CN115319311B - Laser cutting equipment - Google Patents
Laser cutting equipment Download PDFInfo
- Publication number
- CN115319311B CN115319311B CN202211250547.8A CN202211250547A CN115319311B CN 115319311 B CN115319311 B CN 115319311B CN 202211250547 A CN202211250547 A CN 202211250547A CN 115319311 B CN115319311 B CN 115319311B
- Authority
- CN
- China
- Prior art keywords
- laser cutting
- plate
- parameters
- correction
- structural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
Abstract
The invention relates to the technical field of laser cutting, in particular to laser cutting equipment. The equipment comprises a laser cutting machine body and a laser cutting machine parameter correction system. The laser cutting machine parameter correction system comprises a correction controller, a data acquisition module and a data analysis module, wherein the data acquisition module and the data analysis module are in signal connection with the correction controller. And collecting and recording the cutting data through a data acquisition module, and performing predictive analysis on the data by using a data analysis module to obtain an optimal correction period. And the correction controller maintains the galvanometer system of the laser cutting equipment according to the optimal correction period. The invention realizes the timely correction of the galvanometer system and the self-adaptive adjustment function of the laser cutting equipment by a data prediction analysis method.
Description
Technical Field
The invention relates to the technical field of laser cutting, in particular to laser cutting equipment.
Background
Generally, before the laser cutting machine is initially used, the method for adjusting the precision of the optical path system of the laser cutting machine manually compares an ideal position in a standard coordinate network with an actual position on a horizontal correction plate through cutting, and adjusts a laser pulse parameter and an angle adjustment of a galvanometer group in the optical path system. However, in the use process of the manually adjusted laser cutting system, mechanical deviation often occurs due to long-time mechanical vibration, so that the cutting accuracy of the laser cutting system is reduced. The existing solution is to manually correct the laser cutting system periodically, and because the material type of the workpiece cut by the laser cutting system is different, the numerical control operation parameters are different, and the mechanical offset which may be generated is also different, so that the corresponding laser cutting correction periods are different, and the corresponding adjustment parameters are also different, and if the laser equipment is corrected by adopting a fixed correction period, the working task of the laser cutting equipment is affected because the laser equipment is not corrected in time.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide a laser cutting apparatus, which adopts the following technical solutions:
the invention provides laser cutting equipment, which comprises a laser cutting machine body and a laser cutting machine parameter correction system, wherein the laser cutting machine body is provided with a laser cutting machine parameter correction system; the parameter correction system of the laser cutting machine comprises a correction controller, a data acquisition module and a data analysis module, wherein the data acquisition module and the data analysis module are in signal connection with the correction controller;
the data acquisition module is used for acquiring a periodic correction period of the laser cutting equipment and theoretical galvanometer system adjusting parameters under the periodic correction period; acquiring infrared sensor data and plate structure parameters on a plate in each cutting process of laser cutting equipment;
the data analysis module is used for acquiring the heat influence difference between different heat influence areas on each plate according to the data of the infrared sensor; in an actual use time period, obtaining a chain distance under each sampling period according to heat influence difference between different sampling moments under a preset sampling period, and selecting at least two sampling periods corresponding to the minimum chain distance to obtain a long time sequence length; obtaining a structural similarity mean value among different plates under a long time sequence length according to the plate structural parameters; acquiring actual galvanometer system adjusting parameters according to laser cutting information under the long time sequence length; inputting the actual galvanometer system adjusting parameters and the structural similarity mean value into a pre-trained prediction neural network, and outputting the predicted actual galvanometer system adjusting parameters and the predicted structural similarity mean value at a future moment; obtaining an optimal correction cycle according to the theoretical mirror-vibrating system adjusting parameters, the predicted actual mirror-vibrating system adjusting parameters and the predicted structure similarity mean value;
and the correction controller is used for maintaining the galvanometer system of the laser cutting equipment according to the optimal correction period.
Further, the acquiring the difference of the heat influence between different heat-affected zones on each plate material comprises:
the heat-affected difference comprises a first heat-affected difference and a second heat-affected difference;
taking the absolute value of the data difference value of the infrared sensors at two sides of the laser cut on the plate as a first heat influence difference; and taking the absolute value of the data difference value of the infrared sensor before and after continuous laser cutting on the plate as a second heat influence difference.
Further, the method for acquiring the structural similarity comprises the following steps:
obtaining the structural similarity between the plates according to a structural similarity formula, wherein the structural similarity formula comprises the following steps:
wherein the content of the first and second substances,
in order to be of structural similarity, the method of the invention,
structural parameters for the sheet AThe number of the components is equal to or less than the total number of the components,
the number of the structural parameters of the plate B,
for the nth structural parameter on the plate material a,
is the m-th structural parameter on the plate material B,
and
are similar weights; if the structural parameters on the plate A and the plate B are the same in type, the structural parameters on the plate A and the plate B are the same in type
(ii) a If the structural parameters on the plate A and the plate B are different in type, the structural parameters are different
，
Wherein, in the step (A),
the number of the types of the structural parameters of the plate A,
the structural parameters of the plate B are the types and the number.
Further, obtaining the chained distance in each sampling period according to the difference of thermal influences between different sampling moments in the preset sampling period includes:
acquiring first heat influence differences and second heat influence differences of all corresponding plates at each sampling moment, selecting the average value of the largest K first heat influence differences as a reference first heat influence difference at the corresponding sampling moment, and selecting the average value of the largest K second heat influence differences as a reference second heat influence difference at the corresponding sampling moment; k is a positive integer greater than 2;
and acquiring a reference first thermal influence difference distance and a reference second thermal influence difference distance between every two adjacent sampling moments in a sampling period, and accumulating all the reference first thermal influence difference distances and the reference second thermal influence difference distances in one sampling period to acquire a chained distance in the corresponding sampling period.
Further, the galvanometer system adjusting parameters comprise galvanometer angle parameters and pulse correction parameters.
Further, obtaining an optimal correction cycle according to the theoretical galvanometer system adjusting parameter, the predicted actual galvanometer system adjusting parameter and the predicted structure similarity mean value comprises the following steps:
setting an objective function:
wherein, the first and the second end of the pipe are connected with each other,
the value of the objective function is,
in order to be a theoretical galvanometer angle parameter,
in order to predict the actual galvanometer angle parameter,
in order to be a theoretical pulse correction parameter,
in order to predict the actual pulse correction parameters,
the average value of the predicted structural similarity is obtained;
and continuously updating the predicted actual galvanometer system adjusting parameters and the predicted structural similarity in the objective function, stopping updating when the objective function value reaches the minimum value, and taking the time corresponding to the predicted actual galvanometer system adjusting parameters and the predicted structural similarity corresponding to the minimum objective function value as the time of the optimal correction period.
Further, the predictive neural network includes:
the prediction neural network is an LSTM network structure, and when the prediction neural network is trained, the target function is used as a loss function of the prediction neural network for training, and an optimal correction period is output.
The invention has the following beneficial effects:
according to the embodiment of the invention, the laser cutting machine parameter correction system is arranged on the laser cutting equipment, the data acquisition module in the laser cutting machine parameter correction system is used for acquiring and recording the infrared sensor data and the plate structure data generated by cutting the plate each time, and the offset state of the machine under the continuous cutting task can be reflected according to the infrared sensor data and the plate structure data. The long time series length in the actual use period is further analyzed by a data analysis module. The minimum chain distance reflects the difference characteristic of the heat influence difference in the actual use time period, namely the time period corresponding to the minimum chain distance is the time period in which the laser cutting equipment works stably, namely the long time sequence length is the reference time period in the actual use time period. The information in the reference time period can be used as the reference information in the actual use time period, so that the calculation amount of the algorithm is saved, and the accuracy of the data is ensured. And further taking the adjustment parameters of the actual galvanometer system and the structural similarity mean value under the long time sequence length as reference information of an actual using time period, predicting the reference information, and obtaining an optimal correction period according to a prediction result. The correction controller corrects the laser cutting equipment according to the optimal correction period, and the optimal correction period is determined through the prediction result of the neural network, so that the laser cutting equipment can be corrected and controlled in time, and the influence on a cutting task due to untimely correction of the regular correction period is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a block diagram of a laser cutting apparatus according to an embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, a laser cutting apparatus according to the present invention, and the detailed description, structure, features and effects thereof will be described below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the laser cutting device provided by the present invention in detail with reference to the accompanying drawings.
Referring to fig. 1, a structural block diagram of a laser cutting apparatus according to an embodiment of the present invention is shown, where the apparatus includes a laser cutting machine body and a laser cutting machine parameter calibration system. The laser cutting machine parameter correction system comprises a correction controller, a data acquisition module and a data analysis module, wherein the data acquisition module and the data analysis module are in signal connection with the correction controller.
It should be noted that the laser cutting machine body is composed of the conventional structure of the existing laser cutting equipment, including but not limited to the basic structure such as the galvanometer system. The laser cutting machine body is used for preparing a mechanical workpiece by utilizing the machine tool cutting platform and adjusting the cutting position of the workpiece through multi-coordinate plane rotation, so that the cutting operation is realized.
The data acquisition module aims at collecting and recording plate information and equipment information in each cutting process. In the embodiment of the invention, the data acquisition module trains the subsequent prediction neural network by using historical characteristic data generated by recording historical cutting data. It should be noted that, because the embodiment of the present invention requires the historical data as a basis, the laser cutting device needs to be manually corrected before the historical database is completely established, and a specific manual correction method is a known technique well known to those skilled in the art and is not described herein again.
In the embodiment of the invention, the data acquisition module acquires infrared sensor data on the plate in each cutting process of the laser cutting equipment by using an infrared sensor, and acquires the structural parameters of the plate by using image data acquired by a camera. It should be noted that identifying the structural parameters of the plate material through the image is a common technical means for those skilled in the art, for example, determining the structural parameters of the plate material, such as the size, the shape, and the cutting angle, through the image edge, and is not limited and described herein.
Because the heat affected zones are generated on the two sides of the laser cut in the laser cutting process, when the galvanometer system is normal, the heat affected zones on the two sides have the characteristics of symmetry and fixed and unchangeable heat affected value; when the precision of the galvanometer system is not enough, the laser cutting position is slightly shifted, the symmetrical range of a heat affected zone is changed, and partial cutting area under a laser cutting path is not cut through. However, there are many reasons why laser-cut sheet material does not cut through, such as: the cutting speed is too fast, the precision of a galvanometer system is not enough, the voltage is unstable, and the focusing lens is damaged and has poor focusing effect. Generally, a cooling device is arranged on the focusing lens, so that the focusing lens is cooled continuously, and the damage of the focusing lens cannot be caused; laser cutting speed and voltage are fixed numerical control parameters, generally can not cause not cut thoroughly because of this problem, can acquire the stable parameter of voltage very easily moreover through voltage monitoring waveform. Therefore, the lack of cut-through of the cutting plate is usually the laser tangent point shift caused by insufficient precision of the galvanometer system.
And theoretical galvanometer system adjusting parameters under a periodic correction period are also prestored in the data acquisition module. The galvanometer system comprises a galvanometer driver, a reflecting mirror and a focusing mirror. Preferably, the galvanometer system adjusting parameters comprise pulse correction parameters and galvanometer angle adjusting parameters. In general, the periodic correction period is half a year or about 3 months.
The data analysis module is used for analyzing the data acquired in the data acquisition module, and firstly needs to analyze the heat affected zone characteristics reflected by the infrared sensor data. Acquiring the heat influence difference between different heat influence areas on each plate according to the data of the infrared sensor, specifically comprising the following steps: the heat affected difference comprises a first heat affected difference and a second heat affected difference; taking the absolute value of the data difference value of the infrared sensors on two sides of the laser cut on the plate as a first heat influence difference; and taking the absolute value of the data difference value of the infrared sensor before and after continuous laser cutting on the plate as a second heat influence difference. It should be noted that the heat influence difference reflects the stability of the cutting task, and when the heat influence difference is 0, it indicates that the laser cutting equipment does not need to adjust the galvanometer system, and the pulse correction parameter and the galvanometer angle adjustment parameter that need to be adjusted by the galvanometer system of the current laser cutting equipment can be determined through the heat influence area. Referring to the prior patent with publication No. CN106425120B, determining the adjustment parameter of the galvanometer system through the grid offset, that is, determining the adjustment parameter of the galvanometer system of the current laser cutting device through the heat affected zone, is a well-known technical means of those skilled in the art, and is not described herein again.
And in the actual use time period, obtaining the chain distance in each sampling period according to the thermal influence difference between different sampling moments in the preset sampling period. It should be noted that the actual usage time period is a time period from a current real-time to a last adjustment end time, and in the embodiment of the present invention, the sampling period is set to 7 days, and the sampling time is set to 1 day. The method for specifically obtaining the chain distance comprises the following steps:
and taking data corresponding to all sampling moments in the actual using time period as a data point, mapping all the data points into a two-dimensional space, wherein the abscissa of a two-dimensional space coordinate system is time, the unit length step length is day, and the ordinate is a corresponding parameter value, and performing normalization processing on all parameter values to eliminate the influence of dimension in order to perform chain distance calculation under the same space coordinate system. Acquiring first heat influence differences and second heat influence differences of all corresponding plates at each sampling moment, selecting the average value of the largest K first heat influence differences as a reference first heat influence difference at the corresponding sampling moment, and selecting the average value of the largest K second heat influence differences as a reference second heat influence difference at the corresponding sampling moment; k is a positive integer greater than 2, and in the embodiment of the invention, K is 10. And acquiring a reference first thermal influence difference distance and a reference second thermal influence difference distance between every two adjacent sampling moments in a sampling period, and accumulating all the reference first thermal influence difference distances and the reference second thermal influence difference distances in one sampling period to acquire a chained distance in the corresponding sampling period. The larger the chain distance is, the more unstable the equipment works in the corresponding sampling period is, so that at least two sampling periods corresponding to the minimum chain distance are selected to obtain the long time sequence length, that is, the long time sequence length is the reference time period of the actual use time period, and the information in the reference time period is taken as the whole analysis information of the actual use time period, thereby reducing the calculation amount and ensuring the accuracy of the subsequent data analysis.
Further obtaining a mean value of structural similarity between different plates under the long-time sequence length according to the plate structural parameters, wherein the specific obtaining method of the structural similarity comprises the following steps:
obtaining the structural similarity between the plates according to a structural similarity formula, wherein the structural similarity formula comprises the following steps:
wherein the content of the first and second substances,
in order to have a structural similarity to each other,
the number of the structural parameters of the plate material A,
the number of the structural parameters of the plate B,
for the nth structural parameter on the plate material a,
is the m-th structural parameter on the plate material B,
and
are similar weights; if the structural parameters on the plate A and the plate B are the same in type, the structural parameters on the plate A and the plate B are the same in type
(ii) a If the structural parameters on the plate A and the plate B are different in type, the structural parameters are different
，
Wherein, in the step (A),
the number of the types of the structural parameters of the plate A,
the number of the structural parameter types of the plate B.
That is, the smaller the mean value of structural similarity is, the more complicated the type of the cut plate material is in the corresponding long-time sequence length, and the greater the possibility of mechanical system deviation caused by the laser cutting equipment is, the less suitable the adjustment of the galvanometer system is.
And acquiring the actual galvanometer system adjusting parameters according to the laser cutting information under the long time sequence length, wherein the laser cutting information is the heat affected zone information acquired in the data acquisition module.
And inputting the actual galvanometer system adjusting parameters and the structure similarity mean value into a pre-trained prediction neural network, and outputting the predicted actual galvanometer system adjusting parameters and the predicted structure similarity mean value at the future moment. The prediction neural network is trained according to a database constructed by the data acquisition module, and can predict the actual adjustment parameters of the galvanometer system and the average value of similarity of the prediction structure at any time in the future on the basis of the database. Obtaining an optimal correction cycle according to the theoretical galvanometer system adjusting parameters, the predicted actual galvanometer system adjusting parameters and the predicted structural similarity mean value, and specifically comprising the following steps of:
setting an objective function:
wherein the content of the first and second substances,
the value of the objective function is,
in order to be a theoretical galvanometer angle parameter,
in order to predict the actual galvanometer angle parameter,
in order to be a theoretical pulse correction parameter,
to predict the actual pulseThe parameters are corrected in such a way that,
the average value of the predicted structural similarity is obtained;
and continuously updating the adjustment parameters of the predicted actual galvanometer system and the similarity of the predicted structure in the objective function, stopping updating when the objective function value reaches the minimum value, and taking the time corresponding to the adjustment parameters of the predicted actual galvanometer system and the similarity of the predicted structure corresponding to the minimum objective function value as the time of the optimal correction period. Namely, the smaller the difference between the adjustment parameter of the predicted galvanometer system and the adjustment parameter of the theoretical galvanometer system is, the larger the average value of the similarity of the predicted structure is, and the more accurate the corresponding time node is taken as the actual correction period is.
Preferably, the prediction neural network is an LSTM network structure, and when the prediction neural network is trained, the objective function is trained as a loss function of the prediction neural network, and an optimal correction period is output. Namely, a network branch is added in the LSTM network, and the network branch is used for outputting the optimal correction period. It should be noted that the LSTM network is a network structure well known to those skilled in the art, and a specific network structure is not described in detail, in the embodiment of the present invention, the LSTM network is trained by using the historical galvanometer system adjustment parameters in the historical database and the historical structure similarity mean as network training data, and a specific training method is still a technical means well known to those skilled in the art and is not described herein again.
The calibration controller maintains the galvanometer system of the laser cutting equipment according to the optimal calibration period, the maintenance period is controlled by the calibration controller, the cutting precision and the self-adaptive adjustment capability of the laser cutting system under a long time sequence can be improved, and the problem of poor laser cutting precision caused by the deviation of the galvanometer system of a single laser cutting system under the limitation of the length of the traditional fixed maintenance period is solved. In the embodiment of the present invention, the galvanometer system is maintained at the time corresponding to the optimal correction period according to the corresponding predicted galvanometer system adjustment parameter, and the specific maintenance means includes but is not limited to: the self-adaptive correction period length of the laser cutting system and the vibration mirror correction parameters corresponding to the correction period length are obtained through the vibration mirror correction module in the light path correction module, the pulse parameters are adjusted by controlling a vibration mirror driver, and the adjusted pulse parameters are used for driving a reflector adjusting roller to adjust the angle of the reflector in the vibration mirror system. Therefore, the self-adaptive adjustment of the angle of the reflector under the self-adaptive correction period length is realized.
In summary, in the embodiments of the present invention, it is considered that the calibration method of the galvanometer system in the existing laser cutting system is manual debugging and periodic calibration, when the working environment of the laser cutting device is different from the type of the workpiece to be cut, the cutting precision of the laser cutting system is insufficient due to mechanical deviation, and the calibration period required by the laser cutting device is different under different conditions such as different cutting contents and different cutting durations. Therefore, the maintenance period of the galvanometer system is controlled by the parameter correction system of the laser cutting machine, so that the laser cutting equipment can be maintained in time, and the self-adaptive adjustment of the galvanometer system by the laser cutting equipment is realized.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. The processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (4)
1. The laser cutting equipment comprises a laser cutting machine body and is characterized by further comprising a laser cutting machine parameter correction system; the parameter correction system of the laser cutting machine comprises a correction controller, a data acquisition module and a data analysis module, wherein the data acquisition module and the data analysis module are in signal connection with the correction controller;
the data acquisition module is used for acquiring a periodic correction period of the laser cutting equipment and theoretical galvanometer system adjusting parameters under the periodic correction period; acquiring infrared sensor data and plate structure parameters on a plate in each cutting process of laser cutting equipment;
the data analysis module is used for acquiring the heat influence difference between different heat influence areas on each plate according to the data of the infrared sensor; in an actual use time period, obtaining a chain distance under each sampling period according to heat influence difference between different sampling moments under a preset sampling period, and selecting at least two sampling periods corresponding to the minimum chain distance to obtain a long time sequence length; obtaining a structural similarity mean value of different plates under a long time sequence length according to the plate structural parameters; acquiring actual galvanometer system adjusting parameters according to laser cutting information under the long time sequence length; inputting the actual galvanometer system adjusting parameters and the structural similarity mean value into a pre-trained prediction neural network, and outputting the predicted actual galvanometer system adjusting parameters and the predicted structural similarity mean value at a future moment; obtaining an optimal correction cycle according to the theoretical galvanometer system adjusting parameters, the predicted actual galvanometer system adjusting parameters and the predicted structural similarity mean value;
the correction controller is used for maintaining a galvanometer system of the laser cutting equipment according to the optimal correction period;
the method for acquiring the structural similarity comprises the following steps:
obtaining the structural similarity between the plates according to a structural similarity formula, wherein the structural similarity formula comprises the following steps:
wherein the content of the first and second substances,
in order to be of structural similarity, the method of the invention,
the number of the structural parameters of the plate material A,
the number of the structural parameters of the plate B,
for the nth structural parameter on the plate material a,
is the m-th structural parameter on the plate material B,
and
are similar weights; if the structural parameters on the plate A and the plate B are the same in type, the structural parameters on the plate A and the plate B are the same in type
(ii) a If the structural parameters on the plate A and the plate B are different in type, the structural parameters are different
，
Wherein, in the process,
the number of the structural parameter types of the plate A,
the number of structural parameter types of the plate B;
the step of obtaining the optimal correction cycle according to the theoretical mirror-vibrating system adjusting parameter, the predicted actual mirror-vibrating system adjusting parameter and the predicted structure similarity mean value comprises the following steps:
the galvanometer system adjusting parameters comprise galvanometer angle parameters and pulse correction parameters; setting an objective function:
wherein the content of the first and second substances,
is the value of the objective function and is,
in order to be a theoretical galvanometer angle parameter,
in order to predict the actual galvanometer angle parameter,
in order to be a theoretical pulse correction parameter,
in order to predict the actual pulse correction parameters,
the average value of the predicted structural similarity is obtained;
and continuously updating the predicted actual galvanometer system adjusting parameters and the predicted structural similarity in the objective function, stopping updating when the objective function value reaches the minimum value, and taking the time corresponding to the predicted actual galvanometer system adjusting parameters and the predicted structural similarity corresponding to the minimum objective function value as the time of the optimal correction period.
2. The laser cutting apparatus of claim 1, wherein said obtaining a difference in heat influence between different heat affected zones on each sheet material comprises:
the heat affected difference comprises a first heat affected difference and a second heat affected difference;
taking the absolute value of the data difference value of the infrared sensors on two sides of the laser cut on the plate as a first heat influence difference; and taking the absolute value of the data difference value of the infrared sensors before and after continuous laser cutting on the plate as a second heat influence difference.
3. The laser cutting device according to claim 2, wherein the obtaining of the chained distance for each sampling period according to the heat influence difference between different sampling moments for a preset sampling period comprises:
acquiring first heat influence differences and second heat influence differences of all corresponding plates at each sampling moment, selecting the average value of the largest K first heat influence differences as a reference first heat influence difference at the corresponding sampling moment, and selecting the average value of the largest K second heat influence differences as a reference second heat influence difference at the corresponding sampling moment; k is a positive integer greater than 2;
and acquiring a reference first thermal influence difference distance and a reference second thermal influence difference distance between every two adjacent sampling moments in a sampling period, and accumulating all the reference first thermal influence difference distances and the reference second thermal influence difference distances in one sampling period to acquire a chained distance in the corresponding sampling period.
4. The laser cutting apparatus of claim 1, wherein the predictive neural network comprises:
the prediction neural network is of an LSTM network structure, and when the prediction neural network is trained, the target function is used as a loss function of the prediction neural network for training, and an optimal correction period is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211250547.8A CN115319311B (en) | 2022-10-13 | 2022-10-13 | Laser cutting equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211250547.8A CN115319311B (en) | 2022-10-13 | 2022-10-13 | Laser cutting equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115319311A CN115319311A (en) | 2022-11-11 |
| CN115319311B true CN115319311B (en) | 2023-03-17 |
Family
ID=83913678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211250547.8A Active CN115319311B (en) | 2022-10-13 | 2022-10-13 | Laser cutting equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115319311B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2804027B2 (en) * | 1987-07-13 | 1998-09-24 | ファナック 株式会社 | Laser output correction method |
| JP3209078B2 (en) * | 1996-03-18 | 2001-09-17 | 三菱電機株式会社 | Laser processing equipment |
| JP3797980B2 (en) * | 2003-05-09 | 2006-07-19 | ファナック株式会社 | Laser processing equipment |
| US7244906B2 (en) * | 2005-08-30 | 2007-07-17 | Electro Scientific Industries, Inc. | Energy monitoring or control of individual vias formed during laser micromachining |
| DE102009038590B4 (en) * | 2009-08-26 | 2017-02-16 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Process for machining workpieces with laser radiation |
| JP6344361B2 (en) * | 2015-10-08 | 2018-06-20 | コニカミノルタ株式会社 | Image forming apparatus and image forming method |
| JP6923484B2 (en) * | 2018-05-15 | 2021-08-18 | ファナック株式会社 | Machining condition adjustment device and machine learning device |
| CN109048082B (en) * | 2018-09-18 | 2021-02-23 | 大族激光科技产业集团股份有限公司 | Distance control method based on Kalman filtering |
| CN112872628B (en) * | 2020-12-24 | 2023-02-21 | 苏州维嘉科技股份有限公司 | Calibration method of laser drilling machine and laser drilling machine adopting same |
-
2022
- 2022-10-13 CN CN202211250547.8A patent/CN115319311B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115319311A (en) | 2022-11-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1260544C (en) | Compatible and accurate calibration method for double eye line structure photo-sensor and implementing apparatus | |
| JP5172041B2 (en) | Laser machining head and method for compensating for changes in the focal position of the laser machining head | |
| EP3462236B1 (en) | Variable focal length lens system with optical power monitoring | |
| CN113741343B (en) | Machine tool double-shaft synchronous control method and system and machine tool | |
| CN116643393B (en) | Microscopic image deflection-based processing method and system | |
| CN111521119B (en) | Casting blank thickness self-adaptive online image acquisition method | |
| CN115319311B (en) | Laser cutting equipment | |
| CN110539309A (en) | Mechanical arm hole-making positioning system and method based on laser alignment and vision measurement | |
| CN113610054A (en) | Underwater structure disease depth detection method, system and device and storage medium | |
| US20210190999A1 (en) | Tunable acoustic gradient lens system utilizing amplitude adjustments for acquiring images focused at different z-heights | |
| US11125967B2 (en) | System and method for calibrating variable focal length lens system using calibration object with planar tilted pattern surface | |
| WO2020165091A1 (en) | Open-loop control system, optical system and method | |
| CN114800049B (en) | Grating ruler processing operation signal error compensation system | |
| CN114131200B (en) | Process control method, system and device for laser-arc hybrid welding | |
| CN102749884B (en) | Light transmission scanning-detecting controlling method for ceramic antenna cover | |
| CN116179840A (en) | Laser surface heat treatment temperature monitoring control system and control method | |
| CN114279311A (en) | GNSS deformation monitoring method and system based on inertia | |
| CN113221452A (en) | Office space temperature prediction system based on distributed optical fiber | |
| DE102020211914A1 (en) | CONTROL, CONTROL SYSTEM AND PROGRAM | |
| CN111709325A (en) | Automatic illumination method for hot rolling heating furnace slab | |
| CN110006630A (en) | Sports equipment is put in position detecting method and high speed based on the sampling of multicycle difference | |
| JP5858265B1 (en) | Reduction control device and reduction control method | |
| CN111250545B (en) | Control system and method for reducing swing steel coil over-thickness rate | |
| CN117780733A (en) | Hydraulic cylinder piston stroke control method and system | |
| CN117406666A (en) | Automatic change digit control machine tool control system |
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 |