An autoclave pressure control system
By introducing a steam pressure control system into the autoclave, the steam pressure progress of the preform is monitored in real time using images and sensors. Combined with a convolutional neural network model, the temperature and pressure inside the autoclave are precisely adjusted, solving the problem of inaccurate adjustment in existing technologies and improving the quality of autoclaved aerated concrete blocks.
Patent Information
- Application Number
- CN202310385869.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-04-07
- Publication Date
- 2026-01-30
- Estimated Expiration
- 2043-04-07
AI Technical Summary
Existing autoclaves cannot accurately adjust the temperature and pressure according to the autoclaving progress of the preform, resulting in low quality of autoclaved aerated concrete blocks.
The autoclave control system employs modules for embryo image acquisition, weight acquisition, expansion acquisition, temperature monitoring, and air pressure monitoring, combined with an environmental control module, to adjust the temperature and air pressure inside the autoclave in real time. A temperature and air pressure model of the autoclave is established using a convolutional neural network, and the heating device and steam valves are precisely adjusted according to the autoclaving progress parameters of the embryo.
This technology enables precise adjustment of the temperature and pressure inside the autoclave based on the autoclaving progress of the preform, improving the quality of autoclaved aerated concrete blocks and avoiding quality problems such as black core and curing cracks.
Smart Images

Figure CN116214702B_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of building materials production technology, and more specifically, relates to a steam pressure control system for an autoclave. Background Technology
[0002] The main materials for autoclaved aerated concrete (AAC) blocks include desulfurized gypsum, aluminum powder paste, fly ash, sand, and cement. These blocks are porous silicate products that undergo processes such as batching, mixing, expansion, static curing, autoclaving, and final product removal. The autoclaving process for AAC blocks requires an autoclave, also known as a steam curing autoclave or pressure autoclave. An autoclave is a large, heavy pressure vessel where the hydrothermal reaction of CaO—SiO2—H2O is completed.
[0003] In current autoclave processes, the autoclave is generally pre-set with fixed temperature and pressure. However, since the hydrothermal reaction in the autoclave process of autoclaved aerated concrete (AAC) blocks is not instantaneous but a gradual process from the surface of the block inwards, the constant temperature and pressure settings can lead to technical problems in adjusting the temperature and pressure inside the autoclave according to the autoclave's autoclaving progress. This results in insufficient quality of the AAC blocks. Summary of the Invention
[0004] In view of this, the present invention provides a steam pressure control system for an autoclave, which can precisely adjust the temperature and pressure inside the autoclave according to the steam pressure progress of the embryo.
[0005] This invention is implemented as follows:
[0006] This invention provides a autoclave control system, wherein the autoclave is used for the autoclaving process of aerated concrete blocks, the autoclave has a heating device, and the autoclave control system includes the following modules:
[0007] An embryo image acquisition module is used to acquire images of a specified embryo inside the autoclave;
[0008] The embryo weight acquisition module is used to acquire the weight of a specified embryo inside the autoclave;
[0009] The embryo expansion measurement module is used to obtain the expansion dimensions of a specified embryo on its front, back, left, and right sides inside the autoclave.
[0010] The temperature monitoring module is used to acquire the temperature inside the autoclave;
[0011] The air pressure monitoring module is used to acquire the air pressure inside the autoclave;
[0012] An environmental control module is used to control the heating device of the autoclave, as well as the opening and closing of the steam valve and the steam inflow rate of the autoclave.
[0013] Based on the above technical solution, the autoclave control system of the present invention can be further improved as follows:
[0014] The environmental control module is used to implement the steps of obtaining the autoclaving environment parameters based on the autoclaving progress parameters, and adjusting the heating device and autoclaving valve based on the autoclaving environment parameters. The autoclaving process data includes the autoclaving progress parameters of the specified embryo and the autoclaving environment parameters of the autoclave. The autoclaving progress parameters include embryo image, weight increment, and surface expansion. The autoclaving environment parameters include the temperature and air pressure inside the autoclave.
[0015] The steps of obtaining the autoclaving environment parameters based on the autoclaving progress parameters, and adjusting the heating device and autoclaving valves based on the autoclaving environment parameters, specifically include:
[0016] Multiple sets of autoclaving progress parameters and corresponding autoclaving environment parameters are collected to form a historical dataset, and the collection time interval of the historical dataset is 1 min to 15 min.
[0017] Select the datasets from historical datasets that correspond to factory-produced autoclaved aerated concrete blocks that meet the quality standards as the base dataset;
[0018] Surface pore contours are extracted from the embryonic images of each item in the basic dataset to obtain a basic embryonic contour set.
[0019] Calculate the similarity between the basic embryonic contour set and the standard embryonic contour set for each item in the basic dataset, and record it as the basic embryonic image similarity.
[0020] A training dataset is established, wherein the input of the training dataset is the basic embryo autoclave autoclave rate parameter of each item in the basic dataset, and the output of the training dataset is the autoclave environment parameter of the same group corresponding to the basic embryo autoclave rate parameter.
[0021] A preliminary model of the temperature and pressure of the autoclave was established using a convolutional neural network, and trained using a training dataset to obtain the autoclave temperature and pressure model.
[0022] Surface pore contours are extracted from the embryo image to obtain the current embryo contour set;
[0023] Calculate the similarity between the current embryo body contour set and the standard embryo body contour set, and denote it as the current embryo body image similarity.
[0024] Using the current autoclaving progress parameters as model input, the target temperature and target pressure inside the autoclave are calculated using the autoclave temperature and pressure model.
[0025] Adjust the heating device and steam valve of the autoclave according to the target temperature and target pressure inside the autoclave.
[0026] The beneficial effects of adopting the above-mentioned improved scheme are as follows: By setting the collection time interval of historical datasets to 1 min to 15 min, the entire autoclaving process can be divided into multiple time periods according to the specified time interval. Each time period corresponds to a different target temperature and target pressure. The target temperature and target pressure of each time period are not obtained according to the sequential time period from start to finish, but according to the correspondence between different embryo images, weight increments, and surface expansion data. This solves the technical problem that the temperature and pressure inside the autoclave cannot be accurately adjusted according to the autoclaving progress parameters of the embryo in the autoclaving process.
[0027] The historical data requires experienced operators to adjust the temperature and pressure inside the autoclave in real time for different preform autoclaving progress parameters.
[0028] The quality standard mentioned is "Autoclaved Aerated Concrete Blocks" (GB / T 11968-2020).
[0029] The designated embryos include two groups, each group including 2 or 4 embryos, namely the image weight acquisition group and the surface dilatation acquisition group;
[0030] In this process, each embryo in the image weight acquisition group is placed on a spring scale. When the number of embryos in the image weight acquisition group is 2, one spring scale is placed at each of the two longitudinal ends of the autoclave. When the number of embryos in the image weight acquisition group is 4, two spring scales are placed at each of the two longitudinal ends of the autoclave, with one embryo placed on every other spring scale.
[0031] A set of high-definition cameras is respectively installed on the inner wall of both longitudinal ends of the autoclave. The high-definition cameras are used to acquire the reading images of the elastic scale and the images of the front, back, left, right and top surface of the embryo of the image weight acquisition group as embryo images.
[0032] The weight of the corresponding embryo is obtained by recognizing the image of the elastic scale captured by the high-definition camera.
[0033] In the surface expansion acquisition group, a displacement sensor is installed close to the center of each of the four faces (front, back, left, and right) of the embryo. The displacement sensor is used to acquire the displacement caused by the external expansion of the corresponding embryo.
[0034] The formula for calculating the embryo expansion degree is P(x,y)=(x1+x2) / 2+(y1+y2) / 2, where P(x,y) represents the embryo expansion degree, including the transverse expansion degree x and the longitudinal expansion degree y, x1 and x2 are the displacements caused by the outward expansion of the front and rear surfaces of the embryo, respectively; y1 and y2 are the displacements caused by the outward expansion of the left and right surfaces of the embryo, respectively.
[0035] The high-definition camera is installed in a heat-insulated, sealed, transparent cover. The high-definition camera has a resolution greater than 720P. Each group of high-definition cameras consists of 6 cameras. The lenses of five high-definition cameras face the front, back, left, right, and top surface of the embryo in the image weight acquisition group. The other high-definition camera is used to acquire the reading image of the elastic scale.
[0036] The embryo weight increment is the average of the differences between the current weight and the initial weight of multiple embryos;
[0037] The surface swelling of the embryo is the average value of the swelling of multiple embryos.
[0038] Furthermore, the step of extracting the surface pore contour from the embryo image specifically includes:
[0039] The embryo image is processed to obtain a grayscale image;
[0040] The grayscale image is enhanced to obtain an enhanced image;
[0041] The enhanced image is subjected to mean filtering to obtain a filtered image;
[0042] Edge detection is performed on the filtered image to obtain all the contours of the embryo surface.
[0043] Furthermore, the calculation steps for the basic embryo image similarity and the current embryo image similarity are as follows:
[0044] Obtain the normalized central moments of all contours on the surface of the embryo in the basic embryo contour set, and use them as the basic normalized central moments, denoted as a0. Calculate the average value of a0 for multiple specified embryos, denoted as a.
[0045] Obtain the normalized central moments of all contours on the surface of the embryo in the standard embryo contour set, and use them as the standard normalized central moments, denoted as b.
[0046] Obtain the normalized central moments of all contours on the surface of the embryo in the current embryo contour set, and use them as the current normalized central moments, denoted as c0. Calculate the average value of c0 for multiple specified embryos, denoted as c.
[0047] The formula for calculating the similarity of the basic embryonic images is |ab| / b, and the formula for calculating the similarity of the current embryonic images is |cb| / b.
[0048] Furthermore, the specific steps for adjusting the heating device and steam valve of the autoclave according to the target temperature and target pressure inside the autoclave are as follows:
[0049] If the target temperature is lower than the current temperature, reduce the power of the heating device or turn off the heating device so that the difference between the current temperature and the target temperature is within ±5% to ±10%, where the current temperature is the temperature inside the autoclave collected by the current temperature monitoring module.
[0050] If the target temperature is higher than the current temperature, increase the power of the heating device so that the difference between the current temperature and the target temperature is within ±5% to ±10%.
[0051] If the target pressure is lower than the current pressure, reduce the steam inflow rate of the steam valve or close the steam valve so that the difference between the current pressure and the target pressure is within ±5% to ±10%, where the current pressure is the pressure inside the autoclave collected by the current pressure monitoring module.
[0052] If the target pressure is higher than the current pressure, increase the steam inflow rate of the steam valve so that the difference between the current pressure and the target pressure is within ±5% to ±10%.
[0053] Furthermore, the temperature inside the autoclave includes the temperature of multiple points inside the autoclave, and the multiple points include at least the eight fixed points of the largest cuboid inside the autoclave and the center point of the autoclave.
[0054] Furthermore, it also includes a steam convection device, which is disposed on the inner wall of the autoclave.
[0055] Furthermore, it also includes a convection control module, which is used to implement the steps of controlling the steam convection device, specifically:
[0056] If the temperature difference between any two of the multiple points is greater than 1% to 2%, then increase the power of the steam convection device.
[0057] The beneficial effects of adopting the above-mentioned improvement scheme are as follows: by increasing the power of the steam convection device, the steam convection speed in the autoclave is increased, which is used to quickly achieve temperature balance in the autoclave.
[0058] Furthermore, the historical dataset is identical to the current embryo's formula and the process treatment prior to the autoclaving process.
[0059] Compared with existing technologies, the beneficial effects of the autoclave autoclave control system provided by this invention are as follows: By setting the historical dataset acquisition interval to 1-15 minutes, the entire autoclaving process can be divided into multiple time periods according to the specified time intervals. Each time period corresponds to a different target temperature and target pressure. The target temperature and target pressure for each time period are not obtained based on the sequential time periods from start to finish, but rather based on the correspondence between different embryo images, weight increments, and surface expansion data. This solves the technical problem that the temperature and pressure inside the autoclave cannot be accurately adjusted based on the autoclaving progress parameters of the embryo during the autoclaving process. By setting multiple temperature acquisition points, the temperature at different points inside the autoclave can be obtained. By increasing the power of the steam convection device, the steam convection velocity inside the autoclave is increased, enabling rapid temperature balance to be achieved within the autoclave. Attached Figure Description
[0060] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0061] Figure 1 A block diagram of a steam pressure control system for an autoclave provided by the present invention. Detailed Implementation
[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0063] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.
[0064] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.
[0065] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.
[0066] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.
[0067] like Figure 1 The diagram illustrates an embodiment of a autoclave control system provided by the present invention. In this embodiment, the autoclave is used for the autoclaving process of aerated concrete blocks. The autoclave has a heating device, and the autoclave control system includes the following modules:
[0068] The embryo image acquisition module is used to acquire images of a specified embryo inside the autoclave;
[0069] The embryo weight acquisition module is used to acquire the weight of a specified embryo inside the autoclave;
[0070] The embryo expansion acquisition module is used to acquire the expansion dimensions of a specified embryo on its front, back, left, and right sides inside the autoclave.
[0071] The temperature monitoring module is used to acquire the temperature inside the autoclave.
[0072] The air pressure monitoring module is used to obtain the air pressure inside the autoclave;
[0073] The environmental control module is used to control the heating device of the autoclave, as well as the opening and closing of the steam valve and the steam inflow rate.
[0074] In the above technical solution, the environmental control module is used to realize the steps of obtaining the autoclaving environment parameters according to the autoclaving progress parameters, and adjusting the heating device and autoclaving valve according to the autoclaving environment parameters. The autoclaving process data includes the autoclaving progress parameters of the specified embryo and the autoclaving environment parameters of the autoclave. The autoclaving progress parameters include embryo image, weight increment, and surface expansion. The autoclaving environment parameters include the temperature and air pressure inside the autoclave.
[0075] The steps of obtaining the autoclaving environment parameters based on the autoclaving progress parameters, and adjusting the heating device and autoclaving valves based on the autoclaving environment parameters, specifically include:
[0076] Multiple sets of autoclaving progress parameters and corresponding autoclaving environment parameters were collected to form a historical dataset. The time interval for collecting the historical dataset was 1 min to 15 min.
[0077] Select the datasets from historical datasets that correspond to factory-produced autoclaved aerated concrete blocks that meet the quality standards as the base dataset;
[0078] Surface pore contours are extracted from the embryo images of each item in the basic dataset to obtain the basic embryo contour set;
[0079] Calculate the similarity between the basic embryonic contour set and the standard embryonic contour set for each item in the basic dataset, and denote it as the basic embryonic image similarity.
[0080] Establish a training dataset. The input of the training dataset is the basic embryo autoclave autoclave rate parameter for each item in the basic dataset. The output of the training dataset is the autoclave environment parameter corresponding to the basic embryo autoclave rate parameter in the same group.
[0081] A preliminary model of the temperature and pressure of the autoclave was established using a convolutional neural network, and trained using a training dataset to obtain the autoclave temperature and pressure model.
[0082] Surface pore contours are extracted from the embryo image to obtain the current embryo contour set;
[0083] Calculate the similarity between the current embryo body contour set and the standard embryo body contour set, and denote it as the current embryo body image similarity.
[0084] Using the current autoclaving progress parameters as model input, the target temperature and target pressure inside the autoclave are calculated using the autoclave temperature and pressure model.
[0085] Adjust the heating device and steam valve of the autoclave according to the target temperature and target pressure inside the autoclave.
[0086] The steam valve of the autoclave is an electronically controlled steam valve.
[0087] In the above technical solution, the specified embryo includes two groups, each group including 2 or 4 embryos, namely the image weight acquisition group and the surface dilatation acquisition group.
[0088] In this process, each embryo in the image weight acquisition group is placed on a spring scale. When the number of embryos in the image weight acquisition group is 2, one spring scale is placed at each of the two longitudinal ends of the autoclave. When the number of embryos in the image weight acquisition group is 4, two spring scales are placed at each of the two longitudinal ends of the autoclave, with one embryo placed on every other spring scale.
[0089] A set of high-definition cameras are installed on the inner walls of both longitudinal ends of the autoclave. The high-definition cameras are used to acquire the reading images of the elastic scale and the images of the front, back, left, right and top surfaces of the embryo as images of the embryo.
[0090] The weight of the corresponding embryo is obtained by recognizing the image of the elastic scale captured by the high-definition camera;
[0091] In the surface expansion acquisition group, a displacement sensor is placed close to the center of each of the four faces (front, back, left, and right) of the embryo. The displacement sensor is used to acquire the displacement caused by the external expansion of the corresponding embryo.
[0092] The formula for calculating embryo expansion is P(x,y)=(x1+x2) / 2+(y1+y2) / 2, where P(x,y) represents embryo expansion, including transverse expansion x and longitudinal expansion y, x1 and x2 are the displacements caused by the outward expansion of the front and rear surfaces of the embryo, respectively; y1 and y2 are the displacements caused by the outward expansion of the left and right surfaces of the embryo, respectively.
[0093] The high-definition camera is set inside a heat-insulated, sealed, transparent cover. The high-definition camera has a resolution greater than 720P. There are 6 high-definition cameras in each group. The lenses of five high-definition cameras are facing the front, back, left, right and top surfaces of the embryo in the image weight acquisition group. The other high-definition camera is used to acquire the reading image of the elastic scale.
[0094] The embryo weight increment is the average of the differences between the current weight and the initial weight of multiple embryos;
[0095] The surface swelling of the embryo is the average value of the swelling of multiple embryos.
[0096] Among them, the elastic scale is a pointer-type elastic scale. Chinese invention patent (application number CN201110359130.0), publication number CN102521560B, provides a highly robust instrument pointer image recognition method, mainly including two stages: offline calibration and online recognition. The offline calibration stage includes: image acquisition, image preprocessing, label learning, instrument position calibration, instrument characteristic learning, pointer recognition method and parameter selection, database establishment, and calibration result saving. The online recognition stage includes: image acquisition, image preprocessing, instrument positioning, instrument image grayscale adjustment, pointer extraction, and pointer reading calculation. This highly robust instrument pointer image recognition method exhibits high robustness, showing strong resistance to instrument translation, rotation, occlusion, changes in lighting, instrument deformation caused by different viewing angles, and changes in image size caused by different distances. It can accurately identify pointer readings and operate stably in real-world environments.
[0097] Similarly, Chinese invention patent CN101650198B (application number CN200910042108.6) provides an image processing method for reading the readings of pointer instruments, and Chinese invention patent CN115331014B (application number CN202211265949.5) provides a machine vision-based pointer instrument reading method, system, and storage medium. In this solution, one of the methods in the above inventions can be selected to identify the reading image of the elastic scale.
[0098] Furthermore, in the above technical solution, the step of extracting the surface pore contour from the embryo image specifically includes:
[0099] The embryonic image is processed to obtain a grayscale image;
[0100] An enhanced image is obtained by performing enhancement processing on a grayscale image;
[0101] The enhanced image is subjected to mean filtering to obtain the filtered image;
[0102] Edge detection is performed on the filtered image to obtain all the contours of the embryo surface.
[0103] Among them, the method for enhancing grayscale images is median filtering; the edge detection method is Sobel edge detection.
[0104] Furthermore, in the above technical solution, the calculation steps for the basic embryo image similarity and the current embryo image similarity are as follows:
[0105] Obtain the normalized central moments of all contours on the surface of the embryo in the basic embryo contour set, and use them as the basic normalized central moments, denoted as a0. Calculate the average value of a0 for multiple specified embryos, denoted as a.
[0106] Obtain the normalized central moments of all contours on the surface of the embryo in the standard embryo contour set, and use them as the standard normalized central moments, denoted as b.
[0107] Obtain the normalized central moments of all contours on the surface of the embryo in the current embryo contour set, and use them as the current normalized central moments, denoted as c0. Calculate the average value of c0 for multiple specified embryos, denoted as c.
[0108] The formula for calculating the similarity of the basic embryonic images is |ab| / b, and the formula for calculating the similarity of the current embryonic images is |cb| / b.
[0109] The method for calculating the normalized central moments of all contours is to use the Moments class in OpenCV.
[0110] Furthermore, in the above technical solution, the specific steps for adjusting the heating device and steam valve of the autoclave according to the target temperature and target pressure inside the autoclave are as follows:
[0111] If the target temperature is lower than the current temperature, reduce the power of the heating device or turn off the heating device so that the difference between the current temperature and the target temperature is within ±5% to ±10%, where the current temperature is the temperature inside the autoclave collected by the current temperature monitoring module.
[0112] If the target temperature is higher than the current temperature, increase the power of the heating device so that the difference between the current temperature and the target temperature is within ±5% to ±10%.
[0113] If the target pressure is lower than the current pressure, reduce the steam inflow rate of the steam valve or close the steam valve so that the difference between the current pressure and the target pressure is within ±5% to ±10%, where the current pressure is the pressure inside the autoclave collected by the current pressure monitoring module.
[0114] If the target pressure is higher than the current pressure, increase the steam inflow rate of the steam valve so that the difference between the current pressure and the target pressure is within ±5% to ±10%.
[0115] Because the autoclave itself dissipates heat, reducing the power of the heating device, or even stopping the heating device altogether, will lower the temperature inside the autoclave. Therefore, the temperature and pressure of the autoclave are adjusted simultaneously.
[0116] Furthermore, in the above technical solution, the temperature inside the autoclave includes the temperature of multiple points inside the autoclave, and the multiple points include at least the eight fixed points of the largest cuboid inside the autoclave and the center point of the autoclave.
[0117] The temperature of multiple points inside the autoclave was collected using an electronic thermometer.
[0118] Furthermore, the above technical solution also includes a steam convection device, which is installed on the inner wall of the autoclave.
[0119] The steam convection device is a fan.
[0120] Furthermore, the above technical solution also includes a convection control module, which is used to implement the steps of controlling the steam convection device, specifically:
[0121] When the temperature difference between multiple points is greater than 1% to 2%, the power of the steam convection device should be increased.
[0122] Furthermore, in the above technical solution, the historical dataset is the same as the current embryo's formula and the process treatment before the autoclaving process.
[0123] Specifically, the principle of this invention is:
[0124] Common autoclaved aerated concrete (AAC) blocks are prone to quality problems such as black core and curing cracks during the autoclaving process.
[0125] (1) Black-hearted
[0126] The "black core" refers to the middle layer extending about 10 centimeters upwards from the bottom five centimeters of the product's building block after it exits the reactor. Because its color is darker than the rest of the block, it's called the "black core." This material has very low strength and is prone to breakage during handling. The main causes of this are high steam moisture content, insufficient lime content, low steam pressure, and untimely condensate drainage.
[0127] (2) Steam curing cracks
[0128] The steam curing stage is a crucial step in the transformation of the preform into the final product. After high-temperature autoclaving, the calcium and silica materials within the aerated concrete preform will form silicate compounds, thereby achieving the required strength. However, during steam curing, the preform will shrink and expand. Due to the uneven temperature distribution inside and on the surface of the preform, if the temperature changes rapidly and the strength is low, cracking and damage can easily occur.
[0129] Therefore, it is necessary to adjust the temperature and pressure inside the autoclave based on the current autoclaving progress parameters of the embryo. The black-heart phenomenon is mainly caused by high steam moisture content, which manifests as excessive weight gain of the embryo during autoclaving. Steam-curing cracks manifest as surface cracks or excessive surface expansion of the embryo during autoclaving. Therefore, collecting autoclaving progress parameters, including embryo images, weight gain, and surface expansion, and precisely adjusting the temperature and pressure inside the autoclave based on these parameters, is crucial to effectively avoid quality problems such as black-heart and steam-curing cracks.
[0130] On the other hand, by setting the historical dataset collection interval to 1 min to 15 min, the entire autoclaving process can be divided into multiple time periods according to the specified time interval. Each time period corresponds to a different target temperature and target pressure. The target temperature and target pressure for each time period are not obtained according to the sequential time period from start to finish, but according to the correspondence between different preform images, weights, and surface expansion data. This solves the technical problem that the temperature and pressure inside the autoclave cannot be accurately adjusted according to the autoclaving progress parameters of the preform in the autoclaving process, and can improve the quality of autoclaved aerated concrete blocks.
[0131] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A pressure control system for an autoclave, characterized in that, The autoclave is used in the autoclaving process of autoclaved aerated concrete blocks, and the autoclaving control system of the autoclave comprises the following modules: a green body image acquisition module for acquiring images of specified green bodies in the autoclave; a green body weight acquisition module for acquiring weights of the specified green bodies in the autoclave; a green body expansion degree acquisition module for acquiring expansion sizes of the front, back, left and right four surfaces of the specified green bodies in the autoclave; a temperature monitoring module for acquiring the temperature in the autoclave; an air pressure monitoring module for acquiring the air pressure in the autoclave; an environment control module for controlling the heating device of the autoclave and controlling the opening and closing of the steam valve of the autoclave and the steam inflow speed; the environment control module is used to realize the steps of obtaining autoclaving environment parameters according to autoclaving progress parameters and adjusting the heating device and the steam valve according to the autoclaving environment parameters, wherein the autoclaving progress parameters include green body images, weight increments and surface expansion degrees, and the autoclaving environment parameters include the temperature and the air pressure in the autoclave; the steps of obtaining autoclaving environment parameters according to autoclaving progress parameters and adjusting the heating device and the steam valve according to the autoclaving environment parameters specifically include: collecting multiple sets of autoclaving progress parameters and corresponding autoclaving environment parameters to form a historical data set, and the collection time interval of the historical data set is 1 min to 15 min; screening data sets corresponding to autoclaved aerated concrete blocks meeting the quality standards in the historical data set as a basic data set; extracting surface pore profiles from the green body images in each item of the basic data set to obtain a basic green body profile set; calculating the similarity of the basic green body profile set in each item of the basic data set and a standard green body profile set, which is recorded as a basic green body image similarity; establishing a training data set, the input of the training data set is the basic green body autoclaving progress parameters in each item of the basic data set, and the output of the training data set is the autoclaving environment parameters corresponding to the same group of the basic green body autoclaving progress parameters; using a convolutional neural network to establish a preliminary form of an autoclave temperature and air pressure model, and training the preliminary form using the training data set to obtain the autoclave temperature and air pressure model; extracting surface pore profiles from the green body images to obtain a current green body profile set; calculating the similarity of the current green body profile set and the standard green body profile set, which is recorded as a current green body image similarity; using the autoclave temperature and air pressure model to calculate the target temperature and the target air pressure in the autoclave by taking the current autoclaving progress parameters as the model input; adjusting the heating device and the steam valve of the autoclave according to the target temperature and the target air pressure in the autoclave.
2. The autoclave control system according to claim 1, wherein The specified green bodies include two groups, each group including 2 or 4 green bodies, which are an image weight acquisition group and a surface expansion degree acquisition group; wherein each green body of the image weight acquisition group is placed on an elastic scale, when the number of green bodies of the image weight acquisition group is 2, one elastic scale is placed at each longitudinal end of the autoclave; when the number of green bodies of the image weight acquisition group is 4, two elastic scales are placed at each longitudinal end of the autoclave, and one green body is placed on each elastic scale. The inner wall of the longitudinal two ends of the autoclave is respectively provided with a set of high-definition cameras, the high-definition cameras are used to obtain the reading image of the elastic scale and the images of the front, back, left and right and the upper surface of the blank of the image weight acquisition group as the blank image; The weight of the corresponding blank is obtained after identifying the image of the elastic scale collected by the high-definition camera; A displacement sensor is tightly arranged at the center of each of the front, back, left and right four surfaces of the surface expansion acquisition group, and the displacement sensor is used to obtain the displacement caused by the outer expansion of the corresponding blank; The calculation formula of the blank expansion degree is P(x, y) = (x1+x2) / 2 + (y1+y2) / 2, wherein P(x, y) represents the blank expansion degree, including the transverse expansion degree x and the longitudinal expansion degree y, x1 and x2 are respectively the displacement caused by the outer expansion of the front and back two surfaces of the blank, and y1 and y2 are respectively the displacement caused by the outer expansion of the left and right two surfaces of the blank; The high-definition camera is arranged in a heat-insulating and airtight transparent cover, the high-definition camera is a camera with a resolution greater than 720P, each set of high-definition camera is six, wherein the lenses of five high-definition cameras are directly opposite the front, back, left and right and the upper surface of the blank of the image weight acquisition group, and the other high-definition camera is used to obtain the reading image of the elastic scale; The weight increment is the average value of the difference between the current weight and the initial weight of a plurality of blanks; The surface expansion degree is the average value of the expansion degrees of a plurality of blanks.
3. The autoclave control system of claim 2, wherein The step of performing surface pore profile extraction on the blank image specifically includes: Performing gray scale processing on the blank image to obtain a gray scale image; Performing enhancement processing on the gray scale image to obtain an enhanced image; Performing mean filter processing on the enhanced image to obtain a filtered image; Performing edge detection on the filtered image to obtain all the profiles of the blank surface.
4. The autoclave control system according to claim 3, wherein The calculation steps of the base blank image similarity and the current blank image similarity are: Obtain the normalized central moments of all the profiles of the blank surface in the base blank profile set as the base normalized central moments, denoted as a0, and calculate the average value of a0 of a plurality of specified blanks, denoted as a; Obtain the normalized central moments of all the profiles of the blank surface in the standard blank profile set as the standard normalized central moments, denoted as b; Obtain the normalized central moments of all the profiles of the blank surface in the current blank profile set as the current normalized central moments, denoted as c0, and calculate the average value of c0 of a plurality of specified blanks, denoted as c; The calculation formula of the base blank image similarity is |a-b| / b, and the calculation formula of the current blank image similarity is |c-b| / b.
5. The autoclave control system according to claim 4, wherein The specific steps of adjusting the heating device and the steam valve of the autoclave according to the target temperature and the target pressure in the current autoclave are: If the target temperature is lower than the current temperature, reduce the power of the heating device or turn off the heating device, so that the difference between the current temperature and the target temperature is within-10%~10%, wherein the current temperature is the temperature in the autoclave collected by the current temperature monitoring module; If the target temperature is higher than the current temperature, increase the power of the heating device, so that the difference between the current temperature and the target temperature is within-10%~10%. If the target pressure is lower than the current pressure, the steam valve is closed or the steam inflow rate is reduced so that the difference between the current pressure and the target pressure is within 10%. If the target pressure is higher than the current pressure, the steam inflow rate is increased so that the difference between the current pressure and the target pressure is within 10%.
6. The autoclave control system of claim 5, wherein, The temperature in the autoclave includes the temperature of multiple points in the autoclave, and the multiple points at least include eight vertices of a maximum cuboid in the autoclave and a center point of the autoclave.
7. The autoclave control system of claim 6, wherein, The steam convection device is arranged on the inner wall of the autoclave.
8. The autoclave control system of claim 7, wherein, The convection control module is used to implement the steam convection device control, and specifically includes the following steps: When the temperature difference between any two points is greater than 1% to 2%, the power of the steam convection device is increased.
9. The autoclave control system according to any one of claims 1 to 8, wherein The historical data set is the same as the formula of the current blank and the process treatment before the autoclaving process.
Citation Information
Patent Citations
Image processing method for reading pointer type instrument indication value
CN101650198B
Instrument pointer image identification method of high-robustness rod
CN102521560A
Instrument pointer image identification method of high-robustness rod
CN102521560B
Pointer instrument reading method and system based on machine vision, and storage medium
CN115331014A
A machine vision-based method and system for reading pointer instruments, and a storage medium.
CN115331014B