Automatic control system for foaming mixer

Abstract

The present invention relates to the field of automatic control technology. The present invention discloses an automatic control system for a foaming mixer, comprising collecting stirring speed training data and collecting fluid speed training data; training a first machine learning model based on the stirring speed training data of the foaming mixer, and training a second machine learning model based on the fluid speed training data of foamed concrete; acquiring stirring speed characteristic data of the foaming mixer, and acquiring an optimal stirring speed based on the stirring speed characteristic data and the first machine learning model; acquiring fluid speed characteristic data of the foamed concrete in real time, and grasping the fluid speed of the foamed concrete in real time based on the fluid speed characteristic data and the second machine learning model; acquiring expected effect data input by a user, and controlling the start and stop of the foaming mixer according to the expected effect data and the fluid speed grasped in real time; the present invention reduces the deviation caused by manual intervention, so that the prepared foamed concrete can meet user needs.

Description

Technical Field

[0001] The present invention relates to the field of automatic control technology, and more specifically, to an automatic control system for a foaming mixer. Background Art

[0002] Foamed concrete is a new type of building material that is lightweight, heat-insulating, heat-insulating and sound-insulating. It has excellent performance characteristics and has therefore been widely used in the construction industry. In the preparation process of foamed concrete, the foaming mixer is a crucial equipment, which forms the foamed body of foamed concrete by mixing and stirring raw materials such as water, cement, and foaming agent, and injecting gas. However, traditional foaming mixers have some problems. First, the operation process requires manual intervention and is easily affected by human factors, resulting in unstable production processes. Second, the production efficiency is low and cannot meet the needs of large-scale production. In addition, the quality of foamed concrete is affected by factors such as mixing speed, and precise control of these parameters is required.

[0003] At present, there is a lack of systems for realizing automatic control of foaming mixers. Although there are some relevant technical documents, for example, the Chinese patent with authorization announcement number CN101739000B discloses an intelligent control system for asphalt foaming devices; although the above method can realize intelligent control of the foaming device, research and practical application of the above method and the prior art have found that the above method and the prior art have at least the following defects:

[0004] (1) It is difficult to apply to concrete foaming scenarios. It is impossible to accurately determine the optimal mixing speed of the foaming mixer, and thus it is impossible to ensure the mixing quality of the foamed concrete;

[0005] (2) It is impossible to control the mixing effect of the foaming mixer in real time during the mixing process according to the optimal mixing speed, and it is impossible to reduce the deviation caused by manual intervention. As a result, it is impossible to automatically control the foaming mixer according to the actual needs of the user, making it difficult to make the foamed concrete meet the actual needs of the user, and the production efficiency is low. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an automatic control system for a foaming mixer.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The automatic control system of a foaming mixer comprises:

[0009] A data collection module is used to collect the mixing speed training data of the foaming mixer and the fluid speed training data of the foamed concrete;

[0010] A model training module, for training a first machine learning model for predicting an optimal stirring speed of a foaming mixer based on stirring speed training data of the foaming mixer, and for training a second machine learning model for the fluid velocity of foamed concrete based on the fluid velocity training data of foamed concrete;

[0011] A speed determination module, used to obtain stirring speed characteristic data of the foaming stirrer in an actual scenario, and to obtain an optimal stirring speed of the foaming stirrer based on the stirring speed characteristic data and a first machine learning model;

[0012] A performance mastering module, for acquiring fluid velocity characteristic data of foamed concrete in real time when the foaming mixer is stirred and controlled according to an optimal stirring speed, and mastering the fluid velocity of the foamed concrete in real time based on the fluid velocity characteristic data and a second machine learning model;

[0013] The automatic control module is used to obtain the expected effect data input by the user, and control the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed. The expected effect data is the required fluid speed range.

[0014] Furthermore, the stirring speed training data of the foaming mixer includes stirring speed characteristic data and its corresponding optimal stirring speed; wherein, the stirring speed characteristic data includes material requirement data, raw material ratio data and machine internal environment data; the material requirement data is the demand for foamed concrete; the raw material ratio data includes water-cement ratio, foam group dosage and filler; the machine internal environment data includes machine internal air pressure value and machine internal temperature value.

[0015] Furthermore, the raw material ratio data is obtained after matching the mapping relationship between the material demand data and the raw material ratio data;

[0016] The determination logic of the optimal stirring speed is as follows:

[0017] a1: In the test scenario, the initial stirring speed of the foaming mixer is set to r according to the stirring speed characteristic data, where r is an integer greater than or equal to zero;

[0018] a2: Increase the initial stirring speed, set R = r + u, and obtain the stirring adjustment speed R, where u and R are integers greater than zero;

[0019] a3: When the foaming mixer is controlled to mix according to the stirring adjustment speed R, a material mixing image in the foaming mixer is collected, and the RGB value and the number of color types of each pixel in the material mixing image are recorded using RGB color space analysis technology;

[0020] a4: Calculate the mixing uniformity coefficient of the materials in the foaming mixer based on the number of color types and the RGB values ​​of the pixels, and compare the mixing uniformity coefficient with the preset standard range of the mixing uniformity coefficient. If the mixing uniformity coefficient belongs to the preset standard range of the mixing uniformity coefficient, record the stirring adjustment speed R as the optimal stirring speed; if the mixing uniformity coefficient does not belong to the preset standard range of the mixing uniformity coefficient, set R=R+L, and return to step a2;

[0021] a5: Repeat the above steps a2 to a4 until the optimal stirring speed is obtained, and then end the cycle.

[0022] Furthermore, the calculation of the mixing uniformity coefficient of the materials in the foaming mixer includes:

[0023] Extract the RGB value and color number of each pixel in the material mixture image, and call the preset standard uniform frequency;

[0024] The RGB value of the pixel point, the number of color types and the preset standard uniform frequency are input into the preconfigured uniformity coefficient mathematical model to obtain the mixed uniformity coefficient; wherein the uniformity coefficient mathematical model is: ; Where: is the mixing uniformity coefficient, is the frequency of the i-th color category, is the total number of pixels in the material mixture image, is the number of pixels of the i-th color category, To preset the standard uniform frequency, is the number of color types.

[0025] Furthermore, the fluid velocity training data of the foamed concrete includes fluid velocity characteristic data of the foamed concrete and its corresponding fluid velocity; wherein the fluid velocity characteristic data includes density, shear stress and viscosity coefficient of the foamed concrete.

[0026] Furthermore, the generation logic of the first machine learning model is as follows:

[0027] Extract stirring speed training data, and divide the stirring speed training data into a stirring speed training set and a stirring speed test set;

[0028] Constructing a first regression network, taking the stirring speed characteristic data in the stirring speed training set as input data of the first regression network, taking the best stirring speed in the stirring speed training set as output data of the first regression network, training the first regression network, and obtaining a first initial regression network;

[0029] The stirring speed test set is used to perform a model test on the first initial regression network, and the corresponding first initial regression network that is less than or equal to a preset test error threshold is used as the first initial regression network.

[0030] Furthermore, the generation logic of the second machine learning model is as follows:

[0031] Extracting fluid velocity training data, and dividing the fluid velocity training data into a fluid velocity training set and a fluid velocity test set;

[0032] Constructing a second regression network, taking the fluid velocity feature data in the fluid velocity training set as input data of the second regression network, taking the fluid velocity in the fluid velocity training set as output data of the second regression network, training the second regression network, and obtaining a second initial regression network;

[0033] The second initial regression network is model tested using the fluid velocity test set, and the corresponding second initial regression network that is less than or equal to a preset test error threshold is used as the second initial regression network.

[0034] Furthermore, the process of obtaining the optimal stirring speed of the foaming mixer is as follows:

[0035] Extract stirring speed characteristic data obtained in the actual scene, and convert the stirring speed characteristic data into a vector form;

[0036] The stirring speed feature data in vector form is input into the first machine learning model to obtain the optimal stirring speed of the foaming mixer.

[0037] Furthermore, the process of obtaining the fluid velocity of the foamed concrete is as follows:

[0038] Extracting the fluid velocity characteristic data obtained in the actual scene, and converting the fluid velocity characteristic data into a vector form;

[0039] The fluid velocity feature data in vector form is input into the second machine learning model to obtain the fluid velocity of the foamed concrete.

[0040] Furthermore, the method of controlling the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed comprises:

[0041] Compare the real-time fluid velocity with the required fluid velocity range;

[0042] If the real-time fluid velocity is within the required fluid velocity range, it is determined that the foamed concrete being mixed has achieved the expected effect, and the foaming mixer is controlled to stop running;

[0043] If the fluid velocity obtained in real time is not within the required fluid velocity range, it is determined that the foamed concrete being mixed has not achieved the expected effect, and the foaming mixer is controlled to continue to operate.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] (1) The present application discloses an automatic control system for a foaming mixer, including collecting stirring speed training data and collecting fluid speed training data; training a first machine learning model based on the stirring speed training data of the foaming mixer, and training a second machine learning model based on the fluid speed training data of foamed concrete; obtaining stirring speed characteristic data of the foaming mixer, and obtaining an optimal stirring speed based on the stirring speed characteristic data and the first machine learning model; obtaining fluid speed characteristic data of the foamed concrete in real time, and grasping the fluid speed of the foamed concrete in real time based on the fluid speed characteristic data and the second machine learning model; obtaining expected effect data input by a user, and controlling the start and stop of the foaming mixer according to the expected effect data and the fluid speed grasped in real time; based on the above content, the present invention can accurately determine the optimal stirring speed of the foaming mixer, which is conducive to ensuring the mixing quality of the foamed concrete and is suitable for concrete foaming scenarios; in addition, in the process of controlling the foaming mixer to stir according to the optimal stirring speed, the stirring effect is grasped in real time, which is conducive to reducing the deviation caused by manual intervention, and then the foaming mixer can be automatically controlled according to the actual needs of the user, which is conducive to making the prepared foamed concrete meet the actual needs of the user and improving production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A module structure diagram of the automatic control system of the foaming mixer provided by the present invention;

[0047] Figure 2 The present invention provides a flowchart of the automatic control method of the foaming mixer. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] Example 1: Please refer to Figure 1 As shown, this embodiment discloses an automatic control system for a foaming mixer, the system comprising:

[0050] The data collection module 110 is used to collect the mixing speed training data of the foaming mixer and the fluid speed training data of the foamed concrete;

[0051] It should be understood that the general preparation process of foamed concrete is as follows: (1) Preparation of raw materials: ordinary silicate cement is selected for cement; appropriate surfactant or bubble stabilizer is used for foaming agent; fly ash is selected as filler to improve the lightweight performance of foamed cement; water is used to mix into a slurry-like substance; (2) Foaming: a professional foaming machine is used to inject the foaming agent into the water and stir to produce foam to form a foam group; (3) Mixing and stirring: cement, fly ash and an appropriate amount of water are mixed to form a uniform slurry-like substance, and the formed slurry-like substance is poured into the foam group and stirred to obtain lightweight foamed concrete;

[0052] Based on the above introduction, it should be understood that the present application is applied to the mixing process, that is, after the foam group is prepared and the raw materials are prepared, the mixing control is performed, aiming to realize the automatic mixing control of the foam concrete, so as to ensure that the prepared foam concrete can meet the needs of users and cater to different application scenarios, while reducing manual intervention and improving production efficiency;

[0053] Specifically, the stirring speed training data of the foaming mixer includes stirring speed characteristic data and its corresponding optimal stirring speed; wherein the stirring speed characteristic data includes material demand data, raw material ratio data and machine internal environment data; the material demand data is the demand for foamed concrete; the raw material ratio data includes water-cement ratio, foam group dosage and filler, and the filler is fly ash; the machine internal environment data includes machine internal air pressure value and machine internal temperature value;

[0054] It should be noted that: the material demand data, i.e., the demand for foamed concrete, is determined according to the volume of foamed concrete input by the user in the historical construction scene; further explained is that the foaming mixer includes a data input module, and the user (i.e., the on-site construction personnel) estimates the demand for foamed concrete according to the actual construction scene, and then inputs it into the data input module in the foaming mixer; the internal environment data is actually collected by various sensors preset in the foaming mixer, and the various sensors include but are not limited to air pressure sensors and temperature sensors;

[0055] The raw material ratio data is obtained by matching the mapping relationship between the material demand data and the raw material ratio data;

[0056] It should be noted that: a plurality of mapping relationships between material demand data and raw material ratio data are pre-stored in the system database, and in each mapping relationship, a demand for a foamed concrete is associated and bound with a raw material ratio data; wherein the raw material ratio data is determined by the technicians based on historical experience or specific experimental simulation results;

[0057] Wherein, the determination logic of the optimal stirring speed is as follows:

[0058] a1: In the test scenario, the initial stirring speed of the foaming mixer is set to r according to the stirring speed characteristic data, where r is an integer greater than or equal to zero;

[0059] It should be noted that the initial stirring speed r of the foaming stirrer is automatically assigned by the system program, and the initial value r of r is usually initialized to zero;

[0060] a2: Increase the initial stirring speed, set R = r + u, and obtain the stirring adjustment speed R, where u and R are integers greater than zero;

[0061] a3: When the foaming mixer is controlled to mix according to the stirring adjustment speed R, a material mixing image in the foaming mixer is collected, and the RGB value and the number of color types of each pixel in the material mixing image are recorded using RGB color space analysis technology;

[0062] It should be noted that: a camera device is also provided on the foaming mixer to collect images of material mixing in the foaming mixer; in addition, the RGB color space analysis technology includes but is not limited to color histogram, color quantization, color segmentation and color feature extraction, etc., and its actual tools include but are not limited to OpenCV, Pillow and MATLAB, etc. In image processing and analysis, the RGB color space is often used to extract and analyze image data, including but not limited to RGB values ​​and the number of color types, etc., which is a prior art and will not be described in detail;

[0063] a4: Calculate the mixing uniformity coefficient of the materials in the foaming mixer based on the number of color types and the RGB values ​​of the pixels, and compare the mixing uniformity coefficient with the preset standard range of the mixing uniformity coefficient. If the mixing uniformity coefficient belongs to the preset standard range of the mixing uniformity coefficient, record the stirring adjustment speed R as the optimal stirring speed; if the mixing uniformity coefficient does not belong to the preset standard range of the mixing uniformity coefficient, set R=R+L, and return to step a2;

[0064] In implementation, the calculation of the mixing uniformity coefficient of the materials in the foaming mixer includes:

[0065] Extract the RGB value and color number of each pixel in the material mixture image, and call the preset standard uniform frequency;

[0066] It should be noted that the preset standard uniform frequency is set and determined in advance by the technicians, which indicates the uniform frequency of each color type under ideal circumstances;

[0067] The RGB value of the pixel point, the number of color types and the preset standard uniform frequency are input into the preconfigured uniformity coefficient mathematical model to obtain the mixed uniformity coefficient; wherein the uniformity coefficient mathematical model is: ; Where: is the mixing uniformity coefficient, is the frequency of the i-th color category, is the total number of pixels in the material mixture image, is the number of pixels of the i-th color category, To preset the standard uniform frequency, is the number of color types;

[0068] a5: Repeat the above steps a2 to a4 until the optimal stirring speed is obtained, and then end the cycle;

[0069] Specifically, the fluid velocity training data of the foamed concrete includes fluid velocity characteristic data of the foamed concrete and its corresponding fluid velocity; wherein the fluid velocity characteristic data includes density, shear stress and viscosity coefficient of the foamed concrete;

[0070] The shear stress is calculated by an existing rheological model, and the formula of the existing rheological model is as follows: ; Where: is the shear stress in Pascals (Pa), K is the rheological constant of the fluid, is the shear rate of the velocity field, n is the power law exponent;

[0071] Wherein, the viscosity coefficient is obtained by measuring with a rotational viscometer, and the measuring formula of the rotational viscometer is: ; Where: is the initial viscosity coefficient value; , is the radius of the coaxial inner and outer cylinders; is the depth of the inner cylinder immersed in the liquid; is the viscous torque, is the angular velocity of the rotating cylinder; where ; Where: is the viscosity force, is the surface area of ​​the cylinder;

[0072] It should be noted that the above-mentioned fluid velocity characteristic data is measured by various fluid measurement sensors, including but not limited to density meters, rotational viscometers and shear stress meters; the fluid velocity in the fluid velocity training data is determined by technicians after recording the values ​​collected by the flow velocity sensor.

[0073] A model training module 120 is used to train a first machine learning model for predicting an optimal stirring speed of a foaming mixer based on stirring speed training data of the foaming mixer, and to train a second machine learning model for the fluid velocity of foamed concrete based on the fluid velocity training data of foamed concrete;

[0074] In implementation, the generation logic of the first machine learning model is as follows:

[0075] Extract stirring speed training data, and divide the stirring speed training data into a stirring speed training set and a stirring speed test set;

[0076] Constructing a first regression network, taking the stirring speed characteristic data in the stirring speed training set as input data of the first regression network, taking the best stirring speed in the stirring speed training set as output data of the first regression network, training the first regression network, and obtaining a first initial regression network;

[0077] It should be understood that the stirring speed characteristic data and the optimal stirring speed in the stirring speed training data are obtained through actual collection and data analysis, respectively. The specific acquisition logic is described above and will not be repeated here.

[0078] The first initial regression network is tested by using the stirring speed test set, and the corresponding first initial regression network that is less than or equal to a preset test error threshold is used as the first initial regression network;

[0079] It should be noted that: the first regression network is a specific one of algorithms such as random forest regression, decision tree regression, polynomial regression, linear regression or neural network model;

[0080] In implementation, the generation logic of the second machine learning model is as follows:

[0081] Extracting fluid velocity training data, and dividing the fluid velocity training data into a fluid velocity training set and a fluid velocity test set;

[0082] Constructing a second regression network, taking the fluid velocity feature data in the fluid velocity training set as input data of the second regression network, taking the fluid velocity in the fluid velocity training set as output data of the second regression network, training the second regression network, and obtaining a second initial regression network;

[0083] Wherein, the acquisition logic of the fluid velocity training data and the fluid velocity in the fluid velocity training data is as described above, and will not be repeated here;

[0084] The second initial regression network is tested by using the fluid velocity test set, and the corresponding second initial regression network that is less than or equal to a preset test error threshold is used as the second initial regression network;

[0085] It should be noted that: like the above-mentioned first regression network, the second regression network is a specific one of algorithms such as random forest regression, decision tree regression, polynomial regression, linear regression or neural network model.

[0086] The speed determination module 130 is used to obtain the stirring speed characteristic data of the foaming mixer in an actual scenario, and obtain the optimal stirring speed of the foaming mixer based on the stirring speed characteristic data and the first machine learning model;

[0087] It should be noted that: in the actual scenario, the specific process of obtaining the stirring speed characteristic data is: obtaining the material demand data input by the user; traversing the mapping relationship between the material demand data and the raw material ratio data in the system database according to the material demand data to obtain the raw material ratio data; obtaining the in-machine environment data based on the sensor, and fusing the material demand data, the raw material ratio data and the in-machine environment data as the stirring speed characteristic data; further, the specific process of obtaining the material demand data, the raw material ratio data and the in-machine environment data is described above;

[0088] In practice, the process of obtaining the optimal stirring speed of the foaming stirrer is as follows:

[0089] Extract stirring speed characteristic data obtained in the actual scene, and convert the stirring speed characteristic data into a vector form;

[0090] The stirring speed feature data in vector form is input into the first machine learning model to obtain the optimal stirring speed of the foaming mixer.

[0091] The performance mastering module 140 is used to obtain the fluid velocity characteristic data of the foamed concrete in real time when the foaming mixer is stirred and controlled according to the optimal stirring speed, and to master the fluid velocity of the foamed concrete in real time based on the fluid velocity characteristic data and the second machine learning model;

[0092] In practice, the process of obtaining the fluid velocity of the foamed concrete is as follows:

[0093] Extracting the fluid velocity characteristic data obtained in the actual scene, and converting the fluid velocity characteristic data into a vector form;

[0094] The fluid velocity feature data in vector form is input into the second machine learning model to obtain the fluid velocity of the foamed concrete.

[0095] The automatic control module 150 is used to obtain the expected effect data input by the user, and control the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed, wherein the expected effect data is the required fluid speed range;

[0096] It can be understood that the fluid velocity of foamed concrete is an important indicator for judging the performance of foamed concrete. In addition, the required fluid velocity range refers to the expected effect that the mixed foamed concrete should achieve. Further explanation is that users will prepare foamed concrete in accordance with different construction scene requirements.

[0097] In implementation, the method of controlling the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed includes:

[0098] Compare the real-time fluid velocity with the required fluid velocity range;

[0099] If the real-time fluid velocity is within the required fluid velocity range, it is determined that the foamed concrete being mixed has achieved the expected effect, and the foaming mixer is controlled to stop running;

[0100] If the real-time fluid velocity is not within the required fluid velocity range, it is determined that the foamed concrete being mixed has not achieved the expected effect, and the foaming mixer is controlled to continue to operate;

[0101] It should be understood that the "high or low" fluid velocity does not reflect the excellence of foamed concrete, which depends on the application object and application scenario of foamed concrete. In some scenarios, higher flow performance may be beneficial. For example, foamed concrete with high fluid performance is suitable for large-area indoor backfill and can reduce foundation load. Foamed concrete with low fluid performance can make foamed concrete have good energy absorption performance, absorb impact energy, reduce the impact of external impact on structures or devices, and is suitable for manufacturing light structures such as floor slabs and wall panels.

[0102] The foaming mixer is automatically controlled according to the actual needs of the user. The present invention can ensure that the prepared foam concrete is suitable for actual construction scenarios, that is, the prepared foam concrete can meet the needs of the user; at the same time, through automated feedback judgment, the deviation caused by manual intervention can be reduced, which is conducive to improving production efficiency.

[0103] Example 2: Please refer to Figure 2As shown, based on the same inventive concept, referring to Example 1, this embodiment discloses a method for automatically controlling a foaming mixer. For details not provided in this embodiment, please refer to the description of the above-mentioned Example 1. The method includes:

[0104] S201: collecting mixing speed training data of a foaming mixer and collecting fluid speed training data of foamed concrete;

[0105] S201: Based on the training data of the stirring speed of the foaming mixer, a first machine learning model for predicting the optimal stirring speed of the foaming mixer is trained, and based on the training data of the fluid speed of the foamed concrete, a second machine learning model for the fluid speed of the foamed concrete is trained;

[0106] S203: in an actual scenario, obtaining stirring speed characteristic data of the foaming stirrer, and obtaining an optimal stirring speed of the foaming stirrer based on the stirring speed characteristic data and the first machine learning model;

[0107] S204: when the foaming mixer is stirred and controlled according to the optimal stirring speed, the fluid velocity characteristic data of the foamed concrete is obtained in real time, and the fluid velocity of the foamed concrete is grasped in real time based on the fluid velocity characteristic data and the second machine learning model;

[0108] S205: Acquire the expected effect data input by the user, and control the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed, wherein the expected effect data is the required fluid speed range.

[0109] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.

[0110] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired network or a wireless network. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media sets. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD) or a semiconductor medium. The semiconductor medium may be a solid-state hard disk.

[0111] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0113] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0116] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0117] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. Automatic control system for foaming mixer, characterized in that: The system comprises: A data collection module is used to collect the mixing speed training data of the foaming mixer and the fluid speed training data of the foamed concrete; The stirring speed training data of the foaming mixer includes stirring speed characteristic data and its corresponding optimal stirring speed; the stirring speed characteristic data includes material demand data, raw material ratio data and machine internal environment data; the material demand data is the demand for foamed concrete; the raw material ratio data includes water-cement ratio, foam group dosage and filler; the machine internal environment data includes machine internal air pressure value and machine internal temperature value; the raw material ratio data is obtained after matching the mapping relationship between the material demand data and the raw material ratio data; Wherein, the determination logic of the optimal stirring speed is as follows: a1: In the test scenario, the initial stirring speed of the foaming mixer is set to r according to the stirring speed characteristic data, where r is an integer greater than or equal to zero; a2: Increase the initial stirring speed, set R = r + u, and obtain the stirring adjustment speed R, where u and R are integers greater than zero; a3: When the foaming mixer is controlled to mix according to the stirring adjustment speed R, a material mixing image in the foaming mixer is collected, and the RGB value and the number of color types of each pixel in the material mixing image are recorded using RGB color space analysis technology; a4: Calculate the mixing uniformity coefficient of the materials in the foaming mixer based on the number of color types and the RGB values ​​of the pixels, and compare the mixing uniformity coefficient with the preset standard range of the mixing uniformity coefficient. If the mixing uniformity coefficient belongs to the preset standard range of the mixing uniformity coefficient, record the stirring adjustment speed R as the optimal stirring speed; if the mixing uniformity coefficient does not belong to the preset standard range of the mixing uniformity coefficient, set R=R+L, and return to step a2; a5: Repeat the above steps a2 to a4 until the optimal stirring speed is obtained, and then end the cycle; The fluid velocity training data of the foamed concrete includes the fluid velocity characteristic data of the foamed concrete and its corresponding fluid velocity; wherein the fluid velocity characteristic data includes the density, shear stress and viscosity coefficient of the foamed concrete; A model training module, for training a first machine learning model for predicting an optimal stirring speed of a foaming mixer based on stirring speed training data of the foaming mixer, and for training a second machine learning model for the fluid velocity of foamed concrete based on the fluid velocity training data of foamed concrete; A speed determination module, used to obtain stirring speed characteristic data of the foaming stirrer in an actual scenario, and to obtain an optimal stirring speed of the foaming stirrer based on the stirring speed characteristic data and a first machine learning model; A performance mastering module, for acquiring fluid velocity characteristic data of foamed concrete in real time when the foaming mixer is stirred and controlled according to an optimal stirring speed, and mastering the fluid velocity of the foamed concrete in real time based on the fluid velocity characteristic data and a second machine learning model; The automatic control module is used to obtain the expected effect data input by the user, and control the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed. The expected effect data is the required fluid speed range.

2. The automatic control system for a foaming mixer according to claim 1, characterized in that: The method of calculating the mixing uniformity coefficient of the materials in the foaming mixer comprises: Extract the RGB value and color number of each pixel in the material mixture image, and call the preset standard uniform frequency; The RGB value of the pixel point, the number of color types and the preset standard uniform frequency are input into the preconfigured uniformity coefficient mathematical model to obtain the mixed uniformity coefficient; wherein the uniformity coefficient mathematical model is: ; Where: is the mixing uniformity coefficient, is the frequency of the i-th color category, is the total number of pixels in the material mixture image, is the number of pixels of the i-th color category, To preset the standard uniform frequency, is the number of color types.

3. The automatic control system of the foaming mixer according to claim 2, characterized in that: The generation logic of the first machine learning model is as follows: Extract stirring speed training data, and divide the stirring speed training data into a stirring speed training set and a stirring speed test set; Constructing a first regression network, taking the stirring speed characteristic data in the stirring speed training set as input data of the first regression network, taking the best stirring speed in the stirring speed training set as output data of the first regression network, training the first regression network, and obtaining a first initial regression network; The stirring speed test set is used to perform a model test on the first initial regression network, and the corresponding first initial regression network that is less than or equal to a preset test error threshold is used as the first initial regression network.

4. The automatic control system for a foaming mixer according to claim 3, characterized in that: The generation logic of the second machine learning model is as follows: Extracting fluid velocity training data, and dividing the fluid velocity training data into a fluid velocity training set and a fluid velocity test set; Constructing a second regression network, taking the fluid velocity feature data in the fluid velocity training set as input data of the second regression network, taking the fluid velocity in the fluid velocity training set as output data of the second regression network, training the second regression network, and obtaining a second initial regression network; The second initial regression network is model tested using the fluid velocity test set, and the corresponding second initial regression network that is less than or equal to a preset test error threshold is used as the second initial regression network.

5. The automatic control system for a foaming mixer according to claim 4, characterized in that: The process of obtaining the optimal stirring speed of the foaming mixer is as follows: Extract stirring speed characteristic data obtained in the actual scene, and convert the stirring speed characteristic data into a vector form; The stirring speed feature data in vector form is input into the first machine learning model to obtain the optimal stirring speed of the foaming mixer.

6. The automatic control system for a foaming mixer according to claim 5, characterized in that: The process of obtaining the fluid velocity of the foamed concrete is as follows: Extracting the fluid velocity characteristic data obtained in the actual scene, and converting the fluid velocity characteristic data into a vector form; The fluid velocity feature data in vector form is input into the second machine learning model to obtain the fluid velocity of the foamed concrete.

7. The automatic control system of the foaming mixer according to claim 6, characterized in that: The method of controlling the start and stop of the foaming mixer according to the expected effect data and the real-time fluid speed comprises: Compare the real-time fluid velocity with the required fluid velocity range; If the real-time fluid velocity is within the required fluid velocity range, it is determined that the foamed concrete being mixed has achieved the expected effect, and the foaming mixer is controlled to stop running; If the fluid velocity obtained in real time is not within the required fluid velocity range, it is determined that the foamed concrete being mixed has not achieved the expected effect, and the foaming mixer is controlled to continue to operate.

Images