine failure diagnosis, can effectively improve fault diagnosis precision.
S102: cloud receives mechanical characteristic and numerical control characteristic, uses preset fault diagnosis and prediction model
Fault diagnosis and prediction are carried out, and fault diagnosis and prediction result are sent to client.
Beyond the clouds, the mechanical features data and numerical control characteristic of communication unit reception ball-screw, write-in store first
Unit is simultaneously transmitted to computing unit；Then computing unit carries out event to the mechanical features data and numerical control characteristic of ball-screw
Barrier diagnosis and prediction, and by the fault diagnosis of ball-screw and prediction result write storage unit.
It should be noted that preset fault diagnosis and prediction model include but are not limited to neural network model.In addition
The training of fault diagnosis and prediction model is the prior art, and which is not described herein again.
S103: client shows fault diagnosis and prediction result to lathe expert, and receives lathe expert to fault diagnosis
With the feedback result of prediction result, feedback result is sent to cloud；
Firstly, the fault diagnosis of ball-screw and prediction result are pushed to client by business unit；Then client to
Lathe expert shows the fault diagnosis and prediction result of ball-screw, and lathe expert ties the fault diagnosis of ball-screw and prediction
Fruit is judged, and feeds back judging result；Last cloud business unit receives the feedback result of lathe expert, and write-in storage is single
Member.
S104: cloud receives feedback result, marks mechanical characteristic and numerical control characteristic, obtains sample data；Root
According to sample data training fault diagnosis and prediction model, and return to step S102.
Then, it using lathe expert to the fault diagnosis of ball-screw and the feedback result of prediction result, completes to generate rolling
The mechanical features data of ballscrew and the mark of numerical control characteristic；Then labeled data is screened, sample data is obtained；Last root
According to sample data, using the parameter in the fault diagnosis and prediction model of machine learning amendment ball-screw, and calculating is fed back to
Unit, to guarantee that computing unit uses updated model treatment subsequent mechanical characteristic and numerical control characteristic.
Using embodiment illustrated in fig. 1 of the present invention, the present invention is based on cooperateing with for edge calculations and cloud, in marginal end using passing
The machine performance data of sense node acquisition lathe mechanical system simultaneously extract feature, obtain mechanical features data, adopt in gateway node
Collect the operating state data of machine tool numerical control system and extract feature, numerical control characteristic is obtained, then beyond the clouds to mechanical features
Data and numerical control characteristic carry out fault diagnosis and prediction, then mark mechanical characteristic using expert feedback and numerical control is special
It levies data and obtains sample data, the update of fault diagnosis and prediction model is then carried out using sample data, then carry out more
Secondary circular treatment obtains more accurate fault diagnosis and prediction model, to improve the precision of fault diagnosis and prediction.
In a kind of specific embodiment of the embodiment of the present invention, using gateway node as root node, sensing node is based on
Wireless sensor network network is synchronous by the FTSP deadline；Digital control system is based on cable network and passes through fieldbus NCUC-bus
Deadline is synchronous.
In a kind of specific embodiment of the embodiment of the present invention, method further include:
Gateway node receives the instruction that client is sent, and instruction includes but is not limited to that adjustment characteristic frequency acquisition is adjusted
The acquisition duration of whole characteristic, updates feature extraction algorithm library, restarts or close sensing node the type for adjusting characteristic
Or gateway node.
User sends instructions in the case where client is to lathe first；Then beyond the clouds, business unit receives instruction, and write-in storage is single
Member, and by communication unit to sending instructions under the gateway node of corresponding edge acies；Last gateway node receives instruction, destination node
It is then directly executed instruction for gateway node, is otherwise transmitted to sensing node execution.
The embodiment of the present invention substitutes extensive centralized calculation with edge calculations a large amount of, synchronize, real-time, with small-scale
Characteristic uploads substitution large-scale data and uploads, solid with machine learning fault diagnosis and the prediction model substitution of sustainable improvement
The fault knowledge library expert system of change improves the extended capability of system with cloud adjustment edge calculations, thus with real-time characteristic
The continuous accumulation of data is realized fault diagnosis and prediction technique that low discharge, high efficiency, diagnostic accuracy are continuously improved, is had more
Excellent input-output ratio, better industry universal and higher promotional value.
Embodiment 2
Fig. 2 is the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
Structural schematic diagram, Fig. 3 are the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The data of marginal end go out processing schematic in system；As shown in Figures 2 and 3, the machine failure cooperateed with based on edge calculations and cloud is examined
Disconnected and forecasting system, system include marginal end and cloud, wherein
Marginal end, including gateway node and sensing node.Sensing node is arranged on the component of lathe, and gateway node can be with
It is deployed near lathe, such as by the station of lathe.Gateway node is by cable network and numerical control system communication, by wirelessly passing
Feel ad-hoc network and sensing node communication, is communicated by 4G network or cable network and cloud.Gateway node be responsible for data acquisition,
Feature extraction uploads data to cloud；Sensing node is responsible for data acquisition, feature extraction, uploads data to gateway node.
Sensing node is used for, according to preset first acquisition strategies acquisition component machine performance data and extract feature,
Mechanical features data are received, and characteristic is uploaded to gateway node.
Gateway node is used for, and is acquired the operating state data of digital control system according to preset second strategy and is extracted feature,
Numerical control characteristic is obtained, and mechanical features data and numerical control characteristic are sent to cloud；
Gateway node is sent in the data in cloud, and mechanical features data include but is not limited to temperature, humidity, revolving speed, torsion
One of square, amplitude, form factor, crest factor and kurtosis coefficient etc. combine；Numerical control characteristic includes but unlimited
In a kind of in instruction code, alarm code, the speed of mainshaft, the direction of motion, coordinate etc. or combination；
Cloud, including communication unit, computing unit, storage unit, business unit, training unit, wherein communication unit,
For receiving mechanical characteristic and numerical control characteristic, write storage unit is simultaneously transmitted to computing unit；Computing unit is used for
Fault diagnosis and prediction are carried out to mechanical features data and numerical control characteristic, and fault diagnosis and prediction result write-in are stored
Unit；Storage unit, for storing mechanical features data and numerical control characteristic, the feedback result of lathe expert, various businesses
Data；Business unit, for showing fault diagnosis and prediction result to lathe expert, reception lathe expert is to fault diagnosis and in advance
Survey the feedback result of result；Training unit is used for according to feedback result, mechanical features data and numerical control characteristic training failure
Diagnosis and prediction model, so that fault diagnosis and the result of prediction model are identical as the feedback result of lathe expert, and by model
Parameter feedback is to computing unit.
Beyond the clouds, communication unit receives mechanical characteristic first and numerical control characteristic, write storage unit simultaneously forward
To computing unit；Then computing unit carries out fault diagnosis and prediction to mechanical features data and numerical control characteristic, and will be former
Barrier diagnosis and prediction result write storage unit.
Beyond the clouds, special to the received mechanical features data of institute and numerical control using preset fault diagnosis and prediction model first
It levies data and carries out fault diagnosis and prediction；Then fault diagnosis and prediction result are shown to lathe expert, lathe expert according to
The actual state of lathe judges fault diagnosis and the whether correct simultaneously feedback result of prediction result, and then is marked according to feedback result
Mechanical features data and numerical control characteristic obtain sample data；Finally using machine learning to fault diagnosis and prediction model
It is modified and evolves, and feed back to computing unit, to guarantee that computing unit is special using model treatment subsequent mechanical adjusted
Levy data and numerical control characteristic.
Using embodiment illustrated in fig. 2 of the present invention, the present invention is based on cooperateing with for edge calculations and cloud, in marginal end, utilize
The machine performance data of sensing node acquisition lathe mechanical system simultaneously extract feature, and obtain mechanical features data, in gateway section
The operating state data of point acquisition machine tool numerical control system simultaneously extracts feature, and obtains numerical control characteristic, then beyond the clouds to machine
Tool characteristic and numerical control characteristic carry out fault diagnosis and prediction, are then marked using lathe expert feedback result mechanical special
It levies data and numerical control characteristic and obtains sample data, then carry out fault diagnosis and prediction model more using sample data
Newly, then carry out multiple circular treatment, and then obtain most accurate fault diagnosis and prediction model, so improve fault diagnosis and
The precision of prediction.
In addition, the embodiment of the present invention also has flexible edge calculations ability, data type abundant has more comprehensively
, more accurate fault diagnosis and predictive ability；Storage and processing ability based on cloud, has better scalability；Not office
It is limited to fixed brand or model lathe, there is more good applicability；Collaboration based on edge calculations and cloud, the number of transmission
It is greatly reduced according to amount, effectively improves efficiency of fault diagnosis, find potential risks in advance, there is preferable versatility；Based on side
Edge calculates and the two-way collaboration in cloud, remotely adjusts edge calculations, effectively reduces cost, improves income, has higher economy
Value；Based on diagnosis/prediction-feedback mechanism, data mark is rapidly completed, pushes model training, there is high technology valence
Value.
The embodiment of the present invention, by cooperateing with edge calculations that communication is greatly lowered under the premise of retaining data core feature
Data volume, and finally being formed with cloud includes data uplink and the closed loop collaborative diagnosis method for instructing downlink, is effectively utilized machine
The causal relation of bed digital control system and mechanical system in machine failure, and realize flexible data acquisition and mentioned with characteristic
It takes mechanism and cloud to adjust the mechanism of edge calculations on demand, wireless internet of things is allowed to diagnose and predict extensive in machine failure
Using being possibly realized.
Embodiment 3
Fig. 4 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The process schematic issued is instructed, as shown in figure 4, the embodiment of the present invention 3 and the difference of the embodiment of the present invention 2 are, business sheet
Member is used for, to marginal end under send instructions, instruction includes but is not limited to the frequency acquisition or duration, the data of acquisition for adjusting data
Type updates feature extraction algorithm library, restarts or close one of sensing node or gateway node or combination.
User issues instruction to marginal end in client first, and instruction includes but is not limited to the frequency acquisition for adjusting data
Or it duration, the data type of acquisition, updates feature extraction algorithm library, restart or close sensing node or gateway node etc.；Then
Cloud business unit receives instruction, and write storage unit is simultaneously transmitted to communication unit；Cloud communication unit receives instruction after again, to
Send instructions under the gateway node of corresponding edge acies；Last gateway node receives instruction, and destination node is that gateway node is then directly held
Otherwise row instruction is transmitted to sensing node execution.
Using the embodiment of the present invention, the flexible control to cloud to marginal end may be implemented.
Embodiment 4
The embodiment of the present invention 4 and the difference of the embodiment of the present invention 2 are that client is also used to, and the operation for receiving user refers to
It enables, and client includes that Web is applied and mobile phone A pp.
In practical applications, fault diagnosis and prediction result are pushed to client by cloud business unit first；Then objective
Family end shows that fault diagnosis and prediction result, lathe expert judge fault diagnosis and prediction result to lathe expert, and
Feed back judging result；Last cloud business unit receives the feedback result of lathe expert, write storage unit.
Using the embodiment of the present invention, it can be convenient expert and carry out the judgement of fault diagnosis and prediction result and provide in time anti-
Feedback.
Embodiment 5
Fig. 5 is in the machine failure diagnosis and prediction system provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
The first process schematic of time synchronization；Fig. 6 is the lathe event provided in an embodiment of the present invention cooperateed with based on edge calculations and cloud
Hinder the second process schematic diagram of time synchronization in diagnosis and prediction system；Fig. 7 is provided in an embodiment of the present invention based on edge
Calculate the third process schematic with time synchronization in the machine failure diagnosis and prediction system of cloud collaboration；As seen in figs. 5-6,
The embodiment of the present invention 5 and the difference of the embodiment of the present invention 2 are that gateway node is used for, and complete gateway node by NTP network
Time synchronization, as marginal end time synchronization basis.
In practical applications, since the synchronous real-time data collection of marginal end is higher to time required precision, so each section
The higher the better for the precision of point time synchronization.
When Industrial Ethernet supports time synchronization, gateway node is based on cable network and passes through NTP (Network Time
Protocol, Network Time Protocol) deadline synchronization (precision is generally less than 50ms), otherwise gateway node is based on wireless network
It is synchronous by the NTP deadline.
As root node, sensing node is based on wireless sensor network network and passes through FTSP (Flooding Time gateway node
Synchronization Protocol, Flooding Time-Synchronization agreement) deadline synchronization (precision is less than 100 μ s).
When Industrial Ethernet supports time synchronization, digital control system is based on cable network and passes through fieldbus NCUC-bus (NC
Union of China Field Bus, numerical control alliance bus) deadline is synchronous (precision is less than 100ns), otherwise numerical control system
System is synchronous by the fieldbus NCUC-bus deadline by main website of gateway node.
Further, as shown in fig. 7,1 gateway node and 8 sensing node ad hoc network can be had 3 R sensing sections
Point becomes sensing relay node；Two sensing nodes in left side are connected to by sensing relay node with the sensing node on right side, into
And it is communicated to gateway node GW.FTSP is used at this time, and gateway node is root node, passes through the secondary completion in three batches of sensing relay node
All sensing node time synchronizations.The time is carried out to sensing relay node R 3 and sensing node S2 and S4 by gateway node first
It is synchronous；Then the time is carried out to sensing relay node R 1 and R5 and sensing node S6 by synchronized sensing relay node R 3
It is synchronous；Time synchronization is carried out to sensing node S7 and S9 finally by synchronized sensing relay node R 5.
Using the embodiment of the present invention, precise synchronization may be implemented, and then be conducive to effectively excavate machine tool numerical control system
With causality of the mechanical system data in machine failure；
Embodiment 6
The embodiment of the present invention 6 and the difference of the embodiment of the present invention 2 are that gateway node is used for, and judge whether lathe is in
It does not shut down and non-standby mode, if mechanical features data and numerical control characteristic are then sent to cloud.
When carrying out data acquisition, digital control system, sensing node, gateway node are respectively same according to set acquisition strategies first
When acquire data, time duration is identical；Then digital control system upload the data to gateway node, and sensing node extracts feature
Data simultaneously upload to gateway node；Last gateway node extracts characteristic from the data that digital control system acquires, and judges lathe
Whether in not shutting down and whether non-standby mode, i.e. lathe are in normal operating conditions, if lathe is in normal operating conditions,
Gateway node summarizes characteristic and uploads to cloud, does not otherwise upload.
The above is merely preferred embodiments of the present invention, be not intended to limit the invention, it is all in spirit of the invention and
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within principle.
Claims (9)
1. a kind of machine failure diagnosis and prediction method cooperateed with based on edge calculations and cloud, which is characterized in that the method packet
It includes:
1), sensing node acquires the machine performance data of machine tool component according to default first acquisition strategies and extracts feature, obtains
Mechanical features data, and the mechanical features data are uploaded into gateway node；The gateway node is according to default second acquisition
The operating state data of strategy acquisition digital control system simultaneously extracts feature, obtains numerical control characteristic, and by the mechanical features number
Cloud is sent to according to numerical control characteristic；
2), the cloud receives the mechanical features data and numerical control characteristic, uses preset fault diagnosis and prediction mould
Type carries out fault diagnosis and prediction, and fault diagnosis and prediction result are sent to client；
3), the client shows the fault diagnosis and prediction result to lathe expert, receives lathe expert to the failure
The feedback result of diagnosis and prediction result, and the feedback result is sent to the cloud；
4), the cloud receives the feedback result, marks the mechanical features data and numerical control characteristic, obtains sample number
According to；According to the sample data training fault diagnosis and prediction model, and returns and execute the step 2).
2. the machine failure diagnosis and prediction method according to claim 1 cooperateed with based on edge calculations and cloud, feature
Be: as root node, the sensing node is based on wireless sensor network network and passes through the FTSP deadline gateway node
It is synchronous；It is synchronous by the fieldbus NCUC-bus deadline that the digital control system is based on cable network.
3. the machine failure diagnosis and prediction method according to claim 1 cooperateed with based on edge calculations and cloud, feature
It is, the method also includes:
The gateway node receives the instruction for the sensing node and gateway node that the client is sent, described instruction
Including but not limited to, adjust characteristic frequency acquisition, adjust characteristic acquisition duration, adjustment characteristic type,
It updates feature extraction algorithm library, restart or close sensing node or gateway node.
4. the machine failure diagnosis and prediction system cooperateed with based on edge calculations and cloud, which is characterized in that the system comprises sides
Acies and cloud, wherein
The marginal end, including the gateway node and sensing node, the sensing node is arranged on the component of lathe, and presses
Machine performance data according to preset first acquisition strategies acquisition component simultaneously extract feature, obtain mechanical features data；
The gateway node is used for, and is acquired the operating state data of digital control system according to preset second strategy and is extracted feature,
Numerical control characteristic is obtained, and the mechanical features data and numerical control characteristic are sent to the cloud；
The gateway node is used to the mechanical features data and the numerical control characteristic being sent to cloud, wherein described
Mechanical features data include but is not limited to temperature, humidity, revolving speed, torque, amplitude, form factor, crest factor and kurtosis system
One of number or combination；The numerical control characteristic includes but is not limited to instruction code, alarm code, the speed of mainshaft, movement side
To a kind of in, coordinate or combination；
The cloud, including communication unit, computing unit, storage unit, business unit, training unit, wherein the communication is single
Member, the mechanical features data and numerical control characteristic uploaded for receiving the gateway node, is written the storage unit
And it is transmitted to the computing unit；
The computing unit, for carrying out fault diagnosis and prediction to the mechanical features data and numerical control characteristic, and will
The storage unit is written in fault diagnosis and prediction result；
The storage unit, for storing the mechanical features data and numerical control characteristic, the feedback result of lathe expert, each
Kind business datum；
The business unit receives lathe expert to described for showing the fault diagnosis and prediction result to lathe expert
The feedback result of fault diagnosis and prediction result；
The training unit, for according to the feedback result, the mechanical features data and numerical control characteristic training failure
Diagnosis and prediction model, so that the fault diagnosis and the result of prediction model are identical as the feedback result, and model are joined
Number feeds back to the computing unit.
5. the machine failure diagnosis and prediction system according to claim 4 cooperateed with based on edge calculations and cloud, feature
Be, the business unit is used for, to marginal end under send instructions, wherein described instruction includes but is not limited to adjust adopting for data
Collection frequency or duration, update feature extraction algorithm library, restart or close the sensing node or gateway section the data type of acquisition
One of point or combination.
6. the machine failure diagnosis and prediction system according to claim 4 cooperateed with based on edge calculations and cloud, feature
It is, the gateway node is used for, and the time synchronization of the gateway node is completed by NTP, as marginal end time synchronization
Basis.
7. the machine failure diagnosis and prediction system according to claim 4 cooperateed with based on edge calculations and cloud, feature
It is, the gateway node is used for, and is judged whether lathe is in and is not shut down and non-standby mode, if then by the mechanical features
Data and numerical control characteristic are sent to the cloud.
8. the machine failure diagnosis and prediction system according to claim 4 cooperateed with based on edge calculations and cloud, feature
It is, the system also includes clients, for showing the fault diagnosis and prediction result, and receiver to lathe expert
Feedback result of the bed expert to the fault diagnosis and prediction result.
9. the machine failure diagnosis and prediction system according to claim 4 cooperateed with based on edge calculations and cloud, feature
It is, the client is also used to, and receives the operational order of user, and the client includes that Web is applied and mobile phone A pp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235933.1A CN109933004B (en) | 2019-03-27 | 2019-03-27 | Machine tool fault diagnosis and prediction method and system based on edge computing and cloud cooperation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235933.1A CN109933004B (en) | 2019-03-27 | 2019-03-27 | Machine tool fault diagnosis and prediction method and system based on edge computing and cloud cooperation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109933004A true CN109933004A (en) | 2019-06-25 |
| CN109933004B CN109933004B (en) | 2022-05-24 |
Family
ID=66988473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235933.1A Active CN109933004B (en) | 2019-03-27 | 2019-03-27 | Machine tool fault diagnosis and prediction method and system based on edge computing and cloud cooperation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109933004B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110394688A (en) * | 2019-09-02 | 2019-11-01 | 太原科技大学 | Conditions of machine tool monitoring method based on edge calculations |
| CN110554657A (en) * | 2019-10-16 | 2019-12-10 | 河北工业大学 | Health diagnosis system and diagnosis method for operation state of numerical control machine tool |
| CN110749462A (en) * | 2019-07-19 | 2020-02-04 | 华瑞新智科技（北京）有限公司 | Industrial equipment fault detection method and system based on edge calculation |
| CN110781612A (en) * | 2019-11-14 | 2020-02-11 | 哈工大机器人（山东）智能装备研究院 | Fault diagnosis method and device for ball screw, computer device and storage medium |
| CN111507489A (en) * | 2020-04-20 | 2020-08-07 | 电子科技大学中山学院 | Cloud-edge-coordinated amusement equipment fault prediction and health management system and method |
| CN111596629A (en) * | 2020-06-02 | 2020-08-28 | 曲阜师范大学 | Cloud-edge-collaborative industrial data fusion method and security controller |
| CN111594201A (en) * | 2020-05-28 | 2020-08-28 | 中铁工程装备集团有限公司 | TBM key parameter intelligent control system and method |
| CN111737061A (en) * | 2020-06-11 | 2020-10-02 | 石霜霜 | Data processing method based on edge computing and 5G communication and central cloud server |
| CN111783968A (en) * | 2020-06-30 | 2020-10-16 | 山东信通电子股份有限公司 | Power transmission line monitoring method and system based on cloud edge cooperation |
| CN111928334A (en) * | 2020-07-30 | 2020-11-13 | 瑞纳智能设备股份有限公司 | Heat supply control method and system based on edge cloud cooperative framework and computer equipment |
| CN112051800A (en) * | 2020-09-17 | 2020-12-08 | 珠海格力智能装备有限公司 | Method and device for processing abnormality of machine tool, and computer-readable storage medium |
| CN112101532A (en) * | 2020-11-18 | 2020-12-18 | 天津开发区精诺瀚海数据科技有限公司 | Self-adaptive multi-model driving equipment fault diagnosis method based on edge cloud cooperation |
| CN112216085A (en) * | 2020-09-15 | 2021-01-12 | 青岛科技大学 | Equipment key load-bearing structural member health monitoring system based on edge calculation and intelligent identification of updated samples |
| CN112241145A (en) * | 2019-07-16 | 2021-01-19 | 神通资讯科技股份有限公司 | Abnormality detection system and method for automatic processing machine |
| CN112394703A (en) * | 2019-08-14 | 2021-02-23 | 中车时代电动汽车股份有限公司 | Vehicle fault management system |
| CN112486136A (en) * | 2019-09-11 | 2021-03-12 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN112947290A (en) * | 2021-05-16 | 2021-06-11 | 北京赛博联物科技有限公司 | Edge cloud cooperation-based equipment state monitoring method and system and storage medium |
| CN113253037A (en) * | 2021-06-22 | 2021-08-13 | 北京赛博联物科技有限公司 | Current ripple-based edge cloud cooperative equipment state monitoring method and system and medium |
| CN113742855A (en) * | 2021-07-27 | 2021-12-03 | 清华大学 | Fault prediction method, system, electronic equipment and readable storage medium |
| CN113759854A (en) * | 2021-09-18 | 2021-12-07 | 深圳市裕展精密科技有限公司 | Intelligent factory management and control system and method based on edge calculation |
| CN113867285A (en) * | 2021-09-24 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Edge cloud platform-based edge side equipment fault diagnosis method and system |
| CN114273979A (en) * | 2021-12-10 | 2022-04-05 | 无锡市信昌电子科技有限公司 | On-line monitoring system for machining of engraving, milling, drilling and tapping numerical control system |
| CN115185234A (en) * | 2022-09-09 | 2022-10-14 | 中科航迈数控软件(深圳)有限公司 | Adaptive fault monitoring method and system for numerical control machine tool |
| WO2022222657A1 (en) * | 2021-04-21 | 2022-10-27 | 深圳市道通科技股份有限公司 | Automobile diagnosis system and method, and cloud server |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU5201079A (en) * | 1978-11-13 | 1980-05-22 | Goodyear Tire And Rubber Company, The | Sequential event monitor |
| CN101118437A (en) * | 2007-09-03 | 2008-02-06 | 石毅 | New style numerically controlled machine remote condition monitoring and failure diagnosis system realizing method |
| CN107160834A (en) * | 2017-07-14 | 2017-09-15 | 武汉红金龙印务股份有限公司 | During a kind of silk-screen printing of sheet paper in printing process anti-moire method |
| 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 |
| CN108363382A (en) * | 2018-02-09 | 2018-08-03 | 哈尔滨工业大学（威海） | A kind of complex equipment fault diagnosis method and system |
| EP3370125A1 (en) * | 2017-03-01 | 2018-09-05 | PLETHORA IIoT, S.L. | Device and system including multiple devices for supervision and control of machines in industrial installation |
| CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN108667725A (en) * | 2018-04-25 | 2018-10-16 | 哈尔滨电气股份有限公司 | A kind of industrial AnyRouter and implementation method based on a variety of accesses and edge calculations |
| CN108710362A (en) * | 2018-06-25 | 2018-10-26 | 济南浪潮高新科技投资发展有限公司 | A kind of CNC Machine Network diagnostic method based on industry internet platform |
| CN108768843A (en) * | 2018-06-27 | 2018-11-06 | 安徽国讯芯微科技有限公司 | A kind of multi-internet integration edge calculations gateway |
| CN108805300A (en) * | 2018-05-30 | 2018-11-13 | 上海理工大学 | Numerically controlled machine remote live collaboration fault diagnosis and maintenance system |
| CN108828409A (en) * | 2018-08-03 | 2018-11-16 | 南方电网科学研究院有限责任公司 | A kind of fault detection system based on edge calculations |
| CN109118732A (en) * | 2018-08-27 | 2019-01-01 | 中国科学院上海微系统与信息技术研究所 | Sensor perception event judgement and alarm system and method based on marginal information |
| US20190046037A1 (en) * | 2017-08-14 | 2019-02-14 | Amrita Vishwa Vidyapeetham | Systems, methods, and devices for remote health monitoring and management using internet of things sensors |
| CN109460003A (en) * | 2018-10-17 | 2019-03-12 | 南京凯奥思数据技术有限公司 | Vehicle trouble predicts modeling method and system |
-
2019
- 2019-03-27 CN CN201910235933.1A patent/CN109933004B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU5201079A (en) * | 1978-11-13 | 1980-05-22 | Goodyear Tire And Rubber Company, The | Sequential event monitor |
| CN101118437A (en) * | 2007-09-03 | 2008-02-06 | 石毅 | New style numerically controlled machine remote condition monitoring and failure diagnosis system realizing method |
| EP3370125A1 (en) * | 2017-03-01 | 2018-09-05 | PLETHORA IIoT, S.L. | Device and system including multiple devices for supervision and control of machines in industrial installation |
| CN107160834A (en) * | 2017-07-14 | 2017-09-15 | 武汉红金龙印务股份有限公司 | During a kind of silk-screen printing of sheet paper in printing process anti-moire method |
| 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 |
| US20190046037A1 (en) * | 2017-08-14 | 2019-02-14 | Amrita Vishwa Vidyapeetham | Systems, methods, and devices for remote health monitoring and management using internet of things sensors |
| CN108363382A (en) * | 2018-02-09 | 2018-08-03 | 哈尔滨工业大学（威海） | A kind of complex equipment fault diagnosis method and system |
| CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN108667725A (en) * | 2018-04-25 | 2018-10-16 | 哈尔滨电气股份有限公司 | A kind of industrial AnyRouter and implementation method based on a variety of accesses and edge calculations |
| CN108805300A (en) * | 2018-05-30 | 2018-11-13 | 上海理工大学 | Numerically controlled machine remote live collaboration fault diagnosis and maintenance system |
| CN108710362A (en) * | 2018-06-25 | 2018-10-26 | 济南浪潮高新科技投资发展有限公司 | A kind of CNC Machine Network diagnostic method based on industry internet platform |
| CN108768843A (en) * | 2018-06-27 | 2018-11-06 | 安徽国讯芯微科技有限公司 | A kind of multi-internet integration edge calculations gateway |
| CN108828409A (en) * | 2018-08-03 | 2018-11-16 | 南方电网科学研究院有限责任公司 | A kind of fault detection system based on edge calculations |
| CN109118732A (en) * | 2018-08-27 | 2019-01-01 | 中国科学院上海微系统与信息技术研究所 | Sensor perception event judgement and alarm system and method based on marginal information |
| CN109460003A (en) * | 2018-10-17 | 2019-03-12 | 南京凯奥思数据技术有限公司 | Vehicle trouble predicts modeling method and system |
Non-Patent Citations (2)
| Title |
|---|
| SHAO JIE: "Research on intelligent recognition of axis orbit based on Hu moment invariants and fractal box dimension", 《2017 14TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS AND AMBIENT INTELLIGENCE (URAI)》 * |
| 陈祥芹: "振动信号多元统计分析特征提取及传动系统关键部件故障诊断应用", 《中国优秀硕士学位论文全文数据库工程科技II辑》 * |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112241145A (en) * | 2019-07-16 | 2021-01-19 | 神通资讯科技股份有限公司 | Abnormality detection system and method for automatic processing machine |
| CN110749462A (en) * | 2019-07-19 | 2020-02-04 | 华瑞新智科技（北京）有限公司 | Industrial equipment fault detection method and system based on edge calculation |
| CN110749462B (en) * | 2019-07-19 | 2021-05-07 | 华瑞新智科技（北京）有限公司 | Industrial equipment fault detection method and system based on edge calculation |
| CN112394703A (en) * | 2019-08-14 | 2021-02-23 | 中车时代电动汽车股份有限公司 | Vehicle fault management system |
| CN110394688A (en) * | 2019-09-02 | 2019-11-01 | 太原科技大学 | Conditions of machine tool monitoring method based on edge calculations |
| CN112486136A (en) * | 2019-09-11 | 2021-03-12 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN112486136B (en) * | 2019-09-11 | 2022-03-15 | 中科云谷科技有限公司 | Fault early warning system and method |
| CN110554657B (en) * | 2019-10-16 | 2023-03-03 | 河北工业大学 | Health diagnosis system and diagnosis method for operation state of numerical control machine tool |
| CN110554657A (en) * | 2019-10-16 | 2019-12-10 | 河北工业大学 | Health diagnosis system and diagnosis method for operation state of numerical control machine tool |
| CN110781612A (en) * | 2019-11-14 | 2020-02-11 | 哈工大机器人（山东）智能装备研究院 | Fault diagnosis method and device for ball screw, computer device and storage medium |
| CN111507489A (en) * | 2020-04-20 | 2020-08-07 | 电子科技大学中山学院 | Cloud-edge-coordinated amusement equipment fault prediction and health management system and method |
| CN111507489B (en) * | 2020-04-20 | 2023-04-18 | 电子科技大学中山学院 | Cloud-edge-coordinated amusement equipment fault prediction and health management system and method |
| CN111594201A (en) * | 2020-05-28 | 2020-08-28 | 中铁工程装备集团有限公司 | TBM key parameter intelligent control system and method |
| CN111596629A (en) * | 2020-06-02 | 2020-08-28 | 曲阜师范大学 | Cloud-edge-collaborative industrial data fusion method and security controller |
| CN111737061B (en) * | 2020-06-11 | 2021-01-12 | 深圳千通科技有限公司 | Data processing method based on edge computing and 5G communication and central cloud server |
| CN111737061A (en) * | 2020-06-11 | 2020-10-02 | 石霜霜 | Data processing method based on edge computing and 5G communication and central cloud server |
| CN111783968A (en) * | 2020-06-30 | 2020-10-16 | 山东信通电子股份有限公司 | Power transmission line monitoring method and system based on cloud edge cooperation |
| CN111928334A (en) * | 2020-07-30 | 2020-11-13 | 瑞纳智能设备股份有限公司 | Heat supply control method and system based on edge cloud cooperative framework and computer equipment |
| CN112216085A (en) * | 2020-09-15 | 2021-01-12 | 青岛科技大学 | Equipment key load-bearing structural member health monitoring system based on edge calculation and intelligent identification of updated samples |
| CN112051800A (en) * | 2020-09-17 | 2020-12-08 | 珠海格力智能装备有限公司 | Method and device for processing abnormality of machine tool, and computer-readable storage medium |
| CN112101532B (en) * | 2020-11-18 | 2021-02-12 | 天津开发区精诺瀚海数据科技有限公司 | Self-adaptive multi-model driving equipment fault diagnosis method based on edge cloud cooperation |
| CN112101532A (en) * | 2020-11-18 | 2020-12-18 | 天津开发区精诺瀚海数据科技有限公司 | Self-adaptive multi-model driving equipment fault diagnosis method based on edge cloud cooperation |
| WO2022222657A1 (en) * | 2021-04-21 | 2022-10-27 | 深圳市道通科技股份有限公司 | Automobile diagnosis system and method, and cloud server |
| CN112947290A (en) * | 2021-05-16 | 2021-06-11 | 北京赛博联物科技有限公司 | Edge cloud cooperation-based equipment state monitoring method and system and storage medium |
| CN112947290B (en) * | 2021-05-16 | 2021-08-20 | 北京赛博联物科技有限公司 | Edge cloud cooperation-based equipment state monitoring method and system and storage medium |
| CN113253037A (en) * | 2021-06-22 | 2021-08-13 | 北京赛博联物科技有限公司 | Current ripple-based edge cloud cooperative equipment state monitoring method and system and medium |
| CN113253037B (en) * | 2021-06-22 | 2021-10-08 | 北京赛博联物科技有限公司 | Current ripple-based edge cloud cooperative equipment state monitoring method and system and medium |
| CN113742855B (en) * | 2021-07-27 | 2022-03-18 | 清华大学 | Fault prediction method, system, electronic equipment and readable storage medium |
| CN113742855A (en) * | 2021-07-27 | 2021-12-03 | 清华大学 | Fault prediction method, system, electronic equipment and readable storage medium |
| CN113759854A (en) * | 2021-09-18 | 2021-12-07 | 深圳市裕展精密科技有限公司 | Intelligent factory management and control system and method based on edge calculation |
| CN113759854B (en) * | 2021-09-18 | 2023-09-05 | 富联裕展科技(深圳)有限公司 | Intelligent factory management and control system and method based on edge calculation |
| CN113867285A (en) * | 2021-09-24 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Edge cloud platform-based edge side equipment fault diagnosis method and system |
| CN114273979A (en) * | 2021-12-10 | 2022-04-05 | 无锡市信昌电子科技有限公司 | On-line monitoring system for machining of engraving, milling, drilling and tapping numerical control system |
| CN114273979B (en) * | 2021-12-10 | 2024-02-02 | 无锡市信昌电子科技有限公司 | Online monitoring system for processing engraving, milling, drilling and tapping numerical control system |
| CN115185234A (en) * | 2022-09-09 | 2022-10-14 | 中科航迈数控软件(深圳)有限公司 | Adaptive fault monitoring method and system for numerical control machine tool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109933004B (en) | 2022-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109933004A (en) | The machine failure diagnosis and prediction method and system cooperateed with based on edge calculations and cloud | |
| CN102929210B (en) | Control and optimization system for feature-based numerical control machining process and control and optimization method therefor | |
| CN101870075B (en) | Method for predicting service life of screw pair of numerical control machine on basis of performance degradation model | |
| CN110394688B (en) | Machine tool state monitoring method based on edge calculation | |
| CN113569475B (en) | Subway axle box bearing fault diagnosis system based on digital twin technology | |
| CN101870076B (en) | Method for predicting service life of guide pair of numerical control machine on basis of performance degradation model | |
| US8639454B2 (en) | Method of efficacy anticipation and failure examination for an apparatus | |
| Marinescu et al. | An automated monitoring solution for avoiding an increased number of surface anomalies during milling of aerospace alloys | |
| CN107765651A (en) | The manufacturing management system of abnormality detection condition is changed by manufacturing time information | |
| CN112051799A (en) | Self-adaptive control method for machining | |
| CN104950808A (en) | Machine tool thermal error compensation method based on augmented naive Bayes network | |
| CN103439919B (en) | CAD/CAM/CNC closed-loop control method based on dynamic feature model | |
| Albano et al. | Sensors: the enablers for proactive maintenance in the real world | |
| CN104423323A (en) | Numerical control machine tool remote control system | |
| Uhlmann et al. | Monitoring of slowly progressing deterioration of computer numerical control machine axes | |
| CN116628544A (en) | Fault diagnosis method based on hydraulic winch state on-line monitoring | |
| CN108490876B (en) | Method for improving synchronization accuracy of numerical control machining monitoring threshold and signal | |
| CN115364992A (en) | Coal mill health monitoring system and health monitoring method | |
| CN115509194A (en) | Cigarette equipment digital twin monitoring system and method based on AR intelligent technology | |
| Shi et al. | Integration of multiple platforms for real-time remote model-based condition monitoring | |
| He et al. | Low-cost and small-sample fault diagnosis for 3D printers based on echo state networks | |
| Pagitsch et al. | Estimation of internal gearbox loads for condition monitoring in wind turbines based on physical modeling | |
| Stoop et al. | Fleet learning of thermal error compensation in machine tools | |
| 강민규 et al. | Deep Learning-Based Analysis for Abnormal Diagnosis of Air Compressors | |
| Dai et al. | The principle and application of intelligent machine tools |
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 |