CN116651971A - Online detection method and system for automobile stamping die - Google Patents
Online detection method and system for automobile stamping die Download PDFInfo
- Publication number
- CN116651971A CN116651971A CN202310953652.6A CN202310953652A CN116651971A CN 116651971 A CN116651971 A CN 116651971A CN 202310953652 A CN202310953652 A CN 202310953652A CN 116651971 A CN116651971 A CN 116651971A
- Authority
- CN
- China
- Prior art keywords
- stamping die
- die
- performance
- time
- performance evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 72
- 238000011156 evaluation Methods 0.000 claims abstract description 150
- 238000000034 method Methods 0.000 claims abstract description 87
- 239000011159 matrix material Substances 0.000 claims abstract description 85
- 238000012512 characterization method Methods 0.000 claims abstract description 64
- 230000008569 process Effects 0.000 claims abstract description 48
- 238000012549 training Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 20
- 238000007689 inspection Methods 0.000 claims description 18
- 230000003746 surface roughness Effects 0.000 claims description 17
- 230000006870 function Effects 0.000 claims description 16
- 238000004556 laser interferometry Methods 0.000 claims description 15
- 238000003754 machining Methods 0.000 claims description 15
- 238000012423 maintenance Methods 0.000 claims description 15
- 238000013135 deep learning Methods 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 13
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 238000010276 construction Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000011897 real-time detection Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 6
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005299 abrasion Methods 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 claims description 3
- 230000001678 irradiating effect Effects 0.000 claims description 3
- 238000012797 qualification Methods 0.000 abstract description 10
- 230000008859 change Effects 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 5
- 239000002699 waste material Substances 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 208000033986 Device capturing issue Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011049 filling Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011423 initialization method Methods 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 238000005461 lubrication Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004660 morphological change Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B21—MECHANICAL METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL; PUNCHING METAL
- B21C—MANUFACTURE OF METAL SHEETS, WIRE, RODS, TUBES OR PROFILES, OTHERWISE THAN BY ROLLING; AUXILIARY OPERATIONS USED IN CONNECTION WITH METAL-WORKING WITHOUT ESSENTIALLY REMOVING MATERIAL
- B21C51/00—Measuring, gauging, indicating, counting, or marking devices specially adapted for use in the production or manipulation of material in accordance with subclasses B21B - B21F
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Force Measurement Appropriate To Specific Purposes (AREA)
- Shaping Metal By Deep-Drawing, Or The Like (AREA)
Abstract
The invention relates to the technical field of die detection, in particular to an on-line detection method for an automobile stamping die, which can timely and accurately discover the performance change of the stamping die and improve the qualification rate of finished parts; the method comprises the following steps: collecting die performance evaluation factors of the stamping die in the working process; the die performance evaluation elements comprise the temperature of at least four preset points on the stamping die, the instantaneous pressure of the stamping die on a plate during stamping, the vibration frequency and the vibration amplitude of the stamping die in the lifting process, the roughness of the working surface of the stamping die and the roughness of the positioning surface of the stamping die; constructing at least five continuous time windows with the same width according to the time sequence; calculating the characteristic average value of each mold performance evaluation element in each time window; and converting the calculated characteristic mean value into a two-dimensional matrix according to the time sequence and the preset arrangement sequence of the die performance evaluation elements to obtain a performance characterization matrix of the stamping die.
Description
Technical Field
The invention relates to the technical field of die detection, in particular to an on-line detection method and system for an automobile stamping die.
Background
The automobile stamping die is a special die for stamping process in automobile manufacturing. The stamping process plays a critical role in automotive manufacturing for processing sheet metal into parts of desired shape at high speed and high pressure.
In the stamping process, the self performance of the stamping die is worn along with the increase of the processing time, and the qualification rate of finished parts is affected. In order to ensure the qualification rate of finished parts, the existing solution is to periodically check the stamping die by a worker or to reversely push the performance of the die by the qualification rate of the parts, and the method has a blank window period that the die performance is reduced to the extent that the qualification rate of the parts is affected, but the processing is still continued, so that the reduction of the die performance is difficult to find in time, and the waste of the parts and the construction period is caused.
Disclosure of Invention
In order to solve the technical problems, the invention provides the on-line detection method for the automobile stamping die, which can timely and accurately discover the performance change of the stamping die and improve the qualification rate of finished parts.
In a first aspect, the present invention provides an on-line detection method for an automobile stamping die, the method comprising:
collecting die performance evaluation factors of the stamping die in the working process; the die performance evaluation elements comprise the temperature of at least four preset points on the stamping die, the instantaneous pressure of the stamping die on a plate during stamping, the vibration frequency and the vibration amplitude of the stamping die in the lifting process, the roughness of the working surface of the stamping die and the roughness of the positioning surface of the stamping die;
Constructing at least five continuous time windows with the same width according to the time sequence;
calculating the characteristic average value of each mold performance evaluation element in each time window;
converting the calculated characteristic mean value into a two-dimensional matrix according to the time sequence and a preset arrangement sequence of the die performance evaluation elements to obtain a performance characterization matrix of the stamping die;
performing manual performance evaluation on the stamping die, and performing association marking on a performance evaluation result and a performance characterization matrix of a time node;
uploading the marking result to a deep learning platform for training and learning to generate a stamping die performance online detection model, wherein a performance characterization matrix of the stamping die is used as input of the stamping die performance online detection model, and a performance evaluation result is used as output of the stamping die performance online detection model;
acquiring a die performance evaluation element in the working process of the stamping die in real time, and converting the evaluation element into a real-time performance characterization matrix;
and carrying out feature recognition on the real-time performance characterization matrix by utilizing the stamping die performance on-line detection model, and outputting the performance of the stamping die under the time node.
On the other hand, the application also provides an on-line detection system of the automobile stamping die, which comprises:
The data acquisition module is used for acquiring die performance evaluation factors of the stamping die in the working process by using a sensor, wherein the die performance evaluation factors comprise temperature, instantaneous pressure, vibration frequency, vibration amplitude, working surface roughness and positioning surface roughness;
the data processing module is used for processing the acquired data according to the time sequence to construct continuous time windows with the same width; calculating the characteristic average value of each mold performance evaluation element in each time window;
the feature conversion module is used for converting the calculated feature mean value into a two-dimensional matrix according to a preset arrangement sequence of the die performance evaluation elements; constructing a performance characterization matrix of the stamping die for subsequent performance evaluation and model training;
the manual evaluation module is used for performing manual performance evaluation on the stamping die and performing association marking on a performance evaluation result and a performance characterization matrix of the time node;
the model training module is used for uploading the marking result to the deep learning platform for training and learning, and generating an online detection model of the stamping die performance by using a deep learning algorithm and training samples;
the real-time detection module is used for acquiring the die performance evaluation elements in the working process of the stamping die in real time and converting the evaluation elements into a real-time performance characterization matrix; and carrying out feature recognition and performance evaluation on the real-time performance characterization matrix by using the trained online detection model of the performance of the stamping die, and outputting the performance condition of the stamping die under the time node.
In a third aspect, the present application provides an electronic device comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, the computer program when executed by the processor implementing the steps of any of the methods described above.
In a fourth aspect, the application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of any of the methods described above.
Further, the roughness of the working surface of the stamping die and the roughness of the positioning surface of the stamping die in the working state are detected in real time by adopting laser interferometry equipment, and the detection method comprises the following steps:
ensuring that the laser interferometry equipment is in a working environment which maintains stable temperature and vibration conditions;
the position and the direction of the laser beam are adjusted to enable the laser beam to be normally irradiated on the surface of the stamping die, so that a sufficient projection angle and a measurement range exist between the laser beam and the surface of the stamping die;
starting a laser interferometry device, irradiating a laser beam to the surface of the stamping die, generating interference fringes by the laser beam and reflected light of the surface of the stamping die, and capturing and recording by the laser interferometry device;
The laser interferometry equipment performs image processing and data analysis on the captured interference fringes; the roughness of the stamping die surface was determined by analyzing the pitch and morphology changes of the fringes.
Further, the method of constructing at least five consecutive time windows of the same width comprises:
determining a proper starting time point according to the characteristics of the stamping process and the operation period of the stamping die;
calculating the ending time of the window according to the width of the window, wherein the ending time is obtained by adding the starting time of the window and the width of the window;
constructing a first window according to the start time and the end time calculated in the first two steps;
the construction of subsequent windows continues in the same manner by taking the end time of the first window as the start time of the next window until the required number of windows is met.
Further, the method for calculating the characteristic mean value of any mold performance evaluation element in a single time window comprises the following steps: acquiring die performance evaluation element data of at least 3 time points in a time window; and summing the acquired die performance evaluation element data, and dividing the die performance evaluation element data by the number of the die performance evaluation element data to obtain the characteristic average value of the die performance evaluation element in the time window.
Further, the method for converting the calculated characteristic mean value into the two-dimensional matrix comprises the following steps:
setting the arrangement sequence of the mold performance evaluation elements; sequentially arranging the temperature, the instantaneous pressure, the vibration frequency, the vibration amplitude, the working surface roughness and the positioning surface roughness of four preset points from left to right in sequence;
sequentially arranging characteristic average values of all the die performance evaluation elements from top to bottom according to the sequence of time windows to obtain a die performance evaluation element record list;
extracting the data content recorded in the die performance evaluation element record table to obtain a performance characterization matrix of the stamping die;
wherein each row of the performance characterization matrix represents a characteristic mean value of different mold performance evaluation elements over the same time window; each column represents the characteristic mean of the same mold performance evaluation element over a different time window.
Further, the artificial performance assessment includes:
checking whether damage, abrasion, crack or deformation existing on the surface of the die exceeds a preset appearance threshold, and if so, evaluating the result as follows: surface anomalies, requiring maintenance; if not, the evaluation result is: normal, no maintenance is required;
and (3) observing the working stability and vibration condition of the stamping die in actual working, judging whether the working state of the die exceeds a preset state threshold value, and if so, evaluating the working state as follows: the running state is abnormal and needs to be maintained; if not, the evaluation result is: normal, no maintenance is required;
Checking whether the punched part meets the quality requirements, including dimensional accuracy and surface defects; judging whether the machining precision of the die is lower than a preset precision threshold value, and if so, evaluating the machining precision of the die as follows: the running state is abnormal and needs to be maintained; if not, the evaluation result is: normal, no maintenance is required;
the evaluation result is represented in a binary marking mode in a data mode:
if the appearance inspection result is surface abnormality, the corresponding binary flag is 1;
if the appearance inspection result is normal, the corresponding binary flag is 0;
if the working state is abnormal, the corresponding binary flag is 1;
if the working state is normal, the corresponding binary flag is 0;
if the machining precision is abnormal, the corresponding binary mark is 1;
if the machining precision is normal, the corresponding binary mark is 0;
combining the above cases into a binary flag vector: [ x, x, x ], wherein the first element represents an appearance inspection result, the second element represents a working state inspection result, and the third element represents a machining accuracy inspection result.
Further, when the stamping die performance online detection model is applied to online detection of an actual stamping die, the stamping die performance online detection model comprises the following steps:
Preprocessing the acquired mold performance characterization matrix;
designing a structure of a convolutional neural network; the device comprises a convolution layer, a pooling layer and a full connection layer;
initializing weight and bias parameters in a network;
inputting the preprocessed mold performance characterization matrix into a network, and sequentially calculating an output value of each layer along the hierarchy of the network; after each convolution layer, adding a nonlinear activation function;
selecting an appropriate loss function to evaluate the performance of the model;
updating weights and bias parameters in the network by a back propagation algorithm based on the defined loss function;
the parameters of the model are continuously optimized through back propagation and parameter updating of multiple iterations.
Compared with the prior art, the invention has the following beneficial effects:
real-time detection: the method can collect the performance evaluation factors of the stamping die in the working process in real time and convert the performance evaluation factors into a real-time performance characterization matrix; compared with a method for periodically checking or reversely pushing based on the part qualification rate, the method has the advantages that the performance state of the stamping die can be known more timely, and the blank window period of continuous processing after the die performance is reduced to the degree of influencing the part qualification rate is avoided;
Comprehensive evaluation: the performance state of the stamping die can be comprehensively evaluated by collecting a plurality of die performance evaluation factors such as temperature, instantaneous pressure, vibration frequency, vibration amplitude, working surface roughness, positioning surface roughness and the like; the change and degradation of the performance of the die can be more accurately captured, and potential problems can be found in time;
deep learning model: uploading the marked performance evaluation result and the performance characterization matrix to a deep learning platform for training and learning to generate an online detection model of the stamping die performance; the model based on deep learning can learn a complex model performance change mode, predict the performance of the model performance in a future working process and provide a more accurate performance detection result;
saving resources and improving efficiency: the performance of the stamping die is detected on line in real time, so that resource waste and labor hour waste caused by a method of regular inspection or reverse pushing based on the part qualification rate can be avoided; only when the detection result prompts that the performance of the stamping die is reduced, the stamping die is required to be stopped for maintenance or replacement, so that the production efficiency is improved and the cost is saved;
the on-line detection method for the automobile stamping die has the advantages of timely and accurately finding out the performance change of the stamping die, improving the qualification rate of finished parts, avoiding the waste of the parts and the construction period, improving the production efficiency and reducing the cost through the advantages of real-time detection, comprehensive evaluation, deep learning of the model and resource saving and efficiency improvement.
Drawings
FIG. 1 is a flow chart of an on-line detection method of an automobile stamping die;
FIG. 2 is a schematic diagram of a mold performance evaluation element record table;
FIG. 3 is a schematic illustration of a performance characterization matrix of a stamping die;
fig. 4 is a schematic diagram of a stamping die performance online detection model identification performance characterization matrix.
Detailed Description
In the description of the present application, those skilled in the art will appreciate that the present application may be embodied as methods, apparatus, electronic devices, and computer-readable storage media. Accordingly, the present application may be embodied in the following forms: complete hardware, complete software (including firmware, resident software, micro-code, etc.), a combination of hardware and software. Furthermore, in some embodiments, the application may also be embodied in the form of a computer program product in one or more computer-readable storage media, which contain computer program code.
Any combination of one or more computer-readable storage media may be employed by the computer-readable storage media described above. The computer-readable storage medium includes: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer readable storage medium include the following: portable computer magnetic disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disk read-only memories, optical storage devices, magnetic storage devices, or any combination thereof. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, device.
The technical scheme of the application obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws.
The application provides a method, a device and electronic equipment through flow charts and/or block diagrams.
It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer readable program instructions may also be stored in a computer readable storage medium that can cause a computer or other programmable data processing apparatus to function in a particular manner. Thus, instructions stored in a computer-readable storage medium produce an instruction means which implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The present application will be described below with reference to the drawings in the present application.
Examples
As shown in fig. 1 to 4, the on-line detection method of the automobile stamping die of the application comprises the following steps:
s1, collecting a die performance evaluation element of a stamping die in the working process; the die performance evaluation elements comprise the temperature of at least four preset points on the stamping die, the instantaneous pressure of the stamping die on a plate during stamping, the vibration frequency and the vibration amplitude of the stamping die in the lifting process, the roughness of the working surface of the stamping die and the roughness of the positioning surface of the stamping die;
the selection and monitoring of the performance evaluation element of the stamping die in the step S1 specifically includes the following:
Temperature: the temperature has important influence on the performance and the service life of the stamping die; the high temperature may cause deformation of the stamping die, increased wear and reduced lubrication;
the method comprises the steps of collecting the surface or key parts of a stamping die in real time by using a temperature sensor; it should be noted that, because the preset points on the stamping die are arranged on the working surface of the stamping die, it is not practical to directly install a temperature sensor on the surface of the stamping die or to install a contact temperature sensor in the stamping die, so that a plurality of infrared temperature sensors are used to separate and measure the temperature of a plurality of preset points when the stamping die moves to a designated position; the consistency of data can be ensured, and the normal use of the stamping die is not influenced.
Instantaneous pressure of stamping die to plate during stamping: the instantaneous pressure can reflect the load condition and the bearing stress level of the stamping die;
the pressure sensor is directly arranged on the stamping die or connected with the punch press, and the instantaneous pressure applied to the plate in the stamping process is determined by measuring the pressure born by the sensor; the pressure sensor can be a resistance type sensor, a diaphragm type sensor, a piezoelectric type sensor and the like, and the selection of the proper sensor depends on the specific application requirement and the measurement range; force sensors can also be adopted, the force sensors are used for converting the pressure of the punching machine into force signals, and then the instantaneous pressure of the plate is calculated through the force signals; the force sensor can be a strain gauge type, an electronic weighing sensor and the like; the force sensor needs to be mounted in place on the punch press so that it is subjected to the pressure exerted by the punch press.
Vibration frequency and vibration amplitude in the lifting process of stamping die: vibration is a common problem in stamping die operation, which can lead to stamping die fatigue and breakage, thus requiring timely monitoring and evaluation;
the vibration frequency and the vibration amplitude in the lifting process of the stamping die can be measured by installing a vibration sensor or an acceleration sensor; the vibration sensor is a sensor specially used for measuring the vibration of an object; typically working according to the principle of vibration or the piezoelectric effect; the vibration sensor can be directly fixed on the upper surface of the stamping die and other structures which do not affect the stamping working surface so as to measure vibration signals; the sensors convert vibration signals into corresponding electric signals, and then the corresponding electric signals are transmitted to a data acquisition system for analysis through connecting wires; the acceleration sensor can measure the acceleration of an object in a specific direction, and the relation between the second law of Newton and the product of the mass is used; the acceleration sensor is arranged on the stamping die, so that the linear acceleration change condition in the lifting process of the stamping die can be measured, and the information of the vibration frequency and the vibration amplitude can be indirectly obtained.
Roughness of stamping die working face and stamping die locating face: the roughness of the working surface directly influences the surface quality of the part and the friction condition between the stamping die and the plate; the roughness of the positioning surface plays an important role in the positioning precision and stability of the stamping die;
Detecting the surface roughness of the die in real time by adopting laser interferometry equipment; the laser interferometry is a precise measurement method based on an optical interference principle, utilizes reflected light of a laser beam and the surface of a measured object to generate interference fringes, and determines the roughness of the surface of the measured object by analyzing the distance and morphological changes of the interference fringes; the method specifically comprises the following steps:
s11, ensuring that the laser interferometry equipment is in a proper working environment, such as maintaining stable temperature and vibration conditions; calibrating the device to ensure accuracy of the measurement;
s12, the position and the direction of the laser beam are adjusted to enable the laser beam to irradiate the surface of the stamping die normally; ensuring that there is sufficient projection angle and measurement range between the laser beam and the stamping die surface;
s13, starting laser interferometry equipment, and irradiating a laser beam to the surface of the stamping die; the laser beam and the reflected light of the stamping die surface generate interference fringes, and the fringes can be captured and recorded by the equipment;
s14, performing image processing and data analysis on the captured interference fringes by using software or an algorithm provided by the laser interferometry equipment; by analyzing the pitch and morphology changes of the fringes, the roughness of the stamping die surface can be determined.
In the step S1, through the measurement and collection, key performance indexes of the stamping die in the working process can be obtained; the indexes reflect the working state and the quality condition of the stamping die in the processing process, and provide a data basis for subsequent online detection and performance evaluation.
S2, constructing at least five continuous time windows with the same width according to the time sequence;
in step S2, a suitable time window needs to be determined for performance evaluation; the time window should have the following characteristics:
continuity: the time windows should be consecutive, i.e. the end time of each window should be contiguous with the start time of the next window;
identical width: to ensure efficient comparison and analysis of the data, the width of the window should remain the same; in general, the width of the window is determined according to specific process steps and characteristics of the stamping die; the specific method for constructing the time window is as follows:
s21, determining the starting time of a window: determining a proper starting time point according to the characteristics of the stamping process and the operation period of the stamping die; the start time of the window may be determined based on a stamping die detection period or other suitable time unit;
S22, determining the ending time of the window: calculating the ending time of the window according to the width of the window; the end time is obtained by adding the start time of the window to the window width;
s23, determining continuous windows: constructing a first window according to the start time and the end time calculated in the first two steps;
s24, continuing to construct subsequent windows in the same mode by taking the ending time of the current window as the starting time of the next window until the required number of windows is met;
it should be noted that the width of the window should be determined according to the specific stamping die and process requirements; too small a width may result in large data noise and too large a width may result in failure to capture details of the performance change; therefore, reasonable selection is required according to actual conditions; through the steps, a continuous time window with the same width can be obtained and used for evaluating the performance of the stamping die.
S3, calculating the characteristic average value of each mold performance evaluation element in each time window;
the method comprises the steps of carrying out statistical analysis on collected stamping die performance evaluation element data to obtain performance indexes of each time window;
The feature mean is a common statistic that represents the mean of a set of data, which can help to understand the central trend of the data; in the step S3, for the die performance evaluation element data in each time window, calculating the characteristic mean value of the die performance evaluation element data to obtain the performance index in the time window;
specifically, for each time window, summing the collected stamping die performance evaluation element data, and dividing the summed data by the number of data points to obtain the characteristic average value of each die performance evaluation element in the time window; for example, for a mold performance evaluation element, temperature data for a plurality of time points is collected within each time window; we add these data and then divide by the number of data points to get the characteristic mean of the temperature in the time window;
likewise, for other die performance evaluation factors, such as the instantaneous pressure of the stamping die on the plate during stamping, the vibration frequency during lifting of the stamping die, the vibration amplitude, the roughness of the working face of the stamping die, and the roughness of the positioning face of the stamping die, the characteristic average values of the die performance evaluation factors in each time window can be calculated according to the same method;
By calculating the characteristic average value of each die performance evaluation element in each time window, a group of performance indexes related to the time window can be obtained and used for subsequent construction of a performance characterization matrix and training and learning of a stamping die performance online detection model; it should be noted that the feature mean is only one of many possible feature statistics, and in practical application, other statistics may be selected to describe the distribution features of the data according to specific situations, for example, variance, maximum value, minimum value, etc. are all within the protection scope of the present invention; the selection of the appropriate statistics requires consideration of the nature of the data and the purpose of the analysis.
S4, converting the calculated characteristic mean value into a two-dimensional matrix according to the time sequence and a preset arrangement sequence of the die performance evaluation elements to obtain a performance characterization matrix of the stamping die;
specifically, how to convert the characteristic mean values of various mold performance evaluation elements into a two-dimensional matrix comprises the following steps:
setting the arrangement sequence of the mold performance evaluation elements; sequentially arranging the temperature, the instantaneous pressure, the vibration frequency, the vibration amplitude, the working surface roughness and the positioning surface roughness of four preset points from left to right in sequence;
Sequentially arranging the characteristic average values of the performance evaluation elements of each die from top to bottom according to the sequence of the time windows to obtain a die performance evaluation element record table, as shown in fig. 2;
extracting the data content recorded in the die performance evaluation element record table to obtain a performance characterization matrix of the stamping die; as shown in fig. 3, each row of the performance characterization matrix represents the same time window, each column represents a characteristic average value of a die performance evaluation element, the characteristic average value is filled in a corresponding position as an element in the matrix, and the two-dimensional matrix can effectively characterize the performance characteristics of the stamping die in different time windows;
the performance characterization matrix of the stamping die is used as input data of the subsequent steps; by utilizing the matrix, training and learning of a model can be performed, online detection of the performance of the stamping die is realized, and feature recognition is performed through the real-time performance characterization matrix, so that a performance evaluation result of the stamping die under the current time node is obtained; it should be noted that the specific feature extraction and matrix construction method needs to be adjusted according to actual conditions so as to meet the requirements of the stamping die on-line detection method; the above description provides a basic framework, and specific implementation details may vary according to different application scenarios and requirements.
S5, carrying out manual performance evaluation on the stamping die, and carrying out association marking on a performance evaluation result and a performance characterization matrix of the time node;
the purpose of the step S5 is to manually evaluate the stamping die to obtain marking data about the performance state of the stamping die, and correlate the marking data with a performance characterization matrix of the same time node; the marking data are used for training a deep learning model to perform performance online detection;
manual performance assessment is accomplished by die state assessment by a professional stamping die operator or related technician; specific evaluations included observations and recordings of:
checking whether damage, abrasion, crack or deformation existing on the surface of the die exceeds a preset appearance threshold, and if so, evaluating the result as follows: surface anomalies, requiring maintenance; if not, the evaluation result is: normal, no maintenance is required;
and (3) observing the working stability and vibration condition of the stamping die in actual working, judging whether the working state of the die exceeds a preset state threshold value, and if so, evaluating the working state as follows: the running state is abnormal and needs to be maintained; if not, the evaluation result is: normal, no maintenance is required;
Checking whether the punched part meets the quality requirements, including dimensional accuracy and surface defects; judging whether the machining precision of the die is lower than a preset precision threshold value, and if so, evaluating the machining precision of the die as follows: the running state is abnormal and needs to be maintained; if not, the evaluation result is: normal, no maintenance is required;
after the artificial performance evaluation is completed, performing association marking on the performance evaluation result and a performance characterization matrix of the same time node; these evaluation results may represent the performance state of the mold in a binary or other labeled manner, specifically including:
if the appearance inspection result is surface abnormality, the corresponding binary flag is 1;
if the appearance inspection result is normal, the corresponding binary flag is 0;
if the working state is abnormal, the corresponding binary flag is 1;
if the working state is normal, the corresponding binary flag is 0;
if the machining precision is abnormal, the corresponding binary mark is 1;
if the machining precision is normal, the corresponding binary mark is 0;
combining the above cases into a binary flag vector: [ x, x, x ], wherein the first element represents an appearance inspection result, the second element represents a working state inspection result, and the third element represents a machining accuracy inspection result.
Providing supervised training data for the deep learning model through manual performance evaluation and an association mark with a performance characterization matrix so as to establish a mold performance online detection model; the model will use these data to learn the characteristics of the mold performance and can predict the performance state of the mold from the real-time performance characterization matrix;
in summary, the step S5 involves manually evaluating the performance of the stamping die, and performing association labeling on the evaluation result and the performance characterization matrix to provide labeling data for subsequent deep learning model training; therefore, the online detection and prediction of the performance of the stamping die are realized, the degradation of the die performance is found in time, and corresponding maintenance or replacement measures are adopted.
S6, uploading the marking result to a deep learning platform for training and learning, and generating a stamping die performance online detection model, wherein a performance characterization matrix of the stamping die is used as input of the stamping die performance online detection model, and a performance evaluation result is used as output of the stamping die performance online detection model;
in the S6 step, a convolutional neural network model is adopted as a core for the online detection model of the stamping die performance; in the online detection of the performance of the stamping die, the performance characterization matrix of the stamping die can be used as input data, and the performance of the stamping die can be learned and predicted through a convolutional neural network model; meanwhile, the convolutional neural network can predict and evaluate the performance of the stamping die by learning and identifying modes and rules between the performance characterization matrix of the stamping die and the performance evaluation result of the artificial mark; specifically, the following is the construction process of the online detection model of the stamping die performance in the step S6:
S61, carrying out proper pretreatment on the acquired mold performance characterization matrix; the method comprises the operations of data normalization, scaling, smoothing, filling and the like so as to ensure the consistency and reasonable range of input data;
s62, designing a structure of a convolutional neural network; the device comprises a convolution layer, a pooling layer and a full connection layer; the convolution layer is used for extracting the characteristics of input data, the pooling layer is used for reducing the data dimension, and the full connection layer is used for mapping the high-level characteristics to the output layer;
s63, initializing weight and bias parameters in a network; common initialization methods include random initialization and pre-training model loading;
s64, inputting the preprocessed mold performance characterization matrix into a network, and sequentially calculating an output value of each layer along the hierarchy of the network; after each convolution layer, adding some nonlinear activation functions, such as ReLU, to introduce nonlinear transformations;
s65, selecting a proper loss function to evaluate the performance of the model; for classification problems, common loss functions include cross entropy loss functions;
s66, updating weight and bias parameters in the network through a back propagation algorithm based on the defined loss function so as to minimize the loss function and improve the performance of the model; the process uses a gradient descent method to continuously optimize parameters;
S67, continuously optimizing parameters of the model through back propagation and parameter updating of multiple iterations, so that the model is better adapted to input data, and the performance is improved;
s68, evaluating the performance of the model by using a part of data, wherein indexes such as accuracy, precision, recall and the like can be used for evaluating the performance of the model on a stamping die performance prediction task;
s69, saving the trained model for future use;
in general, the convolutional neural network model in the step S6 can realize the online detection of the performance of the stamping die by learning and predicting the mode and rule between the performance characterization matrix and the performance evaluation result of the stamping die; the model can be trained and learned through a deep learning platform, a performance online detection model is generated, and the performance level of the stamping die can be judged in real time by inputting the real-time performance characterization matrix into the model, so that guidance and decision basis are provided for further optimizing and maintaining the stamping process.
More specifically, the process of identifying the performance characterization matrix by the online detection model of the stamping die performance is shown in fig. 4, wherein the matrix { a, b, c; x, y, z; m, n, p } with the size of 3*3 is used as a convolution kernel of the online detection model of the stamping die performance, the transverse step length of the convolution kernel is 2, and the vertical step length of the convolution kernel is 1; convolution operation of the convolution kernel is carried out to obtain a 4*3-sized output matrix { W } 1 ,W 2 ,W 3 ,W 4 ;W 5 ,W 6 ,W 7 ,W 8 ; W 9 ,W 10 ,W 11 ,W 12 -a }; through the association mark between the output matrix and the performance evaluation result in the training process, the stamping die performance online detection model can map out a unique performance evaluation result according to the output matrix in the subsequent practical application.
S7, acquiring a die performance evaluation element in the working process of the stamping die in real time, and converting the evaluation element into a real-time performance characterization matrix;
the method comprises the steps of performing feature recognition on acquired real-time data by utilizing a trained online detection model of the performance of the stamping die so as to output the performance of the stamping die under the time node; when the step S7 is implemented, the method comprises the following steps:
s71, sensor data acquisition: collecting performance evaluation factors in the working process of the stamping die in real time by using the same sensor equipment as that in the step S1; the method comprises the steps of collecting data such as temperature, pressure, vibration frequency, vibration amplitude, roughness of a working surface and a positioning surface of a preset point position;
s72, data preprocessing: preprocessing the collected original data, including steps of filtering, denoising, data correction, standardization and the like; thus, the quality and consistency of data input into the online detection model of the stamping die performance can be ensured;
S73, extracting features: extracting features from the preprocessed data; the feature extraction is a process of extracting effective information capable of representing the performance of the stamping die from the original data; according to the requirements of the model and the training mode, the characteristic mean value of each element is calculated in the same process as in the S3;
s74, constructing a real-time performance characterization matrix: organizing the real-time feature mean value obtained from the feature extraction step into a matrix; the dimensions of the matrix are consistent with the stamping die performance characterization matrix used in step S6 so as to be able to match the trained model;
it should be noted that the present step is an actual application performed on the basis of a trained online detection model of the stamping die performance; training of the model uses historical data and related algorithms to learn and identify the performance of the stamping die.
S8, performing feature recognition on the real-time performance characterization matrix by using a stamping die performance online detection model, and outputting the performance of the stamping die under the time node;
in the embodiment, inputting the real-time performance characterization matrix constructed in the step S74 into a trained online detection model of the stamping die performance for feature recognition; the model maps the input real-time performance characterization matrix to a corresponding performance evaluation result according to the existing training data and model structure; according to the result of the model application, obtaining the performance evaluation result of the stamping die under the time node; these results indicate the condition of the stamping die, such as whether there is an abnormality, maintenance or replacement is required;
In practical application, corresponding measures can be taken according to the output result of the model, such as maintaining the die in time, replacing parts or adjusting the production process, so as to ensure the stability and the high efficiency of the stamping process. Real-time sensor data are converted into an evaluation result of the performance of the stamping die by using the trained model, so that real-time monitoring and diagnosis of the performance of the die are realized. The method can effectively discover the descending trend of the performance of the die in advance, reduce the generation of unqualified parts, and improve the production efficiency and the quality stability.
Examples
An automobile stamping die on-line detection system, comprising:
the data acquisition module is used for acquiring die performance evaluation factors of the stamping die in the working process by using a sensor, wherein the die performance evaluation factors comprise temperature, instantaneous pressure, vibration frequency, vibration amplitude, working surface roughness and positioning surface roughness;
the data processing module is used for processing the acquired data according to the time sequence to construct continuous time windows with the same width; calculating the characteristic average value of each mold performance evaluation element in each time window;
the feature conversion module is used for converting the calculated feature mean value into a two-dimensional matrix according to a preset arrangement sequence of the die performance evaluation elements; constructing a performance characterization matrix of the stamping die for subsequent performance evaluation and model training;
The manual evaluation module is used for performing manual performance evaluation on the stamping die and performing association marking on a performance evaluation result and a performance characterization matrix of the time node;
the model training module is used for uploading the marking result to the deep learning platform for training and learning, and generating an online detection model of the stamping die performance by using a deep learning algorithm and training samples;
the real-time detection module is used for acquiring the die performance evaluation elements in the working process of the stamping die in real time and converting the evaluation elements into a real-time performance characterization matrix; and carrying out feature recognition and performance evaluation on the real-time performance characterization matrix by using the trained online detection model of the performance of the stamping die, and outputting the performance condition of the stamping die under the time node.
The system can monitor the die performance evaluation factors including temperature, instantaneous pressure, vibration frequency, vibration amplitude, working surface roughness, positioning surface roughness and the like in the working process of the stamping die in real time; compared with the traditional periodic inspection method, the system can capture the change of the performance of the die in time, and avoid the problem of empty window period;
the combination of the data acquisition module and the data processing module enables the system to automatically process the acquired data; the data processing module processes the acquired data according to time sequence and calculates the characteristic mean value of each mold performance evaluation element in each time window; the automatic treatment reduces the manual burden and improves the treatment efficiency;
The feature conversion module converts the calculated feature mean value into a two-dimensional matrix, and constructs a performance characterization matrix of the stamping die for subsequent performance evaluation and model training; through a deep learning algorithm and training samples, the system can generate an online detection model of the performance of the stamping die; the high-efficiency performance evaluation can evaluate the performance of the stamping die rapidly and accurately, and improves the production efficiency and the product quality;
the manual evaluation module is used for performing manual performance evaluation on the stamping die and performing association marking on a performance evaluation result and a performance characterization matrix of the time node; the expertise and experience of manual evaluation can be fully utilized, an accurate marking result is provided for model training, and the accuracy and reliability of the model are improved;
the real-time detection module can perform feature identification and performance evaluation on the real-time performance characterization matrix according to the trained online detection model of the performance of the stamping die, and output the performance condition of the stamping die under the time node; through real-time detection, the performance problem of the stamping die can be found in time, the waste of parts and construction period is avoided, and the production efficiency and economic benefit are improved.
The various modifications and embodiments of the method for detecting the stamping die on line in the first embodiment are equally applicable to the system for detecting the stamping die on line in the present embodiment, and those skilled in the art can clearly know the implementation method of the system for detecting the stamping die on line in the present embodiment through the foregoing detailed description of the method for detecting the stamping die on line in the present embodiment, so that the description is omitted herein for brevity.
In addition, the application also provides an electronic device, which comprises a bus, a transceiver, a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the transceiver, the memory and the processor are respectively connected through the bus, and when the computer program is executed by the processor, the processes of the method embodiment for controlling output data are realized, and the same technical effects can be achieved, so that repetition is avoided and redundant description is omitted.
The foregoing is merely a preferred embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and variations can be made without departing from the technical principles of the present application, and these modifications and variations should also be regarded as the scope of the application.
Claims (10)
1. An on-line detection method for an automobile stamping die is characterized by comprising the following steps:
collecting die performance evaluation factors of the stamping die in the working process; the die performance evaluation elements comprise the temperature of at least four preset points on the stamping die, the instantaneous pressure of the stamping die on a plate during stamping, the vibration frequency and the vibration amplitude of the stamping die in the lifting process, the roughness of the working surface of the stamping die and the roughness of the positioning surface of the stamping die;
constructing at least five continuous time windows with the same width according to the time sequence;
calculating the characteristic average value of each mold performance evaluation element in each time window;
converting the calculated characteristic mean value into a two-dimensional matrix according to the time sequence and a preset arrangement sequence of the die performance evaluation elements to obtain a performance characterization matrix of the stamping die;
performing manual performance evaluation on the stamping die, and performing association marking on a performance evaluation result and a performance characterization matrix of a time node;
uploading the marking result to a deep learning platform for training and learning to generate a stamping die performance online detection model, wherein a performance characterization matrix of the stamping die is used as input of the stamping die performance online detection model, and a performance evaluation result is used as output of the stamping die performance online detection model;
Acquiring a die performance evaluation element in the working process of the stamping die in real time, and converting the evaluation element into a real-time performance characterization matrix;
and carrying out feature recognition on the real-time performance characterization matrix by utilizing the stamping die performance on-line detection model, and outputting the performance of the stamping die under the time node.
2. The on-line detection method for an automobile stamping die according to claim 1, wherein the roughness of the working face of the stamping die and the roughness of the positioning face of the stamping die in the working state are detected in real time by using a laser interferometry device, and the detection method comprises:
ensuring that the laser interferometry equipment is in a working environment which maintains stable temperature and vibration conditions;
the position and the direction of the laser beam are adjusted to enable the laser beam to be normally irradiated on the surface of the stamping die, so that a sufficient projection angle and a measurement range exist between the laser beam and the surface of the stamping die;
starting a laser interferometry device, irradiating a laser beam to the surface of the stamping die, generating interference fringes by the laser beam and reflected light of the surface of the stamping die, and capturing and recording by the laser interferometry device;
the laser interferometry equipment performs image processing and data analysis on the captured interference fringes; the roughness of the stamping die surface was determined by analyzing the pitch and morphology changes of the fringes.
3. The method for on-line inspection of an automotive stamping die according to claim 1, wherein the method for constructing at least five consecutive time windows of the same width comprises:
determining a proper starting time point according to the characteristics of the stamping process and the operation period of the stamping die;
calculating the ending time of the window according to the width of the window, wherein the ending time is obtained by adding the starting time of the window and the width of the window;
constructing a first window according to the start time and the end time calculated in the first two steps;
the construction of subsequent windows continues in the same manner by taking the end time of the first window as the start time of the next window until the required number of windows is met.
4. The method for online detection of an automotive stamping die according to claim 3, wherein the step of calculating the feature mean value of any die performance evaluation element within a single time window comprises: acquiring die performance evaluation element data of at least 3 time points in a time window; and summing the acquired die performance evaluation element data, and dividing the die performance evaluation element data by the number of the die performance evaluation element data to obtain the characteristic average value of the die performance evaluation element in the time window.
5. The method for online detection of an automobile stamping die according to claim 4, wherein the method for converting the calculated characteristic mean value into a two-dimensional matrix comprises:
setting the arrangement sequence of the mold performance evaluation elements; sequentially arranging the temperature, the instantaneous pressure, the vibration frequency, the vibration amplitude, the working surface roughness and the positioning surface roughness of four preset points from left to right in sequence;
sequentially arranging characteristic average values of all the die performance evaluation elements from top to bottom according to the sequence of time windows to obtain a die performance evaluation element record list;
extracting the data content recorded in the die performance evaluation element record table to obtain a performance characterization matrix of the stamping die;
wherein each row of the performance characterization matrix represents a characteristic mean value of different mold performance evaluation elements over the same time window; each column represents the characteristic mean of the same mold performance evaluation element over a different time window.
6. The method for online detection of an automobile stamping die according to claim 1, wherein the manual performance evaluation comprises:
checking whether damage, abrasion, crack or deformation existing on the surface of the die exceeds a preset appearance threshold, and if so, evaluating the result as follows: surface anomalies, requiring maintenance; if not, the evaluation result is: normal, no maintenance is required;
And (3) observing the working stability and vibration condition of the stamping die in actual working, judging whether the working state of the die exceeds a preset state threshold value, and if so, evaluating the working state as follows: the running state is abnormal and needs to be maintained; if not, the evaluation result is: normal, no maintenance is required;
checking whether the punched part meets the quality requirements, including dimensional accuracy and surface defects; judging whether the machining precision of the die is lower than a preset precision threshold value, and if so, evaluating the machining precision of the die as follows: the running state is abnormal and needs to be maintained; if not, the evaluation result is: normal, no maintenance is required;
the evaluation result is represented in a binary marking mode in a data mode:
if the appearance inspection result is surface abnormality, the corresponding binary flag is 1;
if the appearance inspection result is normal, the corresponding binary flag is 0;
if the working state is abnormal, the corresponding binary flag is 1;
if the working state is normal, the corresponding binary flag is 0;
if the machining precision is abnormal, the corresponding binary mark is 1;
if the machining precision is normal, the corresponding binary mark is 0;
combining the above cases into a binary flag vector: [ x, x, x ], wherein the first element represents an appearance inspection result, the second element represents a working state inspection result, and the third element represents a machining accuracy inspection result.
7. The method for online detection of an automobile stamping die according to claim 6, wherein the online detection model of stamping die performance is applied to online detection of an actual stamping die, and comprises:
preprocessing the acquired mold performance characterization matrix;
designing a structure of a convolutional neural network; the device comprises a convolution layer, a pooling layer and a full connection layer;
initializing weight and bias parameters in a network;
inputting the preprocessed mold performance characterization matrix into a network, and sequentially calculating an output value of each layer along the hierarchy of the network; after each convolution layer, adding a nonlinear activation function;
selecting an appropriate loss function to evaluate the performance of the model;
updating weights and bias parameters in the network by a back propagation algorithm based on the defined loss function;
the parameters of the model are continuously optimized through back propagation and parameter updating of multiple iterations.
8. An on-line detection system for an automobile stamping die, the system comprising:
the data acquisition module is used for acquiring die performance evaluation factors of the stamping die in the working process by using a sensor, wherein the die performance evaluation factors comprise temperature, instantaneous pressure, vibration frequency, vibration amplitude, working surface roughness and positioning surface roughness;
The data processing module is used for processing the acquired data according to the time sequence to construct continuous time windows with the same width; calculating the characteristic average value of each mold performance evaluation element in each time window;
the feature conversion module is used for converting the calculated feature mean value into a two-dimensional matrix according to a preset arrangement sequence of the die performance evaluation elements; constructing a performance characterization matrix of the stamping die for subsequent performance evaluation and model training;
the manual evaluation module is used for performing manual performance evaluation on the stamping die and performing association marking on a performance evaluation result and a performance characterization matrix of the time node;
the model training module is used for uploading the marking result to the deep learning platform for training and learning, and generating an online detection model of the stamping die performance by using a deep learning algorithm and training samples;
the real-time detection module is used for acquiring the die performance evaluation elements in the working process of the stamping die in real time and converting the evaluation elements into a real-time performance characterization matrix; and carrying out feature recognition and performance evaluation on the real-time performance characterization matrix by using the trained online detection model of the performance of the stamping die, and outputting the performance condition of the stamping die under the time node.
9. An electronic device for on-line detection of a stamping die of a motor vehicle, comprising a bus, a transceiver, a memory, a processor and a computer program stored on the memory and executable on the processor, the transceiver, the memory and the processor being connected by the bus, characterized in that the computer program when executed by the processor realizes the steps in the method according to any one of claims 1-7.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953652.6A CN116651971B (en) | 2023-08-01 | 2023-08-01 | Online detection method and system for automobile stamping die |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953652.6A CN116651971B (en) | 2023-08-01 | 2023-08-01 | Online detection method and system for automobile stamping die |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116651971A true CN116651971A (en) | 2023-08-29 |
| CN116651971B CN116651971B (en) | 2023-10-24 |
Family
ID=87712230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310953652.6A Active CN116651971B (en) | 2023-08-01 | 2023-08-01 | Online detection method and system for automobile stamping die |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116651971B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117048113A (en) * | 2023-10-13 | 2023-11-14 | 江苏爱箔乐铝箔制品有限公司 | Dynamic precision detection method and system for stamping aluminum foil cutlery box |
| CN117086175A (en) * | 2023-10-18 | 2023-11-21 | 南通品杰模塑科技有限公司 | Deformation compensation control method and system for stamping die |
| CN117553665A (en) * | 2024-01-12 | 2024-02-13 | 深圳市京鼎工业技术股份有限公司 | Delivery detection device for automobile air conditioner evaporation box die |
| CN118839580A (en) * | 2024-09-23 | 2024-10-25 | 江苏华灿电讯集团股份有限公司 | Production method of mold for cold stamping 6G antenna parts |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102764798A (en) * | 2012-08-07 | 2012-11-07 | 江苏扬力集团有限公司 | System for detecting wear of mould of numerical control turret punch press on line and working method thereof |
| US20180169975A1 (en) * | 2016-12-19 | 2018-06-21 | GM Global Technology Operations LLC | Online die face monitoring |
| CN109604442A (en) * | 2018-06-05 | 2019-04-12 | 襄阳博亚精工装备股份有限公司 | Stamping dies with embedded sensors and video surveillance |
| CN110027139A (en) * | 2019-03-12 | 2019-07-19 | 湖北民族大学 | A kind of mould preparation method, mold, mold heating system and method for heating and controlling |
| CN114491822A (en) * | 2022-03-14 | 2022-05-13 | 大捷智能科技(广东)有限公司 | Automobile stamping die process optimization method and device, storage medium and server |
| CN116037705A (en) * | 2023-01-09 | 2023-05-02 | 河北工业大学 | Real-time monitoring system for working status of cold stamping die |
-
2023
- 2023-08-01 CN CN202310953652.6A patent/CN116651971B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102764798A (en) * | 2012-08-07 | 2012-11-07 | 江苏扬力集团有限公司 | System for detecting wear of mould of numerical control turret punch press on line and working method thereof |
| US20180169975A1 (en) * | 2016-12-19 | 2018-06-21 | GM Global Technology Operations LLC | Online die face monitoring |
| CN109604442A (en) * | 2018-06-05 | 2019-04-12 | 襄阳博亚精工装备股份有限公司 | Stamping dies with embedded sensors and video surveillance |
| CN110027139A (en) * | 2019-03-12 | 2019-07-19 | 湖北民族大学 | A kind of mould preparation method, mold, mold heating system and method for heating and controlling |
| CN114491822A (en) * | 2022-03-14 | 2022-05-13 | 大捷智能科技(广东)有限公司 | Automobile stamping die process optimization method and device, storage medium and server |
| CN116037705A (en) * | 2023-01-09 | 2023-05-02 | 河北工业大学 | Real-time monitoring system for working status of cold stamping die |
Non-Patent Citations (1)
| Title |
|---|
| 许俊海;李嘉荣;洪炽杰;: "模具在线检测功能研究", 锻造与冲压, no. 10, pages 30 - 33 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117048113A (en) * | 2023-10-13 | 2023-11-14 | 江苏爱箔乐铝箔制品有限公司 | Dynamic precision detection method and system for stamping aluminum foil cutlery box |
| CN117048113B (en) * | 2023-10-13 | 2023-12-22 | 江苏爱箔乐铝箔制品有限公司 | Dynamic precision detection method and system for stamping aluminum foil cutlery box |
| CN117086175A (en) * | 2023-10-18 | 2023-11-21 | 南通品杰模塑科技有限公司 | Deformation compensation control method and system for stamping die |
| CN117086175B (en) * | 2023-10-18 | 2023-12-29 | 南通品杰模塑科技有限公司 | Deformation compensation control method and system for stamping die |
| CN117553665A (en) * | 2024-01-12 | 2024-02-13 | 深圳市京鼎工业技术股份有限公司 | Delivery detection device for automobile air conditioner evaporation box die |
| CN117553665B (en) * | 2024-01-12 | 2024-04-16 | 深圳市京鼎工业技术股份有限公司 | Delivery detection device for automobile air conditioner evaporation box die |
| CN118839580A (en) * | 2024-09-23 | 2024-10-25 | 江苏华灿电讯集团股份有限公司 | Production method of mold for cold stamping 6G antenna parts |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116651971B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116651971B (en) | Online detection method and system for automobile stamping die | |
| CN117726240B (en) | A quality evaluation classification method and system based on convolutional neural network | |
| CN119147740B (en) | Method, device, equipment and storage medium for monitoring concrete crack resistance in simulation manner | |
| CN118657030B (en) | Mold life prediction method based on simulation | |
| CN119197373B (en) | Dynamic monitoring method and system for carbon brush abrasion of collecting ring based on laser scanning | |
| CN117349947B (en) | Structural safety intelligent monitoring method based on SN curve and SVM | |
| CN118313259A (en) | Steel template service life assessment method and device based on deep learning | |
| CN118690507B (en) | A rivet forming force analysis method and system | |
| CN119475896A (en) | Online monitoring and analysis method and system for pump equipment in hydropower station | |
| CN118965850B (en) | Life prediction method of electronic component | |
| CN118246134B (en) | Double-tower cable-stayed bridge life cycle safety control system based on machine learning | |
| CN119168106B (en) | Fatigue accumulation prediction method and system for hydropower units based on holographic perception | |
| CN119333501A (en) | Brake health prediction method and device, electronic device, and storage medium | |
| CN117806233A (en) | Intelligent monitoring system and method for numerical control machine tool | |
| CN117272844A (en) | Method and system for predicting service life of distribution board | |
| CN119929621B (en) | Intelligent risk early warning method and system for elevator | |
| CN119886762B (en) | Equipment state-aware production scheduling control method, system and storage medium | |
| CN119915503B (en) | Linear guide rail fault diagnosis method and system based on deep learning | |
| CN118942019B (en) | Electric cylinder system fault warning system based on artificial intelligence | |
| CN119675591B (en) | PID detection method and device for photovoltaic module and electronic equipment | |
| CN117708508B (en) | Method, device, equipment and storage medium for predicting service life of disconnecting switch | |
| CN119670452B (en) | A deformation prediction method and system for injection molded gears of automobile wipers | |
| CN118505443B (en) | Method and system for managing jacking assembly of disc buckle frame | |
| CN118965123B (en) | Online evaluation method and system for AGC performance of thermal power plant unit | |
| CN118979907B (en) | Combined displacement sensing method and platform for oil cylinder |
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 |