CN114241252A - Spraying state identification method, device, equipment and readable storage medium - Google Patents
Spraying state identification method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN114241252A CN114241252A CN202111365508.8A CN202111365508A CN114241252A CN 114241252 A CN114241252 A CN 114241252A CN 202111365508 A CN202111365508 A CN 202111365508A CN 114241252 A CN114241252 A CN 114241252A
- Authority
- CN
- China
- Prior art keywords
- spraying state
- recognition model
- spraying
- trained
- waterproof coating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Application Of Or Painting With Fluid Materials (AREA)
Abstract
The application discloses a spraying state identification method, a device, equipment and a readable storage medium, wherein the method comprises the following steps: acquiring a target spraying state identification model; inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set. In the application, the spraying state of the waterproof coating is identified by the target spraying state identification model which achieves higher accuracy after training, and the accuracy of determining the spraying state is higher, so that the spraying state of the waterproof coating can be well determined by identifying the spraying state of the waterproof coating through the target spraying state identification model, and the waterproof effect of the precast beam through the waterproof coating is improved.
Description
Technical Field
The present disclosure relates to the field of engineering equipment technologies, and in particular, to a method, an apparatus, a device, and a readable storage medium for identifying a spraying status.
Background
With the rapid development of national capital construction, the precast beam is more and more frequently used, and the precast beam faces the threat of rain in the using process, so that the precast beam needs to be subjected to waterproof treatment.
The existing waterproof treatment is to spray waterproof paint on the surface of the precast beam, and in the process of spraying the waterproof paint, the spraying state of the waterproof paint reflects the waterproof effect of the precast beam after the waterproof paint is solidified, however, currently, there is no good means to determine the spraying state of the waterproof paint, for example, the spraying state of the waterproof paint is determined manually, and the accuracy of determination is low, so that the waterproof effect of spraying the waterproof paint on the precast beam is poor.
That is, the waterproof effect of waterproofing the precast beam by the waterproof coating is poor at present.
Disclosure of Invention
The application mainly aims to provide a spraying state identification method, a spraying state identification device, spraying state identification equipment and a readable storage medium, and aims to solve the technical problem of how to improve the waterproof effect of waterproofing a precast beam through waterproof paint.
In order to achieve the above object, the present application provides a spraying status recognition method, including the steps of:
acquiring a target spraying state identification model;
inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam;
and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set.
Optionally, the inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result includes:
and executing corresponding equipment response operation based on the identification result.
Optionally, the recognition result includes an attachment result, and the performing the corresponding device response operation based on the recognition result includes:
if the adhesion result is uneven adhesion, acquiring a solidification state picture of the waterproof coating;
classifying the solidification state pictures based on a preset solidification state classification model to obtain a classification result;
and executing corresponding equipment response operation based on the classification result.
Optionally, the performing a corresponding device response operation based on the classification result includes:
judging whether the waterproof coating is partially solidified or not based on the classification result;
if so, controlling a preset filtering device to filter the waterproof coating so as to filter the solidified part in the waterproof coating.
Optionally, the identification result is a splash result, and the executing the corresponding device response operation based on the identification result further includes:
if the splash results in the generation of splash, the spray speed of a nozzle that sprays the waterproof coating material is reduced.
Optionally, the inputting the real-time spraying state picture to the target spraying state recognition model and before obtaining the recognition result includes:
acquiring a spraying state training data set and a spraying state recognition model to be trained;
training the spraying state recognition model to be trained based on the spraying state training data set to obtain an updated spraying state recognition model to be trained, and determining whether the updated spraying state recognition model to be trained meets a preset iteration end condition;
if the updated spraying state recognition model to be trained meets the preset iteration end condition, taking the updated spraying state recognition model to be trained as the target spraying state recognition model;
and if the updated spraying state recognition model to be trained does not meet the preset iteration ending condition, returning to the step of performing iterative training on the spraying state recognition model to be trained based on the spraying state training data set until the updated spraying state recognition model to be trained meets the preset iteration ending condition.
Optionally, the acquiring the spraying state training data set includes:
obtaining a training sample;
and receiving a marking instruction, and marking the training sample based on the marking instruction to obtain a standard detection result.
In addition, in order to achieve the above object, the present application also provides a painting status recognition apparatus including:
the first acquisition module is used for acquiring a target spraying state identification model;
the input module is used for inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set.
Optionally, the spraying status recognition device further includes:
and the execution module executes corresponding equipment response operation based on the identification result.
Optionally, the execution module is further configured to:
if the adhesion result is uneven adhesion, acquiring a solidification state picture of the waterproof coating;
classifying the solidification state pictures based on a preset solidification state classification model to obtain a classification result;
and executing corresponding equipment response operation based on the classification result.
Optionally, the execution module is further configured to:
judging whether the waterproof coating is partially solidified or not based on the classification result;
if so, controlling a preset filtering device to filter the waterproof coating so as to filter the solidified part in the waterproof coating.
Optionally, the execution module is further configured to:
if the splash results in the generation of splash, the spray speed of a nozzle that sprays the waterproof coating material is reduced.
Optionally, the spraying status recognition device further includes:
the second acquisition module is used for acquiring a spraying state training data set and a spraying state recognition model to be trained;
the training module is used for training the spraying state recognition model to be trained based on the spraying state training data set, obtaining an updated spraying state recognition model to be trained, and determining whether the updated spraying state recognition model to be trained meets a preset iteration ending condition; if the updated spraying state recognition model to be trained meets the preset iteration end condition, taking the updated spraying state recognition model to be trained as the target spraying state recognition model; and if the updated spraying state recognition model to be trained does not meet the preset iteration ending condition, returning to the step of performing iterative training on the spraying state recognition model to be trained based on the spraying state training data set until the updated spraying state recognition model to be trained meets the preset iteration ending condition.
Optionally, the second obtaining module is further configured to:
obtaining a training sample;
and receiving a marking instruction, and marking the training sample based on the marking instruction to obtain a standard detection result.
In addition, to achieve the above object, the present application also provides a spraying status recognition apparatus comprising a memory, a processor, and a spraying status recognition program stored on the memory and executable on the processor, wherein the spraying status recognition program, when executed by the processor, implements the steps of the spraying status recognition method as described above.
Further, to achieve the above object, the present application also provides a computer-readable storage medium having stored thereon a painting status recognition program which, when executed by a processor, implements the steps of the painting status recognition method as described above.
Compared with the prior art that the state of the waterproof coating is not determined by a good means, so that the waterproof effect of the waterproof coating sprayed on the precast beam is poor, the target spraying state identification model is obtained; inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set. In the application, the spraying state of the waterproof coating is identified by the target spraying state identification model which achieves higher accuracy after training, and the accuracy of determining the spraying state is higher, so that the spraying state of the waterproof coating can be well determined by identifying the spraying state of the waterproof coating through the target spraying state identification model, and the waterproof effect of the precast beam through the waterproof coating is improved.
Drawings
FIG. 1 is a schematic flow chart of a first embodiment of a spray status identification method of the present application;
FIG. 2 is a functional block diagram of a preferred embodiment of the spray condition recognition apparatus of the present application;
fig. 3 is a schematic structural diagram of a hardware operating environment according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, fig. 1 is a schematic flow chart of a first embodiment of the spraying state identification method.
While the embodiments of the present application provide examples of spray status identification methods, it should be noted that although a logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that shown or described herein. The spraying state identification method can be applied to terminals or servers, wherein the terminals comprise mobile phones, personal computers and the like. For convenience of description, the following omits to perform various steps of the subject description spray condition recognition method. The spraying state identification method comprises the following steps:
and step S10, acquiring a target spraying state identification model.
In this embodiment, since the model training process generally takes a lot of time, before the target spraying state recognition model recognizes the spraying state in the real-time spraying state picture, the target spraying state recognition model is generally trained, rather than being trained when the target spraying state recognition model needs to be acquired.
Step S20, inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set.
In this embodiment, the real-time spraying state picture reflects the effect of the waterproof coating sprayed on the precast beam, and it can be understood that the spraying state of the waterproof coating affects the use effect, the service life and the like of the waterproof coating, and further the service life of the precast beam is reduced. For example, if the waterproof coating adhered to the precast beam is not uniformly adhered in the spraying state, the non-uniformly adhered part is easy to fall off, because the waterproof coating is partially solidified during spraying, and the solidified waterproof coating has poor adhesion to the precast beam during spraying, the waterproof coating is easy to fall off, so that the use effect and the service life of the waterproof coating are reduced; if the spraying state is that the waterproof paint splashes in the spraying process, the sprayed part of the waterproof paint splashes to other places (including other places of the precast beam) completely or thinly, so that the splashed place is easy to enter water, and the using effect and the service life of the waterproof paint are reduced.
It should be noted that, in order to further ensure the spraying effect of the waterproof coating material, when the picture is obtained in real time, the obtaining time interval can be reduced, that is, the obtaining frequency is increased, wherein the picture can be obtained by a camera or a camera arranged on the waterproof coating material spraying machine.
It should be noted that the spraying state training data set is a collection of spraying state pictures collected during the spraying of the waterproof paint.
It should be noted that the spraying state recognition model to be trained is constructed by an image recognition algorithm, and the image recognition algorithm includes AlexNet, VGG19, ResNet _152, inclusion v4, DenseNet, and the like.
Wherein, the inputting a real-time spraying state picture to the target spraying state recognition model before obtaining a recognition result comprises:
step a, acquiring a spraying state training data set and a spraying state recognition model to be trained;
training the spraying state recognition model to be trained based on the spraying state training data set to obtain an updated spraying state recognition model to be trained, and determining whether the updated spraying state recognition model to be trained meets a preset iteration end condition;
step c, if the updated spraying state recognition model to be trained meets the preset iteration end condition, taking the updated spraying state recognition model to be trained as the target spraying state recognition model;
and d, if the updated spraying state recognition model to be trained does not meet the preset iteration ending condition, returning to the step of performing iterative training on the spraying state recognition model to be trained based on the spraying state training data set until the updated spraying state recognition model to be trained meets the preset iteration ending condition.
In this embodiment, iterative training is performed on the spraying state recognition model to be trained based on the spraying state training data set to obtain an updated spraying state recognition model to be trained, and whether the updated spraying state recognition model to be trained meets a preset iteration end condition is determined; if the updated spraying state recognition model to be trained meets the preset iteration end condition, taking the updated spraying state recognition model to be trained as a target spraying state recognition model; and if the updated spraying state recognition model to be trained does not meet the iteration ending condition, continuously performing iterative training and updating on the updated spraying state recognition model to be trained until the updated spraying state recognition model to be trained meets the iteration ending condition.
Specifically, iterative training is performed on the spraying state recognition model to be trained through the spraying state picture, so that the updated spraying state recognition model to be trained is obtained. After the updated spraying state recognition model to be trained is obtained each time, whether the updated spraying state recognition model to be trained meets a preset iteration ending condition or not is determined, if the updated spraying state recognition model to be trained meets the preset iteration ending condition, the iteration is ended, and the last updated spraying state recognition model to be trained is used as a target spraying state recognition model; and if the updated spraying state recognition model to be trained does not meet the iteration ending condition, the updated spraying state recognition model to be trained does not meet the use condition, and the updated spraying state recognition model to be trained is continuously subjected to iterative training and updating until the updated spraying state recognition model to be trained meets the iteration ending condition.
It should be noted that the iterative training is a process of training the spraying state recognition model to be trained through the spraying state pictures for multiple times, and generally, the target spraying state recognition model obtained by the spraying state recognition model to be trained needs to be updated through multiple rounds of training. It should be noted that, when the preset iteration end condition is that the spraying state recognition model to be trained is input or the updated spraying state recognition model to be trained is that the prediction accuracy of the model reaches the preset accuracy threshold, the iteration is ended.
Further, the acquiring the spraying state training data set includes:
step a1, obtaining a training sample;
step a2, receiving a marking instruction, and marking the training sample based on the marking instruction to obtain a standard detection result.
In this embodiment, the training sample is an original spraying state picture, and obtaining the spraying state picture in the spraying state training data set from the original spraying state picture needs to be implemented by manual labeling. Specifically, the part of the spraying state picture with paint splashing or uneven paint adhesion is marked manually through a marking instruction, so that when the spraying state recognition model to be trained is trained, the spraying state recognition model to be trained can learn the result of the possible existence of the spraying state through the marked part of the spraying state picture, and the part of the real-time spraying state picture with paint splashing or uneven paint adhesion can be recognized when the target spraying state recognition model recognizes the real-time spraying state picture.
Further, after the reason which influences the use effect, the service life and the like of the waterproof paint is obtained through the analysis of the identification result, the reason is solved according to the corresponding solution. Specifically, the inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result includes:
and e, executing corresponding equipment response operation based on the identification result.
The recognition result comprises an attachment result, and the executing the corresponding device response operation based on the recognition result comprises:
and e1, if the adhesion result is uneven adhesion, acquiring a solidification state picture of the waterproof paint.
In this embodiment, if the adhesion result is uniform adhesion, it indicates that the spraying state of the waterproof coating sprayed on the precast beam satisfies the use requirement, and the waterproof coating can well perform a waterproof function on the precast beam.
It should be noted that the reason for the uneven adhesion may be partial solidification of the waterproof coating material, wherein the waterproof coating material gradually solidifies after contacting air, and therefore, the waterproof coating material needs to be used up within a certain time, and the time is influenced by external complex factors and is not easily estimated, for example, the air humidity is different, and the time is different, so that when the uneven adhesion is found, the solidification state of the waterproof coating material stored in a mixing tank (generally, the waterproof coating material is a multi-component coating material, and each single-component coating material needs to be mixed in the mixing tank in a certain proportion before spraying to obtain the waterproof coating material) can be determined, and thus, whether the uneven adhesion is caused by the partial solidification of the waterproof coating material is determined.
Wherein the solidification state of the waterproof coating is determined by the solidification state picture. It can be understood that if the waterproof coating material is partially solidified, larger solidified particles can appear in the solidified state picture, and when the waterproof coating material is solidified, the larger solidified particles cannot appear in the solidified state picture, so that the solidified state of the waterproof coating material can be determined by searching the solidified particles in the solidified state picture.
And e2, classifying the solidification state pictures based on a preset solidification state classification model to obtain a classification result.
In this embodiment, the solidification state of the waterproof coating is determined by the preset solidification state classification model, and the result is solidification or non-solidification, specifically, similar to the target spraying state recognition model, and the specific implementation manner corresponding to the training process of the preset solidification state classification model is substantially the same as the embodiment corresponding to the training process of the target spraying state recognition model, and is not described herein again.
And e3, executing corresponding equipment response operation based on the classification result.
Wherein the performing of the respective device response operation based on the classification result includes:
step e31, judging whether the waterproof coating is partially solidified or not based on the classification result;
and e32, if yes, controlling a preset filtering device to filter the waterproof coating so as to filter the solidified part in the waterproof coating.
In this embodiment, after it is determined that the waterproof coating material is partially solidified, the waterproof coating material may be subjected to a filtering process by a preset filtering device, for example, the waterproof coating material is filtered by a filter screen, so as to filter the solidified portion of the waterproof coating material.
Wherein the identification result is a splash result, and the executing the corresponding device response operation based on the identification result further comprises:
and e33, if the splashing result is that splashing is generated, reducing the spraying speed of the nozzle for spraying the waterproof paint.
In this embodiment, if the splashing result is that no splashing is generated, the current spraying speed of the nozzle is appropriate, and therefore, the nozzle is controlled to continue spraying the waterproof coating at the current spraying speed, so that the precast beam after spraying the waterproof coating can have a relatively good waterproof effect.
Compared with the prior art that the state of the waterproof coating is not determined by a good means, so that the waterproof effect of the waterproof coating sprayed on the precast beam is poor, the target spraying state identification model is obtained; inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set. In the application, the spraying state of the waterproof coating is identified by the target spraying state identification model which achieves higher accuracy after training, and the accuracy of determining the spraying state is higher, so that the spraying state of the waterproof coating can be well determined by identifying the spraying state of the waterproof coating through the target spraying state identification model, and the waterproof effect of the precast beam through the waterproof coating is improved.
In addition, the present application also provides a spraying state recognition apparatus, as shown in fig. 2, the spraying state recognition apparatus includes:
the first acquisition module 10 is used for acquiring a target spraying state identification model;
the input module 20 is configured to input a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set.
Optionally, the spraying status recognition device further includes:
and the execution module executes corresponding equipment response operation based on the identification result.
Optionally, the execution module is further configured to:
if the adhesion result is uneven adhesion, acquiring a solidification state picture of the waterproof coating;
classifying the solidification state pictures based on a preset solidification state classification model to obtain a classification result;
and executing corresponding equipment response operation based on the classification result.
Optionally, the execution module is further configured to:
judging whether the waterproof coating is partially solidified or not based on the classification result;
if so, controlling a preset filtering device to filter the waterproof coating so as to filter the solidified part in the waterproof coating.
Optionally, the execution module is further configured to:
if the splash results in the generation of splash, the spray speed of a nozzle that sprays the waterproof coating material is reduced.
Optionally, the spraying status recognition device further includes:
the second acquisition module is used for acquiring a spraying state training data set and a spraying state recognition model to be trained;
the training module is used for training the spraying state recognition model to be trained based on the spraying state training data set, obtaining an updated spraying state recognition model to be trained, and determining whether the updated spraying state recognition model to be trained meets a preset iteration ending condition; if the updated spraying state recognition model to be trained meets the preset iteration end condition, taking the updated spraying state recognition model to be trained as the target spraying state recognition model; and if the updated spraying state recognition model to be trained does not meet the preset iteration ending condition, returning to the step of performing iterative training on the spraying state recognition model to be trained based on the spraying state training data set until the updated spraying state recognition model to be trained meets the preset iteration ending condition.
Optionally, the second obtaining module is further configured to:
obtaining a training sample;
and receiving a marking instruction, and marking the training sample based on the marking instruction to obtain a standard detection result.
The specific implementation of the spraying status recognition apparatus of the present application is substantially the same as that of each embodiment of the spraying status recognition method, and is not described herein again.
In addition, this application still provides a spraying state identification equipment. As shown in fig. 3, fig. 3 is a schematic structural diagram of a hardware operating environment according to an embodiment of the present application.
It should be noted that fig. 3 is a schematic structural diagram of a hardware operating environment of the spraying state identification device.
As shown in fig. 3, the spray status recognition apparatus may include: a processor 1001, such as a CPU, a memory 1005, a user interface 1003, a network interface 1004, a communication bus 1002. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Optionally, the spray status identification device may further include RF (Radio Frequency) circuitry, sensors, audio circuitry, a WiFi module, and the like.
It will be appreciated by those skilled in the art that the spray condition recognition device configuration shown in fig. 3 does not constitute a limitation of the spray condition recognition device, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 3, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a spray status recognition program. The operating system is a program for managing and controlling hardware and software resources of the spraying state identification device, and supports the operation of the spraying state identification program and other software or programs.
In the spraying status recognition apparatus shown in fig. 3, the user interface 1003 is mainly used for connecting a terminal and performing data communication with the terminal, such as receiving user signaling data sent by the terminal; the network interface 1004 is mainly used for the background server and performs data communication with the background server; the processor 1001 may be configured to invoke the spray status identification program stored in the memory 1005 and perform the steps of the spray status identification method as described above.
The specific implementation of the spraying state identification device of the present application is substantially the same as that of each embodiment of the spraying state identification method, and is not described herein again.
In addition, an embodiment of the present application further provides a computer-readable storage medium, where a spraying status recognition program is stored, and when being executed by a processor, the spraying status recognition program implements the steps of the spraying status recognition method as described above.
The specific implementation of the computer-readable storage medium of the present application is substantially the same as the embodiments of the spraying status identification method, and is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, a device, or a network device) to execute the method according to the embodiments of the present application.
The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.
Claims (10)
1. A spraying state recognition method is characterized by comprising the following steps:
acquiring a target spraying state identification model;
inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam;
and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set.
2. The method of claim 1, wherein the inputting a real-time painting status picture to the target painting status recognition model, and after obtaining the recognition result, comprises:
and executing corresponding equipment response operation based on the identification result.
3. The method of claim 2, wherein the recognition result comprises an attachment result, and wherein performing the respective device response operation based on the recognition result comprises:
if the adhesion result is uneven adhesion, acquiring a solidification state picture of the waterproof coating;
classifying the solidification state pictures based on a preset solidification state classification model to obtain a classification result;
and executing corresponding equipment response operation based on the classification result.
4. The method of claim 3, wherein said performing respective device response operations based on said classification results comprises:
judging whether the waterproof coating is partially solidified or not based on the classification result;
if so, controlling a preset filtering device to filter the waterproof coating so as to filter the solidified part in the waterproof coating.
5. The method of claim 2, wherein the identification result is a spatter result, the performing the respective device response operation based on the identification result further comprises:
if the splash results in the generation of splash, the spray speed of a nozzle that sprays the waterproof coating material is reduced.
6. The method of claim 1, wherein inputting the real-time spray status picture to the target spray status recognition model before obtaining the recognition result comprises:
acquiring a spraying state training data set and a spraying state recognition model to be trained;
training the spraying state recognition model to be trained based on the spraying state training data set to obtain an updated spraying state recognition model to be trained, and determining whether the updated spraying state recognition model to be trained meets a preset iteration end condition;
if the updated spraying state recognition model to be trained meets the preset iteration end condition, taking the updated spraying state recognition model to be trained as the target spraying state recognition model;
and if the updated spraying state recognition model to be trained does not meet the preset iteration ending condition, returning to the step of performing iterative training on the spraying state recognition model to be trained based on the spraying state training data set until the updated spraying state recognition model to be trained meets the preset iteration ending condition.
7. The method of claim 6, wherein the spray condition training dataset includes one or more training samples and standard test results corresponding to each of the training samples, and wherein the obtaining the spray condition training dataset includes:
obtaining a training sample;
and receiving a marking instruction, and marking the training sample based on the marking instruction to obtain a standard detection result.
8. A painting status recognition apparatus, characterized by comprising:
the first acquisition module is used for acquiring a target spraying state identification model;
the input module is used for inputting a real-time spraying state picture to the target spraying state recognition model to obtain a recognition result; the real-time spraying state picture is obtained in real time when the waterproof coating is sprayed on the precast beam; and the target spraying state recognition model is obtained by performing iterative training on a spraying state recognition model to be trained based on a spraying state training data set.
9. A painting status recognition device characterized by comprising a memory, a processor, and a painting status recognition program stored on the memory and executable on the processor, the painting status recognition program, when executed by the processor, implementing the steps of the painting status recognition method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that a spraying status recognition program is stored thereon, which when executed by a processor implements the steps of the spraying status recognition method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111365508.8A CN114241252A (en) | 2021-11-17 | 2021-11-17 | Spraying state identification method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111365508.8A CN114241252A (en) | 2021-11-17 | 2021-11-17 | Spraying state identification method, device, equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114241252A true CN114241252A (en) | 2022-03-25 |
Family
ID=80749898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111365508.8A Pending CN114241252A (en) | 2021-11-17 | 2021-11-17 | Spraying state identification method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114241252A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629085A (en) * | 2023-06-15 | 2023-08-22 | 中国建筑第二工程局有限公司 | Particle swarm algorithm and convolutional neural network-based waterproof coating optimization method |
-
2021
- 2021-11-17 CN CN202111365508.8A patent/CN114241252A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116629085A (en) * | 2023-06-15 | 2023-08-22 | 中国建筑第二工程局有限公司 | Particle swarm algorithm and convolutional neural network-based waterproof coating optimization method |
| CN116629085B (en) * | 2023-06-15 | 2024-07-05 | 中国建筑第二工程局有限公司 | Particle swarm algorithm and convolutional neural network-based waterproof coating optimization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112749081B (en) | User interface testing method and related device | |
| CN111845647B (en) | Automobile camera cleaning system and method | |
| CN114241252A (en) | Spraying state identification method, device, equipment and readable storage medium | |
| CN110290280B (en) | Terminal state identification method and device and storage medium | |
| CN112712498B (en) | Vehicle damage assessment method and device executed by mobile terminal, mobile terminal and medium | |
| CN112507087B (en) | Terminal equipment identification method, equipment, storage medium and device | |
| CN113506211B (en) | Polishing method and device for hub rib window, terminal device and storage medium | |
| CN109948107B (en) | Area curved surface integral calculation method, device, equipment and storage medium | |
| CN105468161A (en) | Instruction execution method and device | |
| CN108460388B (en) | Method and device for detecting positioning mark and computer readable storage medium | |
| CN111353719A (en) | Diagnostic task execution method, device, equipment and medium | |
| CN112246469A (en) | Method and apparatus for controlling spray coating of vehicle | |
| CN111325880A (en) | Bluetooth-based positioning door opening method and device, intelligent terminal and storage medium | |
| CN115158230A (en) | Cleaning method, device, equipment and medium based on image analysis | |
| CN112766138B (en) | Positioning method, device, equipment and storage medium based on image recognition | |
| CN112365883B (en) | Cabin system voice recognition test method, device, equipment and storage medium | |
| CN107231624B (en) | Method for retaining data information, storage device and mobile terminal | |
| CN110853364A (en) | Data monitoring method and device | |
| CN113245092A (en) | Waterproof paint spraying scheme updating method and device and readable storage medium | |
| CN114360055A (en) | Behavior detection method, device and storage medium based on artificial intelligence | |
| CN111813681B (en) | Dynamic case priority ordering method and device | |
| CN113222037A (en) | Waterproof coating raw material mixing method and equipment and readable storage medium | |
| CN114495173A (en) | Posture recognition method and device, electronic equipment and computer readable medium | |
| CN113642556A (en) | Image processing method and device, electronic equipment and storage medium | |
| CN113312799B (en) | Spraying system flushing method, device, equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |