CN116642594A - Board infrared temperature measurement method based on image vision - Google Patents
Board infrared temperature measurement method based on image vision Download PDFInfo
- Publication number
- CN116642594A CN116642594A CN202310778159.5A CN202310778159A CN116642594A CN 116642594 A CN116642594 A CN 116642594A CN 202310778159 A CN202310778159 A CN 202310778159A CN 116642594 A CN116642594 A CN 116642594A
- Authority
- CN
- China
- Prior art keywords
- temperature
- gypsum board
- image
- infrared
- point
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000009529 body temperature measurement Methods 0.000 title claims abstract description 36
- 229910052602 gypsum Inorganic materials 0.000 claims abstract description 245
- 239000010440 gypsum Substances 0.000 claims abstract description 245
- 230000002159 abnormal effect Effects 0.000 claims abstract description 75
- 238000004519 manufacturing process Methods 0.000 claims abstract description 56
- 230000000007 visual effect Effects 0.000 claims abstract description 20
- 230000035807 sensation Effects 0.000 claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 238000013135 deep learning Methods 0.000 claims abstract description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 24
- 238000013528 artificial neural network Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000002310 reflectometry Methods 0.000 claims description 5
- 238000003702 image correction Methods 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 241001270131 Agaricus moelleri Species 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 claims 2
- 238000004861 thermometry Methods 0.000 claims 1
- 230000005856 abnormality Effects 0.000 abstract description 6
- 230000008859 change Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 238000005259 measurement Methods 0.000 description 5
- 238000001035 drying Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 239000007921 spray Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/02—Constructional details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radiation Pyrometers (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The application discloses an image view-based plate infrared temperature measurement method, which comprises the following steps of: an infrared visual field point is arranged above a three-control collecting belt of a gypsum board production line, a visual field temperature capturing component is arranged at the infrared visual field point, a gypsum board temperature abnormal point is mapped into a gypsum board thermal sensation image to construct a temperature abnormal recognition model for carrying out temperature abnormal point modeling recognition based on the gypsum board thermal sensation image, and a thermal sensation temperature fault positioning model is obtained by utilizing the gypsum board thermal sensation image and fault equipment to carry out deep learning. According to the application, the gypsum board temperature measurement is carried out in a mode of long distance, no contact and no change of a target structure, the temperature abnormality point is directly positioned in the image view to improve the timeliness of monitoring the board temperature abnormality, quickly check out the reason of the board temperature abnormality, and reduce the loss caused by the temperature abnormality.
Description
Technical Field
The application relates to the technical field of gypsum board production, in particular to an infrared board temperature measurement method based on an image view field.
Background
In the production process of the gypsum board, the temperature control process of the gypsum board is the most central link, and plays a leading role in the processes of product quality, production stability, yield, molding process adjustment and the like. Therefore, the accurate acquisition of the temperature of the gypsum board in real time is the first step for realizing the temperature control of the gypsum board and is an indispensable important step. The application patent of the prior art CN114857875B discloses an online monitoring device and method for gypsum board drying, comprising a dryer, wherein a plurality of drying spaces are formed in the dryer along the vertical direction, a plurality of lap rollers for placing gypsum boards are arranged in the drying spaces, and a temperature measuring mechanism is also arranged in the drying spaces and used for detecting the temperature of the surface of the gypsum board; the spray head sprays water to the gypsum board to increase humidity when the surface temperature of the gypsum board is too high; and the main controller is used for receiving the signals of the temperature measuring mechanism and controlling the spray head according to the signals.
In the prior art, in the temperature measurement aspect, the temperature measurement sensor is utilized to perform contact measurement, and because the temperature measurement sensor is not stopped on the surface of the gypsum board for enough temperature measurement time due to high-speed operation of the gypsum board production line, the gypsum board is conveyed to the next position, so that the sensitivity of the contact measurement is limited, and the sensitivity of the gypsum board temperature detection effect is poor.
Disclosure of Invention
The application aims to provide an infrared plate temperature measurement method based on an image visual field, which aims to solve the technical problem of limited sensitivity of contact measurement in the prior art.
In order to solve the technical problems, the application specifically provides the following technical scheme:
an infrared plate temperature measurement method based on image vision comprises the following steps:
step S1, arranging an infrared view point position above a three-control collecting belt of a gypsum board production line, and installing a view temperature capturing component at the infrared view point position, wherein the infrared view point position is an optimal image view for infrared temperature measurement of a gypsum board, and the view temperature capturing component is an infrared image shooting component arranged at the infrared view point position;
s2, a view temperature capturing component at an infrared view point position is utilized to scan a gypsum board transmitted by a three-control collecting belt in real time to obtain a gypsum board thermal sensation image, the gypsum board thermal sensation image is abstracted into a gypsum board temperature domain curved surface under an image coordinate system where the gypsum board thermal sensation image is located, and the gypsum board temperature domain curved surface is a data curved surface formed by arranging and combining temperature numerical values represented by each pixel point in the gypsum board thermal sensation image according to the image coordinate system;
s3, positioning an intersection point based on a gypsum board temperature domain curved surface at an infrared view point position and a safety temperature domain threshold value at the infrared view point position to obtain a gypsum board temperature abnormal point, wherein the safety temperature domain threshold value is a normal temperature value allowed by the gypsum board at the infrared view point position;
and S4, after the gypsum board thermal images and the gypsum board temperature abnormal points with preset quantity are accumulated in the steps S1-S3, mapping the gypsum board temperature abnormal points into the gypsum board thermal images to construct a temperature abnormal recognition model for carrying out temperature abnormal point modeling recognition based on the gypsum board thermal images, so that the temperature abnormal points are directly positioned in an image view to improve the timeliness of monitoring the temperature abnormal of the board.
As a preferable scheme of the application, the infrared vision point position is arranged above the three-control collecting belt of the gypsum board production line, and the method comprises the following steps:
abstracting production equipment positioned at a front position of a three-control collecting belt in a gypsum board production line as network nodes, abstracting the three-control collecting belt positioned between two network nodes as network connecting edges for connecting the two network nodes, and carrying out topological connection on the network nodes by utilizing the network connecting edges to obtain a production line topology association network for representing the topological structure of the gypsum board production line;
carrying out community analysis on a topology association network of a production line to abstract and divide each production device into a plurality of device groups, wherein all production devices in the same device group have tight working condition connection, and two production devices in different device groups have sparse working condition connection;
and taking the production equipment corresponding to the network node positioned at the central point in each equipment group as central equipment, and arranging infrared vision point positions on a three-control collecting belt positioned behind the central equipment.
As a preferred scheme of the present application, the method for obtaining the thermal image of the gypsum board by scanning the gypsum board conveyed by the three-control collecting belt in real time by using the field temperature capturing component at the infrared field point comprises the following steps:
the visual field temperature capturing component scans the gypsum board passing through the visual field temperature capturing component at a preset speed in real time to obtain a thermal image of the gypsum board;
the preset speed is the conveying speed of the three-control collecting belt corresponding to the infrared vision point position where the vision temperature capturing component is located.
As a preferred solution of the present application, the abstraction of the thermal image of the gypsum board into the curved surface of the gypsum board temperature domain under the image coordinate system where the thermal image of the gypsum board is located includes:
converting RBG values of all pixel points and gray scales of all pixel points in the thermal image of the gypsum board into radiation energy at the corresponding position of the gypsum board;
converting radiant energy at each location of the gypsum board to a surface temperature at each location of the gypsum board based on the optical parameters of the field temperature capture assembly;
comparing the surface temperature of each position of the gypsum board with a color meter to determine the physical absolute temperature of each position of the gypsum board;
and mapping the physical absolute temperature at each position of the gypsum board to the temperature value of each pixel point in the gypsum board thermal image, which is used as the gypsum board thermal image, and combining the temperature values of each pixel point in the gypsum board thermal image into a gypsum board temperature domain curved surface according to the image coordinate system of the gypsum board thermal image.
As a preferable scheme of the application, the method for locating the intersection point between the gypsum board temperature curved surface based on the infrared view point position and the safety temperature threshold value based on the infrared view point position to obtain the gypsum board temperature abnormal point comprises the following steps:
determining a safety temperature threshold value at an infrared temperature measuring point, and projecting the safety temperature threshold value at the infrared temperature measuring point to an image coordinate system where a gypsum board temperature curved surface at an infrared view point is positioned to form a safety temperature threshold plane, wherein the safety temperature threshold plane is a data plane in which normal temperature values allowed by gypsum boards at the infrared view point are arranged and combined according to the image coordinate system;
and taking a pixel coordinate point corresponding to the intersection point of the gypsum board temperature curved surface and the safety temperature range threshold plane in the image coordinate system as a gypsum board temperature abnormal point.
As a preferred embodiment of the present application, the construction of the temperature anomaly identification model includes:
taking the thermal image of the gypsum board as an input item of a YOLO network, and taking the abnormal point position of the gypsum board temperature as an output item of the YOLO network;
performing learning training on input items of the YOLO network and output items of the YOLO network by utilizing the YOLO network to obtain a temperature anomaly identification model;
the model expression of the temperature anomaly identification model is as follows:
P＝YOLO(G)；
wherein P is the abnormal point of the gypsum board temperature, G is the thermal image of the gypsum board, and YOLO is a YOLO network.
As a preferred embodiment of the present application, the method further comprises step S5;
s5, counting the number of abnormal gypsum board temperature points monitored at the infrared view point positions, wherein,
if the number of the abnormal gypsum board temperature points monitored at the infrared view point is smaller than the abnormal allowable frequency, indicating that the abnormal gypsum board temperature at the infrared view point is an accidental operation event of the equipment;
if the number of the abnormal gypsum board temperature points monitored at the infrared view point is greater than or equal to the abnormal allowable frequency, indicating that the abnormal gypsum board temperature at the infrared view point is a necessary event of equipment failure;
marking the infrared visual field point position with the equipment fault necessary event as a fault checking point position, and mapping the fault checking point position into the topological structure of the affiliated equipment group;
and carrying out working condition detection and positioning on all production equipment in the equipment group to which the fault check point belongs to obtain fault equipment, and carrying out deep learning by using the gypsum board thermal image and the fault equipment to obtain a thermal sensing temperature and fault positioning model.
As a preferable scheme of the application, the construction method of the thermal sensing temperature fault positioning model comprises the following steps:
taking the gypsum board thermal image as an input item of the CNN neural network, and taking fault equipment as an output item of the CNN neural network;
performing network training on an input item of the CNN neural network and an output item of the CNN neural network by utilizing the CNN neural network to obtain the thermal sensing temperature fault positioning model;
the model expression of the thermal sensing temperature measurement fault positioning model is as follows:
P_Mechine＝CNN(G)；
wherein P_Meine is fault equipment, G is gypsum board thermal image, and CNN is CNN neural network.
As a preferable mode of the application, after the thermal image of the gypsum board is obtained, the thermal image of the gypsum board is subjected to image correction of the reflectivity of the surface of the gypsum board and the ambient temperature so as to reduce image recognition errors.
As a preferred embodiment of the present application, the community analysis uses a modular density as an objective function.
Compared with the prior art, the application has the following beneficial effects:
according to the application, an infrared view point is arranged above a three-control collecting belt of a gypsum board production line, a view temperature capturing component is arranged at the infrared view point, so that the gypsum board temperature measurement is carried out in a manner of realizing long-distance, non-contact and non-change of a target structure, a temperature anomaly point of the gypsum board is mapped into a gypsum board thermal image, a temperature anomaly identification model for carrying out temperature anomaly point modeling identification based on the gypsum board thermal image is constructed, the temperature anomaly point is directly positioned in an image view to realize the improvement of timeliness of monitoring the board temperature anomaly, the thermal sensing temperature fault positioning model is obtained by carrying out deep learning by utilizing the gypsum board thermal image and fault equipment, the quick detection of the reason of the board temperature anomaly is realized, and the loss caused by the temperature anomaly is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
FIG. 1 is a flow chart of a method for infrared temperature measurement of a plate according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the gypsum board temperature control process, in the aspect of temperature measurement, a temperature sensor is utilized for contact measurement, and because the temperature sensor is not remained on the surface of the gypsum board for enough time for temperature measurement due to high-speed operation of a gypsum board production line, the gypsum board is conveyed to the next position, so that the accuracy of contact measurement is limited, and the sensitivity of the gypsum board temperature detection effect is poor. The application provides an image view-based plate infrared temperature measurement method, which utilizes an infrared thermal imaging technology to measure the temperature of a plate, realizes non-contact temperature measurement, does not need to stay for a long time, stores temperature information into an acquired thermal image, decodes the temperature information from the thermal image, performs abnormal temperature analysis, and can directly locate abnormal positions and causes (fault devices) of temperature abnormality through thermal image modeling after a certain number of samples are accumulated.
As shown in fig. 1, the application provides an infrared plate temperature measurement method based on image vision, which comprises the following steps:
step S1, arranging an infrared view point position above a three-control collecting belt of a gypsum board production line, and installing a view temperature capturing component at the infrared view point position, wherein the infrared view point position is an optimal image view for infrared temperature measurement of a gypsum board, and the view temperature capturing component is an infrared image shooting component arranged at the infrared view point position;
s2, a view temperature capturing component at an infrared view point position is utilized to scan a gypsum board transmitted by a three-control collecting belt in real time to obtain a gypsum board thermal sensation image, the gypsum board thermal sensation image is abstracted into a gypsum board temperature domain curved surface under an image coordinate system where the gypsum board thermal sensation image is located, and the gypsum board temperature domain curved surface is a data curved surface formed by arranging and combining temperature numerical values represented by each pixel point in the gypsum board thermal sensation image according to the image coordinate system;
s3, positioning an intersection point based on a gypsum board temperature domain curved surface at an infrared view point position and a safety temperature domain threshold value at the infrared view point position to obtain a gypsum board temperature abnormal point, wherein the safety temperature domain threshold value is a normal temperature value allowed by the gypsum board at the infrared view point position;
and S4, after the gypsum board thermal images and the gypsum board temperature abnormal points with preset quantity are accumulated in the steps S1-S3, mapping the gypsum board temperature abnormal points into the gypsum board thermal images to construct a temperature abnormal recognition model for carrying out temperature abnormal point modeling recognition based on the gypsum board thermal images, so that the temperature abnormal points are directly positioned in an image view to improve the timeliness of monitoring the temperature abnormal of the board.
The application utilizes complex network technology to carry out topology analysis on the structure topology of the production line in the gypsum board production line, can analyze the relevance of production equipment, and grabs the production equipment of important production links in the production line, thereby arranging infrared view points, realizing the purpose of monitoring a plurality of production equipment in an equipment group by utilizing one infrared view point, achieving the maximum monitoring range by the arrangement of the simplest view point, and realizing the acquisition of the optimal image view, and is specifically as follows:
the infrared vision field point position is laid to belt top is collected in three accuse of gypsum board production line, includes:
abstracting production equipment positioned at a front position of a three-control collecting belt in a gypsum board production line as network nodes, abstracting the three-control collecting belt positioned between two network nodes as network connecting edges for connecting the two network nodes, and carrying out topological connection on the network nodes by utilizing the network connecting edges to obtain a production line topology association network for representing the topological structure of the gypsum board production line;
carrying out community analysis on a topology association network of a production line to abstract and divide each production device into a plurality of device groups, wherein all production devices in the same device group have tight working condition connection, and two production devices in different device groups have sparse working condition connection;
and taking the production equipment corresponding to the network node positioned at the central point in each equipment group as central equipment, and arranging infrared vision point positions on a three-control collecting belt positioned behind the central equipment.
According to the application, the field-of-view temperature capturing component is arranged at the infrared field point, the non-contact temperature measurement is realized at the optimal image field, the time is not required to stay, the temperature information is stored in the acquired gypsum board thermal image in real time, the temperature information is decoded from the gypsum board thermal image only after that, the abnormal position can be determined by carrying out abnormal temperature analysis, and the method comprises the following steps:
the field of view temperature that utilizes infrared field point position department catches subassembly real-time scanning by three accuse collection belt conveying gypsum board obtain gypsum board thermal sensation image, include:
the visual field temperature capturing component scans the gypsum board passing through the visual field temperature capturing component at a preset speed in real time to obtain a thermal image of the gypsum board;
the preset speed is the conveying speed of the three-control collecting belt corresponding to the infrared visual field point position where the visual field temperature capturing component is located, and the conveying speed of the three-control collecting belt is 72m/min generally.
The application decodes the temperature information of the gypsum board by utilizing the thermal image of the gypsum board, and displays the decoded temperature information in an image coordinate system so as to conveniently position the position of the abnormal temperature in the image coordinate system, and then converts the image coordinate system into a real coordinate system of the gypsum board to determine the actual position of the abnormal temperature of the gypsum board, wherein the decoding process of the temperature information of the gypsum board is as follows:
the method for abstracting the thermal image of the gypsum board into the curved surface of the temperature domain of the gypsum board under the image coordinate system where the thermal image of the gypsum board is located comprises the following steps:
converting RBG values of all pixel points and gray scales of all pixel points in the thermal image of the gypsum board into radiation energy at the corresponding position of the gypsum board;
converting radiant energy at each location of the gypsum board to a surface temperature at each location of the gypsum board based on the optical parameters of the field temperature capture assembly;
comparing the surface temperature of each position of the gypsum board with a color meter to determine the physical absolute temperature of each position of the gypsum board;
and mapping the physical absolute temperature at each position of the gypsum board to the temperature value of each pixel point in the gypsum board thermal image, which is used as the gypsum board thermal image, and combining the temperature values of each pixel point in the gypsum board thermal image into a gypsum board temperature domain curved surface according to the image coordinate system of the gypsum board thermal image. It should be noted that different field temperature capture components (e.g., infrared cameras) and colorimeters have different parameters and coordinate systems, and thus it is desirable to ensure that the parameters and coordinate systems used are consistent when performing the temperature calculations. In addition, attention is paid to the influence of external factors such as object surface reflectivity and ambient temperature in the infrared thermal image, and the image correction of the gypsum board surface reflectivity and the ambient temperature is performed on the gypsum board thermal image so as to reduce the decoding error of the image information.
The method for positioning the intersection point between the gypsum board temperature curved surface based on the infrared view point position and the safety temperature range threshold value of the infrared view point position to obtain the gypsum board temperature abnormal point comprises the following steps:
determining a safety temperature threshold value at an infrared temperature measuring point, and projecting the safety temperature threshold value at the infrared temperature measuring point to an image coordinate system where a gypsum board temperature curved surface at an infrared view point is positioned to form a safety temperature threshold plane, wherein the safety temperature threshold plane is a data plane in which normal temperature values allowed by gypsum boards at the infrared view point are arranged and combined according to the image coordinate system;
and taking a pixel coordinate point corresponding to the intersection point of the gypsum board temperature curved surface and the safety temperature range threshold plane in the image coordinate system as a gypsum board temperature abnormal point.
In the process, the gypsum board temperature abnormal point can be obtained only by carrying out pixel graying, radiation energy conversion, colorimetric card comparison and coordinate system conversion on the gypsum board thermal image, and the process is tedious and complex, so that after a sufficient number of data samples are accumulated, the data samples of the gypsum board thermal image and the gypsum board temperature abnormal point are subjected to deep learning training to construct a model, the gypsum board temperature abnormal point identification and positioning can be realized by the subsequent model directly through the gypsum board thermal image, the method is simpler and has higher timeliness, the gypsum board temperature abnormal point output by the temperature abnormal identification model can be obtained when the gypsum board thermal image is obtained, the hysteresis of abnormal positioning is reduced, the application scene of preventing overburning of the gypsum board can be met, the timeliness is high, the response to the gypsum board abnormal temperature is quicker, the loss caused by the abnormal temperature is reduced, and the concrete model is constructed as follows:
the construction of the temperature anomaly identification model comprises the following steps:
taking the thermal image of the gypsum board as an input item of a YOLO network, and taking the abnormal point position of the gypsum board temperature as an output item of the YOLO network;
performing learning training on input items of the YOLO network and output items of the YOLO network by utilizing the YOLO network to obtain a temperature anomaly identification model;
the model expression of the temperature anomaly identification model is as follows:
P＝YOLO(G)；
wherein P is the abnormal point of the gypsum board temperature, G is the thermal image of the gypsum board, and YOLO is a YOLO network.
After the temperature abnormal point of the gypsum board is positioned, the fault equipment causing the temperature abnormality is positioned by reversely utilizing the topological structure of the production equipment relevance for laying the infrared visual field point, namely the fault positioning of the gypsum board production line can be realized, the fault position is positioned while the temperature abnormal positioning is realized, and the fault of the production line is removed while the temperature measurement is realized by fruit finding, and the concrete process is as follows:
further comprising a step S5;
s5, counting the number of abnormal gypsum board temperature points monitored at the infrared view point positions, wherein,
if the number of the abnormal gypsum board temperature points monitored at the infrared view point is smaller than the abnormal allowable frequency, indicating that the abnormal gypsum board temperature at the infrared view point is an accidental operation event of the equipment;
if the number of the abnormal gypsum board temperature points monitored at the infrared view point is greater than or equal to the abnormal allowable frequency, indicating that the abnormal gypsum board temperature at the infrared view point is a necessary event of equipment failure;
marking the infrared visual field point position with the equipment fault necessary event as a fault checking point position, and mapping the fault checking point position into the topological structure of the affiliated equipment group;
and carrying out working condition detection and positioning on all production equipment in the equipment group to which the fault check point belongs to obtain fault equipment, and carrying out deep learning by using the gypsum board thermal image and the fault equipment to obtain a thermal sensing temperature and fault positioning model.
The construction method of the thermal sensing temperature measurement fault positioning model comprises the following steps:
taking the gypsum board thermal image as an input item of the CNN neural network, and taking fault equipment as an output item of the CNN neural network;
performing network training on an input item of the CNN neural network and an output item of the CNN neural network by utilizing the CNN neural network to obtain the thermal sensing temperature fault positioning model;
the model expression of the thermal sensing temperature measurement fault positioning model is as follows:
P_Mechine＝CNN(G)；
wherein P_Meine is fault equipment, G is gypsum board thermal image, and CNN is CNN neural network.
After the thermal image of the gypsum board is obtained, the thermal image of the gypsum board is subjected to image correction of the reflectivity of the surface of the gypsum board and the ambient temperature so as to reduce image recognition errors.
The visual field temperature capturing component at the infrared visual field point position monitors the temperature distribution of the gypsum board moving on the gypsum board production line at the speed of 72m/min in real time, and simultaneously controls the visual field temperature capturing component to take a picture according to a trigger signal given by the PLC, record and store a thermal image of the gypsum board, and store the temperature of the gypsum board in decoding so as to prepare for subsequent data curved surface generation and program call. The stored image may be selected for a cycle of cyclical saving based on the hard disk capacity.
Further, according to the gypsum board temperature curved surface stored in the hard disk, the highest temperature and the average temperature of the gypsum board are automatically analyzed, a temperature curve is generated, and the temperature change condition in the temperature measuring area is effectively monitored and analyzed. And the linkage is supported, and after the temperature abnormal point is positioned, an audible and visual alarm is triggered to remind workers of timely processing. The method can support networking of a plurality of devices to be connected to a software platform, support video preview of a plurality of real-time pictures, view monitoring pictures of a plurality of devices deployed in a production line area in real time, and can arbitrarily set a concerned area including points, lines and areas; and rapidly identifying the high-temperature abnormal position.
The community analysis uses modular density as an objective function.
According to the application, an infrared view point is arranged above a three-control collecting belt of a gypsum board production line, a view temperature capturing component is arranged at the infrared view point, so that the gypsum board temperature measurement is carried out in a manner of realizing long-distance, non-contact and non-change of a target structure, a temperature anomaly point of the gypsum board is mapped into a gypsum board thermal image, a temperature anomaly identification model for carrying out temperature anomaly point modeling identification based on the gypsum board thermal image is constructed, the temperature anomaly point is directly positioned in an image view to realize the improvement of timeliness of monitoring the board temperature anomaly, the thermal sensing temperature fault positioning model is obtained by carrying out deep learning by utilizing the gypsum board thermal image and fault equipment, the quick detection of the reason of the board temperature anomaly is realized, and the loss caused by the temperature anomaly is reduced.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this application will occur to those skilled in the art, and are intended to be within the spirit and scope of the application.
Claims (10)
1. An infrared plate temperature measurement method based on image vision is characterized by comprising the following steps:
step S1, arranging an infrared view point position above a three-control collecting belt of a gypsum board production line, and installing a view temperature capturing component at the infrared view point position, wherein the infrared view point position is an optimal image view for infrared temperature measurement of a gypsum board, and the view temperature capturing component is an infrared image shooting component arranged at the infrared view point position;
s2, a view temperature capturing component at an infrared view point position is utilized to scan a gypsum board transmitted by a three-control collecting belt in real time to obtain a gypsum board thermal sensation image, the gypsum board thermal sensation image is abstracted into a gypsum board temperature domain curved surface under an image coordinate system where the gypsum board thermal sensation image is located, and the gypsum board temperature domain curved surface is a data curved surface formed by arranging and combining temperature numerical values represented by each pixel point in the gypsum board thermal sensation image according to the image coordinate system;
s3, positioning an intersection point based on a gypsum board temperature domain curved surface at an infrared view point position and a safety temperature domain threshold value at the infrared view point position to obtain a gypsum board temperature abnormal point, wherein the safety temperature domain threshold value is a normal temperature value allowed by the gypsum board at the infrared view point position;
and S4, after the gypsum board thermal images and the gypsum board temperature abnormal points with preset quantity are accumulated in the steps S1-S3, mapping the gypsum board temperature abnormal points into the gypsum board thermal images to construct a temperature abnormal recognition model for carrying out temperature abnormal point modeling recognition based on the gypsum board thermal images, so that the temperature abnormal points are directly positioned in an image view to improve the timeliness of monitoring the temperature abnormal of the board.
2. The image view-based panel infrared temperature measurement method according to claim 1, wherein the method comprises the following steps of: the infrared vision field point position is laid to belt top is collected in three accuse of gypsum board production line, includes:
abstracting production equipment positioned at a front position of a three-control collecting belt in a gypsum board production line as network nodes, abstracting the three-control collecting belt positioned between two network nodes as network connecting edges for connecting the two network nodes, and carrying out topological connection on the network nodes by utilizing the network connecting edges to obtain a production line topology association network for representing the topological structure of the gypsum board production line;
carrying out community analysis on a topology association network of a production line to abstract and divide each production device into a plurality of device groups, wherein all production devices in the same device group have tight working condition connection, and two production devices in different device groups have sparse working condition connection;
and taking the production equipment corresponding to the network node positioned at the central point in each equipment group as central equipment, and arranging infrared vision point positions on a three-control collecting belt positioned behind the central equipment.
3. The image view-based panel infrared temperature measurement method according to claim 2, wherein the method comprises the following steps: the field of view temperature that utilizes infrared field point position department catches subassembly real-time scanning by three accuse collection belt conveying gypsum board obtain gypsum board thermal sensation image, include:
the visual field temperature capturing component scans the gypsum board passing through the visual field temperature capturing component at a preset speed in real time to obtain a thermal image of the gypsum board;
the preset speed is the conveying speed of the three-control collecting belt corresponding to the infrared vision point position where the vision temperature capturing component is located.
4. The image view-based panel infrared temperature measurement method according to claim 1, wherein the method comprises the following steps of: the method for abstracting the thermal image of the gypsum board into the curved surface of the temperature domain of the gypsum board under the image coordinate system where the thermal image of the gypsum board is located comprises the following steps:
converting RBG values of all pixel points and gray scales of all pixel points in the thermal image of the gypsum board into radiation energy at the corresponding position of the gypsum board;
converting radiant energy at each location of the gypsum board to a surface temperature at each location of the gypsum board based on the optical parameters of the field temperature capture assembly;
comparing the surface temperature of each position of the gypsum board with a color meter to determine the physical absolute temperature of each position of the gypsum board;
and mapping the physical absolute temperature at each position of the gypsum board to the temperature value of each pixel point in the gypsum board thermal image, which is used as the gypsum board thermal image, and combining the temperature values of each pixel point in the gypsum board thermal image into a gypsum board temperature domain curved surface according to the image coordinate system of the gypsum board thermal image.
5. The image view-based panel infrared temperature measurement method according to claim 4, wherein the method comprises the following steps: the method for positioning the intersection point between the gypsum board temperature curved surface based on the infrared view point position and the safety temperature range threshold value of the infrared view point position to obtain the gypsum board temperature abnormal point comprises the following steps:
determining a safety temperature threshold value at an infrared temperature measuring point, and projecting the safety temperature threshold value at the infrared temperature measuring point to an image coordinate system where a gypsum board temperature curved surface at an infrared view point is positioned to form a safety temperature threshold plane, wherein the safety temperature threshold plane is a data plane in which normal temperature values allowed by gypsum boards at the infrared view point are arranged and combined according to the image coordinate system;
and taking a pixel coordinate point corresponding to the intersection point of the gypsum board temperature curved surface and the safety temperature range threshold plane in the image coordinate system as a gypsum board temperature abnormal point.
6. The image view-based panel infrared temperature measurement method according to claim 5, wherein the method comprises the following steps: the construction of the temperature anomaly identification model comprises the following steps:
taking the thermal image of the gypsum board as an input item of a YOLO network, and taking the abnormal point position of the gypsum board temperature as an output item of the YOLO network;
performing learning training on input items of the YOLO network and output items of the YOLO network by utilizing the YOLO network to obtain a temperature anomaly identification model;
the model expression of the temperature anomaly identification model is as follows:
P＝YOLO(G)；
wherein P is the abnormal point of the gypsum board temperature, G is the thermal image of the gypsum board, and YOLO is a YOLO network.
7. The method for infrared temperature measurement of a sheet material based on image field of view according to claim 2, further comprising step S5;
s5, counting the number of abnormal gypsum board temperature points monitored at the infrared view point positions, wherein,
if the number of the abnormal gypsum board temperature points monitored at the infrared view point is smaller than the abnormal allowable frequency, indicating that the abnormal gypsum board temperature at the infrared view point is an accidental operation event of the equipment;
if the number of the abnormal gypsum board temperature points monitored at the infrared view point is greater than or equal to the abnormal allowable frequency, indicating that the abnormal gypsum board temperature at the infrared view point is a necessary event of equipment failure;
marking the infrared visual field point position with the equipment fault necessary event as a fault checking point position, and mapping the fault checking point position into the topological structure of the affiliated equipment group;
and carrying out working condition detection and positioning on all production equipment in the equipment group to which the fault check point belongs to obtain fault equipment, and carrying out deep learning by using the gypsum board thermal image and the fault equipment to obtain a thermal sensing temperature and fault positioning model.
8. The image view-based panel infrared temperature measurement method according to claim 7, wherein the construction method of the thermal sensing temperature fault location model comprises the following steps:
taking the gypsum board thermal image as an input item of the CNN neural network, and taking fault equipment as an output item of the CNN neural network;
performing network training on an input item of the CNN neural network and an output item of the CNN neural network by utilizing the CNN neural network to obtain the thermal sensing temperature fault positioning model;
the model expression of the thermal sensing temperature measurement fault positioning model is as follows:
P_Mechine＝CNN(G)；
wherein P_Meine is fault equipment, G is gypsum board thermal image, and CNN is CNN neural network.
9. The method of infrared thermometry of sheet material based on image field of view according to claim 4, wherein after obtaining the thermal image of the gypsum board, image correction of the reflectivity of the gypsum board surface, the ambient temperature is performed on the thermal image of the gypsum board to reduce image recognition errors.
10. The method of claim 2, wherein the community analysis uses module density as an objective function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310778159.5A CN116642594A (en) | 2023-06-28 | 2023-06-28 | Board infrared temperature measurement method based on image vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310778159.5A CN116642594A (en) | 2023-06-28 | 2023-06-28 | Board infrared temperature measurement method based on image vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116642594A true CN116642594A (en) | 2023-08-25 |
Family
ID=87623173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310778159.5A Pending CN116642594A (en) | 2023-06-28 | 2023-06-28 | Board infrared temperature measurement method based on image vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116642594A (en) |
-
2023
- 2023-06-28 CN CN202310778159.5A patent/CN116642594A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114994061B (en) | Machine vision-based steel rail intelligent detection method and system | |
| CN104142162B (en) | AOI visual detection device | |
| CN102879404B (en) | System for automatically detecting medical capsule defects in industrial structure scene | |
| CN110865077B (en) | Visual inspection system for appearance defects in RFID antenna production | |
| CN112146761A (en) | Human body temperature measurement compensation method based on machine learning | |
| CN204924967U (en) | Image acquisition mechanism of full -automatic AOI complete machine | |
| CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
| CN111274934A (en) | Implementation method and system for intelligently monitoring forklift operation track in warehousing management | |
| CN115171361B (en) | Dangerous behavior intelligent detection and early warning method based on computer vision | |
| CN105548198A (en) | Method for automatically detecting quality of complex product based on cloud platform | |
| CN111604916A (en) | Machine room IT equipment fault cabinet U-position positioning system and method | |
| CN112254827A (en) | Information processing device and method for improving precision of infrared thermometer | |
| CN109784193A (en) | Terminal data acquisition device and system for intelligent refrigerator | |
| CN108521296B (en) | Goods information identification system and method | |
| CN116758060B (en) | Vertical basket of flowers visual detection system of battery piece | |
| CN116642594A (en) | Board infrared temperature measurement method based on image vision | |
| CN102054161B (en) | Fingerprint image inspection method | |
| CN107884049A (en) | A kind of weighing products and three-dimensional dimension measurement apparatus | |
| CN204759441U (en) | Two -dimensional code check out test set and corresponding detecting system | |
| CN114705691B (en) | Industrial machine vision control method and device | |
| CN114821025A (en) | Meter identification method and system based on deep learning | |
| EP4194108B1 (en) | Small-grain agricultural product color selection method combining area scan and line scan photoelectric features | |
| CN213397309U (en) | Dynamic DWS system detection equipment | |
| CN206959789U (en) | Cloth code length measuring apparatus | |
| CN112465081A (en) | Detection system and method for server input test information |
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 |