CN115255405B - Intelligent control method and system of additive manufacturing equipment - Google Patents

Intelligent control method and system of additive manufacturing equipment Download PDF

Info

Publication number
CN115255405B
CN115255405B CN202211161425.1A CN202211161425A CN115255405B CN 115255405 B CN115255405 B CN 115255405B CN 202211161425 A CN202211161425 A CN 202211161425A CN 115255405 B CN115255405 B CN 115255405B
Authority
CN
China
Prior art keywords
acoustic emission
imf component
additive manufacturing
data point
intelligent control
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
Application number
CN202211161425.1A
Other languages
Chinese (zh)
Other versions
CN115255405A (en
Inventor
张言
陈庆安
石全强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiangguo New Material Technology Jiangsu Co ltd
Original Assignee
Xiangguo New Material Technology Jiangsu Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xiangguo New Material Technology Jiangsu Co ltd filed Critical Xiangguo New Material Technology Jiangsu Co ltd
Priority to CN202211161425.1A priority Critical patent/CN115255405B/en
Publication of CN115255405A publication Critical patent/CN115255405A/en
Application granted granted Critical
Publication of CN115255405B publication Critical patent/CN115255405B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F12/00—Apparatus or devices specially adapted for additive manufacturing; Auxiliary means for additive manufacturing; Combinations of additive manufacturing apparatus or devices with other processing apparatus or devices
    • B22F12/90—Means for process control, e.g. cameras or sensors
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B22—CASTING; POWDER METALLURGY
    • B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
    • B22F10/00—Additive manufacturing of workpieces or articles from metallic powder
    • B22F10/80—Data acquisition or data processing
    • B22F10/85—Data acquisition or data processing for controlling or regulating additive manufacturing processes
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y30/00—Apparatus for additive manufacturing; Details thereof or accessories therefor
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B33—ADDITIVE MANUFACTURING TECHNOLOGY
    • B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
    • B33Y50/00—Data acquisition or data processing for additive manufacturing
    • B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
    • 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
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/25—Process efficiency

Landscapes

  • Chemical & Material Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Materials Engineering (AREA)
  • Manufacturing & Machinery (AREA)
  • Analytical Chemistry (AREA)
  • Automation & Control Theory (AREA)
  • Soundproofing, Sound Blocking, And Sound Damping (AREA)

Abstract

The invention relates to the technical field of intelligent control, in particular to an intelligent control method and system of additive manufacturing equipment, which comprises the following steps: collecting acoustic emission signals of the additive manufacturing equipment; carrying out self-adaptive denoising processing on the acoustic emission signal to obtain a denoised acoustic emission signal; performing characteristic extraction on the denoised acoustic emission signal to obtain an acoustic emission characteristic frequency band; and carrying out intelligent control on the additive manufacturing equipment according to the extracted characteristic frequency band of the real-time acoustic emission signal and the acoustic emission characteristic frequency band. The scheme of the invention can accurately carry out intelligent control on the additive manufacturing equipment according to the acoustic emission signals.

Description

Intelligent control method and system of additive manufacturing equipment
Technical Field
The invention relates to the technical field of intelligent control, in particular to an intelligent control method and system of additive manufacturing equipment.
Background
The selective laser melting technology is a promising metal additive manufacturing technology. In the additive manufacturing process, under the action of laser, metal liquid drops can generate a splashing phenomenon, and the splashing phenomenon can generate larger defects on a final formed product. Therefore, in the additive manufacturing process, the parameters of the processing equipment are adjusted in real time according to the splashing phenomenon accurately detected in real time. And in the process of detecting the splashing phenomenon, the acoustic emission signal sensor is arranged to acquire the acoustic emission signal characteristics of the splashing phenomenon, so that the splashing phenomenon is detected.
In the detected acoustic emission signals, due to the interference of background noise and inherent noise of equipment, relatively large noise can be generated for the acquired acoustic emission signals, and then when the characteristics of the acoustic emission signals are extracted, wrong signal characteristics can be extracted, so that the adjustment of equipment parameters is also wrong. The IMF denoising is performed through an empirical mode algorithm and a mathematical morphology method, however, in the traditional mathematical morphology algorithm, denoising is performed by using a structural element with a fixed size and a self-setting size, and the method can cause the noise removing effect to be poor and simultaneously lose part of useful information.
Disclosure of Invention
In order to solve the above technical problems, an object of the present invention is to provide an intelligent control method and system for an additive manufacturing apparatus, wherein the adopted technical scheme is as follows:
the invention provides an intelligent control method of additive manufacturing equipment, which comprises the following steps:
collecting acoustic emission signals of the additive manufacturing equipment;
carrying out self-adaptive denoising processing on the acoustic emission signal to obtain a denoised acoustic emission signal;
extracting the characteristics of the denoised acoustic emission signals to obtain acoustic emission characteristic frequency bands; and carrying out intelligent control on the additive manufacturing equipment according to the extracted characteristic frequency band of the real-time acoustic emission signal and the acoustic emission characteristic frequency band.
Further, the adaptive denoising process includes:
EMD decomposition is carried out on the collected acoustic emission signals to obtain IMF components;
calculating an abnormal degree value of each IMF component;
and obtaining a self-adaptive structural element according to the abnormal degree value of each data point of each IMF component, and performing self-adaptive morphological operation to obtain the denoised acoustic emission signal.
Further, the degree of abnormality value is:
Figure 442466DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 635550DEST_PATH_IMAGE002
，
Figure 603768DEST_PATH_IMAGE003
denotes the first
Figure 656038DEST_PATH_IMAGE004
First of IMF component
Figure 499229DEST_PATH_IMAGE005
Of a data point
Figure 953344DEST_PATH_IMAGE006
In the neighborhood of
Figure 590999DEST_PATH_IMAGE003
A data point;
Figure 130565DEST_PATH_IMAGE007
denotes the first
Figure 777447DEST_PATH_IMAGE004
First of IMF component
Figure 703378DEST_PATH_IMAGE005
Of a data point
Figure 777513DEST_PATH_IMAGE006
A neighborhood;
Figure 397850DEST_PATH_IMAGE008
denotes the first
Figure 723789DEST_PATH_IMAGE004
Second of IMF component
Figure 247437DEST_PATH_IMAGE005
Of a data point
Figure 367839DEST_PATH_IMAGE006
The number of data points in the neighborhood;
Figure 6631DEST_PATH_IMAGE009
is shown as
Figure 729737DEST_PATH_IMAGE004
First of IMF component
Figure 747371DEST_PATH_IMAGE005
Signal amplitude for a data point;
Figure 428888DEST_PATH_IMAGE010
is shown as
Figure 899184DEST_PATH_IMAGE004
Second of IMF component
Figure 190094DEST_PATH_IMAGE005
Neighborhood of individual data points
Figure 62236DEST_PATH_IMAGE006
Inner first
Figure 914654DEST_PATH_IMAGE003
Signal amplitude for a data point;
Figure 996879DEST_PATH_IMAGE011
denotes the first
Figure 202733DEST_PATH_IMAGE004
Second of IMF component
Figure 319593DEST_PATH_IMAGE005
Time coordinates of the data points;
Figure 218279DEST_PATH_IMAGE012
is shown as
Figure 289266DEST_PATH_IMAGE004
Second of IMF component
Figure 33231DEST_PATH_IMAGE005
Neighborhood of individual data points
Figure 4598DEST_PATH_IMAGE006
Inner first
Figure 933240DEST_PATH_IMAGE003
Time coordinates of the individual data points.
Further, the adaptive structural element is:
Figure 131003DEST_PATH_IMAGE013
in the formula (I), the compound is shown in the specification,
Figure 537713DEST_PATH_IMAGE014
representing the second in the IMF component
Figure 504532DEST_PATH_IMAGE005
An anomaly measure for each data point;
Figure 842891DEST_PATH_IMAGE015
represents a rounding symbol;
Figure 652584DEST_PATH_IMAGE016
indicating a hyper-parameter.
Further, the specific process of the intelligent control of the additive manufacturing equipment is as follows:
respectively extracting acoustic emission characteristic frequency bands of acoustic emission signals of the splashing phenomenon under different laser powers and acoustic emission signals of the splashing phenomenon under different scanning speeds in the additive manufacturing process; and according to the characteristic frequency band extraction of the real-time splash phenomenon acoustic emission signal, comparing the characteristic frequency band extraction with the characteristic frequency band of the splash phenomenon acoustic emission signal acquired under the conditions of different laser powers and different laser scanning speeds, and determining whether the additive manufacturing equipment needs to control and modify the laser power and the scanning speed under the current environment.
The invention further provides an intelligent control system of the additive manufacturing equipment, which comprises a memory and a processor, wherein the processor is used for executing the steps stored by the memory and used for realizing the intelligent control method of the additive manufacturing equipment.
The invention has the beneficial effects that:
the scheme of the invention is to self-adapt the self-adaptive structural element of each data point in each IMF component, to carry out the local neighborhood size in each IMF component by considering the information content contained in each IMF component and the corresponding information distribution, to fully consider the characteristics of each IMF component, to further obtain the abnormal degree value meeting the characteristics of the IMF component, and to better accord with the component characteristic value when carrying out the self-adaptive structural element.
Meanwhile, the self-adaptive structural elements are carried out according to the abnormal degree value of each data point in each IMF component, so that self-adaptation is carried out according to the characteristics of each data point during morphological operation, and the defects that the data information noise removing effect is poor and useful information is lost due to the fact that fixed structural elements are arranged in the traditional mathematical morphology algorithm are 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 embodiments or the description of 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 flowchart of an intelligent control method of an additive manufacturing apparatus of the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the embodiments, structures, features and effects thereof according to the present invention will be described in detail 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 present invention is directed to the following scenarios: in the intelligent control of the additive manufacturing equipment, the characteristic of the splashing phenomenon is detected by collecting the acoustic emission signal, and the intelligent control of the additive manufacturing equipment is carried out according to the characteristic of the acoustic emission signal.
The present invention provides an embodiment of an intelligent control method for an additive manufacturing apparatus, which is shown in fig. 1 and includes the following steps:
step 1, collecting acoustic emission signals of the additive manufacturing equipment.
In this embodiment, an acoustic emission signal acquisition system is installed in the additive manufacturing equipment to acquire acoustic emission signals. Wherein the acoustic emission signal acquisition system specifically includes: the system comprises an acoustic emission signal acquisition sensor, an acoustic emission signal amplifier, a data transmission system, a data analysis system, a bracket and the like.
And 2, carrying out self-adaptive denoising treatment on the acoustic emission signal to obtain a denoised acoustic emission signal.
It should be noted that, in this embodiment, an acoustic emission signal sensor is installed, an acoustic emission signal representing a splash phenomenon in the SLM additive manufacturing process is acquired, and then the equipment parameters are adjusted according to characteristics of the acquired acoustic emission signal. And for the interference of background noise and inherent noise of equipment in the acquired acoustic emission signals, the acquired acoustic emission signals can generate larger noise, and further, when the characteristics of the acoustic emission signals are extracted, wrong signal characteristics can be extracted, so that the adjustment of the equipment parameters is also wrong. Therefore, for the collected acoustic emission signal, denoising of the acoustic emission signal needs to be performed first.
Specifically, the specific process of the adaptive denoising process in this embodiment is as follows:
(1) EMD decomposition is carried out on the collected acoustic emission signals to obtain IMF components;
(2) Calculating an abnormal degree value of each IMF component;
(3) And obtaining a self-adaptive structural element according to the abnormal degree value of each data point of each IMF component, and performing self-adaptive morphological operation to obtain the denoised acoustic emission signal.
In the above embodiment, an Empirical Mode Decomposition (EMD) algorithm is used to decompose the collected acoustic emission signal into a plurality of modal components (IMFs), where each IMF component includes information of an original signal and noise information, and each IMF component is denoised and then is subjected to signal reconstruction, so that the denoised acoustic emission signal can be obtained.
In the embodiment, the IMF denoising is performed by an EMD algorithm and a mathematical morphology method, however, in the traditional mathematical morphology algorithm, denoising is performed by using a self-set structural element with a fixed size, and by the method, part of useful information is lost while the noise removing effect is poor. Therefore, in the scheme, the adaptive structural element of each IMF component is subjected to self-adaptation according to the characteristics of the IMF components, so that the acoustic emission signal is denoised, and the parameter selection of the adaptive structural element is related to the abnormal degree of each data point in each IMF component. The EMD algorithm is a known technique, and is not described in detail in this application.
In the above embodiment, the process of calculating the abnormal degree value of each IMF component is as follows:
in the process of self-adapting the structural element for each IMF component, the size of the structural element of each IMF component is related to the abnormal degree value of each data point of each IMF component, and the larger the abnormal degree value of the data point is, the larger the size of the self-adapting structural element is. The abnormal degree value of each data point in each IMF component is related to the information content contained in the corresponding IMF component, so that the information content and the information distribution of each IMF component need to be calculated first.
According to the priori knowledge, if the acoustic emission signal satisfies the Gaussian distribution, the noise belongs to a small probability event, and obeys 3
Figure 738351DEST_PATH_IMAGE017
Rule that noise is distributed over
Figure 684311DEST_PATH_IMAGE018
Out of range, and therefore from the original signal
Figure 95700DEST_PATH_IMAGE018
The distribution characteristics of the range and the distribution characteristics of each IMF component are similar, if the distribution characteristics of the range and the distribution characteristics of each IMF component are similar, the information content of the corresponding IMF component is higher, namely the information content of the IMF component is higher, the corresponding IMF component is higher, and the distribution characteristics of the range and the distribution characteristics of each IMF component are similar, the information content of the corresponding IMF component is higher, namely the range and the distribution characteristics of each IMF component are similar, the corresponding IMF component is higher, and the range is the second IMF component
Figure 861531DEST_PATH_IMAGE004
Information content of IMF component
Figure 377088DEST_PATH_IMAGE019
And a first step of
Figure 318500DEST_PATH_IMAGE004
The calculation expression of the information distribution degree of each IMF component is as follows:
Figure 494266DEST_PATH_IMAGE020
Figure 888338DEST_PATH_IMAGE021
in the formula (I), the compound is shown in the specification,
Figure 706121DEST_PATH_IMAGE022
represents the first in the original signal
Figure 361094DEST_PATH_IMAGE023
Signal amplitude at each time point;
Figure 114286DEST_PATH_IMAGE024
is shown as
Figure 353244DEST_PATH_IMAGE004
The first in each IMF component
Figure 584505DEST_PATH_IMAGE023
Signal amplitude at each time point;
Figure 359563DEST_PATH_IMAGE025
representing the number of collected data points;
Figure 142712DEST_PATH_IMAGE026
representing signal amplitude
Figure 511376DEST_PATH_IMAGE027
In that
Figure 670962DEST_PATH_IMAGE018
Of the rangeData point of
Figure 910313DEST_PATH_IMAGE028
Of a single data point
Figure 631407DEST_PATH_IMAGE023
Coordinates (time points t on the horizontal axis);
Figure 346422DEST_PATH_IMAGE029
representing signal amplitude
Figure 919486DEST_PATH_IMAGE027
In that
Figure 669136DEST_PATH_IMAGE018
The number of data points within the range;
Figure 669453DEST_PATH_IMAGE030
a signal amplitude mean value representing the original acoustic emission signal data;
Figure 871764DEST_PATH_IMAGE017
a signal amplitude standard deviation representing the raw acoustic emission signal data;
Figure 514098DEST_PATH_IMAGE031
is shown as
Figure 368789DEST_PATH_IMAGE004
Signal amplitude means of data in the individual IMF components;
Figure 930220DEST_PATH_IMAGE032
is shown as
Figure 495194DEST_PATH_IMAGE004
Signal amplitude standard deviations of data in the IMF components;
Figure 534694DEST_PATH_IMAGE033
. Wherein each IMF component is passed between the original signal data
Figure 868723DEST_PATH_IMAGE018
The proportion between data point information in the range represents the degree of representation of information in the original signal in the IMF components, and further the information content of each IMF component is calculated; and calculating the distribution degree through the corresponding points of the characterization information to calculate the distribution degree of the information.
When the abnormal degree value of each data point of each IMF component is calculated, the local abnormal degree value of each data is calculated by adopting an abnormal factor detection algorithm. When calculating the local degree of abnormality value, the size of the local neighborhood of a data point needs to be considered, that is, when calculating the local degree of abnormality value of a certain data point, the local degree of abnormality value needs to be compared with the data point in the neighborhood range of the certain data point. If the information content of the current IMF component is larger, the information content of the IMF component is more, and the corresponding neighborhood range of the current IMF component is larger; if the larger the information distribution degree of the current IMF component is, the closer the useful information distribution of the IMF component is, the larger the neighborhood range of the corresponding current IMF component is. Then the corresponding second
Figure 601056DEST_PATH_IMAGE004
Neighborhood range of individual IMF components
Figure 13845DEST_PATH_IMAGE006
The calculation expression of (a) is:
Figure 732402DEST_PATH_IMAGE034
in the formula (I), the compound is shown in the specification,
Figure 45572DEST_PATH_IMAGE035
denotes the first
Figure 824172DEST_PATH_IMAGE004
The information content of each IMF component;
Figure 488372DEST_PATH_IMAGE036
is shown as
Figure 869674DEST_PATH_IMAGE004
The information distribution degree of each IMF component;
Figure 178296DEST_PATH_IMAGE037
expressing a hyperbolic tangent function, and mapping the degree values of the information content and the information distribution, namely normalizing the calculation result;
Figure 485387DEST_PATH_IMAGE015
represents a rounding symbol;
Figure 246670DEST_PATH_IMAGE038
representing hyper-parameters for adjusting
Figure 431664DEST_PATH_IMAGE039
The overall value can be determined according to the specific implementation situation of an implementer and an empirical reference value can be given
Figure 719425DEST_PATH_IMAGE040
Wherein
Figure 839828DEST_PATH_IMAGE041
Indicating the amount of data of the current signal (i.e. the signal strength
Figure 213041DEST_PATH_IMAGE041
Time point). If the information content of the current IMF component is larger, the information content of the IMF component is more, and the corresponding neighborhood range of the current IMF component is larger; if the larger the information distribution degree of the current IMF component is, the closer the useful information distribution of the IMF component is, the larger the neighborhood range of the corresponding current IMF component is. And calculating an information degree value through the information content degree and the information distribution degree to represent the degree value of the k neighborhood.
For each IMF component calculated according to the above-mentioned steps
Figure 437611DEST_PATH_IMAGE039
And neighborhood, calculating the abnormal degree value of each data point in the IMF component. Wherein the first step
Figure 455245DEST_PATH_IMAGE004
First of IMF component
Figure 136762DEST_PATH_IMAGE005
Abnormal degree value of data point
Figure 607058DEST_PATH_IMAGE014
The calculation expression of (a) is:
Figure 133854DEST_PATH_IMAGE042
Figure 130629DEST_PATH_IMAGE043
in the formula (I), the compound is shown in the specification,
Figure 858414DEST_PATH_IMAGE044
is shown as
Figure 179455DEST_PATH_IMAGE004
First of IMF component
Figure 650887DEST_PATH_IMAGE005
Of a single data point
Figure 767748DEST_PATH_IMAGE006
Second in the neighborhood
Figure 259909DEST_PATH_IMAGE003
A data point;
Figure 970376DEST_PATH_IMAGE007
is shown as
Figure 838975DEST_PATH_IMAGE004
Second of IMF component
Figure 46228DEST_PATH_IMAGE005
Of a data point
Figure 115815DEST_PATH_IMAGE006
A neighborhood;
Figure 172633DEST_PATH_IMAGE008
is shown as
Figure 985868DEST_PATH_IMAGE004
Second of IMF component
Figure 77321DEST_PATH_IMAGE005
Of a single data point
Figure 786651DEST_PATH_IMAGE006
The number of data points in the neighborhood;
Figure 596344DEST_PATH_IMAGE009
is shown as
Figure 305280DEST_PATH_IMAGE004
First of IMF component
Figure 126606DEST_PATH_IMAGE005
Signal amplitude for a data point;
Figure 131471DEST_PATH_IMAGE010
is shown as
Figure 38247DEST_PATH_IMAGE004
Second of IMF component
Figure 317919DEST_PATH_IMAGE005
Neighborhood of individual data points
Figure 852805DEST_PATH_IMAGE006
Inner first
Figure 435096DEST_PATH_IMAGE003
Signal amplitude for a data point;
Figure 455267DEST_PATH_IMAGE011
is shown as
Figure 148417DEST_PATH_IMAGE004
Second of IMF component
Figure 803389DEST_PATH_IMAGE005
The time coordinate of the data points (i.e., the t time points);
Figure 415636DEST_PATH_IMAGE012
denotes the first
Figure 31425DEST_PATH_IMAGE004
First of IMF component
Figure 652899DEST_PATH_IMAGE005
Neighborhood of individual data points
Figure 303323DEST_PATH_IMAGE006
Inner first
Figure 579147DEST_PATH_IMAGE003
The time coordinate of the individual data points (i.e. the t time point). Wherein the degree of abnormality of the data point is related to the data point
Figure 806866DEST_PATH_IMAGE039
Data points in the neighborhood are related, i.e., local outliers. In calculating the degree of abnormality of the data points, it is necessary to consider both the magnitude difference (vertical axis) between the data points and the corresponding time point (horizontal axis) difference.
Figure 841818DEST_PATH_IMAGE014
The larger the size, the first
Figure 205804DEST_PATH_IMAGE004
Of the data point of the IMF componentThe greater the anomaly value, the greater the difference between the data point and its local neighborhood data point, and the greater the anomaly.
In this embodiment, in order to adapt to the adaptive structural element of each data point in each IMF component, the size of the local neighborhood in each IMF component is performed by considering the information amount contained in each IMF component and the corresponding information distribution; the characteristics of each IMF component are fully considered, and then an abnormal degree value meeting the characteristics of the IMF component is obtained, and the abnormal degree value better accords with the characteristic value of the component when a self-adaptive structural element is carried out.
In the foregoing embodiment, in the process of performing the adaptive structural element, the adaptive structural element needs to be performed according to the magnitude of the abnormal degree value of each data point in each IMF component. In the scheme, when each IMF component is denoised by using morphology, the data belongs to one-dimensional signal data, so that the shape of the adaptive structural element is set to be a transverse linear structural element, and at the moment, only the size of the adaptive structural element is required. The size of the adaptive structural element is related to the abnormal degree value of the data point, and the larger the abnormal degree value of the data point is, the larger the corresponding structural element is. Thus, first
Figure 300799DEST_PATH_IMAGE004
Second of IMF component
Figure 750234DEST_PATH_IMAGE005
Size of a structuring element of a data point
Figure 214976DEST_PATH_IMAGE045
The calculation expression of (a) is:
Figure 574413DEST_PATH_IMAGE046
in the formula (I), the compound is shown in the specification,
Figure 964943DEST_PATH_IMAGE014
representing the second in the IMF component
Figure 901675DEST_PATH_IMAGE005
An anomaly measure for each data point;
Figure 278430DEST_PATH_IMAGE015
represents a rounding symbol;
Figure 351428DEST_PATH_IMAGE016
the representation hyperparameter is used for adjusting the value of the whole structural element, and the scheme can give an empirical reference value according to the specific implementation situation of an implementer
Figure 83499DEST_PATH_IMAGE047
。
To this end, the adaptive structuring element size for each data point in each IMF component may be obtained, i.e., the first
Figure 215184DEST_PATH_IMAGE004
The first of IMF components
Figure 254684DEST_PATH_IMAGE005
The adaptive structure element size of each data point is as follows:
Figure 713347DEST_PATH_IMAGE048
。
and performing adaptive morphological operation on each IMF component data according to the acquired adaptive structural elements of all data points of each IMF component, namely performing opening operation and closing operation on all data points of each IMF component by using the corresponding data point adaptive structural elements, further acquiring each denoised IMF component, and performing signal reconstruction. And obtaining the denoised acoustic emission signal.
In the embodiment, the self-adaptive structural element is carried out according to the abnormal degree value of each data point in each IMF component, so that self-adaptation is carried out according to the characteristics of each data point during morphological operation, and the defects that the data information noise removal effect is poor and useful information is lost due to the fact that a fixed structural element is arranged in the traditional mathematical morphology algorithm are overcome.
Step 3, extracting the characteristics of the denoised acoustic emission signal to obtain an acoustic emission characteristic frequency band; and carrying out intelligent control on the additive manufacturing equipment according to the extracted characteristic frequency band of the real-time acoustic emission signal and the acoustic emission characteristic frequency band.
Performing characteristic processing according to the acoustic emission signal of the additive manufacturing equipment subjected to denoising obtained in the last step: and respectively extracting acoustic emission characteristic frequency bands of the acoustic emission signals of the splashing phenomenon under different laser powers and the acoustic emission signals of the splashing phenomenon under different scanning speeds in the additive manufacturing process. And according to the characteristic frequency band extraction of the real-time acoustic emission signals of the splashing phenomenon, comparing the characteristic frequency bands of the acoustic emission signals of the splashing phenomenon, which are acquired under the conditions of different laser powers and different laser scanning speeds, and determining whether the additive manufacturing equipment needs to control and modify the laser power and the scanning speed under the current environment.
The invention also provides an intelligent control system of the additive manufacturing equipment, which comprises a memory and a processor, wherein the processor is used for executing the method embodiment stored by the memory and used for realizing the intelligent control method of the additive manufacturing equipment. Since the above description has been made on the method embodiment of the intelligent control method of the additive manufacturing apparatus, redundant description is not repeated here.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims (3)

1. An intelligent control method of an additive manufacturing apparatus, comprising the steps of:
collecting acoustic emission signals of the additive manufacturing equipment;
carrying out self-adaptive denoising processing on the acoustic emission signal to obtain a denoised acoustic emission signal;
performing characteristic extraction on the denoised acoustic emission signal to obtain an acoustic emission characteristic frequency band; according to the extracted characteristic frequency band of the real-time acoustic emission signal and the acoustic emission characteristic frequency band, intelligent control of the additive manufacturing equipment is performed;
the self-adaptive denoising process comprises the following steps:
EMD decomposition is carried out on the collected acoustic emission signals to obtain IMF components;
calculating an abnormal degree value of each IMF component;
obtaining a self-adaptive structural element according to the abnormal degree value of each data point of each IMF component, and performing self-adaptive morphological operation to obtain a denoised acoustic emission signal;
the degree of abnormality value is:
Figure 392706DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 439159DEST_PATH_IMAGE002
，
Figure 830957DEST_PATH_IMAGE003
is shown as
Figure 311355DEST_PATH_IMAGE004
First of IMF component
Figure 913237DEST_PATH_IMAGE005
Of a data point
Figure 373169DEST_PATH_IMAGE006
In the neighborhood of
Figure 744107DEST_PATH_IMAGE003
A data point;
Figure 896871DEST_PATH_IMAGE007
is shown as
Figure 720470DEST_PATH_IMAGE004
Second of IMF component
Figure 984093DEST_PATH_IMAGE005
Of a single data point
Figure 849018DEST_PATH_IMAGE006
A neighborhood;
Figure 31738DEST_PATH_IMAGE008
denotes the first
Figure 483579DEST_PATH_IMAGE004
Second of IMF component
Figure 409947DEST_PATH_IMAGE005
Of a single data point
Figure 630844DEST_PATH_IMAGE006
The number of data points in the neighborhood;
Figure 250044DEST_PATH_IMAGE009
is shown as
Figure 189181DEST_PATH_IMAGE004
Second of IMF component
Figure 27562DEST_PATH_IMAGE005
Signal amplitude for a data point;
Figure 493178DEST_PATH_IMAGE010
denotes the first
Figure 158646DEST_PATH_IMAGE004
Second of IMF component
Figure 178554DEST_PATH_IMAGE005
Neighborhood of individual data points
Figure 587670DEST_PATH_IMAGE006
Inner first
Figure 783159DEST_PATH_IMAGE003
Signal amplitude for a data point;
Figure 383643DEST_PATH_IMAGE011
is shown as
Figure 422006DEST_PATH_IMAGE004
Second of IMF component
Figure 634812DEST_PATH_IMAGE005
Time coordinates of the data points;
Figure 888070DEST_PATH_IMAGE012
is shown as
Figure 925034DEST_PATH_IMAGE004
First of IMF component
Figure 591639DEST_PATH_IMAGE005
Neighborhood of individual data points
Figure 342557DEST_PATH_IMAGE006
Inner first
Figure 778218DEST_PATH_IMAGE003
Time coordinates of the data points;
the self-adaptive structural element is as follows:
Figure 454924DEST_PATH_IMAGE013
in the formula，
Figure 608825DEST_PATH_IMAGE014
Representing the second of the IMF components
Figure 429014DEST_PATH_IMAGE005
An anomaly measure for each data point;
Figure 312656DEST_PATH_IMAGE015
represents a rounding symbol;
Figure 661729DEST_PATH_IMAGE016
representing a hyper-parameter.
2. The intelligent control method of the additive manufacturing apparatus according to claim 1, wherein a specific process of the intelligent control of the additive manufacturing apparatus is:
respectively extracting acoustic emission characteristic frequency bands of acoustic emission signals of the splashing phenomenon under different laser powers and acoustic emission signals of the splashing phenomenon under different scanning speeds in the additive manufacturing process; and according to the characteristic frequency band extraction of the real-time splash phenomenon acoustic emission signal, comparing the characteristic frequency band extraction with the characteristic frequency band of the splash phenomenon acoustic emission signal acquired under the conditions of different laser powers and different laser scanning speeds, and determining whether the additive manufacturing equipment needs to control and modify the laser power and the scanning speed under the current environment.
3. An intelligent control system for an additive manufacturing apparatus, comprising a memory and a processor, the processor being configured to execute steps of the memory to implement an intelligent control method for an additive manufacturing apparatus as claimed in any one of claims 1-2.
CN202211161425.1A 2022-09-23 2022-09-23 Intelligent control method and system of additive manufacturing equipment Active CN115255405B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211161425.1A CN115255405B (en) 2022-09-23 2022-09-23 Intelligent control method and system of additive manufacturing equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211161425.1A CN115255405B (en) 2022-09-23 2022-09-23 Intelligent control method and system of additive manufacturing equipment

Publications (2)

Publication Number Publication Date
CN115255405A CN115255405A (en) 2022-11-01
CN115255405B true CN115255405B (en) 2022-12-23

Family

ID=83757954

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211161425.1A Active CN115255405B (en) 2022-09-23 2022-09-23 Intelligent control method and system of additive manufacturing equipment

Country Status (1)

Country Link
CN (1) CN115255405B (en)

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI482613B (en) * 2011-12-27 2015-05-01 Ind Tech Res Inst Signal analysis method, method for analyzing ultrasound image, and ultrasound imaging system using the same
CN109000926A (en) * 2018-10-25 2018-12-14 中国计量大学 Rolling bearing sound emission signal characteristic extracting method based on EMD and approximate entropy
CN109682678A (en) * 2018-12-29 2019-04-26 上海工程技术大学 A kind of analysis method of fibrous fracture sound
CN109858109A (en) * 2019-01-14 2019-06-07 北京工业大学 A kind of gear signal noise-reduction method combined based on the EMD of correlation with form singular value decomposition
CN110132403A (en) * 2019-04-02 2019-08-16 天津大学 A kind of vacuum pump vibration signal noise-reduction method based on EEMD and wavelet threshold
CN110926386B (en) * 2019-11-25 2021-12-03 国网吉林省电力有限公司电力科学研究院 Transformer winding ultrasonic detection imaging method based on improved wavelet threshold denoising
CN112432861B (en) * 2020-10-28 2023-04-14 扬州大学 Reinforced concrete beam damage state evaluation method based on acoustic emission waveform analysis
CN113217102A (en) * 2021-05-18 2021-08-06 广西中金岭南矿业有限责任公司 Acoustic emission signal feature extraction method, acoustic emission signal feature identification device and storage medium
CN113657217A (en) * 2021-08-02 2021-11-16 金陵科技学院 Concrete state recognition model based on improved BP neural network
CN113887362B (en) * 2021-09-24 2024-07-02 上海电力大学 Feature extraction method of partial discharge signals
CN114079503B (en) * 2021-10-26 2023-03-28 广东工业大学 CEEMDAN-wavelet threshold denoising method, device and equipment and optical time domain reflectometer

Also Published As

Publication number Publication date
CN115255405A (en) 2022-11-01

Similar Documents

Publication Publication Date Title
CN116955938B (en) Dry-type waste gas treatment equipment monitoring method and system based on data analysis
CN112486097A (en) Cutting platform wear state monitoring method and system based on model algorithm and readable storage medium
CN110717472B (en) Fault diagnosis method and system based on improved wavelet threshold denoising
CN112697887A (en) Ultrasonic detection defect qualitative identification method based on neural network
CN110682159A (en) Cutter wear state identification method and device
CN117454085B (en) Vehicle online monitoring method and system
CN113936132B (en) Method and system for detecting water pollution of chemical plant based on computer vision
CN117493778B (en) On-line monitoring method and system for associated data of water supply and drainage equipment
CN117235652B (en) Steel wire processing environment supervision method and system based on big data
CN112506752A (en) Operation and maintenance method, device and equipment based on time series data trend prediction
CN111814825B (en) Apple detection grading method and system based on genetic algorithm optimization support vector machine
CN117251798A (en) Meteorological equipment anomaly detection method based on two-layer progressive process
CN116383754A (en) On-line monitoring system and method for production of locomotive accessories
CN112631881A (en) Operation and maintenance method, device and equipment based on time series data trend prediction
CN115255405B (en) Intelligent control method and system of additive manufacturing equipment
CN109829902B (en) Lung CT image nodule screening method based on generalized S transformation and Teager attribute
CN114492528A (en) Pulse signal denoising method and device, electronic equipment and storage medium
CN115994870B (en) Image processing method for enhancing denoising
CN115200797B (en) Leakage detection system for zero leakage valve
CN112287835B (en) Blade acoustic signal denoising method based on EWT-SE and wavelet threshold
CN112237433A (en) Electroencephalogram signal abnormity monitoring system and method
CN109541549B (en) Intermittent sampling forwarding interference suppression method based on EMD and sparse signal processing
CN115905809A (en) Offshore strong wind forecasting method based on SVM technology
CN112464948A (en) Natural scene target contour extraction method and system based on bionics
CN114170200B (en) Metal pitting defect degree evaluation method and system based on artificial intelligence

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