WO2024066664A1

WO2024066664A1 - Concrete pumpability category identification method and apparatus, and electronic device

Info

Publication number: WO2024066664A1
Application number: PCT/CN2023/106835
Authority: WO
Inventors: 刘真骥; 谭科; 肖长清
Original assignee: 三一汽车制造有限公司
Priority date: 2022-09-26
Filing date: 2023-07-11
Publication date: 2024-04-04
Also published as: CN115546717A

Abstract

The present application discloses a concrete pumpability category identification method and apparatus, and an electronic device. The concrete pumpability category identification method comprises: acquiring an unloading image in a concrete unloading process, determining a concrete area image in the unloading image, and performing calculation on the concrete area image by using a trained classification model to obtain a pumpability category of the concrete. Therefore, the pumpability of the concrete is known before operation of a concrete pump truck, thereby avoiding risks in the concrete pump truck operation process.

Description

A method, device and electronic device for identifying concrete pumpability category

This application claims priority to a Chinese patent application filed with the State Intellectual Property Office of China on September 26, 2022, with application number 202211174178.9 and application name “A method, device and electronic device for identifying the pumpability category of concrete”, the entire contents of which are incorporated by reference into this application.

Technical Field

The present application relates to the technical field of construction engineering material management, and in particular to a method, device and electronic equipment for identifying the category of concrete pumpability.

Background technique

At present, the pumpability of concrete cannot be known in advance during the construction of a pump truck. However, if the pumpability of concrete can be known in advance before the construction of the pump truck, the risks in the construction process of the pump truck can be predicted in advance, such as pipe blockage causing reverse pumping and segregation causing pipe throwing.

The invention patent application with application publication number CN109784436A discloses an intelligent concrete management and control method and system, the system comprising: a demander client, a supplier client, a server, a first electronic tag, a second electronic tag, a third electronic tag, an electronic tag reader 1, an electronic tag reader 2, a weighing management system and a positioning device. The method and system realize the automation of the whole process of material weighing through information technology, and realize the association between the BIM sub-model and the test block detection report information, concrete information, and concrete pouring area information in the BIM system, dynamically reflecting the progress of the project and related information; judging whether the concrete pouring part information matches the pump truck pouring part information, can avoid pouring concrete with wrong performance of building components. However, the above method cannot know the pumpability of concrete in advance during the pump truck construction process, thereby avoiding the risks during the pump truck construction process.

Summary of the invention

In view of this, the embodiments of the present application provide a method, device and electronic equipment for identifying the category of concrete pumpability to avoid risks during the construction process of a pump truck.

According to an embodiment of the first aspect of the present application, a method for identifying a concrete pumpability category is provided. The method comprises the following steps: obtaining a material feeding image of a concrete feeding process; determining a concrete region image in the material feeding image; and calculating the concrete region image using a trained classification model to obtain a pumpability category of the concrete.

In combination with the first aspect, in a first implementation of the first aspect, determining the concrete area image in the cutting image includes: inputting the cutting image into a trained target detection model for identification to obtain a concrete area positioning frame; and using the concrete area positioning frame to crop the cutting image to obtain the concrete area image.

In combination with the first implementation of the first aspect, in the second implementation of the first aspect, the using the concrete area positioning frame to crop the blanking image to obtain the concrete area image includes: when there is one concrete area positioning frame, using the concrete area positioning frame to crop the blanking image to obtain a cropped image, and using the cropped image as the concrete area image; when there are multiple concrete area positioning frames, for any concrete area positioning frame, using the concrete area positioning frame to crop the blanking image to obtain a cropped image corresponding to the concrete area positioning frame; traversing each concrete area positioning frame to obtain a cropped image corresponding to each concrete area positioning frame; and fusing multiple cropped images to obtain the concrete area image.

In combination with the first implementation of the first aspect, in a third implementation of the first aspect, obtaining the trained target detection model includes: obtaining a training image set, wherein the training images in the training image set include at least one of the following: training images including a concrete unloading area, training images including a stacked concrete area, and training images including a concrete area below the screen surface; and using the training image set to train the target detection model to obtain the trained target detection model.

In combination with the first aspect, in a fourth embodiment of the first aspect, obtaining a trained classification model includes the following steps: obtaining multiple images corresponding to each pumpability category in a preset pumpability category set; and training the classification model using the multiple images corresponding to each pumpability category to obtain a trained classification model.

In combination with the fourth implementation of the first aspect, in a fifth implementation of the first aspect, the pumpability categories in the pumpability category set include: normal water-containing concrete with a moisture content less than or equal to a preset first threshold, normal water-containing concrete with a moisture content greater than the first threshold and less than or equal to a preset second threshold, Semi-watered concrete, fully-watered concrete with a water content greater than the second threshold; wherein the normal water-containing concrete includes low coarse aggregate content concrete with a coarse aggregate content less than or equal to a preset third threshold, medium coarse aggregate content concrete with a coarse aggregate content greater than the third threshold and less than or equal to a preset fourth threshold, and high coarse aggregate content concrete with a coarse aggregate content greater than the fourth threshold; the low coarse aggregate content concrete includes a first pebble concrete, a first crushed stone concrete and a first mixed concrete; the medium coarse aggregate content concrete includes a second pebble concrete, a second crushed stone concrete and a second mixed concrete; the high coarse aggregate content concrete includes a third pebble concrete, a third crushed stone concrete and a third mixed concrete.

In combination with the first aspect, in a sixth implementation of the first aspect, after calculating the concrete area image using a trained classification model to obtain the pumpability category of the concrete, it also includes: when the pumpability category of the concrete belongs to a preset alarm range, an alarm is issued.

According to an embodiment of the second aspect of the present application, a device for identifying a concrete pumpability category is provided, comprising an acquisition module, a first processing module and a second processing module, wherein the acquisition module is used to acquire a material discharge image of a concrete discharge process; the first processing module is used to determine a concrete area image in the material discharge image; and the second processing module is used to calculate the concrete area image using a trained classification model to obtain the pumpability category of the concrete.

According to an embodiment of the third aspect of the present application, an electronic device is provided, including a camera device and a processor, wherein the camera device is used to capture images of concrete feeding during a concrete feeding process; the camera device and the processor are communicatively connected, and computer instructions are stored in the processor, and the processor executes the method for identifying the concrete pumpability category described in the first aspect or any one of the embodiments of the first aspect by executing the computer instructions.

In combination with the third aspect, in a first implementation of the third aspect, the electronic device further includes a controller and an alarm device, the controller is communicatively connected to the processor, and the alarm device is communicatively connected to the controller.

According to the concrete pumpability category recognition method, device and electronic device of the embodiment of the present application, by acquiring the material feeding image of the concrete feeding process, determining the concrete area image in the material feeding image, and calculating the concrete area image using the trained classification model, the pumpability category of the concrete is obtained, thereby knowing the pumpability of the concrete before the pump truck is constructed, and Avoid the risks involved in pump truck construction.

BRIEF DESCRIPTION OF THE DRAWINGS

The features and advantages of the present application will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the present application in any way. In the accompanying drawings:

FIG1 is a schematic flow chart of a method for identifying a concrete pumpability category in some embodiments of the present application;

FIG2 is a schematic diagram of a first concrete area positioning frame and a second concrete area positioning frame;

FIG3 is a schematic diagram of the structure of a device for identifying the type of concrete pumpability in some embodiments of the present application;

Among them, 1: first concrete area positioning frame; 2: second concrete area positioning frame; 3: mesh surface.

Detailed ways

In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

The embodiment of the present application provides a method for identifying the pumpability category of concrete. FIG1 is a flow chart of the method for identifying the pumpability category of concrete in some embodiments of the present application. As shown in FIG1 , the method for identifying the pumpability category of concrete in the embodiment of the present application includes the following steps:

S101: Acquire a concrete feeding image during the concrete feeding process.

Specifically, the unloading process may be unloading concrete from a mixer truck to a pump truck. In other words, an unloading image of concrete from a mixer truck to a pump truck is obtained. For example, an image of concrete unloading from a mixer truck to a pump truck may be obtained by a camera device disposed at a hopper light pole or directly above the hopper. The unloading image may be an RGB image.

S102: Determine a concrete area image in the blanking image.

Specifically, the following steps may be used to determine the concrete area image in the blanking image: The blanking image is input into a trained target detection model for identification to obtain a concrete area positioning frame; the blanking image is cropped using the concrete area positioning frame to obtain the concrete area image. For example, the target detection model can be a model based on the YOLO algorithm or the SSD algorithm, so that the target detection accuracy is good and the operation speed is fast.

More specifically, the method of using the concrete area positioning frame to crop the blanking image to obtain the concrete area image includes the following two situations:

In the first case, when there is only one concrete region positioning frame, the cutting image is cropped using the concrete region positioning frame to obtain a cropped image, and the concrete region image is obtained according to the cropped image.

The second case is that when there are multiple concrete area positioning frames, for any concrete area positioning frame, the blanking image is cropped using the concrete area positioning frame to obtain a cropped image corresponding to the concrete area positioning frame; each concrete area positioning frame is traversed to obtain a cropped image corresponding to each concrete area positioning frame; and multiple cropped images are fused to obtain the concrete area image.

For example, as shown in FIG2 , the blanking image is input into a trained target detection model to obtain two concrete area positioning frames, namely, a first concrete area positioning frame 1 and a second concrete area positioning frame 2 .

The first concrete area positioning frame 1 is used to crop the blanking image to obtain a first cropped image corresponding to the first concrete area positioning frame 1, wherein the first cropped image corresponds to the blanking concrete area during the blanking process; the second concrete area positioning frame 2 is used to crop the blanking image to obtain a second cropped image corresponding to the second concrete area positioning frame 2, wherein the second cropped image corresponds to the stacked concrete area during the blanking process.

The first cropped image and the second cropped image are fused to obtain the concrete area. In some embodiments, optionally, the following method can be used to train the target detection model: obtain a training image set, wherein the training image set includes at least one of the following: a training image containing a concrete unloading area, a training image containing a stacked concrete area, and a training image containing a concrete area below the mesh surface; the target detection model is trained using the training image set to obtain the trained target detection model. Specifically, the mesh surface is an interception surface used to intercept impurities in concrete during the concrete unloading process. In some embodiments, optionally, after determining Before the concrete area image in the blanking image is described, the method further includes: preprocessing the blanking image, wherein the preprocessing includes but is not limited to noise reduction processing, generating a grayscale image, etc.

S103: Calculate the concrete area image using the trained classification model to obtain the pumpability category of the concrete. Specifically, the classification model can be trained by the following method: obtain multiple images corresponding to each pumpability category in a preset pumpability category set; train the classification model using the multiple images corresponding to each pumpability category to obtain the trained classification model. For example, the classification model can be a model established based on the FCN algorithm.

Specifically, the pumpability categories in the pumpability category set include: normal water-containing concrete with a moisture content less than or equal to a preset first threshold, semi-water-containing concrete with a moisture content greater than the first threshold and less than or equal to a preset second threshold, and fully water-containing concrete with a moisture content greater than the second threshold; wherein the normal water-containing concrete includes low coarse aggregate content concrete with a coarse aggregate content less than or equal to a preset third threshold, medium coarse aggregate content concrete with a coarse aggregate content greater than the third threshold and less than or equal to a preset fourth threshold, and high coarse aggregate content concrete with a coarse aggregate content greater than the fourth threshold.

This is because, as shown in Table 1, concrete can be divided into normal water-containing concrete, semi-water-containing concrete, and fully water-containing concrete according to different water contents. Specifically, normal water-containing concrete is concrete in which there is no obvious water in the concrete region image, that is, the ratio of the area occupied by water in the concrete region image to the total area of the concrete region image (also referred to as water content) is less than or equal to a preset first threshold; semi-water-containing concrete is concrete in which there is obvious water but less water in the concrete region image, that is, the ratio of the area occupied by water in the concrete region image to the total area of the concrete region image is greater than the first threshold and less than or equal to a preset second threshold; fully water-containing concrete is concrete in which there is obvious water and more water in the concrete region image, that is, the ratio of the area occupied by water in the concrete region image to the total area of the concrete region image is greater than the second threshold. For example, the first threshold can be 30%, that is, the ratio of the area occupied by water in the concrete region image to the total area of the concrete region image is 30%; the second threshold can be 70%, that is, the ratio of the area occupied by water in the concrete region image to the total area of the concrete region image is 70%.

Table 1: Pumpability categories of concrete classified according to moisture content

Further, as shown in Table 2, normal water-containing concrete can be divided into low coarse aggregate content concrete, medium coarse aggregate content concrete and high coarse aggregate content concrete according to the coarse aggregate content. Specifically, low coarse aggregate content concrete means that the ratio of the area occupied by coarse aggregate in the concrete region image to the total area of the concrete region image (also referred to as coarse aggregate content, coarse aggregate proportion) is less than or equal to the preset third threshold, medium coarse aggregate content concrete means that the ratio of the area occupied by coarse aggregate in the concrete region image to the total area of the concrete region image is greater than the third threshold and less than or equal to the preset fourth threshold, and high coarse aggregate content concrete means that the ratio of the area occupied by coarse aggregate in the concrete region image to the total area of the concrete region image is greater than the fourth threshold. For example, the third threshold can be 30%, that is, the ratio of the area occupied by coarse aggregate in the concrete region image to the total area of the concrete region image is 30%; the fourth threshold can be 70%, that is, the ratio of the area occupied by coarse aggregate in the concrete region image to the total area of the concrete region image is 70%.

Table 2: Pumpability categories for concrete with normal water content

Furthermore, as shown in Table 3, according to the type of coarse aggregate, low coarse aggregate content concrete can be divided into first pebble concrete, first crushed stone concrete and first mixed concrete.

Table 3: Pumpability categories of low coarse aggregate concrete according to the type of coarse aggregate

As shown in Table 4, according to the type of coarse aggregate, concrete with medium coarse aggregate content can be divided into second pebble concrete, second crushed stone concrete and second mixed concrete.

Table 4: Pumpability categories of concrete with medium-coarse aggregate content according to the type of coarse aggregate

As shown in Table 5, according to the type of coarse aggregate, high coarse aggregate content concrete can be divided into third pebble concrete, third crushed stone concrete and third mixed concrete.

Table 5: Pumpability categories of high coarse aggregate concrete according to the type of coarse aggregate

As above, the pebble ratio is the ratio of the area occupied by pebbles in the concrete area image to the total area of the concrete area image; the gravel ratio is the ratio of the area occupied by gravel in the concrete area image to the total area of the concrete area image; the total ratio of gravel and pebbles is the ratio of the area occupied by gravel and pebbles in the concrete area image to the total area of the concrete area image.

Specifically, in the first pebble concrete, the second pebble concrete and the third pebble concrete, the type of coarse aggregate is mainly pebbles; in the first crushed stone concrete, the second crushed stone concrete and the third crushed stone concrete, the type of coarse aggregate is mainly crushed stone; in the first mixed concrete, the second mixed concrete In the concrete and the third mixed concrete, the coarse aggregate is a mixture of pebbles and crushed stones. For example, when the ratio of pebbles to crushed stones in the coarse aggregate is 3:7, 4:6, 5:5 or the ratio of crushed stones to pebbles is 3:7, 4:6, 5:5, the type of the coarse aggregate is considered to be a mixture, otherwise, if the amount of pebbles in the coarse aggregate is greater than the amount of crushed stones, the type of the coarse aggregate is considered to be mainly pebbles, and if the amount of crushed stones in the coarse aggregate is greater than the amount of pebbles, the type of the coarse aggregate is considered to be mainly crushed stones.

Specifically, the pumpability category output by the classification model can be represented by the content of the pumpability category or by the category label. Different pumpability categories have different effects on pumpability.

In some embodiments, optionally, after inputting the concrete area into a trained classification model to obtain the pumpability category of the concrete, the method further includes: when the pumpability category of the concrete belongs to a preset alarm range, giving an alarm.

For example, when the pumpability category output by the classification model is category label 3, that is, fully water-containing concrete, an alarm is issued.

According to the method, device and electronic device for identifying the pumpability category of concrete in the embodiments of the present application, by acquiring the unloading image of concrete when it is unloaded from a mixer truck to a pump truck, the concrete area in the unloading image is identified, and the concrete area is input into a trained classification model to obtain the pumpability category of the concrete. In other words, the pumpability category of the concrete can be obtained only by the unloading image, thereby knowing the pumpability of the concrete before the pump truck is constructed, and avoiding risks during the construction of the pump truck.

In order to explain the concrete pumpability category identification method according to the embodiment of the present application in more detail, a specific example is given, which includes the following steps:

1. The RGB camera acquires the data stream and transmits it to the edge computing box device.

2. Preprocess the RGB image, including but not limited to noise reduction, generating grayscale images, etc.

3. Use the deep learning object detection model to crop the image data frame, specifically the positioning box coordinates obtained by the output model, obtain an image in which most of the image is concrete, and transmit it to the downstream task.

4. Input the image obtained in step 3 into the deep learning classification model to obtain the category label number.

5. Transmit the concrete category label digitally obtained in step 4 to the pump truck controller and finally transmit it back To the database server backend.

It can be seen that the concrete pumpability category identification method according to the embodiment of the present application has the following advantages:

(1) It only uses the classic algorithms of traditional computer vision, which is low-cost. It can analyze the pumpability of concrete poured into a pump truck and obtain important parameters, which has extremely high application value.

(2) It can detect excessive water content in concrete and provide early warning of the resulting segregation phenomenon, effectively avoiding the resulting blockage of the pump truck pipe.

The embodiments of the present application also provide a concrete pumpability category identification device. FIG3 is a schematic diagram of the structure of the concrete pumpability category identification device in some embodiments of the present application. As shown in FIG3, the concrete pumpability category identification device in some embodiments of the present application includes an acquisition module 20, a first processing module 21 and a second processing module 22.

The acquisition module 20 is used to acquire the material feeding image of the concrete feeding process;

A first processing module 21 is used to determine a concrete area image in the blanking image;

The second processing module 22 is used to calculate the concrete area image using a trained classification model to obtain the pumpability category of the concrete.

The first processing module 21 is specifically used for: inputting the blanking image into a trained target detection model for recognition to obtain a concrete area positioning frame; and using the concrete area positioning frame to crop the blanking image to obtain the concrete area image.

More specifically, the first processing module 21 is used for: when there is one concrete area positioning frame, using the concrete area positioning frame to crop the blanking image to obtain a cropped image, and obtaining the concrete area image according to the cropped image; when there are multiple concrete area positioning frames, for any concrete area positioning frame, using the concrete area positioning frame to crop the blanking image to obtain a cropped image corresponding to the concrete area positioning frame; traversing each concrete area positioning frame to obtain a cropped image corresponding to each concrete area positioning frame; and fusing multiple cropped images to obtain the concrete area image.

In some embodiments, the concrete pumpability category recognition device may further include a target detection model training module 23. The target detection model training module 23 is specifically used to: obtain a training image set, wherein the training images in the training image set include at least one of the following: a training image containing a concrete unloading area, a training image containing a concrete stacking area, a training image containing a mesh surface The following training images of the concrete area; the target detection model is trained using the training image set to obtain the trained target detection model.

In some embodiments, optionally, the concrete pumpability category identification device further includes a classification model training module 24. The classification model training module is specifically used to: obtain a plurality of images corresponding to each pumpability category in a preset pumpability category set; and train the classification model using the plurality of images corresponding to each pumpability category to obtain the trained classification model.

The specific details of the above-mentioned concrete pumpability category identification device can be understood by referring to the corresponding related descriptions and effects in the embodiments shown in Figures 1 to 2, and will not be repeated here.

The embodiment of the present application further provides an electronic device, which includes a camera device and a processor. The camera device is used to capture images of concrete during the concrete feeding process; and the camera device is in communication with the processor.

Specifically, the camera device is arranged at the hopper light pole or just above the hopper.

The processor includes a processing unit and a storage unit. The processing unit can be a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components and other chips, or a combination of the above chips.

The storage unit, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer executable programs and modules, such as the program instructions/modules corresponding to the concrete pumpability category identification method in the embodiment of the present application (for example, the acquisition module 20, the first processing module 21, the second processing module 22, the target detection model training module 23 and the classification model training module 24 shown in FIG3). The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions and modules stored in the storage unit, that is, the concrete pumpability category identification method in the above method embodiment is implemented.

The storage unit may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the storage unit may include a high-speed random access storage unit, and may also include a non-transitory storage unit, such as at least one disk storage unit device, a flash memory device, or other Other non-transitory solid-state storage units. In some embodiments, the storage unit may optionally include a storage unit remotely disposed relative to the processor, and these remote storage units may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The one or more modules are stored in the storage unit, and when executed by the processor, the concrete pumpability category identification method in the embodiments shown in FIG. 1 to FIG. 2 is performed.

In some embodiments, optionally, the electronic device further includes a controller and an alarm device, wherein the controller is communicatively connected to the processor, and the alarm device is communicatively connected to the controller.

The specific details of the above electronic device can be understood by referring to the corresponding related descriptions and effects in the embodiments shown in Figures 1 to 3, and will not be repeated here.

Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory unit (Flash Memory), a hard disk (Hard Disk Drive, abbreviated: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of storage units.

Although the embodiments of the present application have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present application, and such modifications and variations are all within the scope defined by the appended claims.

Claims

A method for identifying concrete pumpability categories, comprising:

Acquire the unloading image of the concrete unloading process;

Determine a concrete area image in the blanking image;

The concrete region image is calculated using a trained classification model to obtain a pumpability category of the concrete.
The method according to claim 1, wherein determining the concrete area image in the blanking image comprises:

Inputting the blanking image into a trained target detection model for recognition to obtain a concrete area positioning frame;

The concrete area positioning frame is used to crop the blanking image to obtain the concrete area image.
The method according to claim 2, wherein the step of cropping the blanking image using the concrete area positioning frame to obtain the concrete area image comprises:

When there is one concrete region positioning frame, the blanking image is cropped using the concrete region positioning frame to obtain a cropped image, and the cropped image is used as the concrete region image;

When there are multiple concrete area positioning frames, for any concrete area positioning frame, the blanking image is cropped using the concrete area positioning frame to obtain a cropped image corresponding to the concrete area positioning frame; each concrete area positioning frame is traversed to obtain a cropped image corresponding to each concrete area positioning frame; and multiple cropped images are fused to obtain the concrete area image.
The method according to claim 2, wherein obtaining the trained object detection model comprises:

Acquire a training image set, wherein the training images in the training image set include at least one of the following: a training image containing a concrete unloading area, a training image containing a concrete stacking area, and a training image containing a concrete area below a screen surface;

The target detection model is trained using the training image set to obtain the trained target detection model.
The method according to claim 1, wherein obtaining a trained classification model comprises:

acquiring a plurality of images corresponding to each pumpability category in a preset set of pumpability categories;

The classification model is trained using a plurality of images corresponding to each pumpability category to obtain the trained classification model.
The method according to claim 5, wherein the pumpability categories in the pumpability category set include: normal water-containing concrete with a moisture content less than or equal to a preset first threshold, semi-water-containing concrete with a moisture content greater than the first threshold and less than or equal to a preset second threshold, and fully water-containing concrete with a moisture content greater than the second threshold;

The normal water-containing concrete includes low coarse aggregate content concrete with a coarse aggregate content less than or equal to a preset third threshold, medium coarse aggregate content concrete with a coarse aggregate content greater than the third threshold and less than or equal to a preset fourth threshold, and high coarse aggregate content concrete with a coarse aggregate content greater than the fourth threshold.

The low coarse aggregate content concrete includes a first pebble concrete, a first crushed stone concrete and a first mixed concrete; the medium coarse aggregate content concrete includes a second pebble concrete, a second crushed stone concrete and a second mixed concrete; the high coarse aggregate content concrete includes a third pebble concrete, a third crushed stone concrete and a third mixed concrete.
The method according to claim 1, wherein after calculating the concrete area image using a trained classification model to obtain the pumpability category of the concrete, it further comprises:

When the pumpability category of the concrete belongs to a preset alarm range, an alarm is issued.
A device for identifying the category of concrete pumpability, comprising:

An acquisition module is used to acquire the image of the concrete feeding process;

A first processing module is used to determine a concrete area image in the blanking image;

The second processing module is used to calculate the concrete area image using a trained classification model to obtain the pumpability category of the concrete.
An electronic device, comprising:

A camera device, used to capture images of the concrete during the concrete feeding process;

processor, the camera device is in communication with the processor, and the processor stores The computer instructions are used to execute the concrete pumpability category identification method according to any one of claims 1 to 7 by the processor executing the computer instructions.
The electronic device according to claim 9, further comprising a controller and an alarm device, wherein the controller is communicatively connected to the processor, and the alarm device is communicatively connected to the controller.