CN109079583B - Milling machine operational monitoring method and system based on artificial intelligence - Google Patents
Milling machine operational monitoring method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN109079583B CN109079583B CN201810849557.0A CN201810849557A CN109079583B CN 109079583 B CN109079583 B CN 109079583B CN 201810849557 A CN201810849557 A CN 201810849557A CN 109079583 B CN109079583 B CN 109079583B
- Authority
- CN
- China
- Prior art keywords
- milling
- milling machine
- wear condition
- current
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
- B23Q17/0952—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool during machining
- B23Q17/0957—Detection of tool breakage
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/10—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting speed or number of revolutions
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Numerical Control (AREA)
Abstract
The milling machine operational monitoring method based on artificial intelligence that the present invention provides a kind of, milling machine operational monitoring method include the following steps: the Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling depth that monitor milling machine；Monitor the wear condition of milling cutter；Above-mentioned data are sent to milling machine monitoring center；The wear condition of milling cutter is sent to milling machine monitoring center；By the historical data of correlation, while transferring the historical data of the wear condition of milling cutter；The historical data of the wear condition of historical data and milling cutter based on correlation generates the first incidence relation between the Milling Force of milling machine and the wear condition of milling cutter, while generating the second incidence relation between parameters and the wear condition of milling cutter；Current Milling Force based on the first incidence relation and milling machine, judges the current wear condition of milling cutter.Method of the invention is not in restrain slow, the problem of can not restraining, and prediction accuracy has obtained significantly being promoted.
Description
Technical field
The present invention relates to Milling Process field, in particular to a kind of milling machine operational monitoring method based on artificial intelligence and it is
System.
Background technique
Production factors one of of the cutting tool as machining, state directly affects the processing quality and lathe of workpiece
The stability and reliability of operation show that reliable tool condition monitoring system can be improved 50% according to relevant statistical data
Machine tool utilization rate can reduce by up to 70% downtime, and productivity can be made to improve 15% -60%.The system can not only
Significantly extend cutter life, moreover it is possible to effectively reduce the scrap of the product generated by tool failure.Traditional tool condition monitoring is
Off-line type usually needs regular shutdown inspection cutter situation, and shutdown will greatly increase processing non-cutting time, influences machining effect
Rate.And because cutter inspection be periodically carry out, for avoid cutter twice check between fail, can only conservative estimation cutter life,
This will not ensure that making full use of for cutter.For the requirement for adapting to automated production, acquisition based on certain signal specifics with point
Analyse the technology of processing, related personnel had been developed that a variety of processing operating condition bottom tool states automatic monitoring methods and it is online in real time
Monitoring system.The state of timely learning cutter simultaneously changes milling parameter, to reduce processing non-cutting time, extends cutter life, mentions
High production rate.
The information disclosed in the background technology section is intended only to increase the understanding to general background of the invention, without answering
When being considered as recognizing or imply that the information constitutes the prior art already known to those of ordinary skill in the art in any form.
Summary of the invention
The milling machine operational monitoring method and system based on artificial intelligence that the purpose of the present invention is to provide a kind of, to overcome
The shortcomings that prior art.
The milling machine operational monitoring method based on artificial intelligence that the present invention provides a kind of, it is characterised in that: milling machine operation prison
Survey method includes the following steps:
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling for monitoring milling machine are deep
Degree；
Monitor the wear condition of milling cutter；
The Milling Force of milling machine, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and milling depth are sent out
Give milling machine monitoring center；
The wear condition of milling cutter is sent to milling machine monitoring center；
Milling Force, milling machine spindle revolving speed, the milling machine feed shaft feed speed, milling angle of milling machine are transferred by milling machine monitoring center
The historical data of degree and milling depth, while transferring by milling machine monitoring center the historical data of the wear condition of milling cutter；
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle by milling machine monitoring center based on milling machine
The historical data of the wear condition of the historical data and milling cutter of degree and milling depth, generates the Milling Force of milling machine and the mill of milling cutter
The first incidence relation between damage situation, while generating the Milling Force of milling machine, milling machine spindle revolving speed, milling machine feed shaft feeding speed
The second incidence relation between degree, milling angle and milling depth and the wear condition of milling cutter；
Current Milling Force by milling machine monitoring center based on the first incidence relation and milling machine, judges the current abrasion of milling cutter
Situation.
Preferably, in above-mentioned technical proposal, milling machine operational monitoring method further includes following steps:
If it is determined that the current wear condition of milling cutter is greater than thresholding, then halt instruction is issued by milling machine monitoring center；
Determine the currently practical wear condition of milling cutter and the current wear condition of the milling cutter judged by milling machine monitoring center
It is whether consistent；
If it is determined that the current abrasion of the currently practical wear condition of milling cutter and the milling cutter judged by milling machine monitoring center
Situation is consistent, then issues the first instruction to milling machine monitoring center.
Preferably, in above-mentioned technical proposal, after milling machine monitoring center receives the first instruction, continue to close based on first
The current Milling Force of connection relationship and milling machine judges the current wear condition of milling cutter；
When the current wear condition of milling cutter is greater than the second thresholding, the first tool changing instruction is issued by milling machine monitoring center.
Preferably, in above-mentioned technical proposal, milling machine operational monitoring method further includes following steps:
If it is determined that the current abrasion of the currently practical wear condition of milling cutter and the milling cutter judged by milling machine monitoring center
Situation is inconsistent, then issues the second instruction to milling machine monitoring center；
After milling machine monitoring center receives the second instruction, the current milling based on the second incidence relation and milling machine
Power, current milling machine spindle revolving speed, current milling machine feed shaft feed speed, current milling angle and current milling depth, judgement
The current wear condition of milling cutter.
Preferably, in above-mentioned technical proposal, if it is determined that the current wear condition of milling cutter is greater than third thresholding, then by milling machine
Monitoring center issues the second tool changing instruction.
The present invention provides a kind of milling machine operation monitoring system based on artificial intelligence, it is characterised in that: system includes:
First sensor is used to monitor the Milling Force of milling machine；
Second sensor is used to monitor milling machine spindle revolving speed；
3rd sensor is used to monitor milling machine feed shaft feed speed；
4th sensor is used to monitor milling angle；
5th sensor is used to monitor milling depth；
Milling machine monitoring center is configured as executing following operation:
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling for receiving milling machine are deep
Degree；
Receive the wear condition of milling cutter；
Transfer Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling depth of milling machine
Historical data, while transferring the historical data of the wear condition of milling cutter；
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and milling depth based on milling machine
Historical data and milling cutter wear condition historical data, generate between the Milling Force of milling machine and the wear condition of milling cutter
One incidence relation, at the same generate the Milling Force of milling machine, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and
The second incidence relation between milling depth and the wear condition of milling cutter；
Current Milling Force based on the first incidence relation and milling machine, judges the current wear condition of milling cutter.
Preferably, in above-mentioned technical proposal, milling machine monitoring center is additionally configured to execute following operation:
If it is determined that the current wear condition of milling cutter is greater than thresholding, then halt instruction is issued；
Receive the first instruction, wherein the first instruction is sent in the case where there:
Determine the currently practical wear condition of milling cutter and the current wear condition of the milling cutter judged by milling machine monitoring center
Unanimously.
Preferably, in above-mentioned technical proposal, milling machine monitoring center is additionally configured to execute following operation: when receiving first
After instruction, continues the current Milling Force based on the first incidence relation and milling machine, judge the current wear condition of milling cutter；
When the current wear condition of milling cutter is greater than the second thresholding, the first tool changing instruction is issued.
Preferably, in above-mentioned technical proposal, milling machine monitoring center is additionally configured to execute following operation:
Receive the second instruction, wherein the second instruction is sent in the case where there:
Determine the currently practical wear condition of milling cutter and the current wear condition of the milling cutter judged by milling machine monitoring center
It is inconsistent；
After receiving the second instruction, current Milling Force, current milling machine master based on the second incidence relation and milling machine
Axis revolving speed, current milling machine feed shaft feed speed, current milling angle and current milling depth, judge the current abrasion of milling cutter
Situation.
Preferably, in above-mentioned technical proposal, milling machine monitoring center is additionally configured to execute following operation: if it is determined that milling cutter
Current wear condition be greater than third thresholding, then by milling machine monitoring center issue the second tool changing instruction.
Compared with prior art, the invention has the following beneficial effects: have been proposed utilizing nerve net in the prior art
The method that network algorithm, algorithm of support vector machine or genetic algorithm carry out tool wear prediction, the defect of the method for the prior art
It is to consider more irrelevant factor, causes algorithmic statement slower or even algorithm is not restrained (so as to cause the failure of algorithm), this
A little situations are all during tool wear monitors in real time should not the problem.It is needed to improve convergence speed of the algorithm just
Dimension-reduction treatment is carried out to various factors, but will appear information loss again during Data Dimensionality Reduction, this, which may cause, is analyzing
It loses in the process and vital information is predicted for tool wear.In order to solve contradiction in the prior art, the present invention is proposed
A kind of " two steps " algorithm.Inventors have found that cutter and specific abrasive stage for certain materials, tool wear and milling
It cuts between power there are very strong incidence relation, considers that other factors may cause model convergence rate and slow down at this time, but model
Prediction accuracy without significantly being promoted；Cutter and specific abrasive stage simultaneously for other types, tool wear
It is related to Multiple factors, at this time if only considering Milling Force, it will lead to the sharp fall of model prediction accuracy.In order to simultaneously
Using two models, the application is based on the thinking of a kind of " trial and error ", predicts tool wear degree first with naive model, then
Whether the verifying prediction degree of wear is consistent with true wear degree, illustrates that model is incorrect if inconsistent, at this point, of the invention
Method will automatically switch to another model and predict.Method of the invention be not in restrained it is slow, can not be convergent
Problem, and prediction accuracy has obtained significantly being promoted.
Detailed description of the invention
By reading the following detailed description of the preferred embodiment, various other advantages and benefits are common for this field
Technical staff will become clear.The drawings are only for the purpose of illustrating a preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Fig. 1 is the method flow diagram of embodiment according to the present invention.
Specific embodiment
The illustrative embodiments of the disclosure are more fully described below with reference to accompanying drawings.Although showing this public affairs in attached drawing
The illustrative embodiments opened, it being understood, however, that may be realized in various forms the disclosure without the reality that should be illustrated here
The mode of applying is limited.It is to be able to thoroughly understand the disclosure on the contrary, providing these embodiments, and can be by this public affairs
The range opened is fully disclosed to those skilled in the art.
Fig. 1 is the method flow diagram of embodiment according to the present invention.As shown, the milling machine based on artificial intelligence runs prison
Survey method includes:
Step 101: monitor the Milling Force of milling machine, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and
Milling depth；
Step 102: monitoring the wear condition of milling cutter；
Step 103: by the Milling Force of milling machine, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and milling
It cuts depth and is sent to milling machine monitoring center；
Step 104: the wear condition of milling cutter is sent to milling machine monitoring center；
Step 105: Milling Force, milling machine spindle revolving speed, the milling machine feed shaft feeding speed of milling machine are transferred by milling machine monitoring center
The historical data of degree, milling angle and milling depth, while transferring by milling machine monitoring center the history of the wear condition of milling cutter
Data；
Step 106: Milling Force, milling machine spindle revolving speed, milling machine feed shaft feeding speed by milling machine monitoring center based on milling machine
The historical data of the wear condition of the historical data and milling cutter of degree, milling angle and milling depth, generates the Milling Force of milling machine
The first incidence relation between the wear condition of milling cutter, while generating the Milling Force of milling machine, milling machine spindle revolving speed, milling machine feeding
The second incidence relation between axis feed speed, milling angle and milling depth and the wear condition of milling cutter；
Step 107: the current Milling Force by milling machine monitoring center based on the first incidence relation and milling machine judges milling cutter
Current wear condition.
In a preferred embodiment, milling machine operational monitoring method further includes following steps: if it is determined that the current mill of milling cutter
Damage situation is greater than thresholding, then issues halt instruction by milling machine monitoring center；Determine the currently practical wear condition of milling cutter with by milling
Whether the current wear condition for the milling cutter that bed monitoring center is judged is consistent；If it is determined that the currently practical wear condition of milling cutter with
The current wear condition of the milling cutter judged by milling machine monitoring center is consistent, then issues the first instruction to milling machine monitoring center.
In a preferred embodiment, after milling machine monitoring center receives the first instruction, continue to close based on the first association
The current Milling Force of system and milling machine, judges the current wear condition of milling cutter；When the current wear condition of milling cutter is greater than second
In limited time, the first tool changing instruction is issued by milling machine monitoring center.
In a preferred embodiment, milling machine operational monitoring method further includes following steps: if it is determined that the current reality of milling cutter
Border wear condition and the current wear condition of the milling cutter judged by milling machine monitoring center are inconsistent, then send out to milling machine monitoring center
Second instruction out；After milling machine monitoring center receives the second instruction, the current milling based on the second incidence relation and milling machine
Power, current milling machine spindle revolving speed, current milling machine feed shaft feed speed, current milling angle and current milling depth are cut, is sentenced
The current wear condition of disconnected milling cutter.
In a preferred embodiment, it if it is determined that the current wear condition of milling cutter is greater than third thresholding, is then monitored by milling machine
Center issues the second tool changing instruction.
The algorithm for establishing incidence relation is the method for this field e.g. by neural network algorithm realization, neural network calculation
Method itself is the known algorithm of this field, and the application repeats no more.
It has been proposed carrying out knife using neural network algorithm, algorithm of support vector machine or genetic algorithm in the prior art
Having the method for Wear prediction, the defect of the method for the prior art is to consider more irrelevant factor, cause algorithmic statement slower,
Even algorithm is not restrained (so as to cause the failure of algorithm), these situations are all during tool wear monitors in real time should not
The problem.It just needs to improve convergence speed of the algorithm to various factors progress dimension-reduction treatment, but Data Dimensionality Reduction mistake
It will appear information loss again in journey, this, which may cause to lose in the analysis process, predicts vital letter for tool wear
Breath.In order to solve contradiction in the prior art, the invention proposes a kind of " two steps " algorithms.Inventors have found that for certain materials
The cutter of material and specific abrasive stage, there are very strong incidence relations between tool wear and Milling Force, consider at this time other
Factor may cause model convergence rate and slow down, but the prediction accuracy of model is without significantly being promoted；Simultaneously for it
The cutter of its type and specific abrasive stage, tool wear is related to Multiple factors, will at this time if only considering Milling Force
Lead to the sharp fall of model prediction accuracy.In order to apply two models simultaneously, the application is based on the thinking of a kind of " trial and error ",
Tool wear degree is predicted first with naive model, then whether the verifying prediction degree of wear and true wear degree are consistent,
Illustrate that model is incorrect if inconsistent, is predicted at this point, method of the invention will automatically switch to another model.This
The method of invention is not in restrain slow, the problem of can not restraining, and prediction accuracy has obtained significantly being promoted.
The present invention provides a kind of milling machine operation monitoring system based on artificial intelligence, system includes: first sensor,
For monitoring the Milling Force of milling machine；Second sensor is used to monitor milling machine spindle revolving speed；3rd sensor is used to monitor
Milling machine feed shaft feed speed；4th sensor is used to monitor milling angle；5th sensor is used to monitor milling depth
Degree；Milling machine monitoring center is configured as executing following operation: receiving Milling Force, the milling machine spindle revolving speed, milling machine feeding of milling machine
Axis feed speed, milling angle and milling depth；Receive the wear condition of milling cutter；Transfer Milling Force, the milling machine spindle of milling machine
Revolving speed, milling machine feed shaft feed speed, the historical data of milling angle and milling depth, while transferring the wear condition of milling cutter
Historical data；Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and milling based on milling machine
The historical data of the wear condition of the historical data and milling cutter of depth, generates between the Milling Force of milling machine and the wear condition of milling cutter
The first incidence relation, while generating the Milling Force of milling machine, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle
And the second incidence relation between milling depth and the wear condition of milling cutter；It is current based on the first incidence relation and milling machine
Milling Force judges the current wear condition of milling cutter.
In a preferred embodiment, milling machine monitoring center is additionally configured to execute following operation: if it is determined that milling cutter is worked as
Preceding wear condition is greater than thresholding, then issues halt instruction；Receive first instruction, wherein first instruction be in the case where there by
It sends: determining the currently practical wear condition of milling cutter and the current wear condition one of the milling cutter judged by milling machine monitoring center
It causes.
In a preferred embodiment, milling machine monitoring center is additionally configured to execute following operation: when receiving the first instruction
Later, continue the current Milling Force based on the first incidence relation and milling machine, judge the current wear condition of milling cutter；When milling cutter
When current wear condition is greater than the second thresholding, the first tool changing instruction is issued.
In a preferred embodiment, milling machine monitoring center is additionally configured to execute following operation: the second instruction is received,
In, the second instruction is sent in the case where there: determining the currently practical wear condition of milling cutter and by milling machine monitoring center
The current wear condition of the milling cutter judged is inconsistent；After receiving the second instruction, it is based on the second incidence relation and milling
Current Milling Force, current milling machine spindle revolving speed, current milling machine feed shaft feed speed, current milling angle and the current milling of bed
Depth is cut, judges the current wear condition of milling cutter.
In a preferred embodiment, milling machine monitoring center is additionally configured to execute following operation: if it is determined that milling cutter is worked as
Preceding wear condition is greater than third thresholding, then issues the second tool changing instruction by milling machine monitoring center.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention answers the protection model with claim
Subject to enclosing.
Claims (10)
1. a kind of milling machine operational monitoring method based on artificial intelligence, it is characterised in that: the milling machine operational monitoring method includes
Following steps:
Monitor Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling depth of milling machine；
Monitor the wear condition of milling cutter；
The Milling Force of the milling machine, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and milling depth are sent out
Give milling machine monitoring center；
The wear condition of the milling cutter is sent to milling machine monitoring center；
Milling Force, milling machine spindle revolving speed, the milling machine feed shaft feed speed, milling angle of the milling machine are transferred by milling machine monitoring center
The historical data of degree and milling depth, while transferring by milling machine monitoring center the historical data of the wear condition of the milling cutter；
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle by milling machine monitoring center based on the milling machine
The historical data of the wear condition of the historical data and milling cutter of degree and milling depth, generate the Milling Force of the milling machine with
The first incidence relation between the wear condition of the milling cutter, while generating the Milling Force of the milling machine, milling machine spindle revolving speed, milling
The second incidence relation between bed feed shaft feed speed, milling angle and milling depth and the wear condition of the milling cutter；
Current Milling Force by milling machine monitoring center based on first incidence relation and the milling machine, judges the milling cutter
Current wear condition.
2. the milling machine operational monitoring method based on artificial intelligence as described in claim 1, it is characterised in that: the milling machine operation
Monitoring method further includes following steps:
If it is determined that the current wear condition of the milling cutter is greater than thresholding, then halt instruction is issued by the milling machine monitoring center；
Determine the currently practical wear condition of the milling cutter and the current wear condition of the milling cutter judged by milling machine monitoring center
It is whether consistent；
If it is determined that the current abrasion of the currently practical wear condition of the milling cutter and the milling cutter judged by milling machine monitoring center
Situation is consistent, then issues the first instruction to the milling machine monitoring center.
3. the milling machine operational monitoring method based on artificial intelligence as claimed in claim 2, it is characterised in that: when the milling machine is supervised
After control center receives first instruction, continue the current milling based on first incidence relation and the milling machine
Power judges the current wear condition of the milling cutter；
When the current wear condition of the milling cutter is greater than the second thresholding, the first tool changing is issued by the milling machine monitoring center and is referred to
It enables.
4. the milling machine operational monitoring method based on artificial intelligence as claimed in claim 2, it is characterised in that: the milling machine operation
Monitoring method further includes following steps:
If it is determined that the current abrasion of the currently practical wear condition of the milling cutter and the milling cutter judged by milling machine monitoring center
Situation is inconsistent, then issues the second instruction to the milling machine monitoring center；
After the milling machine monitoring center receives the described second instruction, it is based on second incidence relation and the milling machine
Current Milling Force, current milling machine spindle revolving speed, current milling machine feed shaft feed speed, current milling angle and current milling
Depth judges the current wear condition of the milling cutter.
5. the milling machine operational monitoring method based on artificial intelligence as claimed in claim 4, it is characterised in that:
If it is determined that the current wear condition of the milling cutter is greater than third thresholding, then second is issued by the milling machine monitoring center and changed
Knife instruction.
6. a kind of milling machine operation monitoring system based on artificial intelligence, it is characterised in that: the system comprises:
First sensor is used to monitor the Milling Force of milling machine；
Second sensor is used to monitor milling machine spindle revolving speed；
3rd sensor is used to monitor milling machine feed shaft feed speed；
4th sensor is used to monitor milling angle；
5th sensor is used to monitor milling depth；
Milling machine monitoring center is configured as executing following operation:
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling for receiving the milling machine are deep
Degree；
Receive the wear condition of milling cutter；
Transfer Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and the milling depth of the milling machine
Historical data, while transferring the historical data of the wear condition of the milling cutter；
Milling Force, milling machine spindle revolving speed, milling machine feed shaft feed speed, milling angle and milling depth based on the milling machine
Historical data and the milling cutter wear condition historical data, generate the Milling Force of the milling machine and the abrasion of the milling cutter
The first incidence relation between situation, while generating the Milling Force of the milling machine, milling machine spindle revolving speed, milling machine feed shaft feeding speed
The second incidence relation between degree, milling angle and milling depth and the wear condition of the milling cutter；
Current Milling Force based on first incidence relation and the milling machine, judges the current wear condition of the milling cutter.
7. the milling machine operation monitoring system based on artificial intelligence as claimed in claim 6, it is characterised in that: the milling machine monitoring
Center is additionally configured to execute following operation:
If it is determined that the current wear condition of the milling cutter is greater than thresholding, then halt instruction is issued；
Receive the first instruction, wherein first instruction is sent in the case where there:
Determine the currently practical wear condition of the milling cutter and the current wear condition of the milling cutter judged by milling machine monitoring center
Unanimously.
8. the milling machine operation monitoring system based on artificial intelligence as claimed in claim 7, it is characterised in that: the milling machine monitoring
Center is additionally configured to execute following operation: after receiving the described first instruction, continuing based on first incidence relation
And the current Milling Force of the milling machine, judge the current wear condition of the milling cutter；
When the current wear condition of the milling cutter is greater than the second thresholding, the first tool changing instruction is issued.
9. the milling machine operation monitoring system based on artificial intelligence as claimed in claim 7, it is characterised in that: the milling machine monitoring
Center is additionally configured to execute following operation:
Receive the second instruction, wherein second instruction is sent in the case where there:
Determine the currently practical wear condition of the milling cutter and the current wear condition of the milling cutter judged by milling machine monitoring center
It is inconsistent；
After receiving the described second instruction, current Milling Force based on second incidence relation and the milling machine, when
Preceding milling machine spindle revolving speed, current milling machine feed shaft feed speed, current milling angle and current milling depth, judge the milling
The current wear condition of knife.
10. the milling machine operation monitoring system based on artificial intelligence as claimed in claim 9, it is characterised in that: the milling machine prison
Control center is additionally configured to execute following operation: if it is determined that the current wear condition of the milling cutter be greater than third thresholding, then by
The milling machine monitoring center issues the second tool changing instruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810849557.0A CN109079583B (en) | 2018-07-28 | 2018-07-28 | Milling machine operational monitoring method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810849557.0A CN109079583B (en) | 2018-07-28 | 2018-07-28 | Milling machine operational monitoring method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109079583A CN109079583A (en) | 2018-12-25 |
| CN109079583B true CN109079583B (en) | 2019-09-24 |
Family
ID=64833378
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810849557.0A Active CN109079583B (en) | 2018-07-28 | 2018-07-28 | Milling machine operational monitoring method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109079583B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110756868A (en) * | 2019-11-18 | 2020-02-07 | 中航成飞民用飞机有限责任公司 | Milling system and method |
| CN112433509B (en) * | 2020-11-12 | 2021-09-17 | 安徽江机重型数控机床股份有限公司 | Shutdown anti-shake control method and system for numerical control machine tool |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0795560A (en) * | 1993-09-20 | 1995-04-07 | Hitachi Ltd | Method and device for measuring image and distance measuring method for remote operating system |
| FR2758403B1 (en) * | 1997-01-14 | 1999-02-12 | Michel Humbert | AERIAL AND MARINE TERRESTRIAL MOBILE OBJECT SURVEILLANCE AND SECURITY SYSTEM |
| MY141127A (en) * | 2002-11-18 | 2010-03-15 | Univ Putra Malaysia | Artificial intelligence device and corresponding methods for selecting machinability data |
| CN105834834B (en) * | 2016-04-21 | 2017-10-27 | 四川大学 | Cutter wear state monitoring method based on drosophila optimized algorithm |
-
2018
- 2018-07-28 CN CN201810849557.0A patent/CN109079583B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109079583A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108227634B (en) | Machine learning device, CNC device, and machine learning method | |
| Tönshoff et al. | Developments and trends in monitoring and control of machining processes | |
| CN110394688B (en) | Machine tool state monitoring method based on edge calculation | |
| CN110088699A (en) | Information processing method, information processing system and information processing unit | |
| CN109079583B (en) | Milling machine operational monitoring method and system based on artificial intelligence | |
| Marinescu et al. | An automated monitoring solution for avoiding an increased number of surface anomalies during milling of aerospace alloys | |
| US11494252B2 (en) | System and method for detecting anomalies in cyber-physical system with determined characteristics | |
| CN102929210A (en) | Control and optimization system for feature-based numerical control machining process and control and optimization method therefor | |
| Jemielniak | Contemporary challenges in tool condition monitoring | |
| CN107741732A (en) | A kind of machine tool monitoring method and system based on current method | |
| CN106774157A (en) | A kind of Digit Control Machine Tool with fault diagnosis Yu warning function | |
| CN113853275B (en) | Substrate processing system | |
| CN111890124A (en) | On-line cutter monitoring system and method | |
| Cho et al. | The state of machining process monitoring research in Korea | |
| CN108527005A (en) | A kind of CNC cutting tool states detection method and system | |
| Prickett | An integrated approach to autonomous maintenance management | |
| CN109521734A (en) | Production system | |
| CN116187725B (en) | Forging equipment management system for forging automatic line | |
| US20220197273A1 (en) | Method and device for monitoring a milling process | |
| EP3674946B1 (en) | System and method for detecting anomalies in cyber-physical system with determined characteristics | |
| KR102353574B1 (en) | Tool-related abnormal data detection system of CNC machines | |
| CN113199304B (en) | Tool changing monitoring method based on extended Kalman filtering and cutting force model | |
| CN109523030B (en) | Telemetering parameter abnormity monitoring system based on machine learning | |
| KR102474332B1 (en) | Prediction method of machine health stability in smart factory system, and recording medium thereof | |
| CN113941901B (en) | Machine tool cutter monitoring method, machine tool cutter monitoring device and electronic equipment |
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 |