CN116275600A - Intelligent cutting data processing method, device and equipment of laser cutting machine - Google Patents
Intelligent cutting data processing method, device and equipment of laser cutting machine Download PDFInfo
- Publication number
- CN116275600A CN116275600A CN202310564551.XA CN202310564551A CN116275600A CN 116275600 A CN116275600 A CN 116275600A CN 202310564551 A CN202310564551 A CN 202310564551A CN 116275600 A CN116275600 A CN 116275600A
- Authority
- CN
- China
- Prior art keywords
- surface roughness
- nozzle
- deviation
- working
- roughness
- 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
- 238000005520 cutting process Methods 0.000 title claims abstract description 72
- 238000003698 laser cutting Methods 0.000 title claims abstract description 63
- 238000003672 processing method Methods 0.000 title claims abstract description 12
- 230000003746 surface roughness Effects 0.000 claims abstract description 273
- 238000000034 method Methods 0.000 claims abstract description 122
- 238000001514 detection method Methods 0.000 claims abstract description 88
- 230000008569 process Effects 0.000 claims abstract description 84
- 230000002159 abnormal effect Effects 0.000 claims abstract description 56
- 238000005259 measurement Methods 0.000 claims description 25
- 230000009471 action Effects 0.000 claims description 24
- 230000001681 protective effect Effects 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 5
- 230000033001 locomotion Effects 0.000 description 11
- 238000005457 optimization Methods 0.000 description 10
- 230000007246 mechanism Effects 0.000 description 9
- 230000005856 abnormality Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000003754 machining Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000013499 data model Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/36—Removing material
- B23K26/38—Removing material by boring or cutting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23K—SOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
- B23K26/00—Working by laser beam, e.g. welding, cutting or boring
- B23K26/70—Auxiliary operations or equipment
- B23K26/702—Auxiliary equipment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- 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
- Y02P70/00—Climate change mitigation technologies in the production process for final industrial or consumer products
- Y02P70/10—Greenhouse gas [GHG] capture, material saving, heat recovery or other energy efficient measures, e.g. motor control, characterised by manufacturing processes, e.g. for rolling metal or metal working
Abstract
The invention belongs to the technical field of laser cutting control, and particularly provides an intelligent cutting data processing method, device and equipment of a laser cutting machine, wherein the method comprises the following steps: in the normal operation of the laser cutting machine, detecting the working state parameter data of a nozzle of the laser cutting machine and the actual measured surface roughness during the working; calculating the theoretical surface roughness during working based on the detected state parameter data of the working of the laser cutting machine nozzle and an intelligent nozzle detection model; and calculating the difference value between the actually measured surface roughness and the theoretical surface roughness in working, and analyzing whether the roughness in the working process of the nozzle is abnormal or not by combining the surface roughness deviation reference value. The calibrated intelligent detection model has the characteristics of the equipment, the model is used for avoiding the difference of the equipment, and the judgment error is caused by the change of the equipment in use, so that the accuracy of the abnormal judgment of the roughness is effectively improved.
Description
Technical Field
The invention relates to the technical field of laser cutting control, in particular to an intelligent cutting data processing method, device and equipment of a laser cutting machine.
Background
In order to prevent the laser equipment from processing parts which do not meet the standard or generating an alarm in the cutting process to cause the shutdown to affect the production in the operation process, usually, a worker can watch a machine during the mechanical operation, and the main functions are as follows: when the machine tool is stopped, a worker can quickly find an alarm position to release the alarm, or in the machining process, the quality of machined parts is unqualified due to overheating of a nozzle, slag hanging and the like, and the nozzle is required to be replaced or technological parameters are required to be modified immediately, so that a stack of waste products can be avoided from being continuously produced, and larger loss is caused. In the prior art, a worker views a spark generated by cutting or a sound generated by air flow to subjectively judge whether an abnormality occurs.
However, the mechanical structure of each laser device has a slight difference in processing technological parameters, and after the laser device is used for a long time, due to the abrasion of a gas pipeline, the aging of optical fibers, the alternation of workers and other reasons, the same technological parameters may generate different cutting effects, and even experienced workers have difficulty in finding the cutting difference, so that the accuracy of judgment is affected, and even abnormal judgment errors are easily generated. Further, if there is a slight difference in cutting quality during the cutting process, it is difficult for the worker to judge, and further, it is difficult to detect a truly unqualified workpiece, and it is easy to generate waste or to perform secondary processing.
Based on the above related art, it is difficult to accurately detect unqualified machined parts during machining, and therefore, it is very necessary to provide an intelligent cutting data processing method of a laser cutting machine.
Disclosure of Invention
In order to solve the problem that in the related art, unqualified workpieces cut due to nozzles are difficult to accurately detect, the invention provides an intelligent cutting data processing method, device and equipment of a laser cutting machine. When the laser cutting machine is used for cutting, an operator only needs to put the plate on and select the machining conditions. If the machining is faulty, the machine tool can be automatically adjusted, and the reject ratio of products and the loss of customers are reduced.
In a first aspect, the present invention provides an intelligent cutting data processing method for a laser cutting machine, including the following steps:
in the normal operation of the laser cutting machine, detecting the working state parameter data of a nozzle of the laser cutting machine and the actual measured surface roughness during the working;
calculating the theoretical surface roughness during working based on the detected state parameter data of the working of the laser cutting machine nozzle and an intelligent nozzle detection model;
and calculating the difference value between the actually measured surface roughness and the theoretical surface roughness in working, and analyzing whether the roughness in the working process of the nozzle is abnormal or not by combining the surface roughness deviation reference value.
The state parameter data comprise the pressure of gas blown out by the laser head, the actual laser power, the actual cutting speed, the gas flow, the light emitting signal and the temperature of the protective lens;
as an advantage of the technical solution of the present invention, in normal operation of the laser cutting machine, the step of detecting the working state parameter data of the nozzle of the laser cutting machine and the actually measured surface roughness during the working process includes:
performing calibration action by a laser head, detecting state parameter data of a laser cutting machine nozzle in the calibration process, and measuring actual measurement surface roughness of the laser head by an interferometer in the calibration process;
and determining a calibrated intelligent nozzle detection model according to the state parameter data obtained in the calibration process and the actual measurement surface roughness in the calibration process.
The method comprises the steps of executing calibration action through a laser head, and detecting gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signals, protective lens temperature and actual roughness measured by an interferometer during calibration of a laser cutter nozzle in the execution process; and determining a calibrated intelligent nozzle detection model according to the gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light-emitting signal, the protection lens temperature and the actual roughness measured by the interferometer during calibration.
The calibration action acts on the laser head to perform a plurality of calibration actions, including a calibration action from a pattern start position cutting action to a pattern end position, and/or: a calibration movement from the pattern position back to the end position, wherein the laser power and the gas pressure of each calibration movement are different; the pattern is a standard test pattern.
As the optimization of the technical scheme of the invention, the step of determining the calibrated intelligent nozzle detection model according to the state parameter data acquired in the calibration process and the actual measurement surface roughness in the calibration process comprises the following steps:
determining an intelligent nozzle detection model without deviation according to the state parameter data of R calibration times and the actual measurement surface roughness of R calibration times; the intelligent nozzle detection model without deviation is determined according to the gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light emitting signal, the temperature of the lens of the protective lens and the actual measured surface roughness measured by the interferometer during R calibration; wherein R is an integer greater than or equal to 1000;
calculating the calculated surface roughness corresponding to each calibration data according to the state parameter data of the R calibration times and the intelligent nozzle detection model without deviation to obtain the calculated surface roughness of the R calibration times; the method comprises the steps of calculating the surface roughness corresponding to each calibration data according to the non-deviation intelligent nozzle detection model and the R calibration time gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light emitting signal and the protection lens temperature, and obtaining the calculated surface roughness of R calibration time;
Determining the maximum surface roughness deviation according to the actual measured surface roughness of the R standards and the calculated surface roughness of the R standards; and determining the calibrated intelligent nozzle detection model according to the deviation between the intelligent nozzle detection model without deviation and the maximum surface roughness.
As a preferable mode of the technical scheme, the method for determining the maximum roughness deviation comprises the following steps:
calculating the deviation between the measured surface roughness of R standard times and the calculated surface roughness of the corresponding R standard times to obtain R deviation values;
the maximum value of the R deviation values is determined as the maximum roughness deviation.
As the optimization of the technical scheme of the invention, the calibrated intelligent nozzle detection model is as follows:
wherein Ra is surface roughness, pa is gas pressure, W is laser power, V is cutting speed, Q is gas flow, phi is light emitting signal, T is temperature of protective lens, R err Is the maximum roughness deviation.
As a preferred embodiment of the present invention, the method further includes: and calculating parameters of the intelligent nozzle detection model without deviation by adopting a least square method based on the state parameter data in the calibration process and the actual measurement surface roughness in the calibration process. In practice, parameters of the intelligent nozzle detection model without deviation are calculated by adopting a least square method according to actual measured gas pressure, actual laser power, actual cutting speed, gas flow, light emitting signals, protection mirror lens temperature and actual measured surface roughness of the interferometer during calibration.
As the optimization of the technical scheme of the invention, the step of calculating the difference value between the actually measured surface roughness and the theoretical surface roughness in working and combining the surface roughness deviation reference value to analyze whether the roughness in the working process of the nozzle is abnormal comprises the following steps:
calculating the difference between the actual measured surface roughness during working and the theoretical surface roughness during working to be a first difference;
judging whether the first difference value is larger than a first reinspection threshold value or not;
if yes, calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model;
calculating the difference between the actual measured surface roughness and the rechecked theoretical surface roughness during working and recording the difference as a second difference;
if the first difference is larger than the second difference, comparing the second difference with a surface roughness deviation reference value; if the second difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal;
if the first difference value is not greater than the second difference value, comparing the first difference value with a surface roughness deviation reference value; if the first difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal;
If not, executing the steps of: comparing the first difference with a surface roughness deviation reference value; and if the first difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal.
As the optimization of the technical scheme of the invention, the step of calculating the difference value between the actually measured surface roughness and the theoretical surface roughness in working and combining the surface roughness deviation reference value to analyze whether the roughness in the working process of the nozzle is abnormal comprises the following steps:
combining the difference between the actual surface roughness during working and the theoretical surface roughness during working with a surface roughness deviation reference value to obtain a roughness deviation E= (|Ra| -Ra) 0 ∣)/T Ra ；
Judging whether the deviation E is larger than a second reinspection threshold value or not;
if yes, calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model;
combining the difference value of the actual measured surface roughness and the rechecked theoretical surface roughness during working with a surface roughness deviation reference value to obtain rechecked roughness deviation Ec; when the Ec is judged to be continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; when Ec is continuously less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal;
If not, if the E is judged to be continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; e, when the duration of the E is less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal;
wherein Ra is the measured surface roughness at work, ra 0 T is the theoretical surface roughness in operation Ra Is a roughness deviation reference value. Here, the surface roughness deviation reference value is a preset fixed value, or: the ratio of the surface roughness deviation reference value to the theoretical surface roughness during operation is a preset fixed value smaller than 1.
In a second aspect, the technical scheme of the invention provides an intelligent cutting data processing device of a laser cutting machine, which comprises a work detection module, a calculation module and an analysis module;
the working detection module is used for detecting the working state parameter data of the nozzle of the laser cutting machine and the actually measured surface roughness during working in the normal working process of the laser cutting machine;
the calculation module is used for calculating the theoretical surface roughness during working based on the detected state parameter data of the working state of the laser cutting machine nozzle and the intelligent nozzle detection model;
and the analysis module is used for analyzing whether the roughness of the nozzle in the working process is abnormal or not according to the difference value between the actually measured surface roughness and the theoretical surface roughness in the working process and the surface roughness deviation reference value.
The device provided by the invention can calculate the theoretical surface roughness of the equipment under various laser powers and gas pressures in real time according to the calibrated intelligent nozzle detection model, and the deviation of the calculated actual surface roughness and the theoretical surface roughness is used as a basis for judging whether the surface roughness is abnormal or not.
As the optimization of the technical scheme of the invention, the device also comprises a calibration detection module and a model determination module;
the calibration detection module is used for executing a calibration action through the laser head, detecting state parameter data of the laser cutting machine nozzle in the calibration process, and measuring the actual measurement surface roughness of the laser head through the interferometer in the calibration process;
the model determining module is used for determining a calibrated intelligent nozzle detection model according to the state parameter data acquired in the calibration process and the actual measurement surface roughness in the calibration process.
Because this intelligent nozzle detects the model is according to equipment self actual measurement gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signal, protection mirror lens temperature, and then, the intelligent detection model after the demarcation has equipment self characteristic, and this model just avoids the variability of equipment, and the change in the equipment use leads to judging the mistake, has effectively improved the accuracy of roughness abnormal judgement.
As the optimization of the technical scheme of the invention, the model determining module comprises a non-deviation model determining unit, a calculated surface roughness obtaining unit, a maximum deviation determining unit and a calibrated model determining unit;
the non-deviation model determining unit is used for determining a non-deviation intelligent nozzle detection model according to the state parameter data of R calibration and the actual measurement surface roughness of R calibration; wherein R is an integer greater than or equal to 1000;
the calculating surface roughness obtaining unit is used for calculating the roughness corresponding to each calibration data according to the non-deviation intelligent nozzle detection model and the state parameter data of the R calibration times to obtain R calculated surface roughness;
the maximum deviation determining unit is used for determining the maximum surface roughness deviation according to the actual measured surface roughness of the R calibration times and the calculated surface roughness of the R calibration times;
and the calibrated model determining unit is used for determining the calibrated intelligent nozzle detection model according to the deviation between the intelligent nozzle detection model without deviation and the maximum surface roughness.
As an optimization of the technical scheme of the invention, a maximum deviation determining unit is specifically used for calculating the deviation between the actual measured surface roughness of R standard times and the calculated surface roughness of the corresponding R standard times to obtain R deviation values; the maximum value of the R deviation values is determined as the maximum roughness deviation.
As the optimization of the technical scheme of the invention, the calibrated intelligent nozzle detection model output by the calibrated model determining unit is as follows:
wherein Ra is surface roughness, pa is gas pressure, W is laser power, V is cutting speed, Q is gas flow, phi is light emitting signal, T is temperature of protective lens, R err Is the maximum roughness deviation.
As the optimization of the technical scheme of the invention, the unbiased model determining unit is particularly used for calculating the parameters of the unbiased intelligent nozzle detection model by adopting a least square method based on the state parameter data in the calibration and the actual measured surface roughness in the calibration.
As the optimization of the technical scheme of the invention, the analysis module is particularly used for calculating the difference value between the actually measured surface roughness during working and the theoretical surface roughness during working to be a first difference value; judging whether the first difference value is larger than a first reinspection threshold value or not; if yes, calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model; calculating the difference between the actual measured surface roughness and the rechecked theoretical surface roughness during working and recording the difference as a second difference; if the first difference is larger than the second difference, comparing the second difference with a surface roughness deviation reference value; if the second difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining Abnormal roughness occurs in the working process of the nozzle; if the first difference value is not greater than the second difference value, comparing the first difference value with a surface roughness deviation reference value; if the first difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal; if not, comparing the first difference value with a surface roughness deviation reference value; and if the first difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal. Or, combining the difference between the actual surface roughness during working and the theoretical surface roughness during working with the surface roughness deviation reference value to obtain a roughness deviation E= (|Ra| -Ra) 0 ∣)/T Ra The method comprises the steps of carrying out a first treatment on the surface of the Judging whether the deviation E is larger than a second reinspection threshold value or not; if yes, calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model; combining the difference value of the actual measured surface roughness and the rechecked theoretical surface roughness during working with a surface roughness deviation reference value to obtain rechecked roughness deviation Ec; when the Ec is judged to be continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; when Ec is continuously less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal; if not, if the E is judged to be continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; e, when the duration of the E is less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal; wherein Ra is the measured surface roughness at work, ra 0 T is the theoretical surface roughness in operation Ra Is a roughness deviation reference value.
In a third aspect, the present invention provides an electronic device, including:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,
the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of intelligent cutting data processing for a laser cutter according to the first aspect.
From the above technical scheme, the invention has the following advantages:
the theoretical surface roughness of the equipment under various laser powers and gas pressures can be calculated in real time according to the calibrated intelligent nozzle detection model, and the deviation of the calculated actual surface roughness and the theoretical surface roughness is used as a basis for judging whether the surface roughness is abnormal or not.
Because this intelligent nozzle detects the model is according to equipment self actual measurement gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signal, protection mirror lens temperature, and then, the intelligent detection model after the demarcation has equipment self characteristic, and this model just avoids the variability of equipment, and the change in the equipment use leads to judging the mistake, has effectively improved the accuracy of roughness abnormal judgement.
In addition, the invention has reliable design principle, simple structure and very wide application prospect.
It can be seen that the present invention has outstanding substantial features and significant advances over the prior art, as well as its practical advantages.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the description of the embodiments or the prior art will be briefly described below, and it will be obvious to those skilled in the art that other drawings can be obtained from these drawings without inventive effort.
FIG. 1 is a flow chart of a method provided in one embodiment of the invention.
Fig. 2 is a flow chart of a method provided in another embodiment of the invention.
FIG. 3 is a schematic flow chart of a calibrated intelligent nozzle detection model in an embodiment of the invention.
FIG. 4 is a flow chart of an analysis of whether an anomaly is detected in one embodiment of the present invention.
Fig. 5 is a schematic block diagram of an apparatus provided in one embodiment of the invention.
Fig. 6 is a schematic block diagram of an apparatus provided in another embodiment of the invention.
Detailed Description
Those of ordinary skill in the art will appreciate that the elements and method steps of each example described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the elements and steps of each example have been described generally in terms of functionality in the foregoing description to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In order to solve the problem that in the related art, unqualified workpieces cut due to a nozzle are difficult to accurately detect, and stop caused by misjudgment is prevented, the embodiment of the invention provides an intelligent cutting data processing method, device and equipment of a laser cutting machine. The laser cutting machine can be applied to laser cutting machines with different laser heads, and when the laser cutting machine is used for cutting, an operator can only put the plate on the machine, and the machining conditions are selected.
Fig. 1 is a schematic flow chart of an intelligent cutting data processing method of a laser cutting machine, which is provided by an embodiment of the invention, and includes the following steps:
S1: in the normal operation of the laser cutting machine, detecting the working state parameter data of a nozzle of the laser cutting machine and the actual measured surface roughness during the working;
s2: calculating the theoretical surface roughness during working based on the detected state parameter data of the working of the laser cutting machine nozzle and an intelligent nozzle detection model;
s3: and calculating the difference value between the actually measured surface roughness and the theoretical surface roughness in working, and analyzing whether the roughness in the working process of the nozzle is abnormal or not by combining the surface roughness deviation reference value.
As shown in fig. 2, in normal operation of the laser cutting machine, the step of detecting the working state parameter data of the nozzle of the laser cutting machine and the actual measured surface roughness during the working process includes:
s01: performing calibration action by a laser head, detecting state parameter data of a laser cutting machine nozzle in the calibration process, and measuring actual measurement surface roughness of the laser head by an interferometer in the calibration process;
s02: and determining a calibrated intelligent nozzle detection model according to the state parameter data obtained in the calibration process and the actual measurement surface roughness in the calibration process.
The calibration action acts on the laser head to perform a plurality of calibration actions, including a calibration action from a pattern start position cutting action to a pattern end position, and/or: a calibration movement from the pattern position back to the end position, wherein the laser power and the gas pressure of each calibration movement are different; the pattern is a standard test pattern.
It should be noted that the calibration operation is performed before the laser head works, and may be performed before each normal operation, that is, before each normal operation, a calibrated intelligent nozzle detection model matched with the calibration operation is obtained, or may be performed in stages after each normal operation for a period of time, that is, each stage is matched with a calibrated intelligent nozzle detection model.
The calibration action acts on the laser head to perform a plurality of calibration actions, including a calibration action from a pattern start position cutting action to a pattern end position, and/or: a calibration movement from the pattern position back to the end position, wherein the laser power and the gas pressure of each calibration movement are different; the calibration cutting pattern is a standard test pattern.
If the calibration action is to cut from the initial position to the final position of the graph for multiple times, the movement speed, the light-emitting power and the air pressure of each calibration movement are different, the method can be understood as follows: the speed, the light-emitting power and the air pressure of each time from the cutting movement of the initial position to the final position of the graph are different;
the state parameter data comprise gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signal and protective lens temperature blown out by the laser head, the calibration process is to actually execute calibration action by the laser head, and the gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light-emitting signal and the protective lens temperature generated by the executing mechanism in the calibration process are detected, and the actual roughness of the laser head is measured by the interferometer in the calibration process; and determining a calibrated intelligent nozzle detection model according to the gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light-emitting signal, the protection lens temperature and the actual roughness measured by the interferometer during calibration.
In the above steps, the detection of the gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light emitting signal, and the temperature of the protective lens blown by the laser head may be performed by the gas pressure sensor, the power detection sensor, the gas flow sensor, the light sensing sensor, and the temperature sensor. The gas pressure sensor is arranged in the laser head and directly detects the actual gas pressure at the outlet of the nozzle; the laser power sensor is arranged in the laser head and close to the nozzle, and directly detects the actual laser power coming out of the nozzle; the actual cutting speed is in the motor, the motor transmits the actual cutting speed value to the driver, and the driver interacts with the host; the gas flow sensor is placed in the laser head and is close to the mounting position of the gas pressure sensor; the light-emitting signal is a numerical value given by the inside of the system and can be directly used; the temperature of the protective lens can be directly transmitted to the system through laser head software.
According to the method provided by the invention, the theoretical surface roughness of the equipment under various laser powers and gas pressures can be calculated in real time according to the calibrated intelligent nozzle detection model, and the deviation of the measured surface roughness and the theoretical surface roughness detected by the interferometer is used as a basis for judging whether the surface roughness is abnormal or not. Because this intelligent nozzle detects the model and establishes according to equipment self actual measurement gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signal, protection mirror lens temperature, and then, the intelligent detection model after the demarcation has equipment self characteristic, and this model just avoids the variability of equipment, and the change in the equipment use leads to judging the mistake, has effectively improved the accuracy of surface roughness unusual judgement.
Meanwhile, as the calibrated intelligent nozzle detection model is introduced before abnormality judgment, the alternative scheme can be widely adapted to different laser head-carrying devices, so that universality and accuracy are effectively considered, namely: the method is widely applicable to various equipment, and meanwhile, the accuracy of surface roughness abnormality judgment can be improved.
As shown in fig. 3, the step of determining the calibrated intelligent nozzle detection model according to the state parameter data obtained in the calibration process and the actual measurement surface roughness in the calibration process includes:
s021: determining an intelligent nozzle detection model without deviation according to the state parameter data of R calibration times and the actual measurement surface roughness of R calibration times;
in the step, an intelligent nozzle detection model without deviation is determined according to the gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light emitting signal, the lens temperature of the protective lens and the actual measured surface roughness measured by the interferometer in R calibration;
where R is a number greater than or equal to 1000, in order to increase the reliability of the calculation result, in some embodiments, R may be an integer greater than or equal to 2000. It should be noted that if the data of the intelligent nozzle detection model is too small, the function will be disabled.
In one embodiment of the invention, the intelligent nozzle detection model without deviation is:
wherein Ra is surface roughness, pa is gas pressure, W is laser power, V is cutting speed, Q is gas flow, phi is light emitting signal, and T is temperature of the protective lens.
S022: calculating the calculated surface roughness corresponding to each calibration data according to the state parameter data of the R calibration times and the intelligent nozzle detection model without deviation to obtain the calculated surface roughness of the R calibration times;
according to the non-deviation intelligent nozzle detection model and the R calibration time gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signals and protection lens temperature, calculating the rough degree corresponding to each calibration data to obtain R calibration time calculated surface roughness;
the measured gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light-emitting signal, the temperature of the protective lens and the measured surface roughness detected by the interferometer during calibration are in one-to-one correspondence, and the measured gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light-emitting signal, the temperature of the protective lens and the calculated roughness during calibration are in one-to-one correspondence, that is, the measured surface roughness during calibration and the calculated roughness during calibration are also in one-to-one correspondence.
S023: determining the maximum surface roughness deviation according to the actual measured surface roughness of the R standards and the calculated surface roughness of the R standards;
the method for determining the maximum roughness deviation comprises the following steps:
calculating the deviation between the measured surface roughness of R standard times and the calculated surface roughness of the corresponding R standard times to obtain R deviation values;
the maximum value of the R deviation values is determined as the maximum roughness deviation.
S024: and determining the calibrated intelligent nozzle detection model according to the deviation between the intelligent nozzle detection model without deviation and the maximum surface roughness.
The calibrated intelligent nozzle detection model is obtained by adding the intelligent nozzle detection model without deviation and the maximum roughness deviation; the calibrated intelligent nozzle detection model is as follows:
wherein Ra is surface roughness, pa is gas pressure, W is laser power, V is cutting speed, Q is gas flow, phi is light emitting signal, T is temperature of protective lens, R err Is the maximum roughness deviation.
Based on the state parameter data at the time of calibration and the actual measured surface roughness at the time of calibration, the parameters of the intelligent nozzle detection model without deviation are calculated by adopting a least square method. In practice, that is, the parameters of the intelligent nozzle detection model without deviation are calculated by adopting a least square method according to the actual measured gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light-emitting signal, the temperature of the lens of the protective lens and the actual measured surface roughness of the interferometer during calibration. Respectively is 
=26.363654、/>
=69.3452、/>
=28.3475、/>
=70.2154、/>
=13.6522、/>
=3.6985、/>
=32.1245。
In some embodiments, as shown in fig. 4, the step of calculating the difference between the actual surface roughness and the theoretical surface roughness during operation, and combining the surface roughness deviation reference value, and analyzing whether the roughness during the operation of the nozzle is abnormal includes:
s31a: calculating the difference between the actual measured surface roughness during working and the theoretical surface roughness during working to be a first difference;
s32a: judging whether the first difference value is larger than a first reinspection threshold value or not;
if yes, go to step S33a, if no, go to step S38a;
s33a: calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model;
s34a: calculating the difference between the actual measured surface roughness and the rechecked theoretical surface roughness during working and recording the difference as a second difference;
s35a: judging whether the first difference value is larger than the second difference value or not;
if yes, go to step S36a, if no, go to step S38a;
s36a: comparing the second difference with a surface roughness deviation reference;
s37a: judging whether the second difference value is always larger than or equal to the surface roughness deviation reference value within a preset time period; if yes, go to step S40a, otherwise, go to step S41a;
s38a: comparing the first difference with a surface roughness deviation reference value;
That is, by direct comparison of |Ra| -Ra 0 | and T Ra Judging whether abnormality occurs or not;
s39a: judging whether the first difference value is always larger than or equal to the surface roughness deviation reference value within a preset time period; if yes, go to step S40a, otherwise, go to step S41a;
s40a: determining that the roughness of the nozzle is abnormal in the working process so as to determine that the nozzle causes abnormal cutting; that is, it is determined that the roughness of the workpiece cut by the laser head is abnormal.
S41a: determining that no abnormality occurs in the roughness of the nozzle in the working process; that is, it is determined that no abnormality has occurred in the roughness of the workpiece cut by the laser head.
Here, the surface roughness deviation reference value is a preset fixed value, or: the ratio of the surface roughness deviation reference value to the theoretical surface roughness during operation is a preset fixed value smaller than 1.
The intelligent nozzle detection model further comprises a historical data set model, the historical data set model is obtained according to the numerical value collected in the operation process of a traditional machine, the numerical value is processed uniformly, a genetic algorithm is used for optimizing an SVM support vector machine neural network after the processing, the historical data set model is established, however, the historical data model is a reference model mentioned in the application, when the intelligent nozzle detection model detects that the data deviation value is overlarge, secondary detection is carried out by using the historical data model, and then a judging result is given. In the present invention, all mentioned intelligent nozzle models include historical data set models, and will not be described in detail.
In some embodiments, calculating a difference between the measured surface roughness and the theoretical surface roughness during operation, and analyzing whether the roughness during operation of the nozzle is abnormal in combination with the surface roughness deviation reference value includes:
s31b: combining the difference between the actual surface roughness during working and the theoretical surface roughness during working with a surface roughness deviation reference value to obtain a roughness deviation E= (|Ra| -Ra) 0 ∣)/T Ra ；
S32b: judging whether the deviation E is larger than a second reinspection threshold value or not;
if yes, go to step S33b, if no, go to step S36b;
s33b: calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model;
s34b: combining the difference value of the actual measured surface roughness and the rechecked theoretical surface roughness during working with a surface roughness deviation reference value to obtain rechecked roughness deviation Ec;
s35b: judging whether the rechecked roughness deviation Ec is continuously greater than or equal to 1 in a preset time; if yes, go to step S37b, otherwise go to step S38b;
s36b: judging whether the roughness deviation E is continuously greater than or equal to 1 in a preset time; if yes, go to step S37b, otherwise go to step S38b;
s37b: determining that the roughness in the working process of the nozzle is abnormal;
S38b: determining that no abnormality occurs in the roughness of the nozzle in the working process;
wherein Ra is the measured surface roughness at work, ra 0 T is the theoretical surface roughness in operation Ra Is a roughness deviation reference value.
The laser head starts executing NC code actions; acquiring the theoretical surface roughness during working and the actually measured surface roughness during working in real time by the method; judging whether the difference value between the theoretical surface roughness and the actually measured surface roughness is greater than 10% of the theoretical surface roughness during working, if so, continuing executing NC codes; if not, controlling the machine to stop for checking or replacing the nozzle. That is, in this embodiment, the roughness deviation reference value is 10% of the theoretical surface roughness at the time of operation.
In some embodiments, the roughness deviation reference may also be 20% of the theoretical surface roughness during operation.
After step S40a or S37b, that is, after determining that the roughness of the laser head is abnormal at the time of cutting, at least one of the following is included:
controlling a moving mechanism for cutting by the laser head to stop running;
controlling the laser head mechanism to send out an abnormal alarm signal;
and controlling the power-off protection of the laser head mechanism.
The motion mechanism for controlling the laser head to cut stops running, the laser head mechanism is controlled to send out an abnormal alarm signal, and the laser head mechanism is controlled to conduct power-off protection, and the motion mechanism, the laser head mechanism and the power-off protection can be conducted simultaneously or not.
In some embodiments, the abnormal alarm signal may be an audible alarm or a flashing alarm.
In the actual implementation process, the specific process of cutting data processing when the laser head works is as follows:
before the laser head works normally, step S01 is implemented (i.e. the control system executes a preset action according to a specific NC code control device), after calibration actions are completed and the actual measured gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signal, protection mirror lens temperature and actual measured surface roughness measured by the interferometer at calibration are obtained, step S02 may be implemented, after the calibrated intelligent nozzle detection model is obtained, normal work of the laser head for cutting the workpiece may be implemented, after the laser head works normally, step S1 may be implemented (i.e. the gas pressure blown by the laser head, actual laser power, actual cutting speed, gas flow, light-emitting signal, protection mirror lens temperature may be read in real time), after obtaining the actual measured surface roughness of the laser head and the actual measured gas pressure, the actual laser power, the actual cutting speed, the gas flow, the light emitting signal and the protective lens temperature of the laser head during operation, step S2 may be implemented (i.e. calculating the theoretical surface roughness required by the laser head to realize the moving object in real time), after obtaining the theoretical surface roughness during operation, it may be judged whether the difference between the actual measured surface roughness and the theoretical surface roughness during operation is always greater than or equal to the reference value of roughness deviation during the preset time period (i.e. judging whether the difference between the feedback roughness and the theoretical surface roughness is always greater than or equal to the reference value of deviation during the preset time period), if the difference between the actual measured surface roughness and the theoretical surface roughness during operation is always greater than or equal to the reference value of roughness deviation during the preset time period, it may be understood that the judgment result of step S40a or step S37b is yes, the operation of controlling the laser head to stop running, the system to send out an abnormal alarm signal and controlling at least one operation (namely stopping and alarm protection) of carrying out power-off protection on the laser head can be carried out, and if the difference value between the actually measured surface roughness during working and the theoretical surface roughness during working is smaller than the reference value of the roughness deviation within the preset time, the processing task of the equipment can be continuously completed.
FIG. 5 is a schematic block diagram of an intelligent cutting data processing apparatus for a laser cutting machine, including a work detection module 100, a calculation module 200, and an analysis module 300, according to an embodiment of the present invention;
the working detection module 100 is used for detecting the working state parameter data of the nozzle of the laser cutting machine and the actual measured surface roughness during working in the normal working process of the laser cutting machine;
the calculating module 200 is used for calculating the theoretical surface roughness during working based on the detected state parameter data of the working state of the laser cutting machine nozzle and the intelligent nozzle detection model;
the analysis module 300 is used for analyzing whether the roughness of the nozzle in the working process is abnormal according to the difference value between the actually measured surface roughness and the theoretical surface roughness in the working process and the surface roughness deviation reference value.
The device provided by the invention can calculate the theoretical surface roughness of the equipment under various laser powers and gas pressures in real time according to the calibrated intelligent nozzle detection model, and the deviation of the calculated actual surface roughness and the theoretical surface roughness is used as a basis for judging whether the surface roughness is abnormal or not.
As shown in fig. 6, in some embodiments, the apparatus further comprises a calibration detection module 010 and a model determination module 020;
The calibration detection module 010 is used for executing a calibration action through the laser head, detecting state parameter data of the laser cutting machine nozzle in the calibration process, and measuring actual measurement surface roughness of the laser head through the interferometer in the calibration process;
the model determining module 020 is used for determining a calibrated intelligent nozzle detection model according to the state parameter data acquired in the calibration process and the actual measurement surface roughness in the calibration process.
Because this intelligent nozzle detects the model is according to equipment self actual measurement gas pressure, actual laser power, actual cutting speed, gas flow, light-emitting signal, protection mirror lens temperature, and then, the intelligent detection model after the demarcation has equipment self characteristic, and this model just avoids the variability of equipment, and the change in the equipment use leads to judging the mistake, has effectively improved the accuracy of roughness abnormal judgement.
In some embodiments, the model determination module 020 includes a no-bias model determination unit, a calculated surface roughness acquisition unit, a maximum bias determination unit, and a post-calibration model determination unit;
the non-deviation model determining unit is used for determining a non-deviation intelligent nozzle detection model according to the state parameter data of R calibration and the actual measurement surface roughness of R calibration; wherein R is an integer greater than or equal to 1000; the method is particularly used for calculating parameters of the intelligent nozzle detection model without deviation by adopting a least square method based on the state parameter data during calibration and the actual measurement surface roughness during calibration.
The calculating surface roughness obtaining unit is used for calculating the roughness corresponding to each calibration data according to the non-deviation intelligent nozzle detection model and the state parameter data of the R calibration times to obtain R calculated surface roughness;
the maximum deviation determining unit is used for determining the maximum surface roughness deviation according to the actual measured surface roughness of the R calibration times and the calculated surface roughness of the R calibration times; the method is particularly used for calculating the deviation between the actual measurement surface roughness of R standard times and the calculated surface roughness of the corresponding R standard times to obtain R deviation values; the maximum value of the R deviation values is determined as the maximum roughness deviation.
And the calibrated model determining unit is used for determining the calibrated intelligent nozzle detection model according to the deviation between the intelligent nozzle detection model without deviation and the maximum surface roughness.
In some embodiments, the calibrated intelligent nozzle detection model output by the model determination unit is:
wherein Ra is surface roughness, pa is gas pressure, W is laser power, V is cutting speed, Q is gas flow, phi is light emitting signal, T is temperature of protective lens, R err Is the maximum roughness deviation. Can be deduced from the least square method 
Respectively->
=26.363654、/>
=69.3452、/>
=28.3475、/>
=70.2154、/>
=13.6522、/>
=3.6985、/>
=32.1245。
In some embodiments, the analysis module is specifically configured to compare the difference between the actually measured surface roughness during operation and the theoretical surface roughness during operation with a surface roughness deviation reference value; if the difference value between the actually measured surface roughness during working and the theoretical surface roughness during working is always greater than or equal to the surface roughness deviation reference value within a preset time period, determining that the roughness during the working process of the nozzle is abnormal; or, combining the difference between the actual surface roughness during working and the theoretical surface roughness during working with the surface roughness deviation reference value to obtain roughness deviation information err= (|Ra|Ra) 0 ∣)/T Ra The method comprises the steps of carrying out a first treatment on the surface of the If err is continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; if err is continuously less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal;
wherein Ra is the measured surface roughness at work, ra 0 T is the theoretical surface roughness in operation Ra Is a roughness deviation reference value.
The embodiment of the invention also provides electronic equipment, which comprises: the device comprises a processor, a communication interface, a memory and a bus, wherein the processor, the communication interface and the memory are in communication with each other through the bus. The bus may be used for information transfer between the electronic device and the sensor. The processor may call logic instructions in memory to perform the following method: s1: in normal working of laser cutting, detecting state parameter data of the working of a nozzle of a laser cutting machine and actually measured surface roughness in working; s2: calculating the theoretical surface roughness during working based on the detected state parameter data of the working of the laser cutting machine nozzle and an intelligent nozzle detection model; s3: and according to the difference value between the actually measured surface roughness during working and the theoretical surface roughness during working, analyzing whether the roughness during the working process of the nozzle is abnormal or not by combining the surface roughness deviation reference value.
Further, the logic instructions in the memory described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The intelligent cutting data processing method and apparatus of the laser cutting machine of the present invention, which are the units and algorithm steps of the examples described in connection with the embodiments disclosed herein, can be implemented in electronic hardware, computer software, or a combination of both, and to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described in terms of functionality in the foregoing description. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the invention. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the invention.
Although the present invention has been described in detail by way of preferred embodiments with reference to the accompanying drawings, the present invention is not limited thereto. Various equivalent modifications and substitutions may be made in the embodiments of the present invention by those skilled in the art without departing from the spirit and scope of the present invention, and it is intended that all such modifications and substitutions be within the scope of the present invention/be within the scope of the present invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An intelligent cutting data processing method of a laser cutting machine is characterized by comprising the following steps:
in the normal operation of the laser cutting machine, detecting the working state parameter data of a nozzle of the laser cutting machine and the actual measured surface roughness during the working;
calculating the theoretical surface roughness during working based on the detected state parameter data of the working of the laser cutting machine nozzle and an intelligent nozzle detection model;
and calculating the difference value between the actually measured surface roughness and the theoretical surface roughness in working, and analyzing whether the roughness in the working process of the nozzle is abnormal or not by combining the surface roughness deviation reference value.
2. The method for processing intelligent cutting data of a laser cutting machine according to claim 1, wherein the step of detecting the working state parameter data of the laser cutting machine nozzle and the working measured surface roughness before the step of detecting the working state parameter data of the laser cutting machine nozzle comprises the following steps:
performing calibration action by a laser head, detecting state parameter data of a laser cutting machine nozzle in the calibration process, and measuring actual measurement surface roughness of the laser head by an interferometer in the calibration process;
and determining a calibrated intelligent nozzle detection model according to the state parameter data obtained in the calibration process and the actual measurement surface roughness in the calibration process.
3. The method for processing intelligent cutting data of a laser cutting machine according to claim 2, wherein the step of determining the calibrated intelligent nozzle detection model according to the state parameter data obtained in the calibration process and the measured surface roughness in the calibration process comprises:
determining an intelligent nozzle detection model without deviation according to the state parameter data of R calibration times and the actual measurement surface roughness of R calibration times; wherein R is an integer greater than or equal to 1000;
calculating the calculated surface roughness corresponding to each calibration data according to the state parameter data of the R calibration times and the intelligent nozzle detection model without deviation to obtain the calculated surface roughness of the R calibration times;
Determining the maximum surface roughness deviation according to the actual measured surface roughness of the R standards and the calculated surface roughness of the R standards;
and determining the calibrated intelligent nozzle detection model according to the deviation between the intelligent nozzle detection model without deviation and the maximum surface roughness.
4. A method of intelligent cutting data processing for a laser cutting machine according to claim 3 wherein the method of determining the maximum roughness deviation comprises:
calculating the deviation between the measured surface roughness of R standard times and the calculated surface roughness of the corresponding R standard times to obtain R deviation values;
the maximum value of the R deviation values is determined as the maximum roughness deviation.
5. The intelligent cutting data processing method of the laser cutting machine according to claim 4, wherein the state parameter data comprises gas pressure blown out by the laser head, laser power, cutting speed, gas flow, light emitting signal, and protective lens temperature; the calibrated intelligent nozzle detection model is as follows:
wherein Ra is surface roughness, pa is gas pressure, W is laser power, V is cutting speed, Q is gas flow, phi is light-emitting signal, T is lens temperature of the protective lens, and Rerr is maximum roughness deviation; 
Is a model parameter calculated from the state parameter data.
6. The method for processing intelligent cutting data of a laser cutting machine according to claim 1, wherein the step of calculating a difference between the actual measured surface roughness and the theoretical surface roughness during operation and analyzing whether the roughness during operation of the nozzle is abnormal in combination with the surface roughness deviation reference value comprises:
calculating the difference between the actual measured surface roughness during working and the theoretical surface roughness during working to be a first difference;
judging whether the first difference value is larger than a first reinspection threshold value or not;
if yes, calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model;
calculating the difference between the actual measured surface roughness and the rechecked theoretical surface roughness during working and recording the difference as a second difference;
if the first difference is larger than the second difference, comparing the second difference with a surface roughness deviation reference value; if the second difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal;
if the first difference value is not greater than the second difference value, comparing the first difference value with a surface roughness deviation reference value; if the first difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal;
If not, executing the steps of comparing the first difference value with a surface roughness deviation reference value; and if the first difference value is always greater than or equal to the surface roughness deviation reference value within the preset time period, determining that the roughness in the working process of the nozzle is abnormal.
7. The method for processing intelligent cutting data of a laser cutting machine according to claim 1, wherein the step of calculating a difference between the actual measured surface roughness and the theoretical surface roughness during operation and analyzing whether the roughness during operation of the nozzle is abnormal in combination with the surface roughness deviation reference value comprises:
combining the difference between the actual surface roughness during working and the theoretical surface roughness during working with a surface roughness deviation reference value to obtain a roughness deviation E= (|Ra| -Ra) 0 ∣)/T Ra ；
Judging whether the deviation E is larger than a second reinspection threshold value or not;
if yes, calculating the theoretical surface roughness of the recheck by combining the detected state parameter data with a reference model;
combining the difference value of the actual measured surface roughness and the rechecked theoretical surface roughness during working with a surface roughness deviation reference value to obtain rechecked roughness deviation Ec; when the Ec is judged to be continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; when Ec is continuously less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal;
If not, if the E is judged to be continuously greater than or equal to 1 in the preset time, determining that the roughness in the working process of the nozzle is abnormal; e, when the duration of the E is less than 1 in the preset time, determining that the roughness in the working process of the nozzle is not abnormal;
wherein Ra is the measured surface roughness at work, ra 0 T is the theoretical surface roughness in operation Ra Is a roughness deviation reference value.
8. The intelligent cutting data processing device of the laser cutting machine is characterized by comprising a work detection module, a calculation module and an analysis module;
the working detection module is used for detecting the working state parameter data of the nozzle of the laser cutting machine and the actually measured surface roughness during working in the normal working process of the laser cutting machine;
the calculation module is used for calculating the theoretical surface roughness during working based on the detected state parameter data of the working state of the laser cutting machine nozzle and the intelligent nozzle detection model;
and the analysis module is used for analyzing whether the roughness of the nozzle in the working process is abnormal or not according to the difference value between the actually measured surface roughness and the theoretical surface roughness in the working process and the surface roughness deviation reference value.
9. The intelligent cutting data processing device of the laser cutting machine according to claim 8, further comprising a calibration detection module for executing a calibration action by the laser head and detecting state parameter data of the laser cutting machine nozzle during calibration, and measured surface roughness of the laser head during calibration by the interferometer;
The model determining module is used for determining a calibrated intelligent nozzle detection model according to the state parameter data acquired in the calibration process and the actual measurement surface roughness in the calibration process.
10. An electronic device, the electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores computer program instructions executable by the at least one processor to enable the at least one processor to perform the method of intelligent cutting data processing of a laser cutter according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310564551.XA CN116275600B (en) | 2023-05-19 | 2023-05-19 | Intelligent cutting data processing method, device and equipment of laser cutting machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310564551.XA CN116275600B (en) | 2023-05-19 | 2023-05-19 | Intelligent cutting data processing method, device and equipment of laser cutting machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116275600A true CN116275600A (en) | 2023-06-23 |
| CN116275600B CN116275600B (en) | 2023-09-29 |
Family
ID=86789138
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310564551.XA Active CN116275600B (en) | 2023-05-19 | 2023-05-19 | Intelligent cutting data processing method, device and equipment of laser cutting machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116275600B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117086495A (en) * | 2023-10-09 | 2023-11-21 | 河南蓝犀牛工业装备技术有限公司 | Intelligent laser cutting machine system for energy-saving type power transformer iron core |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11320149A (en) * | 1998-05-07 | 1999-11-24 | Koike Sanso Kogyo Co Ltd | Detecting device for cutting condition in laser cutting machine |
| CN101819030A (en) * | 2009-02-27 | 2010-09-01 | 北京京东方光电科技有限公司 | Method and system for monitoring surface roughness of magnetic control spattering target |
| CN108555530A (en) * | 2018-05-30 | 2018-09-21 | 武汉船用机械有限责任公司 | A kind of processing method of negative camber |
| US20190164303A1 (en) * | 2017-04-13 | 2019-05-30 | Fractilia, Llc | System and method for generating and analyzing roughness measurements |
| CN109885918A (en) * | 2019-01-18 | 2019-06-14 | 广东镭奔激光科技有限公司 | The prediction technique of laser-impact surface roughness |
| CN110059442A (en) * | 2019-05-07 | 2019-07-26 | 同济大学 | A kind of turnery processing cutter replacing method based on Part Surface Roughness and power information |
| CN110293323A (en) * | 2019-06-06 | 2019-10-01 | 济南邦德激光股份有限公司 | A kind of intelligent batch cutting process method, CNC control system, laser cutting machine and storage medium |
| CN110543698A (en) * | 2019-08-15 | 2019-12-06 | 合肥工业大学 | method for measuring surface roughness based on wavelet Brownian motion texture fusion model |
| CN110549162A (en) * | 2018-06-01 | 2019-12-10 | 日立汽车系统（中国）有限公司 | Cutting abnormality detection method and cutting abnormality detection device |
| CN110900454A (en) * | 2019-12-04 | 2020-03-24 | 长沙理工大学 | Grinding surface roughness real-time detection and intelligent control system |
| JP2020151725A (en) * | 2019-03-18 | 2020-09-24 | ファナック株式会社 | Machine learning device, control device, laser beam machining machine and machine learning method |
| DE102019207421A1 (en) * | 2019-05-21 | 2020-11-26 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method and device for smoothing a surface of a component by machining with energetic radiation |
| CN113340261A (en) * | 2021-06-28 | 2021-09-03 | 宁波江丰电子材料股份有限公司 | Target roughness monitoring method |
| WO2021174525A1 (en) * | 2020-03-06 | 2021-09-10 | 大连理工大学 | Parts surface roughness and cutting tool wear prediction method based on multi-task learning |
| CN113804091A (en) * | 2021-11-18 | 2021-12-17 | 中认国证(北京)评价技术服务有限公司 | Roughness real-time detection method |
| CN114055249A (en) * | 2020-08-05 | 2022-02-18 | 北京福田康明斯发动机有限公司 | Bore hole surface roughness monitoring method and system and storage medium |
| JPWO2022054158A1 (en) * | 2020-09-09 | 2022-03-17 | ||
| CN114897028A (en) * | 2022-05-27 | 2022-08-12 | 清华大学 | Numerical control machining surface roughness prediction method and device |
| CN115178860A (en) * | 2022-07-27 | 2022-10-14 | 上海波刺自动化科技有限公司 | Laser processing head, detection system and detection method for laser processing |
| CN115406398A (en) * | 2022-09-26 | 2022-11-29 | 中车长春轨道客车股份有限公司 | Method and device for detecting abnormal abrasion of pantograph net of railway vehicle and storage medium |
| JP2023009475A (en) * | 2021-07-07 | 2023-01-20 | 国立研究開発法人産業技術総合研究所 | Method and information processing system for roughness analysis |
-
2023
- 2023-05-19 CN CN202310564551.XA patent/CN116275600B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11320149A (en) * | 1998-05-07 | 1999-11-24 | Koike Sanso Kogyo Co Ltd | Detecting device for cutting condition in laser cutting machine |
| CN101819030A (en) * | 2009-02-27 | 2010-09-01 | 北京京东方光电科技有限公司 | Method and system for monitoring surface roughness of magnetic control spattering target |
| US20190164303A1 (en) * | 2017-04-13 | 2019-05-30 | Fractilia, Llc | System and method for generating and analyzing roughness measurements |
| CN108555530A (en) * | 2018-05-30 | 2018-09-21 | 武汉船用机械有限责任公司 | A kind of processing method of negative camber |
| CN110549162A (en) * | 2018-06-01 | 2019-12-10 | 日立汽车系统（中国）有限公司 | Cutting abnormality detection method and cutting abnormality detection device |
| CN109885918A (en) * | 2019-01-18 | 2019-06-14 | 广东镭奔激光科技有限公司 | The prediction technique of laser-impact surface roughness |
| JP2020151725A (en) * | 2019-03-18 | 2020-09-24 | ファナック株式会社 | Machine learning device, control device, laser beam machining machine and machine learning method |
| CN110059442A (en) * | 2019-05-07 | 2019-07-26 | 同济大学 | A kind of turnery processing cutter replacing method based on Part Surface Roughness and power information |
| DE102019207421A1 (en) * | 2019-05-21 | 2020-11-26 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method and device for smoothing a surface of a component by machining with energetic radiation |
| CN110293323A (en) * | 2019-06-06 | 2019-10-01 | 济南邦德激光股份有限公司 | A kind of intelligent batch cutting process method, CNC control system, laser cutting machine and storage medium |
| CN110543698A (en) * | 2019-08-15 | 2019-12-06 | 合肥工业大学 | method for measuring surface roughness based on wavelet Brownian motion texture fusion model |
| CN110900454A (en) * | 2019-12-04 | 2020-03-24 | 长沙理工大学 | Grinding surface roughness real-time detection and intelligent control system |
| WO2021174525A1 (en) * | 2020-03-06 | 2021-09-10 | 大连理工大学 | Parts surface roughness and cutting tool wear prediction method based on multi-task learning |
| CN114055249A (en) * | 2020-08-05 | 2022-02-18 | 北京福田康明斯发动机有限公司 | Bore hole surface roughness monitoring method and system and storage medium |
| JPWO2022054158A1 (en) * | 2020-09-09 | 2022-03-17 | ||
| CN113340261A (en) * | 2021-06-28 | 2021-09-03 | 宁波江丰电子材料股份有限公司 | Target roughness monitoring method |
| JP2023009475A (en) * | 2021-07-07 | 2023-01-20 | 国立研究開発法人産業技術総合研究所 | Method and information processing system for roughness analysis |
| CN113804091A (en) * | 2021-11-18 | 2021-12-17 | 中认国证(北京)评价技术服务有限公司 | Roughness real-time detection method |
| CN114897028A (en) * | 2022-05-27 | 2022-08-12 | 清华大学 | Numerical control machining surface roughness prediction method and device |
| CN115178860A (en) * | 2022-07-27 | 2022-10-14 | 上海波刺自动化科技有限公司 | Laser processing head, detection system and detection method for laser processing |
| CN115406398A (en) * | 2022-09-26 | 2022-11-29 | 中车长春轨道客车股份有限公司 | Method and device for detecting abnormal abrasion of pantograph net of railway vehicle and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 曹兰剑;龙八军;: "激光切割表面质量预报的Fisher判别分析", 中国高新技术企业, no. 27 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117086495A (en) * | 2023-10-09 | 2023-11-21 | 河南蓝犀牛工业装备技术有限公司 | Intelligent laser cutting machine system for energy-saving type power transformer iron core |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116275600B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI640390B (en) | Tool wear monitoring and predicting method | |
| CN116275600B (en) | Intelligent cutting data processing method, device and equipment of laser cutting machine | |
| TWI302489B (en) | Device checking method for machine tool | |
| JP2014144528A (en) | Method for machining series of workpieces by means of at least one machining jet | |
| US11256229B2 (en) | Industrial machinery and control method thereof | |
| CN111830906A (en) | On-machine monitoring system for failure state of rotary cutter and detection method thereof | |
| JP6697494B2 (en) | Abnormality discrimination device, program, abnormality discrimination system, and abnormality discrimination method | |
| WO2008142386A1 (en) | Machining process monitor | |
| JP2019130632A (en) | Abnormality determination apparatus, program, abnormality determination system, and abnormality determination method | |
| US20020029115A1 (en) | Machine tool maintenance system | |
| KR101626458B1 (en) | Apparatus for detecting malfunction of tool for machine tool | |
| CN110874084B (en) | Machining environment estimating device | |
| CN112720073A (en) | Tool setting gauge control method and device, storage medium and processor | |
| CN108363822A (en) | Cutter rigid predictions are used to inhibit the device and method of cutting-vibration | |
| KR20090056706A (en) | The method of in process chucking miss, tool wear and breakage machine tools | |
| TWM538181U (en) | Monitoring equipment for CNC machining | |
| KR20160079372A (en) | Monitoring device of tool install condition for machine tool | |
| KR20120103993A (en) | Method for safe space decision of tool and tool holer and apparatus thereof | |
| KR101473580B1 (en) | method for monitoring of cutting machine | |
| JPH10286730A (en) | Control device for production state in process and recording medium | |
| JPH09119854A (en) | Environment monitoring device in precision working apparatus or precision measuring apparatus | |
| WO2023063435A1 (en) | Working machine bearing quality determining method and system | |
| JP2020151817A (en) | Diagnostic device, diagnostic system, and diagnostic program | |
| JP7486358B2 (en) | Accuracy diagnosis device and accuracy diagnosis method for machine tools | |
| CN114714149A (en) | Method for automatically detecting tool setting of machine tool and tool setting detection device |
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 |