CN117739819B - Method and system for measuring shape and size of precision-burned product - Google Patents
Method and system for measuring shape and size of precision-burned product Download PDFInfo
- Publication number
- CN117739819B CN117739819B CN202410174623.4A CN202410174623A CN117739819B CN 117739819 B CN117739819 B CN 117739819B CN 202410174623 A CN202410174623 A CN 202410174623A CN 117739819 B CN117739819 B CN 117739819B
- Authority
- CN
- China
- Prior art keywords
- fine
- product
- firing
- temperature
- information
- 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
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000005259 measurement Methods 0.000 claims abstract description 107
- 238000010304 firing Methods 0.000 claims abstract description 78
- 238000001514 detection method Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 11
- 238000003860 storage Methods 0.000 claims description 19
- 238000012545 processing Methods 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 238000000691 measurement method Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000013136 deep learning model Methods 0.000 claims description 4
- 239000013307 optical fiber Substances 0.000 claims description 3
- 238000009529 body temperature measurement Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 claims description 2
- 230000007787 long-term memory Effects 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000006403 short-term memory Effects 0.000 claims 1
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000002485 combustion reaction Methods 0.000 abstract 1
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000005245 sintering Methods 0.000 description 10
- 239000010453 quartz Substances 0.000 description 9
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 239000000463 material Substances 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000002441 X-ray diffraction Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004392 development of vision Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 238000009683 ultrasonic thickness measurement Methods 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application provides a method and a system for measuring the shape and the size of a precision-burned product, and relates to the technical field of measurement. Wherein the method comprises the following steps: acquiring the historical firing information of the refined firing product, constructing a refined firing prediction model of the refined firing product based on the historical firing information of the refined firing product, and training the refined firing prediction model to obtain a trained refined firing prediction model; calculating prediction information of the refined product based on the trained refined combustion prediction model; performing shape detection to obtain a shape and size detection result; calculating and determining a fine measurement target based on the shape and size detection result, firing information and prediction information of the fine fired product; and carrying out three-dimensional scanning measurement on the fine measurement target to obtain measurement data of the fine measurement target, wherein the method improves the measurement efficiency and the target measurement precision, is favorable for subsequent fine burning adjustment and optimization, and ensures the quality of the fine burning product.
Description
Technical Field
The application relates to the technical field of measurement, in particular to a method and a system for measuring the shape and the size of a precision-burned product.
Background
The fine sintering is a high-temperature heat treatment process, and is mainly used for improving the performance and quality of materials. In this process, the material is placed in a special furnace and then subjected to a heat treatment at high temperature for a long period of time. The process can make the internal structure of the material more uniform, improve the hardness and wear resistance of the material, and simultaneously eliminate internal stress and prevent the deformation and cracking of the material. The fine sintering process is widely applied to the processing process of materials such as metal, ceramic, quartz and the like;
The finish firing of quartz products is an important processing step, mainly used for improving the quality and purity of quartz products. In the process, the quartz product is placed in a special fine burning device and then is subjected to heating treatment by high-temperature flame;
Because high-temperature flame is needed in the fine burning process, on one hand, the operation is complex, and on the other hand, the high-temperature conditions influence the shape and size measurement of the fine burning product, and particularly, the shape and size measurement of the fine burning product under the complex shape and high-temperature conditions is very difficult;
Currently, optical measurement technology is mainly adopted for measuring the shape and the size: such as an optical microscope, an electron microscope, etc., can be used to observe the surface morphology of the quartz article and measure its dimensions. Laser scanning measurement technique: such as a laser scanning confocal microscope, a laser scanning measuring system, etc., the three-dimensional shape of the quartz product can be measured at a high speed and with high accuracy without contact. X-ray measurement technique: such as X-ray diffraction, X-ray tomography, etc., can be used to measure the internal structure of the quartz article, as well as its shape and size. Ultrasonic measurement technology: such as ultrasonic flaw detection, ultrasonic thickness measurement, etc., can be used for measuring the internal defects of quartz products, the thickness, etc. of the quartz products. The above measurement methods are mostly used singly and have low automation and intelligence, and especially when facing complex shapes and high temperature conditions, the measurement efficiency and measurement accuracy are not ideal.
In addition, the simple combination of the measurement modes is applied to the measurement of the shape and the size of the finished product, and the measurement efficiency and the data fusion still have challenges; along with the development of vision measurement technology in recent years, vision measurement is applied to the field of high-temperature fine burning, and adaptability is difficult, and mainly the fine burning operation of penetrating high-temperature flame under high-temperature conditions influences the accuracy and precision of vision measurement.
In summary, in the process of fine sintering, how to realize high-precision and high-efficiency automatic detection and measurement of the shape and the size of a product has great challenges, and especially the detection and measurement of the existing fine sintering product in the process of fine sintering are not prospective, cannot be optimally adjusted according to the needs, and influence the measurement efficiency and the measurement precision, so that research on improving the shape detection and size measurement technology of the fine sintering product is urgently needed.
In order to solve the technical problems, a method and a system for measuring the shape and the size of a precision-burned product are provided.
Disclosure of Invention
The application provides a method and a system for measuring the shape and the size of a precision-fired product, which can solve the problem of non-ideal measurement efficiency and measurement precision in the related technology. The technical scheme is as follows:
according to one aspect of the present application, the present disclosure provides a method for measuring shape and size of a precision fired article, comprising:
acquiring the historical firing information of the refined firing product, constructing a refined firing prediction model of the refined firing product based on the historical firing information of the refined firing product, and training the refined firing prediction model to obtain a trained refined firing prediction model; in the fine burning process, the burning information of at least one fine burning product is obtained, the burning information is preprocessed, and the prediction information of the fine burning product is calculated based on the trained fine burning prediction model;
based on firing information and prediction information of the refined product, performing shape detection to obtain a shape and size detection result; calculating and determining a fine measurement target based on the shape and size detection result, firing information and prediction information of the fine fired product; and carrying out three-dimensional scanning measurement on the fine measurement target to obtain measurement data of the fine measurement target.
According to one aspect of the present disclosure, there is provided a precision-fired article shape and size measurement system including an acquisition unit for acquiring historical firing information of a precision-fired article; the measuring module is used for measuring the fine burning time, the temperature and the image; the pretreatment unit is used for data pretreatment of the fine-burned product; the server is used for data processing, storage and calculation including training, prediction, shape detection and dimension measurement; the calculation control unit is used for controlling and processing data of the measurement module; the measuring driving unit is used for driving and controlling the measuring module; and a storage unit for storing data.
The measuring module comprises a high-temperature-resistant camera unit, a temperature measuring unit and a three-dimensional scanning unit; the high-temperature-resistant shooting unit adopts an explosion-proof high-temperature-resistant endoscopic shooting unit; the temperature measuring unit comprises a thermocouple temperature measuring unit, an infrared temperature measuring unit, a laser temperature measuring unit and/or an optical fiber temperature measuring unit; the three-dimensional scanning unit adopts a high-temperature-resistant three-dimensional laser scanning unit.
According to one aspect of the present disclosure, an electronic device is provided, comprising at least one processor and at least one memory, wherein the memory has computer readable instructions stored thereon; the computer readable instructions are executed by one or more of the processors to cause an electronic device to implement the fired article shape and size measurement method as described above.
According to one aspect of the present disclosure, a storage medium having stored thereon computer readable instructions that are executed by one or more processors to implement the precision fired article shape and size measurement method as described above.
The technical scheme provided by the application has the beneficial effects that:
In the technical scheme, the information of the current refined products is obtained by constructing the refined product prediction model, and the prediction information of the refined products is calculated based on the refined product prediction model; the shape detection of the rapid visual identification is carried out by utilizing the current refined product information and the prediction information, the prospective prediction result is obtained while the current shape and size detection result is obtained, the measurement efficiency is improved, and the shape and size detection result is obtained; calculating and determining a fine measurement target based on the shape and size detection result, firing information and prediction information of the fine fired product; tracking and adjusting the measurement target, changing to a high-precision three-dimensional laser scanning measurement technology, carrying out fixed-point tracking measurement on the fine measurement target, improving the measurement efficiency and the target measurement precision, being beneficial to the follow-up fine burning adjustment and optimization and guaranteeing the quality of the fine burning product.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings that are required to be used in the description of the embodiments of the present application will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the application and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a system for measuring shape and size of a finished fired product according to an embodiment of the present application;
FIG. 2 is a block diagram of a measurement module according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a measurement application provided in an embodiment of the present application;
FIG. 4 is a flow chart of a method for measuring the shape and the size of a finished product according to an embodiment of the present application;
FIG. 5 is a flowchart of S1 in a method for measuring shape and size of a finished product according to an embodiment of the present application;
FIG. 6 is a flowchart of S2 in a method for measuring shape and size of a finished product according to an embodiment of the present application;
FIG. 7 is a flowchart of S3 in a method for measuring shape and size of a finished product according to an embodiment of the present application;
FIG. 8 is a flowchart of S4 in a method for measuring shape and size of a finished product according to an embodiment of the present application;
FIG. 9 is a schematic diagram of a fine burn prediction model of a fine burn product according to an embodiment of the present application;
FIG. 10 is a schematic diagram of measurement according to an embodiment of the present application;
FIG. 11 is a schematic diagram of a measurement planning three-dimensional scan path according to an embodiment of the present application;
Wherein: 100. a measurement system; 10. a fine burning device; 11. fine burning table; 12. fine burning gun head; 13. finely burning the product; 101. an acquisition unit; 102. a measurement module; 103. a preprocessing unit; 104. a server; 105. a calculation control unit; 106. a measurement driving unit; 107. a storage unit; 1021. a high temperature resistant camera unit; 1022. a temperature measuring unit; 1023. a three-dimensional scanning unit; 131. a difference region; 132. fine measurement targets; l, three-dimensional scanning path.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the application.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise, as understood by those skilled in the art. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification of this disclosure, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
Referring to fig. 1-11, in one aspect, a system 100 for measuring shape and size of a finished product is provided, the system is applied to a finishing device 10, the finishing device 10 is internally provided with a finishing table 11 and a finishing gun 12, the finished product 13 is placed on the finishing table 11, and the system 100 comprises an acquisition unit 101 for acquiring historical firing information of the finished product; the measurement module 102 is used for measuring the fine burning time, temperature and image; a preprocessing unit 103 for preprocessing data of the precision-burned product; a server 104 for data processing, storage, and computation including training, prediction, shape detection, and dimensional measurement; a calculation control unit 105 for controlling and data processing of the measurement module; a measurement driving unit 106 for driving control of the measurement module; and a storage unit 107 for storing data.
The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, basic cloud computing services such as big data and artificial intelligent platforms. This server is an electronic device for providing a background service, for example, in an exemplary embodiment, the server provides cloud computing and cloud storage services of measurement data for the computing control unit.
In an exemplary embodiment, the measurement module 102 includes at least one high temperature resistant camera 1021, at least one temperature measurement unit 1022, and at least one three-dimensional scanning unit 1023; the high-temperature-resistant camera unit has high-temperature resistance, and in an exemplary embodiment, the high-temperature-resistant camera unit adopts an explosion-proof high-temperature-resistant endoscopic camera unit; the explosion-proof high-temperature-resistant endoscopic photographing unit is arranged and installed in the fine burning device, and photographs the fine burning product in the fine burning device to obtain an image, wherein the image which can be photographed by the explosion-proof high-temperature-resistant endoscopic photographing unit comprises the characteristics of surface condition, color change, texture characteristics, structural integrity, deformation or damage of the fine burning product and the like under the high-temperature working condition;
the temperature measuring unit 1022 comprises a thermocouple temperature measuring unit, an infrared temperature measuring unit, a laser temperature measuring unit and/or an optical fiber temperature measuring unit;
In an exemplary embodiment, the temperature measuring unit is an infrared temperature measuring unit, and is installed in the fine burning device to measure the temperature of the fine burning product; the three-dimensional scanning unit adopts a high-temperature-resistant three-dimensional laser scanning unit, and is arranged in the fine burning device to carry out three-dimensional laser scanning measurement on the fine burning product.
During fine burning, the fine-burned product is put into a fine burning device, a fine burning process is executed, and the fine burning time T, the fine burning temperature H and the fine burning temperature change rate V are preset;
In another aspect, the embodiment of the application provides a method for measuring the shape and the size of a finished product, which comprises the following steps: s1, acquiring historical firing information of a fine fired product, constructing a fine firing prediction model of the fine fired product based on the historical firing information of the fine fired product, training the fine firing prediction model to obtain a trained fine firing prediction model, wherein the historical firing information is a historical t moment firing image, a historical t moment temperature change rate, a historical t moment firing image and a historical t+1 moment temperature;
s2, in the fine burning process, burning information of at least one fine burning product is obtained, the burning information is preprocessed, and prediction information of the fine burning product is calculated based on a trained fine burning prediction model; the shape and the size of the refined product in the refined burning process are known in a prospective mode, targeted tracking adjustment measurement is facilitated, measurement efficiency and measurement precision are improved, burning information of the refined product is a burning image at the time n, temperature and temperature change rate, and predicted information is a burning image at the time n+1 and temperature at the time n+1;
S3, performing shape detection based on firing information and prediction information of the refined product to obtain a shape and size detection result; calculating and determining a fine measurement target based on the shape and size detection result, firing information and prediction information of the fine fired product; firstly, performing quick visual shape detection according to firing information and prediction information of the refined product to obtain a shape and size detection result, improving the shape and size measurement efficiency, and then tracking and adjusting a measurement target based on the shape and size detection result;
s4, carrying out three-dimensional scanning measurement on the fine measurement target to obtain measurement data of the fine measurement target. Based on tracking adjustment of the measurement target, the method is replaced to a high-precision measurement technology, fixed-point tracking measurement is carried out on the fine measurement target, measurement efficiency and target measurement precision are improved, follow-up fine burning adjustment optimization is facilitated, and quality of a fine burning product is guaranteed.
In an exemplary embodiment, the S1 includes: s101, collecting, sorting and summarizing historical firing information of the refined products; s102, extracting a historical firing image, corresponding time, temperature and temperature change rate of the finished product from the historical firing information of the finished product; s103, constructing a historical firing information sequence set of the fine fired product; dividing a historical firing information sequence of the fine fired product into a training set and a testing set; wherein,Wherein/>Historical firing information sequence sets for N finished fired articles; /(I)，/>For/>A historical firing information sequence of each of the finished fired articles; /(I)；/>For/>First/>, of the finished articleTime history firing information,/>Represents the/>First/>, of the finished articleTime image,/>Represents the/>First/>, of the finished articleRate of temperature change at time,/>Represents the/>First/>, of the finished articleTemperature at time;
S104, constructing a fine burning prediction model of the fine burning product, and training the fine burning prediction model by utilizing the historical burning information sequence to obtain a trained fine burning prediction model.
In an exemplary embodiment, the fine sintering prediction model of the fine sintering product is an RNN cyclic neural network model, and has an input layer, an hidden layer and an output layer, wherein 3 input layers of the fine sintering prediction model of the fine sintering product are respectively a firing image at time t, a temperature and a temperature change rate; the number of the output layers is 2, and the output layers are respectively a firing image at the time t+1 and the temperature; and the fine firing prediction model of the fine firing product comprises the following steps of:
；
Wherein, Is a predicted image of the refined product at time t+1,/>A fine burning image prediction model for the fine burning product; /(I)Is the predicted temperature of the refined product at the time t+1,/>The method is a fine burning temperature prediction model of a fine burning product; /(I)The image, the temperature change rate and the temperature of the finished product at the time t are respectively shown.
The method of S2 comprises the following steps:
S201, acquiring an image and temperature information of a finished product under a finish burning working condition;
S202, preprocessing the acquired image and temperature information of the finished product under the finish burning working condition to obtain a burning information set of the finished product k at the time t ; Wherein/>An image of the finished fired article at time t; temperature change rate of the finished fired product,/> The temperature of the finished product;
S203 based on Calculating by using a fine burning prediction model of the fine burning product to obtain。
In an exemplary embodiment, the method of S3 includes:
S301, extracting the firing information of the refined product and the image information in the prediction information, and carrying out image processing and identification to obtain a shape and size detection result; in an exemplary embodiment, the method of S301 specifically includes: s3011, constructing standard key shape characteristics and standard size parameters for the precision-fired product 13 in advance; s3012, extracting firing information of the refined product and images in prediction information; s3013, performing image processing and recognition by using a deep learning model, and extracting key shape characteristics and size parameters of the refined product;
S3014, comparing and calculating the key shape characteristics and the size parameters of the refined product with the standard key shape characteristics and the standard size parameters to obtain a difference value, and obtaining a shape and size detection result based on the difference value.
S302, calculating and determining a fine measurement target based on the shape and size detection result, firing information of the fine fired product and prediction information. In an exemplary embodiment, the method of S302 specifically includes: s3021, judging whether the difference value exceeds a preset threshold value or not based on the difference value in the shape and size detection result;
If S3022 is exceeded, a corresponding precision-fired product difference region 131 is calculated based on the shape and size detection result (difference value), and the precision-fired product difference region is determined as the precision measurement target 132.
If not, the routine loops back to S3012.
In an exemplary embodiment, the deep learning model used for image processing and recognition is a currently popular transducer model; the attention mechanism is introduced, so that the processing and recognition of the shape key features are effectively adapted; in some embodiments, image processing recognition may also employ convolutional neural network models, generate countermeasure network models, self-encoders, or long-term memory network models;
In an exemplary embodiment, the method of S4 includes: s401, planning a three-dimensional scanning path L based on the fine measurement target; s402, performing three-dimensional scanning measurement on the area corresponding to the fine target measurement target according to the three-dimensional scanning path L to obtain measurement data of the fine target. The method of three-dimensional scanning measurement preferably employs a laser-based three-dimensional scanning measurement method, and in some embodiments may also employ a depth camera scanning measurement method based on infrared and light pulses.
Another aspect of an embodiment of the present application provides an electronic device, including: at least one processor and at least one memory, wherein the memory has computer-readable instructions stored thereon;
the computer readable instructions are executable by one or more of the processors to cause an electronic device to implement the above-described method of shape and size measurement of a precision fire-baked article.
In another aspect of the embodiments of the present application, a storage medium has stored thereon computer readable instructions that are executed by one or more processors to implement the method of shape and size measurement of a fired article described above.
In an exemplary embodiment, an electronic device may include: desktop computers, notebook computers, servers, etc. (as needed to adapt according to the specifics of the application).
The electronic device includes at least one processor and at least one memory.
Wherein data interaction between the processor and the memory may be effected via at least one communication bus. The communication bus may include a path for transferring data between the processor and the memory. The communication bus may be a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus or an EISA (Extended Industry Standard Architecture ) bus, or the like. Communication buses may be classified as address buses, data buses, control buses, etc.
Optionally, the electronic device may further comprise a transceiver, which may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data, etc. It should be noted that, in practical applications, the transceiver is not limited to one, and the structure of the electronic device does not limit the embodiments of the present application.
The Processor may be a CPU (Central Processing Unit ), general purpose Processor, DSP (DIGITAL SIGNAL Processor ), ASIC (Application SPECIFIC INTEGRATED Circuit), FPGA (Field Programmable GATE ARRAY ) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. A processor may also be a combination that performs computing functions, e.g., including one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
The Memory may be, but is not limited to, ROM (Read Only Memory) or other type of static storage device that can store static images and instructions, RAM (Random Access Memory ) or other type of dynamic storage device that can store images and instructions, EEPROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY ), CD-ROM (Compact Disc Read Only Memory, compact disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program instructions or code in the form of instructions or data structures and that can be accessed by an electronic device.
The memory has computer readable instructions stored thereon, and the processor can read the computer readable instructions stored in the memory via the communication bus. The computer readable instructions are executable by one or more processors to implement the method of shape and size measurement of the fired article in the embodiments described above.
Further, in an embodiment of the present application, a storage medium having stored thereon computer readable instructions that are executed by one or more processors to implement the method of shape and size measurement of a fired article as described above is provided.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
The foregoing is only a partial embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations are intended to be comprehended within the scope of the present application.
Claims (11)
1. A method for measuring the shape and size of a finished fired product, comprising:
S1, acquiring historical firing information of a fine fired product, constructing a fine firing prediction model of the fine fired product based on the historical firing information of the fine fired product, training the fine firing prediction model to obtain a trained fine firing prediction model, wherein the historical firing information is a historical t moment firing image, a historical t moment temperature change rate, a historical t moment firing image and a historical t+1 moment temperature;
S2, in the fine burning process, burning information of at least one fine burning product is obtained, the burning information is preprocessed, and prediction information of the fine burning product is calculated based on a trained fine burning prediction model; the firing information of the refined fired product is a firing image at the time n, the temperature and the temperature change rate, and the prediction information is a firing image at the time n+1 and the temperature at the time n+1;
s3, performing shape detection based on firing information and prediction information of the refined product to obtain a shape and size detection result; calculating and determining a fine measurement target based on the shape and size detection result, firing information and prediction information of the fine fired product;
s4, carrying out three-dimensional scanning measurement on the fine measurement target to obtain measurement data of the fine measurement target;
The method of S3 comprises the following steps:
s301, extracting the firing information of the refined product and the image information in the prediction information, and carrying out image processing and identification to obtain a shape and size detection result;
s302, calculating and determining a fine measurement target based on the shape and size detection result, firing information and prediction information of the fine fired product;
The method of S301 includes: s3011, constructing standard key shape characteristics and standard size parameters in advance for the fine-burned product; s3012, extracting the firing information of the refined product and the image information in the prediction information, S3013, performing image processing and identification by using a deep learning model, and extracting key shape characteristics and size parameters of the refined product;
s3014, comparing and calculating the key shape characteristics and the size parameters of the refined product with the standard key shape characteristics and the standard size parameters to obtain a shape and size detection result;
the method of S302 includes: s3021, judging whether a difference value in the shape and size detection results exceeds a preset threshold value or not based on the shape and size detection results;
If yes, calculating a corresponding fine fired product difference region based on the shape and size detection result, and determining the fine fired product difference region as a fine measurement target.
2. The method of claim 1, wherein S1 comprises: s101, collecting, sorting and summarizing historical firing information of the refined products; s102, extracting a historical firing image of the finished product, a corresponding time temperature and a corresponding temperature change rate from historical firing information of the finished product; s103, constructing a historical firing information sequence set of the fine fired product; dividing a historical firing information sequence of the fine fired product into a training set and a testing set; wherein,Wherein/>Historical firing information sequence sets for N finished fired articles; /(I)，/>For/>A historical firing information sequence of each of the finished fired articles; /(I)；/>For/>First/>, of the finished articleTime history firing information,/>Represents the/>First/>, of the finished articleTime image,/>Represents the/>First/>, of the finished articleThe rate of change of temperature at the moment in time,Represents the/>First/>, of the finished articleTemperature at time;
S104, constructing a fine burning prediction model of the fine burning product, and training the fine burning prediction model by utilizing the historical burning information sequence to obtain a trained fine burning prediction model.
3. The method of claim 2, wherein the fine burn prediction model of the fine burn product is a neural network model, and has an input layer, an hidden layer and an output layer, wherein the number of the input layers of the fine burn prediction model of the fine burn product is 3, and the input layers are respectively a firing image at time t, a temperature and a temperature change rate; the number of the output layers is 2, and the output layers are respectively a firing image at the time t+1 and the temperature; and the fine firing prediction model of the fine firing product comprises the following steps of:
；
Wherein, Is a predicted image of the refined product at time t+1,/>A fine burning image prediction model for the fine burning product; Is the predicted temperature of the refined product at the time t+1,/> The method is a fine burning temperature prediction model of a fine burning product; /(I)The image, the temperature change rate and the temperature of the finished product at the time t are respectively shown.
4. A method according to claim 3, wherein the method of S2 comprises:
s201, acquiring an image of a fine burning product under a fine burning working condition by using a high-temperature-resistant industrial camera;
acquiring temperature information of a fine-fired product under a fine-fired working condition by using a temperature measuring unit;
S202, preprocessing the acquired image and temperature information of the finished product under the finish burning working condition to obtain a burning information set of the finished product k at the time t ; Wherein/>An image of the finished fired article at time t; /(I)Temperature change rate of the finished fired product,/>The temperature of the finished product;
S203 based on Calculating by using a fine burning prediction model of the fine burning product to obtain。
5. The method of claim 4, wherein the image processing and recognition employs a deep learning model comprising a convolutional neural network model, a generative network model, a self-encoder, a long and short term memory network model, and a transducer model.
6. The method of claim 5, wherein the method of S4 comprises: s401, planning a three-dimensional scanning path based on the fine measurement target;
s402, performing three-dimensional scanning measurement on the fine measurement target according to the three-dimensional scanning path to obtain measurement data of the fine target.
7. The method of claim 6, wherein the method of three-dimensional scanning measurement comprises laser-based three-dimensional scanning measurement and infrared and light pulse-based depth camera scanning measurement.
8. A fired article shape and size measurement system realized based on the one fired article shape and size measurement method according to any one of claims 1-7, characterized in that the system comprises an acquisition unit for acquiring historical firing information of the fired article;
the measuring module is used for measuring the fine burning time, the temperature and the image;
The pretreatment unit is used for data pretreatment of the fine-burned product;
the server is used for data processing, storage and calculation including training, prediction, shape detection and dimension measurement;
The calculation control unit is used for controlling and processing data of the measurement module;
the measuring driving unit is used for driving and controlling the measuring module;
and a storage unit for storing data.
9. The measurement system of claim 8, wherein the measurement module comprises a high temperature resistant camera unit, a temperature measurement unit, and a three-dimensional scanning unit;
The high-temperature-resistant shooting unit adopts an explosion-proof high-temperature-resistant endoscopic shooting unit;
the temperature measuring unit comprises a thermocouple temperature measuring unit, an infrared temperature measuring unit, a laser temperature measuring unit and/or an optical fiber temperature measuring unit;
The three-dimensional scanning unit adopts a high-temperature-resistant three-dimensional laser scanning unit.
10. An electronic device, comprising: at least one processor, and at least one memory, wherein,
The memory has computer readable instructions stored thereon;
the computer readable instructions are executed by one or more of the processors to cause an electronic device to implement the fired article shape and size measurement method of any of claims 1-7.
11. A storage medium having stored thereon computer readable instructions that are executed by one or more processors to implement the method of shape and size measurement of a fired article of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410174623.4A CN117739819B (en) | 2024-02-07 | 2024-02-07 | Method and system for measuring shape and size of precision-burned product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410174623.4A CN117739819B (en) | 2024-02-07 | 2024-02-07 | Method and system for measuring shape and size of precision-burned product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117739819A CN117739819A (en) | 2024-03-22 |
| CN117739819B true CN117739819B (en) | 2024-05-03 |
Family
ID=90283512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410174623.4A Active CN117739819B (en) | 2024-02-07 | 2024-02-07 | Method and system for measuring shape and size of precision-burned product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117739819B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206609467U (en) * | 2017-03-29 | 2017-11-03 | 西安科技大学 | A kind of high temperature ceramic tile real-time online detecting system |
| CN110490866A (en) * | 2019-08-22 | 2019-11-22 | 四川大学 | Metal based on depth characteristic fusion increases material forming dimension real-time predicting method |
| CN110806736A (en) * | 2019-11-19 | 2020-02-18 | 北京工业大学 | Method for detecting quality information of forge pieces of die forging forming intelligent manufacturing production line |
| CN114993188A (en) * | 2022-05-27 | 2022-09-02 | 马鞍山经纬回转支承有限公司 | Length measuring machine capable of solving temperature influence |
| CN116765427A (en) * | 2023-06-21 | 2023-09-19 | 中国科学院合肥物质科学研究院 | Real-time prediction method for size of molten pool in selective laser melting process |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102008024731B4 (en) * | 2008-05-19 | 2020-08-20 | BAM Bundesanstalt für Materialforschung und -prüfung | Method and device for sintering an object by determining the geometric surface profile of the object |
| EP3921141A4 (en) * | 2019-04-10 | 2022-12-07 | Hewlett-Packard Development Company, L.P. | Material phase detection |
-
2024
- 2024-02-07 CN CN202410174623.4A patent/CN117739819B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206609467U (en) * | 2017-03-29 | 2017-11-03 | 西安科技大学 | A kind of high temperature ceramic tile real-time online detecting system |
| CN110490866A (en) * | 2019-08-22 | 2019-11-22 | 四川大学 | Metal based on depth characteristic fusion increases material forming dimension real-time predicting method |
| CN110806736A (en) * | 2019-11-19 | 2020-02-18 | 北京工业大学 | Method for detecting quality information of forge pieces of die forging forming intelligent manufacturing production line |
| CN114993188A (en) * | 2022-05-27 | 2022-09-02 | 马鞍山经纬回转支承有限公司 | Length measuring machine capable of solving temperature influence |
| CN116765427A (en) * | 2023-06-21 | 2023-09-19 | 中国科学院合肥物质科学研究院 | Real-time prediction method for size of molten pool in selective laser melting process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117739819A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Khanzadeh et al. | In-situ monitoring of melt pool images for porosity prediction in directed energy deposition processes | |
| Davoudinejad et al. | 3D finite element simulation of micro end-milling by considering the effect of tool run-out | |
| CN110186570B (en) | Additive manufacturing laser 3D printing temperature gradient detection method | |
| Brili et al. | Automatic identification of tool wear based on thermography and a convolutional neural network during the turning process | |
| CN113591240B (en) | Modeling method for thermal error model of tooth grinding machine based on bidirectional LSTM network | |
| Jafarian et al. | Experimental and numerical investigation of thermal loads in Inocnel 718 machining | |
| Afrasiabi et al. | A numerical-experimental study on orthogonal cutting of AISI 1045 steel and Ti6Al4V alloy: SPH and FEM modeling with newly identified friction coefficients | |
| Le Besnerais et al. | Fast and dense 2D and 3D displacement field estimation by a highly parallel image correlation algorithm | |
| Cuka et al. | Vision-based surface roughness evaluation system for end milling | |
| Yu et al. | An improved tool wear monitoring method using local image and fractal dimension of workpiece | |
| CN117739819B (en) | Method and system for measuring shape and size of precision-burned product | |
| Bautista-Monsalve et al. | A novel machine-learning-based procedure to determine the surface finish quality of titanium alloy parts obtained by heat assisted single point incremental forming | |
| Senin et al. | Three‐dimensional surface topography acquisition and analysis for firearm identification | |
| Kwon et al. | Assessment of speckle-pattern quality using deep-learning-based CNN | |
| EP4146456A1 (en) | Optimising process parameters in additive manufacturing | |
| Xu et al. | A method of defect depth recognition in active infrared thermography based on GRU networks | |
| Shang et al. | Large strain flow curve characterization considering strain rate and thermal effect for 5182-O aluminum alloy | |
| Duan et al. | Forming force prediction in double-sided incremental forming via GNN-based transfer learning | |
| Shibahara et al. | Studies on in-situ full-field measurement for in-plane welding deformation using digital camera | |
| Li et al. | A structured light vision sensor for online measurement of steel-plate width | |
| Lu et al. | A Robust Image Processing Algorithm for Optical-Based Stress–Strain Curve Corrections after Necking | |
| Pivkin et al. | A new method and practical recommendations for measuring geometric accuracy, linear and angular measurements of helical surfaces of end mill for HSM | |
| Hofmann et al. | Porosity prediction in laser-based powder bed fusion of polyamide 12 using infrared thermography and machine learning | |
| Shahid et al. | A neural network-based method for coverage measurement of shot-peened panels | |
| Gu et al. | Uneven intensity change correction of speckle images using morphological top-hat transform in digital image correlation |
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 |