CN107511718A - Single product high-volume repeats the intelligent tool state monitoring method of process - Google Patents

Single product high-volume repeats the intelligent tool state monitoring method of process Download PDF

Info

Publication number
CN107511718A
CN107511718A CN201710823053.7A CN201710823053A CN107511718A CN 107511718 A CN107511718 A CN 107511718A CN 201710823053 A CN201710823053 A CN 201710823053A CN 107511718 A CN107511718 A CN 107511718A
Authority
CN
China
Prior art keywords
cutter
monitoring
signal
single product
product high
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201710823053.7A
Other languages
Chinese (zh)
Inventor
李建刚
秦泽政
楼云江
李衍杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Graduate School Harbin Institute of Technology
Original Assignee
Shenzhen Graduate School Harbin Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Graduate School Harbin Institute of Technology filed Critical Shenzhen Graduate School Harbin Institute of Technology
Priority to CN201710823053.7A priority Critical patent/CN107511718A/en
Publication of CN107511718A publication Critical patent/CN107511718A/en
Pending legal-status Critical Current

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23QDETAILS, 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
    • B23Q17/00Arrangements for observing, indicating or measuring on machine tools
    • B23Q17/09Arrangements 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
    • B23Q17/0952Arrangements 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

Abstract

The invention provides the intelligent tool state monitoring method that a kind of single product high-volume repeats process, comprise the following steps:S1, Sample Storehouse is established, the characteristic signal sample of work pieces process when collection cutter is in different lifetime stages;S2, multiple sensor signals fusion;The factor of the excessively middle effect characteristicses signal of S3, machine tooling;S4, the ability for assigning cutter life monitoring algorithm self study;S5, in the life-span monitoring of cutter early stage, take every processing m parts once to be monitored, then start to monitor in real time when monitoring and also having H parts away from last set N closing is monitored during other processing.The beneficial effects of the invention are as follows:The generation of erroneous judgement can preferably be avoided.

Description

Single product high-volume repeats the intelligent tool state monitoring method of process
Technical field
The present invention relates to tool condition monitoring method, more particularly to a kind of single product high-volume to repeat the intelligent knife of process Has state monitoring method.
Background technology
Tool condition monitoring mainly experienced two development courses from occurring to being developed so far:
1)Traditional monitor stages
In traditional cutting process, the processing staff that is identified by of cutting tool state distinguishes cutting sound, chip color, cut Time etc. is cut to judge, or its damaged degree and wear extent are surveyed after dismounting cutter to judge according between manufacturing procedure.
2)The intelligent monitoring stage
So-called intelligent monitoring refers to that in product processing computer is by detecting various kinds of sensors signal intensity, in advance Survey cutter abrasion and damaged state, so as to determine whether cutter needs to change, conventional tool monitoring signal have vibration signal, Temperature signal, spindle motor current signal, acoustic emission signal etc., cutting-tool wear state are described as shown in figure 1, being divided into:Initial wear Stage, normal wearing stage and drastically wear stage.
The initial wear stage:The defects of rough, micro-flaw, oxidation often be present in the rear knife face of new sharpening cutter, And cutting edge, than sharp, in working angles, rear knife face and machined surface contact area are smaller, contact compared with Greatly, therefore, the initial wear time is shorter.
Normal wearing stage:Into during normal wear, the rear knife face of cutter polishes substantially, and it connects with machined surface Contacting surface product is larger, and contact diminishes, even wearing and comparison is slow.The wear extent of normal wearing stage cutter is substantially and workpiece Process time it is directly proportional.
Drastically wear stage:When tool wear to a certain extent after, workpiece machined surface roughness value increase, cutting Power, cutting temperature rise, cutter drastically wear.Drastically wear stage generally entails strong vibration and abnormal noise, arrives This stage is it is necessary to timely shutting down replacing cutter.
Go out which wear stage current cutter is in by tool condition monitoring system resolution, when in drastically wearing rank Section, then prompt digital control system tool changing.
What traditional tool condition monitoring often relied on is the knowhow of the long term accumulation of skilled worker, so can not keep away That exempts from occurs problems with:
1)If tool abrasion is less than blunt standard but has been removed, does not make full use of the actual life of cutter and make Into waste, increase processing cost;
2)If tool abrasion is higher than blunt standard, i.e. cutter has occurred and that abrasion or damaged, then can influence the processing of workpiece Surface quality and dimensional accuracy, or even damage lathe.
3)The waste on personnel is caused, present industrial trend is manless production, goes to find cutter by personnel Abrasion and the damaged needs that can not have met modern industrial production, and how by dismantling cutter to detect tool wear Amount can then cause the pause of processing, influence production efficiency.
Traditional tool condition monitoring system is often monitored by the way of threshold value is set, using spindle power signal as Example:The spindle power of machine tool in process all the time is not one layer constant, when under heavy cut state, its Cutting power can increase therewith, therefore machine tool chief axis power is during thing is in dynamic change in process, because We can set suitable threshold value for this, and system for prompting tool wear exceedes normal limitation when this value is exceeded, and machine tooling is complete Workpiece tool changing again;We be it should also be appreciated that cutter tipping may occur in process for lathe simultaneously, caused by harm More serious than tool wear is more, it is necessary to which we set a limiting threshold value, and immediately shutdown, prevents cutter from breaking when the threshold value is exceeded Damage to lathe in itself and operating personnel damage.
In lathe normal process, the peak value of machine tool chief axis power is stable in certain section, will not be occurred too big Saltus step, normal process level thresholds threshold value is relatively low;When machine tool chief axis power exceedes wear threshold, illustrate the attrition value of cutter Allow more than processing, when the complete workpiece of machine tooling, tool changing will be shut down;When machine tool chief axis power oversteps the extreme limit threshold value, Illustrate cutter there occurs breakage, tool wear is a slowly varying process, and damaged thing emergency case, to lathe in itself and behaviour Significant damage is caused as personnel, so when spindle power curve oversteps the extreme limit threshold value, it is impossible to changed again when the work pieces process is complete Knife avoids serious harm caused by tool failure, it is necessary to hard stop tool changing.So this signal can be in the form of a kind of mutation Occur, the later stage curve of processing as shown in Figure 2.
Though developing into the intelligent tool status monitoring occurred in recent years has broken away from limitation on personnel, realize intelligence and exist Line monitors, but still suffers from monitoring inaccurately, the doubt problem of tool change time, because existing intellectual monitoring can only often be differentiated Go out current cutter and be in order at initial wear stage, normal wearing stage still drastically wear stage, the tool of cutter can not be provided Body life time, therefore also can usually cause cutter excessively to use the two problems using insufficient and cutter.
And erroneous judgement often occurs in the intellectual monitoring of modern cutter, because monitoring system does not know that cutter is in now Which type of machining state, processed in High-speed machining or low speed, be heavy cut or light cut, monitoring system complete one It is ignorant.When cutter carries out cutting sales volume heavy cut greatly at a high speed, its characteristic signal when cutter often than carrying out the small cutting output of low speed Change during light cut it is violent more, and at this time tool monitoring system perhaps just will be considered that cutter occur at this moment breakage or Beyond cutter blunt standard, it is necessary to tool changing.
The content of the invention
In order to solve the problems of the prior art, the invention provides the intelligence that a kind of single product high-volume repeats process Tool condition monitoring method.
The invention provides the intelligent tool state monitoring method that a kind of single product high-volume repeats process, including it is following Step:
S1, Sample Storehouse is established, the characteristic signal sample of work pieces process when collection cutter is in different lifetime stages;
S2, multiple sensor signals fusion;
The factor of the excessively middle effect characteristicses signal of S3, machine tooling;
S4, the ability for assigning cutter life monitoring algorithm self study;
S5, in the life-span monitoring of cutter early stage, take every processing m parts once to be monitored, other process during then monitoring Close, start to monitor in real time when monitoring and also having H parts away from last set N.
As a further improvement on the present invention, in step sl, characteristic signal include spindle motor current signal, vibration signal, Voice signal, temperature signal.
As a further improvement on the present invention, in step s3, the factor of effect characteristicses signal includes cutting width W, cut Cut depth D, feed speed V.
The beneficial effects of the invention are as follows:By such scheme, the generation of erroneous judgement can be preferably avoided.
Brief description of the drawings
Fig. 1 is cutting-tool wear state schematic diagram in the prior art.
Fig. 2 is the later stage curve map processed in the prior art.
Fig. 3 is the multisensor for the intelligent tool state monitoring method that a kind of single product high-volume of the present invention repeats process Signal fused schematic diagram.
Fig. 4 is the machine tooling for the intelligent tool state monitoring method that a kind of single product high-volume of the present invention repeats process Cross the schematic diagram of the factor of middle effect characteristicses signal.
Fig. 5 is building for the Sample Storehouse for the intelligent tool state monitoring method that a kind of single product high-volume of invention repeats process Vertical flow chart.
Fig. 6 is the training flow for the intelligent tool state monitoring method that a kind of single product high-volume of invention repeats process Figure.
Embodiment
The invention will be further described for explanation and embodiment below in conjunction with the accompanying drawings.
As shown in Figures 3 to 6, the product high-volume that single specification is more and more engaged in for modern machine repeats to add This phenomenon of work, in order to improve the accuracy of Monitoring of Tool Condition, False Rate is reduced, while add self-learning capability, it is really real The on-line monitoring of existing cutting tool state, the result of monitoring is not limited solely to obtain cutter is in for which type of state of wear, but Can obtain current cutter it is remaining can workpieces processing quantity, the invention provides the intelligence that a kind of single product high-volume repeats process Energy tool condition monitoring method, comprises the following steps:
1)Sample Storehouse is established, the characteristic signal sample of work pieces process when collection cutter is in different lifetime stages, this feature letter Number can be spindle motor current signal, vibration signal, voice signal, temperature signal etc..And need to look for from these characteristic signals To the characteristic signal closely related with cutting-tool wear state, insensitive signal is excluded.Wherein samples selection must be complete Face, first workpiece is processed since new knife to tool wear to the sample for causing last unqualified i.e. workpiece of workpieces processing Data are all desirable, it is ensured that the integrality of Sample Storehouse, while the quantity of sample is big, can avoid accidentalia to decision-making Influence.
2)Multiple sensor signals merge, it is necessary to which the problem faced is if only by a kind of monitoring of signal, is The very high degree of accuracy can not possibly be reached, because every kind of signal has the limitation of oneself.Multi-sensor Fusion refers to cutter shape The judgement of state does not depend solely on a kind of signal, but the data of multi-signal are acquired and handled, and utilizes every kind of signal There is respective advantage, have complementary advantages with regard to more accurate result can be obtained.Such as the main shaft gathered simultaneously in process is electric Signal, vibration signal and processing signal etc. are flowed, and characteristic value different in same signal also can be to varying degrees Reflect the state of wear of cutter, therefore different signal characteristic values can be assigned according to the sensitivity of their Cutter wears The weights that they are different are given, and then obtain rational monitoring result, cutter is obtained eventually through the synthetic determination of various features value The state of abrasion.
3)The factor of the excessively middle effect characteristicses signal of machine tooling:Cutting width W, cutting depth D, feed speed V and outer The various disturbing factors in portion, when lathe carry out be that single workpiece high-volume repeats to process when, cutter is all the time in assorted Cutting depth, width and the feed speed of sample are all known, can find out that its normal processing is special from master sample Reference number, the convenient next monitoring to cutter life, this is also the importance for starting sample collection, the success that sample is chosen with It is no directly to determine next to the order of accuarcy of cutter life monitoring.
4) ability of cutter life monitoring algorithm self study is assigned, when judging by accident, such as algorithm judges this cutter It can not continue workpieces processing, but find that after the cutter to changing carries out careful inspection this cutter can also be after At this moment continuous processing, this algorithm just illustrated also imperfection add a penalty mechanism, it is necessary to improved to algorithm itself, when When judging by accident, its algorithm itself carries out some adjustment, assigns a kind of ability of self study of algorithm.Instruction by algorithm to sample Practice to realize monitoring of the algorithm to cutter life.
If 5) monitor last work of tool sharpening from tool sharpening unit one according to above-mentioned monitoring mode Part, the amount of such data processing is just too big, too high to the load of monitoring system, and is also not necessarily in actual production.It is false If a life-span given when new knife is appeared on the scene is N parts, then it is monitored to obtain residue before it processes N/2, or even 2N/3 Number of packages is processed without what meaning, if because breakage does not occur for this when of cutter, the certain thing of its wear extent is allowing In the range of, so in the case that workpiece processing tool number is within 2N/3, the monitor mode that can simplify, monitoring Focus on whether cutter occurs above breakage, reduction procedure is as described below:
In the life-span monitoring of cutter early stage, every processing m parts can be taken once to be monitored, then monitoring during other processing Close, start to monitor in real time when monitoring and also having 10 or 20 away from last set N, because this when, tool wear started Drastically occur, characteristic signal also can substantially change relatively within this period, and this when, monitoring also became relatively easy And necessity.
Because using the monitor mode of multi-sensor information fusion, tool wear initial stage and mid-term in order to Reduce data processing pressure and save data processing time, can be only monitored using a kind of sensor parameters, equally, work as prison Control begins to use multi-sensor information fusion to be monitored when also having 10 or 20 away from last set N.
The intelligent tool state monitoring method that a kind of single product high-volume provided by the invention repeats process has following Advantage:
1) False Rate is reduced
Repeat to process for the high-volume of single specification product so that it is known which type of cutter add all in all the time Work state, it is High-speed machining or low speed, is heavy cut or light cut etc., avoids conventional monitoring system and acutely processing In stage it is possible that erroneous judgement.
2) monitoring is more accurate
Compared to conventional tool condition monitoring, the remaining workpieces processing number of cutter can be obtained, work pieces process can be avoided to arrive Half cutter is scrapped and causes the processing of labor cost to fail, and being processed due to present labor cost successfully needs many steps, therefore is worked into The cost of one workpiece of later stage can greatly improve, and can reduce the disqualification rate of workpiece well using new tool monitoring, enter It is and cost-effective.
Above content is to combine specific preferred embodiment further description made for the present invention, it is impossible to is assert The specific implementation of the present invention is confined to these explanations.For general technical staff of the technical field of the invention, On the premise of not departing from present inventive concept, some simple deduction or replace can also be made, should all be considered as belonging to the present invention's Protection domain.

Claims (3)

1. a kind of single product high-volume repeats the intelligent tool state monitoring method of process, it is characterised in that including following step Suddenly:
S1, Sample Storehouse is established, the characteristic signal sample of work pieces process when collection cutter is in different lifetime stages;
S2, multiple sensor signals fusion;
The factor of the excessively middle effect characteristicses signal of S3, machine tooling;
S4, the ability for assigning cutter life monitoring algorithm self study;
S5, in the life-span monitoring of cutter early stage, take every processing m parts once to be monitored, other process during then monitoring Close, start to monitor in real time when monitoring and also having H parts away from last set N.
2. single product high-volume according to claim 1 repeats the intelligent tool state monitoring method of process, its feature It is:In step sl, characteristic signal includes spindle motor current signal, vibration signal, voice signal, temperature signal.
3. single product high-volume according to claim 1 repeats the intelligent tool state monitoring method of process, its feature It is:In step s3, the factor of effect characteristicses signal includes cutting width W, cutting depth D, feed speed V.
CN201710823053.7A 2017-09-13 2017-09-13 Single product high-volume repeats the intelligent tool state monitoring method of process Pending CN107511718A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710823053.7A CN107511718A (en) 2017-09-13 2017-09-13 Single product high-volume repeats the intelligent tool state monitoring method of process

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710823053.7A CN107511718A (en) 2017-09-13 2017-09-13 Single product high-volume repeats the intelligent tool state monitoring method of process

Publications (1)

Publication Number Publication Date
CN107511718A true CN107511718A (en) 2017-12-26

Family

ID=60725409

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710823053.7A Pending CN107511718A (en) 2017-09-13 2017-09-13 Single product high-volume repeats the intelligent tool state monitoring method of process

Country Status (1)

Country Link
CN (1) CN107511718A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108873814A (en) * 2018-06-25 2018-11-23 深圳精匠云创科技有限公司 Monitoring system, monitoring method and storage equipment
CN109262369A (en) * 2018-09-13 2019-01-25 成都数之联科技有限公司 A kind of cutting tool state detection system and method
CN109298680A (en) * 2018-09-13 2019-02-01 成都数之联科技有限公司 A kind of data collection system of cutting tool for CNC machine detection
TWI649551B (en) * 2018-07-18 2019-02-01 國立勤益科技大學 Method for estimating tool wear by applying chip color
CN109605126A (en) * 2018-12-30 2019-04-12 深圳市五湖智联实业有限公司 A kind of numerically-controlled machine tool on-line checking cutter life system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102073300A (en) * 2010-12-28 2011-05-25 华中科技大学 Tool wear monitoring system capable of realizing self-learning in numerical control machining state
CN102179728A (en) * 2011-03-14 2011-09-14 上海师范大学 Device for intelligently detecting abrasion of numerical control cutting tool
CN103465107A (en) * 2013-09-24 2013-12-25 沈阳利笙电子科技有限公司 Tool wear monitoring method
CN104097115A (en) * 2014-07-02 2014-10-15 无锡烨隆精密机械有限公司 Numerical control machine tool cutting tool service life monitoring method
CN104503361A (en) * 2014-12-30 2015-04-08 重庆大学 Multimodal fusion based gear machining process tool change decision method
CN106181579A (en) * 2016-08-23 2016-12-07 西安交通大学 A kind of Tool Wear Monitoring method based on multisensor current signal
CN106392774A (en) * 2016-10-14 2017-02-15 山东理工大学 Fractal-theory-based online monitoring method for tool wear condition

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102073300A (en) * 2010-12-28 2011-05-25 华中科技大学 Tool wear monitoring system capable of realizing self-learning in numerical control machining state
CN102179728A (en) * 2011-03-14 2011-09-14 上海师范大学 Device for intelligently detecting abrasion of numerical control cutting tool
CN103465107A (en) * 2013-09-24 2013-12-25 沈阳利笙电子科技有限公司 Tool wear monitoring method
CN104097115A (en) * 2014-07-02 2014-10-15 无锡烨隆精密机械有限公司 Numerical control machine tool cutting tool service life monitoring method
CN104503361A (en) * 2014-12-30 2015-04-08 重庆大学 Multimodal fusion based gear machining process tool change decision method
CN106181579A (en) * 2016-08-23 2016-12-07 西安交通大学 A kind of Tool Wear Monitoring method based on multisensor current signal
CN106392774A (en) * 2016-10-14 2017-02-15 山东理工大学 Fractal-theory-based online monitoring method for tool wear condition

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108873814A (en) * 2018-06-25 2018-11-23 深圳精匠云创科技有限公司 Monitoring system, monitoring method and storage equipment
TWI649551B (en) * 2018-07-18 2019-02-01 國立勤益科技大學 Method for estimating tool wear by applying chip color
CN109262369A (en) * 2018-09-13 2019-01-25 成都数之联科技有限公司 A kind of cutting tool state detection system and method
CN109298680A (en) * 2018-09-13 2019-02-01 成都数之联科技有限公司 A kind of data collection system of cutting tool for CNC machine detection
CN109262369B (en) * 2018-09-13 2020-02-21 成都数之联科技有限公司 Cutter state detection system and method
CN109605126A (en) * 2018-12-30 2019-04-12 深圳市五湖智联实业有限公司 A kind of numerically-controlled machine tool on-line checking cutter life system
CN109605126B (en) * 2018-12-30 2021-09-03 深圳市五湖智联实业有限公司 Digit control machine tool on-line measuring cutter life-span system

Similar Documents

Publication Publication Date Title
CN107511718A (en) Single product high-volume repeats the intelligent tool state monitoring method of process
JP2018094686A (en) Machine learning device, cnc device and machine learning method detecting sign of occurrence of chattering of tool in machine tool
JP4860444B2 (en) Abnormality detection method in cutting
CN109909804B (en) Tool wear damage online monitoring method based on spindle driving current and process steps
CN102929210A (en) Control and optimization system for feature-based numerical control machining process and control and optimization method therefor
JP5411055B2 (en) Tool life detection method and tool life detection device
CN103249522A (en) Apparatus and method for detecting damage to tool in machine
CN108972152A (en) A kind of sound-power detection method monitoring abrasion of cutting tool state
CN110421408B (en) Method for monitoring wear state of cutter
CN107756250A (en) A kind of grinding power and energy consumption intelligent monitor system and decision-making technique
O’Donnell et al. Towards the improvement of tool condition monitoring systems in the manufacturing environment
JP2005125480A (en) Cutting method having function for diagnosing tool life
JP4919999B2 (en) Tool life detection method and tool life detection device
Bahr et al. Sensor fusion for monitoring machine tool conditions
CN206105516U (en) Non -contact blade abraded's on -line measuring equipment
Luan et al. Trade-off analysis of tool wear, machining quality and energy efficiency of alloy cast iron milling process
KR101462312B1 (en) Tool monitoring system of machine tools and method thereof
Ritou et al. A new versatile in-process monitoring system for milling
JPH08174379A (en) Chatter vibration suppressing method
CN111890124A (en) On-line cutter monitoring system and method
CN107932186A (en) A kind of cutting tool state recognition methods based on machining coordinate alignment reference signal
CN108015626A (en) A kind of cutting tool state recognition methods for being capable of the adjust automatically monitoring limit
Danai Machine tool monitoring and control
Zhuo et al. Overview on development of acoustic emission monitoring technology in sawing
Wittbrodt et al. Decision support system of machining process based on the elements of fuzzy logic

Legal Events

Date Code Title Description
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20171226