CN115122154B - Operation detection and control method of numerical control milling machine for machining metal components - Google Patents
Operation detection and control method of numerical control milling machine for machining metal components Download PDFInfo
- Publication number
- CN115122154B CN115122154B CN202211043747.6A CN202211043747A CN115122154B CN 115122154 B CN115122154 B CN 115122154B CN 202211043747 A CN202211043747 A CN 202211043747A CN 115122154 B CN115122154 B CN 115122154B
- Authority
- CN
- China
- Prior art keywords
- milling machine
- data
- numerical control
- control milling
- window
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B23—MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
- B23Q—DETAILS, COMPONENTS, OR ACCESSORIES FOR MACHINE TOOLS, e.g. ARRANGEMENTS FOR COPYING OR CONTROLLING; MACHINE TOOLS IN GENERAL CHARACTERISED BY THE CONSTRUCTION OF PARTICULAR DETAILS OR COMPONENTS; COMBINATIONS OR ASSOCIATIONS OF METAL-WORKING MACHINES, NOT DIRECTED TO A PARTICULAR RESULT
- B23Q17/00—Arrangements for observing, indicating or measuring on machine tools
- B23Q17/09—Arrangements for observing, indicating or measuring on machine tools for indicating or measuring cutting pressure or for determining cutting-tool condition, e.g. cutting ability, load on tool
-
- 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
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention relates to the field of computer and auxiliary equipment repair, in particular to a method for detecting and controlling the operation of a numerical control milling machine for machining a metal component, which comprises the following steps: acquiring real-time data of key parameters of a numerical control milling machine; constructing a data matrix; coarsening row vectors in a data matrix, and sequencing each row of data in the coarsely-grained matrix to obtain a reconstructed data matrix; carrying out sliding window detection on row vectors in the reconstructed data matrix, and obtaining window descriptors of each sliding window by utilizing data in each sliding window; and obtaining monitoring indexes of each key parameter of the numerical control milling machine by using the types and the numbers of window descriptors in each row vector in the reconstructed data matrix, controlling the running state of the numerical control milling machine according to the monitoring indexes, and regulating and controlling the cutter of the numerical control milling machine by using the monitoring vectors of the metal member machining cutter. The method is used for detecting and controlling the operation of the numerical control milling machine, and can improve the real-time performance of the operation detection and control.
Description
Technical Field
The invention relates to the field of computer and auxiliary equipment repair, in particular to an operation detection and control method of a numerical control milling machine for machining metal components.
Background
A numerical control machine is an automatic machine equipped with a program control system, and has become one of important marks for measuring the level of manufacturing industry in one country. The numerical control milling machine is mainly used for processing metal products and the like. With the development of production technology, the requirements of users on the performance and the precision of products are higher and higher, and the requirements on the production efficiency are also higher and higher. Therefore, in order to ensure the production efficiency of the numerically controlled milling machine, it is necessary to detect the operation state of the numerically controlled milling machine.
At present, most of detection on the running state of the numerical control milling machine is carried out by related operators at regular intervals or in the working process. However, the detection method has no real-time property, is extremely easy to generate a missing detection condition, can not regulate and control the running state of the numerical control milling machine in real time, and has low detection coverage rate. Aiming at the problems, the invention provides a method for detecting and controlling the operation of a numerical control milling machine for processing metal components, which repairs the numerical control milling machine by using a computer and auxiliary equipment so as to automatically control and adjust the operation state of the numerical control milling machine in the processing process of the metal components.
Disclosure of Invention
The invention provides a method for detecting and controlling the operation of a numerical control milling machine for processing metal components, which comprises the following steps: acquiring real-time data of key parameters of a numerical control milling machine; constructing a data matrix; coarsening row vectors in a data matrix, and sequencing each row of data in the coarsely-grained matrix to obtain a reconstructed data matrix; carrying out sliding window detection on row vectors in the reconstructed data matrix, and obtaining window descriptors of each sliding window by utilizing data in each sliding window; the invention builds a data matrix through the operation data of each key parameter of the numerical control milling machine in the metal component processing process, analyzes the data matrix, acquires the monitoring index of each key parameter, detects the operation condition of each key parameter of the numerical control milling machine in the metal processing process in real time, carries out early warning regulation and control on each key parameter based on the monitoring matrix, avoids the occurrence of accidents in the metal processing process, simultaneously judges the cutter condition in the metal processing process based on the characteristic parameters of the surface image of the cut finished metal component, detects the cutter condition so as to prompt staff to regulate and control the cutter, changes the cutter and the like.
In order to achieve the purpose, the invention adopts the following technical scheme that the operation detection method of the numerical control milling machine for processing the metal component comprises the following steps:
and acquiring real-time data of key parameters of the numerical control milling machine for machining the metal component.
And constructing a data matrix by utilizing real-time data of key parameters of the numerical control milling machine.
Coarsely granularity is carried out on each row vector in the data matrix, and the data in each row vector in the coarsely granularity data matrix is ordered to obtain a reconstructed data matrix.
And carrying out sliding window detection on each row vector in the reconstructed data matrix, and calculating window descriptors of each sliding window by using data in each sliding window.
And calculating the monitoring index of each key parameter of the numerical control milling machine by using the variety number of window descriptors in each row vector in the reconstructed data matrix and the number of various window descriptors.
Further, the operation detection method of the numerical control milling machine for processing the metal component comprises the following steps of:
the data interval is set, and each row vector in the data matrix is divided into a plurality of sequences according to the data interval.
And calculating the average value of each sequence in each row vector to obtain the sequence characterization value of each sequence in each row vector.
And constructing a coarse-grained data matrix by using the sequence characterization values of the sequences in each row vector.
And sequencing each data in the coarse-grained data matrix according to the sequence from large to small to obtain a reconstructed data matrix.
Further, according to the operation detection method of the numerical control milling machine for machining the metal component, the expression of the window descriptor of each sliding window is as follows:
in the method, in the process of the invention,window descriptor for the d-th sliding window,>for the amount of data in the sliding window, +.>For the (r) th data in the window sequence corresponding to sliding window d, <>Is the standard deviation of the data in sliding window d, +.>Is an abnormality factor of data r, +.>Standard parameter data are set for the people of key parameters in normal operation.
Further, according to the operation detection method of the numerical control milling machine for machining the metal component, the monitoring index of each key parameter of the numerical control milling machine is obtained in the following manner:
all window descriptors of each row vector in the reconstructed data matrix are acquired.
The number of various window descriptors in all window descriptors of each row vector is counted.
And calculating the monitoring index of each key parameter of the numerical control milling machine by using the variety and the number of the window descriptors in each row vector.
Further, according to the operation detection method of the numerical control milling machine for machining the metal component, the expression of the monitoring index of each key parameter of the numerical control milling machine is as follows:
in the method, in the process of the invention,monitoring index of ith key parameter of numerically controlled milling machine, < +.>For the number of window descriptor types in the row vector corresponding to the ith key parameter, +.>For the number of c-th window descriptors in the row vector corresponding to the i-th key parameter,/th window descriptor>Is the c-th window descriptor.
The invention also provides a running control method of the numerical control milling machine for processing the metal component, wherein the running state of the numerical control milling machine for processing the metal component is controlled by the monitoring index of each key parameter of the numerical control milling machine.
Further, the operation control method of the numerical control milling machine for processing the metal component comprises the following steps of:
and constructing a monitoring matrix by using the monitoring index of each key parameter of the numerical control milling machine.
And numbering each key parameter.
Setting a threshold value, and judging the data in the monitoring matrix: when the data in the monitoring matrix is higher than the threshold value, the key parameters corresponding to the numbers are subjected to early warning and alarming, and workers are prompted to regulate and control the key parameters.
Further, the operation control method of the numerical control milling machine for machining the metal component further comprises the following steps:
and acquiring a cutting surface image of the machined metal component.
And performing color space conversion on the cut surface image to obtain a brightness channel component image.
And performing super-pixel segmentation on the brightness channel component image, and calculating the brightness index of each super-pixel block by using the brightness values of each pixel point and the central pixel point in each super-pixel block.
And acquiring the brightness distribution index of the cutting surface by using the brightness index of each super pixel block.
And performing edge detection on the cut surface image, and performing Hough straight line detection on the obtained edge image to obtain a straight line segment in the edge image.
And calculating the grain index of the cutting surface by using the horizontal interval between two adjacent straight line sections in the edge image, the length of each straight line section and the number of the straight line sections.
And obtaining a monitoring vector of the metal member processing cutter according to the brightness distribution index and the grain index of the cutting surface.
And regulating and controlling the cutter of the numerical control milling machine for machining the metal component by utilizing the monitoring vector of the cutter for machining the metal component.
The invention has the beneficial effects that:
the invention constructs a data matrix through the operation data of each key parameter of the numerical control milling machine in the metal component processing process, analyzes the data matrix, acquires the monitoring index of each key parameter, detects the operation condition of each key parameter of the numerical control milling machine in the metal processing process in real time, carries out early warning regulation and control on each key parameter based on the monitoring matrix, avoids accidents in the metal processing process, and simultaneously judges the cutter condition in the metal processing process based on the characteristic parameters of the surface image of the cut finished metal component, and detects the cutter condition so as to prompt a worker to regulate and control the cutter, change the cutter and the like.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for detecting and controlling operation of a numerical control milling machine for processing metal components according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Examples
In order to realize the content of the invention, the embodiment designs a method for detecting and controlling the operation of a numerical control milling machine for processing metal components. The embodiment is suitable for operation detection control of the numerical control milling machine in the metal cutting process.
The embodiment of the invention provides a method for detecting and controlling the operation of a numerical control milling machine for processing metal components, which is shown in fig. 1 and comprises the following steps:
s101, acquiring each parameter data and image data.
The system built by the embodiment is used for performing virtual assembly and test in a virtual machine tool model, controlling a numerical control milling machine in the metal machining process, and then performing real-time regulation and control on the numerical control milling machine in the actual metal machining process. Firstly, the embodiment acquires data through various sensors and other devices, and acquires data information of various key parameters of the numerical control milling machine in the metal processing process. The key parameters in the running process of the numerical control milling machine are many: the extraction implementation of specific key parameters such as the running speed, the motor temperature, the power and the spindle rotating speed can be selected by the user according to actual conditions, the number of the key parameters is recorded as N, and the data are acquired in real time through corresponding data acquisition sensors and other devices so as to acquire each data condition in the running process of the metal processing numerical control milling machine. The time interval for detecting and regulating the key parameters of the numerical control milling machine is A, namely data acquisition is carried out every A time, and the data acquisition is specifically as follows: and (3) analyzing the corresponding key parameters based on the M data acquired in the t time period, detecting the running condition of the key parameters, and carrying out real-time early warning on the key parameters with abnormal risks based on the analysis result so as to enable related staff to carry out corresponding regulation and control in time.
Meanwhile, in order to ensure that the processed metal meets the enterprise requirement, the embodiment performs image acquisition on the metal in the processing process through the image acquisition equipment, and realizes the regulation and control on the running state based on the surface image characteristic parameters of the processed metal.
So far, the method can acquire real-time data of each key parameter in the metal processing process according to the method of the embodiment, and is used for automatically regulating and controlling the numerical control milling machine in the metal member processing process.
S102, constructing a data matrix.
After data of each key parameter is acquired through data acquisition equipment such as a sensor, a plurality of real-time data are acquired for each parameter and used for analyzing and regulating the working state of the key parameter, in order to avoid the problems of singleness of data analysis, large data size, inaccuracy in analysis and the like, a data matrix is constructed, each key parameter of the numerical control milling machine in the metal processing process is analyzed based on the data matrix, and the parameters with abnormal risks are monitored and regulated in real time. The data matrixThe method comprises the following steps:
wherein N is the number of key parameters, M is the data volume acquired by the parameters, and the data information of each key parameter of the numerical control milling machine in the metal processing process can be acquired by acquiring each key parameter in real time, so that a corresponding data matrix is obtained and used for detecting and analyzing the running state of the numerical control milling machine.
S103, acquiring a coarse-grained data matrix.
After the data matrix is constructed, the running detection model of the numerical control milling machine is constructed and is used for quickly and accurately detecting the running state of the numerical control milling machine in the metal processing process, and meanwhile, the automatic regulation and control of the parameters of the numerical control milling machine in the metal processing process can be realized. The numerical control milling machine operation detection model specifically comprises the following steps:
firstly, for the data matrix, the present embodiment analyzes the row vectors to extract the key parameter operation index initially, coarsely granularizes the row vectors, sets the data interval T (where M is an integer multiple of T), and then divides each row vector intoThe sequences are specifically:
wherein, the liquid crystal display device comprises a liquid crystal display device,. Then, the present embodiment will construct a coarse-grained data matrix based on this, and take the mean value of each sequence as the sequence characterization value of the sequence, for example: />So far, the sequence characterization value of each sequence can be obtained, and a data matrix after coarse granularity is constructed: />The method can effectively reduce the calculated amount of the system, refine detail components in the coarse granularity process of the data, and accurately analyze the condition of key parameters when the data are less.
S104, acquiring a reconstruction data matrix.
Then, analyzing the coarse-grained data matrix, and arranging the data in the coarse-grained data matrix from large to small to obtain a reconstructed data matrix。
S105, acquiring a window descriptor.
For reconstructing the data matrix, the present embodiment will set a sliding window, and reconstructAnd carrying out sliding window analysis on each row vector in the data matrix, obtaining descriptors of each window, and detecting the distribution condition of the row vector data. The sliding window size is 1The step size is 3,W and the implementation can be set according to the actual situation, the implementation is set to w=5, window data can be obtained based on sliding windows, each window data corresponds to a window sequence, the number of window sequences obtained after each row of vector sliding window is recorded as W, then window descriptors are built based on the data in each window sequence, and the data in the windows are analyzed, wherein the window descriptors specifically are as follows:
in the method, in the process of the invention,for the descriptor of the d-th window, +.>For the amount of data in the window, +.>For the (r) th data in the window sequence corresponding to window d,/v>Is the standard deviation of the data within window d, +.>Is an anomaly factor of the data r to highlight the influence degree of the anomaly data in the corresponding window sequence, ++>Manually setting standard parameters for corresponding key parameters in normal operationData.
S106, acquiring key parameter monitoring indexes.
According to the method, w window descriptors can be obtained from the row vectors to form a window descriptor set, the data distribution condition in the row vectors is analyzed based on the window descriptor set of the row vectors, and the occurrence times of each window descriptor in the window descriptor set are countedAnd detecting the distribution condition of the row vector data based on the detection, and establishing key parameter monitoring indexes:
in the method, in the process of the invention,for the number of classes of window descriptors in the window descriptor subset corresponding to the ith row vector,/for the window descriptor subset corresponding to the ith row vector>For the number of occurrences of the c-th window descriptor in the window descriptor subset,/th window descriptor>For the c-th window descriptor, +.>For the monitoring index of the ith row vector (i.e. the ith key parameter), normalizing the index to ensure that the function value is in [0,1 ]]The larger the index value is, the lower the data regularity in the row vector is, and the more abnormal data is.
S107, acquiring a monitoring matrix.
Thus, according to the method of the present embodiment, the state of the M data acquired by each key parameter in the t period can be obtained, the monitoring index of each key parameter is obtained, and the corresponding monitoring matrix is established：，/>The monitoring matrix is used for detecting and analyzing the states of all key parameters of the numerical control milling machine in the metal processing process.
S108, acquiring brightness distribution indexes of the cutting surfaces of the metal members.
Considering that the cutter of the milling machine repeatedly cuts and processes the metal component for a long time, the conditions such as cutter looseness, cutter angle change and the like are very easy to cause (in the embodiment, the initial state of the cutter is that one side of a cutter edge is vertical downwards), the cut metal surface is not smooth enough, and a large cutting problem exists, therefore, in order to accurately regulate and control the numerical control milling machine in the metal processing process, the processing precision and quality of the metal component are ensured, the embodiment is based on the image acquisition equipment to acquire the cutting surface of the metal component after cutting of the numerical control milling machine so as to extract the surface characteristic information of the metal component after cutting treatment, and based on the condition, the cutter angle of the numerical control milling machine is regulated and controlled in a self-adaptive manner, and the surface characteristic parameter extraction process of the metal component is as follows:
a) Considering that when the angle of the cutter changes, the cutting surface of the metal member is uneven, the surface visual information of the metal member will change in the process of collecting the cutting surface image based on the image collecting equipment due to the factors of light reflection and the like, and the phenomenon of uneven surface brightness exists, therefore, the embodiment firstly carries out color space conversion on the cutting surface image data to obtain a brightness channel component image, and the brightness channel component image is divided into K super-pixel blocks through a super-pixel segmentation algorithm so as to reduce the calculated amount of the system and improve the detection speed;
b) For each super pixel block, the embodiment analyzes the brightness distribution condition of the super pixel block, constructs a super pixel block brightness index model, and obtains the brightness index:
in the method, in the process of the invention,is an indicator of the brightness of the super pixel block k, +.>For the number of pixels contained in the super pixel block k, is->Is the center point of the super pixel block, +.>Representing the spatial Euclidean distance between pixel point p and superpixel block center point o, < ->For the luminance value of pixel p +.>The luminance value of the center point o of the super pixel block k. />Is the weighting factor of the pixel point p.
Acquiring brightness indexes of each super pixel block based on the method to obtain a brightness index set corresponding to the imageThen, the present embodiment will build a metal member cut surface brightness distribution model:
in the method, in the process of the invention,for model parameters greater than zero, the present embodiment is set to +.>，/>For the mean value of the brightness index set, K is the number of super pixel blocks, < >>Is an indicator of the brightness of the super pixel block k, +.>Is used as the brightness distribution index of the cutting surface and normalized to make the function value be in the range of 0,1]The greater the model function value, the more uneven the surface brightness distribution of the cut surface of the metal member is considered, and the higher the possibility of inclination of the cutter angle of the numerically controlled milling machine is considered.
S109, obtaining grain indexes of the cutting surface of the metal component.
c) Meanwhile, considering that when the cutter of the numerical control milling machine loosens and the like, the cutter will cause a clamping phenomenon in the metal cutting process, so that a large number of linear clamping lines appear on the surface of the cut metal member, in the embodiment, an edge image of the cutting surface of the metal member is obtained through an edge detection algorithm, each straight line segment in the edge image is further obtained through Hough straight line detection, the detected straight line segment set is recorded as U, the number of the straight line segments in the image is counted and recorded as Q, and the length of each straight line segment is obtainedMeanwhile, in order to accurately analyze the loosening condition of the cutter, the embodiment is to add the interval between the adjacent straight line segments in the edge image ∈>Analysis is performed (i.e.)>Representing the horizontal interval between two straight line sections adjacent to a and b, wherein the larger the interval is, the more serious the condition of loosening the cutter is considered;
d) So far, can draw the line characteristic information of metal cutting face according to c) the process, detect the metal component cutting face katon line based on this, establish cutting face line analytical model:
the grain index representing the metal cutting surface is normalized, and the value of the guarantee function is in [0,1]The higher the function value, the higher the possibility of tool wobble, looseness, and the more serious the looseness is considered during the metal cutting process. />Represents the horizontal interval between two adjacent straight line segments of a and b, Q is the number of straight line segments in the image, < >>Is the length of the q-th straight line segment.
The texture information of the cutting surface of the metal component is characterized based on the texture information, and the texture information is used for detecting the cutter condition of the milling machine.
S110, establishing a cutter monitoring vector.
e) Based on the extracted feature parameters of the cutting face of the metal component, the embodiment establishes a cutter monitoring vector:for numerical control in the process of processing metal componentsAnd monitoring the milling machine tool in real time.
Thus, the characteristic parameters of the cutting surface of the metal component are extracted.
S111, regulating and controlling the numerical control milling machine.
According to the steps, the operation conditions of key parameters of the numerical control milling machine in the metal member processing process can be obtained, and meanwhile, characteristic parameters of the surface of the metal member after cutting is finished can be obtained and used for detecting the cutter conditions of the numerical control milling machine in the metal processing process.
Firstly, the monitoring matrix according to the embodiment can monitor the operation state of each key parameter in the metal processing process in real time, and the monitoring matrix is used for monitoring the operation state of each key parameter in the metal processing processThe system carries out real-time prompt and early warning on each key parameter, and for a key parameter monitoring matrix, the embodiment sets a monitoring threshold (0.75) and numbers each key parameter so that an operator can intuitively know the state information of each key parameter, and when the data existing in the monitoring matrix is higher than the monitoring threshold, the system carries out early warning and alarm on the corresponding key parameter number to prompt the operator to regulate, control and detect the corresponding key parameter, thereby avoiding the problem of safety accidents of a data milling machine in the metal processing process.
Then, for the extracted surface characteristic parameters of the machined metal component, the embodiment detects and adjusts the condition of the tool in the machining process based on the tool monitoring vector H, and the embodiment sets: in this embodiment, the threshold value setting is performed on the cutter monitoring vector data, when the data is higher than the preset value (0.5), the numerical control milling machine cutter in the metal processing process is considered to have a problem, the system broadcasts the number in the cutter monitoring vector, wherein 1 represents the cutter angle deviation early warning, 2 represents the cutter loosening early warning, the numerical control milling machine cutter is timely regulated and controlled and overhauled based on prompting related operators, so as to ensure the metal processing quality, the numerical control milling machine cutter condition is detected in real time based on the detection, and the related operators are timely prompted to regulate the numerical control milling machine cutter based on the detection, so that the workload of manual detection can be reduced, and the instantaneity is increased.
The beneficial effects of this embodiment lie in:
according to the embodiment, the data matrix is constructed through the operation data of each key parameter of the numerical control milling machine in the metal component machining process, the data matrix is analyzed, the monitoring index of each key parameter is obtained, the operation condition of each key parameter of the numerical control milling machine in the metal machining process is detected in real time, the pre-warning regulation and control are carried out on each key parameter based on the monitoring matrix, the occurrence of accidents in the metal machining process is avoided, meanwhile, the cutter condition in the metal machining process is judged based on the characteristic parameters of the surface image of the cut metal component, the cutter condition is detected, so that workers are prompted to regulate and control the cutter, replace the cutter and the like.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (7)
1. The operation detection method of the numerical control milling machine for machining the metal component is characterized by comprising the following steps of:
acquiring real-time data of key parameters of a numerical control milling machine for machining the metal component;
constructing a data matrix by utilizing real-time data of key parameters of the numerical control milling machine;
coarsely granularity is carried out on each row vector in the data matrix, and the data in each row vector in the coarsely granularity data matrix is sequenced to obtain a reconstructed data matrix;
carrying out sliding window detection on each row vector in the reconstructed data matrix, and calculating to obtain a window descriptor of each sliding window by utilizing data in each sliding window;
calculating the type number of window descriptors in each row vector in the reconstruction data matrix and the number of various window descriptors to obtain the monitoring index of each key parameter of the numerical control milling machine;
collecting a cutting surface image of a metal member after processing;
performing color space conversion on the cut surface image to obtain a brightness channel component image;
performing super-pixel segmentation on the brightness channel component image, and calculating brightness indexes of each super-pixel block by using brightness values of each pixel point and the central pixel point in each super-pixel block;
acquiring brightness distribution indexes of the cutting surface by utilizing the brightness indexes of each super pixel block;
performing edge detection on the cut surface image, and performing Hough straight line detection on the obtained edge image to obtain a straight line segment in the edge image;
calculating to obtain a grain index of the cutting surface by using the horizontal interval between two adjacent straight line sections in the edge image, the length of each straight line section and the number of the straight line sections;
acquiring a monitoring vector of a metal member processing cutter according to the brightness distribution index and the grain index of the cutting surface;
and regulating and controlling the cutter of the numerical control milling machine for machining the metal component by utilizing the monitoring vector of the cutter for machining the metal component.
2. The method for detecting the operation of a numerical control milling machine for machining metal components according to claim 1, wherein the reconstructed data matrix is obtained in the following manner:
setting a data interval, and dividing each row vector in a data matrix into a plurality of sequences according to the data interval;
calculating the average value of each sequence in each row vector to obtain a sequence characterization value of each sequence in each row vector;
constructing a coarse-granularity data matrix by using sequence characterization values of sequences in each row vector;
and sequencing each data in the coarse-grained data matrix according to the sequence from large to small to obtain a reconstructed data matrix.
3. The method for detecting the operation of a numerical control milling machine for machining metal components according to claim 1, wherein the window descriptor of each sliding window has the following expression:
in the method, in the process of the invention,window descriptor for the d-th sliding window,>for the amount of data in the sliding window, +.>For the (r) th data in the window sequence corresponding to sliding window d, <>Is the standard deviation of the data in sliding window d, +.>Is an abnormality factor of data r, +.>Standard parameter data are set for the people of key parameters in normal operation.
4. The method for detecting the operation of the numerical control milling machine for machining metal components according to claim 1, wherein the monitoring index of each key parameter of the numerical control milling machine is obtained in the following manner:
acquiring all window descriptors of each row vector in a reconstruction data matrix;
counting the number of various window descriptors in all window descriptors of each row vector;
and calculating the monitoring index of each key parameter of the numerical control milling machine by using the variety and the number of the window descriptors in each row vector.
5. The method for detecting the operation of a numerically controlled milling machine for processing metal components according to claim 1 or 4, wherein the expression of the monitoring index of each key parameter of the numerically controlled milling machine is as follows:
in the method, in the process of the invention,monitoring index of ith key parameter of numerically controlled milling machine, < +.>For the number of window descriptor types in the row vector corresponding to the ith key parameter, +.>For the number of c-th window descriptors in the row vector corresponding to the i-th key parameter,/th window descriptor>Is the c-th window descriptor.
6. An operation control method of a numerical control milling machine for processing metal components, characterized in that the operation state of the numerical control milling machine for processing metal components is controlled according to the monitoring index of each key parameter of the numerical control milling machine according to any one of claims 1 to 5.
7. The method for controlling the operation of a numerically controlled milling machine for machining metal parts according to claim 6, wherein the process for controlling the operation state of the numerically controlled milling machine for machining metal parts is specifically as follows:
constructing a monitoring matrix by using the monitoring index of each key parameter of the numerical control milling machine;
numbering each key parameter;
setting a threshold value, and judging the data in the monitoring matrix: when the data in the monitoring matrix is higher than the threshold value, the key parameters corresponding to the numbers are subjected to early warning and alarming, and workers are prompted to regulate and control the key parameters.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211043747.6A CN115122154B (en) | 2022-08-30 | 2022-08-30 | Operation detection and control method of numerical control milling machine for machining metal components |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211043747.6A CN115122154B (en) | 2022-08-30 | 2022-08-30 | Operation detection and control method of numerical control milling machine for machining metal components |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115122154A CN115122154A (en) | 2022-09-30 |
| CN115122154B true CN115122154B (en) | 2023-08-18 |
Family
ID=83388114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211043747.6A Active CN115122154B (en) | 2022-08-30 | 2022-08-30 | Operation detection and control method of numerical control milling machine for machining metal components |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115122154B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324139A (en) * | 2013-06-07 | 2013-09-25 | 华中科技大学 | Numerical control machine tool milling tool breakage monitoring method |
| CN106650770A (en) * | 2016-09-29 | 2017-05-10 | 南京大学 | Mura defect detection method based on sample learning and human visual characteristics |
| CN112365468A (en) * | 2020-11-11 | 2021-02-12 | 南通大学 | AA-gate-Unet-based offshore wind power tower coating defect detection method |
| CN113569903A (en) * | 2021-06-09 | 2021-10-29 | 西安电子科技大学 | Method, system, equipment, medium and terminal for predicting abrasion of numerical control machine tool cutter |
| CN114239810A (en) * | 2021-12-21 | 2022-03-25 | 华中科技大学 | Milling cutter wear prediction method based on improved PCANet model |
| CN114581805A (en) * | 2022-03-18 | 2022-06-03 | 上海宝振自动化工程有限公司 | Coating roller surface defect detection method adopting 3D line laser profile technology |
| CN114800041A (en) * | 2022-05-06 | 2022-07-29 | 嘉兴南湖学院 | Cutter state monitoring method and monitoring device thereof |
| CN114842017A (en) * | 2022-07-06 | 2022-08-02 | 济宁市海富电子科技有限公司 | HDMI cable surface quality detection method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9098917B2 (en) * | 2012-07-19 | 2015-08-04 | Samsung Electronics Co., Ltd. | Method and system for accelerating collision resolution on a reconfigurable processor |
-
2022
- 2022-08-30 CN CN202211043747.6A patent/CN115122154B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103324139A (en) * | 2013-06-07 | 2013-09-25 | 华中科技大学 | Numerical control machine tool milling tool breakage monitoring method |
| CN106650770A (en) * | 2016-09-29 | 2017-05-10 | 南京大学 | Mura defect detection method based on sample learning and human visual characteristics |
| CN112365468A (en) * | 2020-11-11 | 2021-02-12 | 南通大学 | AA-gate-Unet-based offshore wind power tower coating defect detection method |
| CN113569903A (en) * | 2021-06-09 | 2021-10-29 | 西安电子科技大学 | Method, system, equipment, medium and terminal for predicting abrasion of numerical control machine tool cutter |
| CN114239810A (en) * | 2021-12-21 | 2022-03-25 | 华中科技大学 | Milling cutter wear prediction method based on improved PCANet model |
| CN114581805A (en) * | 2022-03-18 | 2022-06-03 | 上海宝振自动化工程有限公司 | Coating roller surface defect detection method adopting 3D line laser profile technology |
| CN114800041A (en) * | 2022-05-06 | 2022-07-29 | 嘉兴南湖学院 | Cutter state monitoring method and monitoring device thereof |
| CN114842017A (en) * | 2022-07-06 | 2022-08-02 | 济宁市海富电子科技有限公司 | HDMI cable surface quality detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115122154A (en) | 2022-09-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DE102017011290B4 (en) | Machine learning apparatus, CNC apparatus and machine learning method for detecting an indication of chatter occurrence in a machine tool tool | |
| CN110587377B (en) | Method for monitoring defects of milling cutter on line | |
| CN109766334B (en) | Processing method and system for online monitoring abnormal data of power equipment | |
| CN108490880B (en) | Method for monitoring wear state of cutting tool of numerical control machine tool in real time | |
| CN113255795A (en) | Equipment state monitoring method based on multi-index cluster analysis | |
| CN113369979B (en) | Online monitoring numerically controlled lathe cooling system based on cloud computing | |
| CN109909804A (en) | Tool breakage and abrasion on-line monitoring method based on main shaft drives electric current and work step | |
| CN109739183B (en) | Large-scale digit control machine tool fault monitoring system based on multisensor | |
| WO2015021751A1 (en) | Data-driven exception warning technical method for integrated circuit technology device | |
| CN106845826B (en) | PCA-Cpk-based cold continuous rolling production line service quality state evaluation method | |
| CN105302123A (en) | Online data monitoring method | |
| US7916140B2 (en) | Method and a system for operating a controllable multi-variable process | |
| CN115122154B (en) | Operation detection and control method of numerical control milling machine for machining metal components | |
| CN115471503A (en) | Equipment abnormity detection method for numerical control ingot splitting machine | |
| CN101625564B (en) | Method and system for automatic control and automatic warning | |
| US8380328B2 (en) | Method and system for monitoring and controlling a multi-variable process throughout a plurality of distinct phases of the process | |
| CN107093568B (en) | Method and device for on-line monitoring of crystal element | |
| CN116690313B (en) | Failure monitoring method for machining cutter of web plate of aircraft structural member | |
| CN117309042A (en) | Intelligent manufacturing data real-time monitoring method and system based on Internet of things technology | |
| CN115562163B (en) | Real-time monitoring system based on numerical control machine tool parameter data | |
| CN111444471A (en) | Cable production quality abnormity detection method and system based on multivariate Gaussian distribution | |
| CN111158338A (en) | Chemical risk monitoring method based on principal component analysis | |
| CN111850892B (en) | Method and device for realizing abnormal alarm in dyeing process of overflow dyeing machine | |
| CN113627885A (en) | Power grid power supply abnormity monitoring system and monitoring method thereof | |
| CN107515596B (en) | Statistical process control method based on image data variable window defect monitoring |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230717 Address after: 523000 Building 1, No. 3 Rongfeng street, Chang'an Town, Dongguan City, Guangdong Province Applicant after: Guangdong Zhaoming Electronic Group Co.,Ltd. Address before: No. 135, Yanxin Road, Yudong Town, Haimen District, Nantong City, Jiangsu Province, 226000 Applicant before: Nantong Haimen District Haina Machinery Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |