CN117761048A - Waterproof coating drying stage detection and identification method and system - Google Patents
Waterproof coating drying stage detection and identification method and system Download PDFInfo
- Publication number
- CN117761048A CN117761048A CN202310050898.2A CN202310050898A CN117761048A CN 117761048 A CN117761048 A CN 117761048A CN 202310050898 A CN202310050898 A CN 202310050898A CN 117761048 A CN117761048 A CN 117761048A
- Authority
- CN
- China
- Prior art keywords
- dryness
- paint
- drying
- identification
- waterproof
- 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.)
- Granted
Links
- 238000001035 drying Methods 0.000 title claims abstract description 208
- 238000000576 coating method Methods 0.000 title claims abstract description 152
- 239000011248 coating agent Substances 0.000 title claims abstract description 148
- 238000001514 detection method Methods 0.000 title claims abstract description 134
- 238000000034 method Methods 0.000 title claims abstract description 39
- 239000003973 paint Substances 0.000 claims abstract description 170
- 238000004364 calculation method Methods 0.000 claims abstract description 18
- 230000005855 radiation Effects 0.000 claims description 66
- 230000007613 environmental effect Effects 0.000 claims description 46
- 238000010521 absorption reaction Methods 0.000 claims description 38
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000010276 construction Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 11
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 18
- 238000012545 processing Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007602 hot air drying Methods 0.000 description 1
- 238000007603 infrared drying Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Landscapes
- Drying Of Solid Materials (AREA)
Abstract
The invention discloses a detection and identification method and a detection and identification system for a drying stage of waterproof paint, and relates to the field of data processing, wherein the method comprises the following steps: based on the drying time and the first detection mode, performing physical detection on the waterproof paint, and acquiring a detected paint image; inputting the paint image into a first dryness identification unit to obtain a first dryness identification result; based on a second detection mode, a detection result is obtained, and the detection result is input into a second dryness identification unit to obtain a second dryness identification result; and carrying out weighted calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit to obtain the dryness identification result of the waterproof coating. The waterproof coating identification method solves the technical problems that in the prior art, the accuracy of identifying the dryness of the waterproof coating is insufficient, and then the dryness identification effect of the waterproof coating is poor.
Description
Technical Field
The invention relates to the field of data processing, in particular to a detection and identification method and system for a drying stage of waterproof paint.
Background
With the wide application of waterproof paint, the application environment of waterproof paint is continuously developed towards diversification. In order to meet the increasingly changing application environment of the waterproof coating, the demand for multi-component and multi-color multi-component waterproof coating is continuously increased, so that the difficulty of identifying the dryness degree of the waterproof coating is increasingly greater. Dryness identification has a very important impact on the application of waterproof coatings. In the traditional waterproof coating dryness degree identification mode, the waterproof coating is usually identified by using a manual mechanical test, and the waterproof coating dryness degree identification mode has the defects of strong manual dependency, low automation degree, high identification error, strong destructiveness and the like. How to identify the dryness of waterproof paint with high quality is widely paid attention to.
In the prior art, the accuracy of identifying the dryness of the waterproof paint is insufficient, and the technical problem of poor effect of identifying the dryness of the waterproof paint is caused.
Disclosure of Invention
The application provides a detection and identification method and system for a drying stage of waterproof paint. The waterproof coating identification method solves the technical problems that in the prior art, the accuracy of identifying the dryness of the waterproof coating is insufficient, and then the dryness identification effect of the waterproof coating is poor. The intelligent, efficient and comprehensive multi-dimensional dryness degree identification of the waterproof paint is achieved, the accuracy of dryness degree identification of the waterproof paint is improved, and the technical effect of dryness degree identification quality of the waterproof paint is improved.
In view of the above problems, the present application provides a method and a system for detecting and identifying a drying stage of a waterproof coating.
In a first aspect, the present application provides a method for detecting and identifying a drying stage of a waterproof paint, wherein the method is applied to a system for detecting and identifying a drying stage of a waterproof paint, and the method includes: according to a plurality of environmental indexes influencing the drying speed of the waterproof coating, acquiring environmental parameters of the current environment using the waterproof coating, and acquiring an environmental parameter set; inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time of the waterproof coating in the current environment; after the waterproof paint is used according to the preset coating amount and the drying time is reached, carrying out physical detection on the waterproof paint based on a first detection mode, and acquiring a paint image after detection; inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result; based on a second detection mode, detecting the microwave radiation absorption amount of the waterproof paint to obtain a detection result, and inputting the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result; and carrying out weighted calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit to obtain the dryness identification result of the waterproof coating.
In a second aspect, the present application also provides a drying stage detection and identification system for a waterproof paint, wherein the system comprises: the environment parameter obtaining module is used for obtaining environment parameters of the environment in which the waterproof coating is used currently according to a plurality of environment indexes affecting the drying speed of the waterproof coating, and obtaining an environment parameter set; the drying time acquisition module is used for inputting the environment parameter set and the drying mode of the waterproof coating into a drying time prediction model to acquire the drying time of the waterproof coating in the current environment; the physical detection module is used for physically detecting the waterproof paint based on a first detection mode after the waterproof paint is used according to a preset coating amount and the drying time is reached, and acquiring a paint image after detection; the first dryness identification module is used for inputting the paint image into a first dryness identification unit in the dryness detection model to obtain a first dryness identification result; the second dryness degree identification module is used for detecting the microwave radiation absorption amount of the waterproof paint based on a second detection mode to obtain a detection result, and inputting the detection result into a second dryness degree identification unit in the dryness degree detection model to obtain a second dryness degree identification result; and the weighting calculation module is used for carrying out weighting calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit to obtain the dryness identification result of the waterproof coating.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
collecting environmental parameters of the environment currently using the waterproof coating through a plurality of environmental indexes to obtain an environmental parameter set; inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time; after the waterproof paint is used according to the preset coating amount and the drying time is reached, the waterproof paint is physically detected in a first detection mode, and a detected paint image is obtained; inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result; based on a second detection mode, detecting the microwave radiation absorption amount of the waterproof paint to obtain a detection result, and inputting the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result; and carrying out weighted calculation on the first dryness identification result and the second dryness identification result according to the accuracy of the first dryness identification unit and the second dryness identification unit, so as to obtain the dryness identification result of the waterproof coating. The intelligent, efficient and comprehensive multi-dimensional dryness degree identification of the waterproof paint is achieved, the accuracy of dryness degree identification of the waterproof paint is improved, and the technical effect of dryness degree identification quality of the waterproof paint is improved.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly described below. It is apparent that the figures in the following description relate only to some embodiments of the present disclosure and are not limiting of the present disclosure.
FIG. 1 is a schematic flow chart of a method for detecting and identifying a drying stage of a waterproof coating material;
FIG. 2 is a schematic flow chart of obtaining an environmental parameter set in a method for detecting and identifying a drying stage of a waterproof coating material;
fig. 3 is a schematic structural diagram of a detection and identification system for a drying stage of a waterproof coating material according to the present application.
Reference numerals illustrate: the device comprises an environment parameter obtaining module 11, a drying time obtaining module 12, a physical detection module 13, a first dryness identification module 14, a second dryness identification module 15 and a weighting calculation module 16.
Detailed Description
The application provides a detection and identification method and system for a drying stage of waterproof paint. The waterproof coating identification method solves the technical problems that in the prior art, the accuracy of identifying the dryness of the waterproof coating is insufficient, and then the dryness identification effect of the waterproof coating is poor. The intelligent, efficient and comprehensive multi-dimensional dryness degree identification of the waterproof paint is achieved, the accuracy of dryness degree identification of the waterproof paint is improved, and the technical effect of dryness degree identification quality of the waterproof paint is improved.
Example 1
Referring to fig. 1, the present application provides a method for detecting and identifying a drying stage of a waterproof coating, wherein the method is applied to a system for detecting and identifying a drying stage of a waterproof coating, and the method specifically includes the following steps:
step S100: according to a plurality of environmental indexes influencing the drying speed of the waterproof coating, acquiring environmental parameters of the current environment using the waterproof coating, and acquiring an environmental parameter set;
further, as shown in fig. 2, step S100 of the present application further includes:
step S110: acquiring a preset time period;
step S120: collecting the temperature, humidity and wind speed of the environment currently using the waterproof paint in a plurality of time windows in the preset time period to obtain a temperature parameter set, a humidity parameter set and a wind speed parameter set;
Step S130: calculating to obtain an average temperature parameter, an average humidity parameter and an average wind speed parameter based on the temperature parameter set, the humidity parameter set and the wind speed parameter set;
step S140: the set of environmental parameters is generated based on the average temperature parameter, the average humidity parameter, and the average wind speed parameter.
Specifically, according to a plurality of time windows in a preset period, information acquisition is carried out on the temperature, the humidity and the wind speed of the environment in which the waterproof coating is used currently, and a temperature parameter set, a humidity parameter set and a wind speed parameter set are obtained. Further, average value calculation is performed on the temperature parameter set, the humidity parameter set and the wind speed parameter set respectively to obtain an average temperature parameter, an average humidity parameter and an average wind speed parameter, and the average temperature parameter, the average humidity parameter and the average wind speed parameter are added to the environment parameter set. Wherein the plurality of environmental indicators include temperature, humidity, wind speed. The preset time period comprises a plurality of time nodes which are preset and determined. The plurality of time windows includes a plurality of specific time points within a preset period. For example, if the preset time period includes a certain day, the plurality of time windows includes a plurality of specific time points within the certain day. The temperature parameter set, the humidity parameter set and the wind speed parameter set comprise a plurality of temperature parameters, a plurality of humidity parameters and a plurality of wind speed parameters corresponding to the current environment using the waterproof coating under a plurality of time windows in a preset time period. The average temperature parameter, the average humidity parameter and the average wind speed parameter comprise average values corresponding to the temperature parameter set, the humidity parameter set and the wind speed parameter set. The environment parameter set comprises an average temperature parameter, an average humidity parameter and an average wind speed parameter. The method achieves the technical effects of acquiring the environmental parameters of the environment in which the waterproof coating is currently used according to a plurality of environmental indexes affecting the drying speed of the waterproof coating and a plurality of time windows in a preset period, obtaining a reliable environmental parameter set and laying a foundation for the subsequent identification of the drying degree of the waterproof coating.
Step S200: inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time of the waterproof coating in the current environment;
further, step S200 of the present application further includes:
step S210: acquiring environmental parameters of an environment using the waterproof coating in a historical time, and acquiring a plurality of historical environmental parameter sets;
step S220: when the waterproof paint is used in the historical time, under the plurality of historical environment parameter sets, adopting drying time in different drying modes to obtain a plurality of historical drying time sets;
step S230: the data of the plurality of historical environment parameter sets, the plurality of drying modes and the plurality of historical drying time sets are marked, the data is used as construction data, the drying time prediction model is constructed and supervised and learned based on a feedforward neural network, the input data of the drying time prediction model is the environment parameter sets and the drying modes, and the output data is the drying time;
step S240: and inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time.
Specifically, environmental parameters of the environment using the waterproof paint in the historical time are collected according to a plurality of environmental indexes, and a plurality of historical environmental parameter sets are obtained. When the waterproof paint is used in the historical time, under a plurality of historical environment parameter sets, different drying time of a plurality of drying modes is acquired, and a plurality of historical drying time sets are obtained. And further, marking data of a plurality of historical environment parameter sets, a plurality of drying modes and a plurality of historical drying time sets to obtain construction data. And based on the feedforward neural network, performing supervised learning on the constructed data to a convergence state to obtain a drying time prediction model. And taking the environmental parameter set and the drying mode of the waterproof paint as input information, and inputting the input information into a drying time prediction model to obtain the drying time.
The historical environment parameter sets comprise a plurality of historical average temperature parameters, a plurality of historical average humidity parameters and a plurality of historical average wind speed parameters corresponding to the environment using the waterproof coating in the historical time. The historical time may be determined by adaptive settings. The plurality of historical drying time sets comprise a plurality of historical drying times corresponding to different drying modes under a plurality of historical environment parameter sets when the waterproof coating is used in the historical time. The different drying modes include natural drying, hot air drying, microwave drying, ultraviolet drying, infrared drying, solar drying, high-frequency drying and other drying modes. The construction data comprises a plurality of historical environment parameter sets, a plurality of drying modes and a plurality of historical drying time sets after data labeling. The feedforward neural network comprises an input layer, a plurality of neurons and an output layer. The feedforward neural network is an artificial neural network. In a feed-forward neural network, each neuron starts from an input layer, receives a previous stage input, inputs the previous stage input to a next stage, and outputs the next stage input to an output layer, and no feedback exists in the whole network, so that signals are propagated unidirectionally from the input layer to the output layer. The input data of the drying time prediction model comprises an environment parameter set and a drying mode, and the output data comprises the drying time. The drying time prediction model meets the feed-forward neural network and has the functions of intelligently analyzing an input environment parameter set and a drying mode and predicting the drying time. The drying mode of the waterproof coating comprises a drying mode corresponding to the current environment using the waterproof coating, and can be determined by self-adaptive setting. The drying time comprises an environment parameter set and predicted drying time corresponding to the drying mode of the waterproof coating. The method has the advantages that the environment parameter set and the drying mode of the waterproof coating are accurately and efficiently predicted by the drying time prediction model, and the reliable drying time is obtained, so that the technical effects of suitability and rationality of the drying degree identification of the waterproof coating are improved.
Step S300: after the waterproof paint is used according to the preset coating amount and the drying time is reached, carrying out physical detection on the waterproof paint based on a first detection mode, and acquiring a paint image after detection;
specifically, the environment in which the waterproof paint is currently used is subjected to waterproof paint coating in accordance with a preset coating amount. And after the drying time is reached, carrying out physical detection on the waterproof paint according to a first detection mode, and collecting paint images after detection. The preset coating amount comprises preset coating parameters such as a coating position, a coating area, a coating thickness and the like of the waterproof coating. The first detection mode is a physical detection mode. For example, the first detection mode includes controlling a preset scraping tool according to a preset force to scrape the surface of the waterproof coating after reaching the drying time. The paint image comprises image data corresponding to the waterproof paint after the waterproof paint is physically detected according to the first detection mode. The technical effects of physically detecting the waterproof paint in the first detection mode, collecting the paint image after detection, and providing data support for the subsequent identification of the dryness of the paint image are achieved.
Step S400: inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result;
further, step S400 of the present application further includes:
step S410: obtaining paint images obtained in the first detection mode after the waterproof paint is used according to the preset coating amount and the corresponding drying time is reached in the historical time, and obtaining a plurality of sample paint images;
step S420: performing dryness analysis on the plurality of sample paint images to obtain a first dryness identification result of the plurality of samples;
specifically, based on the historical time, a plurality of sample paint images are collected, and the drying degree identification is performed on the plurality of sample paint images, so that a first drying degree identification result of the plurality of samples is obtained. And the plurality of sample paint images comprise a plurality of historical waterproof paint coatings according to preset coating amounts in historical time, and after reaching the drying time, the plurality of historical waterproof paint coatings are detected in a first detection mode, and a plurality of image data information corresponding to the detected historical waterproof paint coatings is obtained. The first dryness identification result of the plurality of samples comprises a plurality of first dryness parameters of the samples corresponding to the plurality of sample paint images. Illustratively, the deeper the scratch in the sample paint image, the larger the scratch, the more pronounced the scratch, and the smaller the corresponding sample first dryness parameter.
Step S430: constructing the first dryness identification unit by adopting the plurality of sample paint images and the first dryness identification result of the plurality of samples as construction data;
further, step S430 of the present application further includes:
step S431: constructing a network structure of the first dryness degree identification unit based on a convolutional neural network, wherein input data of the first dryness degree identification unit comprises a paint image, and output data comprises a first dryness degree identification result;
step S432: dividing the plurality of sample paint images and the plurality of sample first dryness degree identification results to obtain a first training set and a first verification set;
step S433: based on supervised learning, performing supervised training on the first dryness degree identification unit by adopting the first training set until the first dryness degree identification unit converges or the accuracy rate reaches a preset requirement;
step S434: and verifying the first dryness identification unit by adopting the first verification set, and obtaining the first dryness identification unit if the accuracy rate meets the preset requirement.
Step S440: and inputting the paint image into the first dryness identification unit to obtain the first dryness identification result.
Specifically, a network structure of the first dryness level identification unit is constructed based on the convolutional neural network. And obtaining a first training set and a first verification set by carrying out random data division on the plurality of sample paint images and the first dryness degree identification results of the plurality of samples. Illustratively, the first training set is partitioned from the plurality of sample paint images and the random 70% of the data information in the plurality of sample first dryness identification results. The random 30% data information in the plurality of sample paint images and the plurality of sample first dryness identification results is divided into a first verification set. Further, the first dryness degree identification unit is subjected to supervised training through the first training set in a supervised learning mode until the first dryness degree identification unit converges or the accuracy reaches a preset requirement, and the supervised training is finished. And taking the first verification set as input information, inputting the input information into the first dryness degree identification unit, verifying the first dryness degree identification unit through the first verification set, and obtaining the constructed first dryness degree identification unit if the accuracy rate meets the preset requirement. Then, the paint image is input as input information to a first dryness recognition unit, and a first dryness recognition result is obtained.
The convolution neural network is a feedforward neural network which comprises convolution calculation and has a depth structure. The convolutional neural network has characteristic learning capability and can carry out translation invariant classification on input information according to a hierarchical structure of the convolutional neural network. The network structure of the first dryness identification unit comprises an input layer, an hidden layer and an output layer. The hidden layers comprise a convolution layer, a pooling layer and a full connection layer. The supervised learning is to adjust parameters of the first dryness identification unit by using the first training set, so that the first dryness identification unit can identify the dryness of any input paint image. The preset requirement comprises preset and determined output accuracy threshold of the first dryness identification unit. The input data of the first dryness identification unit includes a paint image, and the output data includes a first dryness identification result. The first dryness recognition unit may be regarded as a convolutional neural network model for performing intelligent dryness recognition on the paint image. The first dryness identification result comprises a first dryness parameter corresponding to the paint image. The intelligent recognition of the paint image through the first dryness degree recognition unit is achieved, and a first dryness degree recognition result is obtained, so that the technical effect of accuracy in recognition of the dryness degree of the waterproof paint is improved.
Step S500: based on a second detection mode, detecting the microwave radiation absorption amount of the waterproof paint to obtain a detection result, and inputting the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result;
further, step S500 of the present application further includes:
step S510: transmitting microwave radiation with preset wavelength to the waterproof paint based on a microwave radiation transmitter;
step S520: based on a microwave radiation receiver, receiving the microwave radiation reflected by the waterproof paint, and acquiring the radiation absorption amount of the microwave radiation absorbed by the waterproof paint;
in particular, the radiation absorption of the waterproof coating depends on the dielectric constant of the waterproof coating, which in turn is related to the dryness of the waterproof coating. The longer the drying time, the better the cure drying degree, and the smaller the radiation absorption. The second detection mode is to detect the microwave radiation absorption amount of the waterproof paint after reaching the drying time through a microwave radiation emitter. Namely, the waterproof paint after reaching the drying time is irradiated with microwave radiation of a preset wavelength by the microwave radiation emitter. The emitted microwave radiation of a predetermined wavelength is absorbed by the waterproof coating as a function of the current dielectric constant, which depends on the degree of curing of the waterproof coating. Subsequently, the microwave radiation reflected by the waterproof paint is received by the microwave radiation receiver, and the radiation absorption amount absorbed by the waterproof paint is output. Wherein the microwave radiation emitter is in communication connection with the drying stage detection and identification system of the waterproof coating. The microwave radiation emitter can be a microwave radiation emitting device for detecting the dryness of the paint in the prior art. The microwave radiation emitter comprises an emitter, a receiver and a radiation absorption amount measuring sensor. The microwave radiation emitter has the function of detecting the microwave radiation absorption amount of the waterproof paint. The preset wavelength may be determined by adaptive setting. The method achieves the technical effects that the microwave radiation absorption capacity of the waterproof paint after reaching the drying time is detected through the microwave radiation emitter, and the accurate radiation absorption capacity is obtained, so that the scientificity and reliability of identifying the drying degree of the waterproof paint are improved.
Step S530: and inputting the radiation absorption amount as the detection result into the second dryness degree identification unit to obtain the second dryness degree identification result.
Further, step S530 of the present application further includes:
step S531: obtaining a detection result obtained by adopting the second detection mode after the waterproof paint is used according to the preset coating amount and the corresponding drying time is reached in the historical time, and obtaining a plurality of sample detection results;
step S532: obtaining a second dryness identification result of a plurality of samples after the historical time is obtained, using the waterproof paint according to the preset coating amount and reaching the corresponding drying time;
step S533: marking data of the detection results of the plurality of samples and the second dryness degree identification result of the plurality of samples, constructing and supervising learning based on a feedforward neural network to obtain a second dryness degree identification unit, wherein the input data of the second dryness degree identification unit is the detection result, and the output data is the second dryness degree identification result;
step S534: and inputting the radiation absorption amount as the detection result into the second dryness degree identification unit to obtain the second dryness degree identification result.
Specifically, the radiation absorption amount is set as the detection result. And based on the historical time, carrying out historical data query on the detection results to obtain a plurality of sample detection results and a plurality of sample second dryness degree identification results. And marking data of the detection results of the plurality of samples and the second dryness degree identification result of the plurality of samples to obtain construction data of the second dryness degree identification unit. Further, based on the feedforward neural network, the construction data is subjected to supervised learning to a convergence state, and a second dryness degree identification unit is obtained. And inputting the detection result as input information into a second dryness degree identification unit to obtain a second dryness degree identification result.
And the plurality of sample detection results comprise a plurality of historical radiation absorption amounts obtained by coating the historical waterproof coating according to the preset coating amount in the historical time and detecting the microwave radiation absorption amount in a second detection mode after reaching the corresponding drying time. The plurality of sample second dryness degree identification results comprise a plurality of sample second dryness degree identification parameters corresponding to the plurality of sample detection results. The smaller the historical radiation absorption, the greater the corresponding sample second dryness identification parameter. The construction data of the second dryness degree identification unit comprises a plurality of sample detection results after data labeling and a plurality of sample second dryness degree identification results. The feedforward neural network is a unidirectional propagation artificial neural network. And the input data of the second dryness degree identification unit is a detection result, and the output data is a second dryness degree identification result. The second dryness level identification unit comprises an input layer, a plurality of neurons and an output layer. The second dryness degree identification unit has the function of intelligently identifying parameters of dryness degree according to the input detection result. And the second dryness degree identification result comprises a second dryness degree identification parameter corresponding to the detection result. The larger the radiation absorption amount in the detection result is, the smaller the corresponding second dryness identification parameter is. The intelligent and efficient analysis of the radiation absorption capacity through the second dryness identification unit is achieved, and an accurate second dryness identification result is obtained, so that the comprehensive and accurate technical effect of dryness identification of the waterproof paint is improved.
Step S600: and carrying out weighted calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit to obtain the dryness identification result of the waterproof coating.
Further, step S600 of the present application further includes:
step S610: judging whether the drying degree identification result is completely dried or not;
step S620: if yes, displaying the drying degree identification result, if not, continuously identifying the drying degree of the waterproof coating, acquiring the actual drying time when the waterproof coating is completely dried, and updating the drying time prediction model.
Specifically, accuracy rate inquiry is performed on the first dryness level identification unit and the second dryness level identification unit respectively, and the first accuracy rate and the second accuracy rate are obtained. And carrying out weighted calculation on the first dryness identification result and the second dryness identification result according to the first accuracy and the second accuracy to obtain the dryness identification result of the waterproof coating, thereby improving the dryness identification accuracy of the waterproof coating. The first accuracy comprises an output accuracy parameter of the first dryness identification unit. The second accuracy includes an output accuracy parameter of the second dryness identification unit. Illustratively, the first accuracy is a, the second accuracy is B, the first dryness degree identification result is a, and the second dryness degree identification result is B. Then, the dryness of the waterproof paint was identified as a×a+b×b.
Further, whether the drying degree identification result is completely dried or not is judged, and if the drying degree identification result is completely dried, the drying degree identification result is displayed. If the drying degree identification result is not complete drying, continuing to identify the drying degree of the waterproof coating until the waterproof coating is completely dried, collecting the actual drying time when the waterproof coating is completely dried, and updating parameters of the drying time prediction model through the actual drying time, thereby improving the accuracy of the drying time prediction model. The actual drying time comprises time parameter information corresponding to the complete drying of the waterproof coating.
In summary, the method for detecting and identifying the drying stage of the waterproof coating provided by the application has the following technical effects:
1. collecting environmental parameters of the environment currently using the waterproof coating through a plurality of environmental indexes to obtain an environmental parameter set; inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time; after the waterproof paint is used according to the preset coating amount and the drying time is reached, the waterproof paint is physically detected in a first detection mode, and a detected paint image is obtained; inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result; based on a second detection mode, detecting the microwave radiation absorption amount of the waterproof paint to obtain a detection result, and inputting the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result; and carrying out weighted calculation on the first dryness identification result and the second dryness identification result according to the accuracy of the first dryness identification unit and the second dryness identification unit, so as to obtain the dryness identification result of the waterproof coating. The intelligent, efficient and comprehensive multi-dimensional dryness degree identification of the waterproof paint is achieved, the accuracy of dryness degree identification of the waterproof paint is improved, and the technical effect of dryness degree identification quality of the waterproof paint is improved.
2. The environment parameter set and the drying mode of the waterproof coating are accurately and efficiently predicted by the drying time prediction model, so that the reliable drying time is obtained, and the adaptation degree and the rationality of the drying degree identification of the waterproof coating are improved.
3. The first dryness identification unit is used for intelligently identifying the paint image to obtain a first dryness identification result, so that the dryness identification accuracy of the waterproof paint is improved.
4. And detecting the microwave radiation absorption capacity of the waterproof coating after reaching the drying time through a microwave radiation emitter to obtain the accurate radiation absorption capacity, thereby improving the scientificity and reliability of identifying the drying degree of the waterproof coating.
5. The radiation absorption capacity is intelligently and efficiently analyzed through the second dryness identification unit, and an accurate second dryness identification result is obtained, so that the comprehensiveness and accuracy of dryness identification of the waterproof coating are improved.
Example two
Based on the same inventive concept as the method for detecting and identifying the drying stage of the waterproof paint in the foregoing embodiment, the present invention also provides a system for detecting and identifying the drying stage of the waterproof paint, referring to fig. 3, the system includes:
The environment parameter obtaining module 11 is used for obtaining environment parameters of the environment in which the waterproof coating is used currently according to a plurality of environment indexes affecting the drying speed of the waterproof coating, and obtaining an environment parameter set;
a drying time obtaining module 12, where the drying time obtaining module 12 is configured to input the environmental parameter set and a drying mode of the waterproof coating into a drying time prediction model, to obtain a drying time of the waterproof coating in a current environment;
the physical detection module 13 is used for physically detecting the waterproof paint based on a first detection mode after the waterproof paint is used according to a preset coating amount and the drying time is reached, and acquiring a paint image after detection;
a first dryness identification module 14, where the first dryness identification module 14 is configured to input the paint image into a first dryness identification unit in a dryness detection model, to obtain a first dryness identification result;
the second dryness identification module 15 is configured to detect an absorption amount of microwave radiation of the waterproof coating based on a second detection manner, obtain a detection result, and input the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result;
And the weighting calculation module 16 is configured to perform weighting calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit, so as to obtain a dryness identification result of the waterproof coating.
Further, the system further comprises:
the period acquisition module is used for acquiring a preset time period;
the parameter acquisition module is used for acquiring the temperature, the humidity and the wind speed of the environment currently using the waterproof coating in a plurality of time windows within the preset time period to obtain a temperature parameter set, a humidity parameter set and a wind speed parameter set;
the parameter calculation module is used for calculating and obtaining an average temperature parameter, an average humidity parameter and an average wind speed parameter based on the temperature parameter set, the humidity parameter set and the wind speed parameter set;
the first execution module is used for generating the environment parameter set based on the average temperature parameter, the average humidity parameter and the average wind speed parameter.
Further, the system further comprises:
the historical environment parameter acquisition module is used for acquiring environment parameters of the environment using the waterproof coating in the historical time and acquiring a plurality of historical environment parameter sets;
the historical drying time acquisition module is used for acquiring the drying time of different drying modes under the plurality of historical environment parameter sets when the waterproof coating is used in the historical time, so as to acquire a plurality of historical drying time sets;
the second execution module is used for marking the data of the plurality of historical environment parameter sets, the plurality of drying modes and the plurality of historical drying time sets, and is used as construction data, the drying time prediction model is constructed and supervised and learned based on a feedforward neural network, the input data of the drying time prediction model is the environment parameter sets and the drying modes, and the output data is the drying time;
and the drying time determining module is used for inputting the environment parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time.
Further, the system further comprises:
the sample paint image acquisition module is used for acquiring paint images obtained in the first detection mode after the waterproof paint is used according to the preset coating amount and the corresponding drying time is reached in the historical time, so as to obtain a plurality of sample paint images;
the sample dryness analysis module is used for carrying out dryness analysis on the plurality of sample paint images to obtain a plurality of sample first dryness identification results;
a third execution module for constructing the first dryness identification unit using the plurality of sample paint images and the plurality of sample first dryness identification results as construction data;
and the fourth execution module is used for inputting the paint image into the first dryness degree identification unit to obtain the first dryness degree identification result.
Further, the system further comprises:
the fifth execution module is used for constructing a network structure of the first dryness degree identification unit based on a convolutional neural network, wherein input data of the first dryness degree identification unit comprise a paint image, and output data comprise a first dryness degree identification result;
The dividing module is used for dividing the plurality of sample paint images and the plurality of sample first dryness degree identification results to obtain a first training set and a first verification set;
the monitoring training module is used for monitoring training the first dryness degree identification unit by adopting the first training set based on monitoring learning until the first dryness degree identification unit converges or the accuracy reaches a preset requirement;
and the verification module is used for verifying the first dryness degree identification unit by adopting the first verification set, and if the accuracy rate meets the preset requirement, the first dryness degree identification unit is obtained.
Further, the system further comprises:
the emission module is used for emitting microwave radiation with preset wavelength to the waterproof paint based on the microwave radiation emitter;
the radiation absorption amount determining module is used for receiving the microwave radiation reflected by the waterproof paint based on a microwave radiation receiver and acquiring the radiation absorption amount of the microwave radiation absorbed by the waterproof paint;
and the sixth execution module is used for inputting the radiation absorption amount serving as the detection result into the second dryness degree identification unit to obtain the second dryness degree identification result.
Further, the system further comprises:
the sample detection result acquisition module is used for acquiring detection results obtained by the second detection mode after the waterproof paint is used according to the preset coating amount and the corresponding drying time is reached in the historical time, so as to obtain a plurality of sample detection results;
the sample second dryness degree identification result acquisition module is used for acquiring a plurality of sample second dryness degree identification results after the sample second dryness degree identification result acquisition module is used for acquiring the historical time, using the waterproof coating according to the preset coating amount and reaching the corresponding drying time;
the seventh execution module is used for marking data of the detection results of the plurality of samples and the second dryness degree identification result of the plurality of samples, constructing and supervising learning based on a feedforward neural network to obtain a second dryness degree identification unit, wherein the input data of the second dryness degree identification unit is the detection result, and the output data is the second dryness degree identification result;
and the eighth execution module is used for inputting the radiation absorption amount serving as the detection result into the second dryness degree identification unit to obtain the second dryness degree identification result.
Further, the system further comprises:
the drying judgment module is used for judging whether the drying degree identification result is completely dried or not;
and the ninth execution module is used for displaying the drying degree identification result if yes, if not, continuously identifying the drying degree of the waterproof coating, acquiring the actual drying time when the waterproof coating is completely dried, and updating the drying time prediction model.
The system for detecting and identifying the drying stage of the waterproof coating provided by the embodiment of the invention can be used for executing the method for detecting and identifying the drying stage of the waterproof coating provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the executing method.
All the included modules are only divided according to the functional logic, but are not limited to the above-mentioned division, so long as the corresponding functions can be realized; in addition, the specific names of the functional modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present invention.
The application provides a method for detecting and identifying a drying stage of waterproof paint, wherein the method is applied to a system for detecting and identifying the drying stage of waterproof paint, and comprises the following steps: collecting environmental parameters of the environment currently using the waterproof coating through a plurality of environmental indexes to obtain an environmental parameter set; inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time; after the waterproof paint is used according to the preset coating amount and the drying time is reached, the waterproof paint is physically detected in a first detection mode, and a detected paint image is obtained; inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result; based on a second detection mode, detecting the microwave radiation absorption amount of the waterproof paint to obtain a detection result, and inputting the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result; and carrying out weighted calculation on the first dryness identification result and the second dryness identification result according to the accuracy of the first dryness identification unit and the second dryness identification unit, so as to obtain the dryness identification result of the waterproof coating. The waterproof coating identification method solves the technical problems that in the prior art, the accuracy of identifying the dryness of the waterproof coating is insufficient, and then the dryness identification effect of the waterproof coating is poor. The intelligent, efficient and comprehensive multi-dimensional dryness degree identification of the waterproof paint is achieved, the accuracy of dryness degree identification of the waterproof paint is improved, and the technical effect of dryness degree identification quality of the waterproof paint is improved.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (9)
1. A method for detecting and identifying a drying stage of a waterproof coating, the method comprising:
according to a plurality of environmental indexes influencing the drying speed of the waterproof coating, acquiring environmental parameters of the current environment using the waterproof coating, and acquiring an environmental parameter set;
inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time of the waterproof coating in the current environment;
after the waterproof paint is used according to the preset coating amount and the drying time is reached, carrying out physical detection on the waterproof paint based on a first detection mode, and acquiring a paint image after detection;
Inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result;
based on a second detection mode, detecting the microwave radiation absorption amount of the waterproof paint to obtain a detection result, and inputting the detection result into a second dryness identification unit in the dryness detection model to obtain a second dryness identification result;
and carrying out weighted calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit to obtain the dryness identification result of the waterproof coating.
2. The method according to claim 1, wherein obtaining environmental parameters of the environment in which the waterproof paint is currently used, according to a plurality of environmental indicators affecting the drying speed of the waterproof paint, to obtain an environmental parameter set, comprises:
acquiring a preset time period;
collecting the temperature, humidity and wind speed of the environment currently using the waterproof paint in a plurality of time windows in the preset time period to obtain a temperature parameter set, a humidity parameter set and a wind speed parameter set;
Calculating to obtain an average temperature parameter, an average humidity parameter and an average wind speed parameter based on the temperature parameter set, the humidity parameter set and the wind speed parameter set;
the set of environmental parameters is generated based on the average temperature parameter, the average humidity parameter, and the average wind speed parameter.
3. The method of claim 1, wherein inputting the set of environmental parameters and the manner of drying the waterproof coating into a drying time prediction model to obtain the drying time of the waterproof coating within the current environment comprises:
acquiring environmental parameters of an environment using the waterproof coating in a historical time, and acquiring a plurality of historical environmental parameter sets;
when the waterproof paint is used in the historical time, under the plurality of historical environment parameter sets, adopting drying time in different drying modes to obtain a plurality of historical drying time sets;
the data of the plurality of historical environment parameter sets, the plurality of drying modes and the plurality of historical drying time sets are marked, the data is used as construction data, the drying time prediction model is constructed and supervised and learned based on a feedforward neural network, the input data of the drying time prediction model is the environment parameter sets and the drying modes, and the output data is the drying time;
And inputting the environmental parameter set and the drying mode of the waterproof coating into a drying time prediction model to obtain the drying time.
4. The method according to claim 1, wherein inputting the paint image into a first dryness identification unit in a dryness detection model to obtain a first dryness identification result, comprises:
obtaining paint images obtained in the first detection mode after the waterproof paint is used according to the preset coating amount and the corresponding drying time is reached in the historical time, and obtaining a plurality of sample paint images;
performing dryness analysis on the plurality of sample paint images to obtain a first dryness identification result of the plurality of samples;
constructing the first dryness identification unit by adopting the plurality of sample paint images and the first dryness identification result of the plurality of samples as construction data;
and inputting the paint image into the first dryness identification unit to obtain the first dryness identification result.
5. The method according to claim 4, wherein constructing the first dryness identification unit using the plurality of sample paint images and the plurality of sample first dryness identification results as construction data, comprises:
Constructing a network structure of the first dryness degree identification unit based on a convolutional neural network, wherein input data of the first dryness degree identification unit comprises a paint image, and output data comprises a first dryness degree identification result;
dividing the plurality of sample paint images and the plurality of sample first dryness degree identification results to obtain a first training set and a first verification set;
based on supervised learning, performing supervised training on the first dryness degree identification unit by adopting the first training set until the first dryness degree identification unit converges or the accuracy rate reaches a preset requirement;
and verifying the first dryness identification unit by adopting the first verification set, and obtaining the first dryness identification unit if the accuracy rate meets the preset requirement.
6. The method according to claim 1, wherein the detecting the absorption amount of the microwave radiation of the waterproof paint based on the second detecting means to obtain a detection result comprises:
transmitting microwave radiation with preset wavelength to the waterproof paint based on a microwave radiation transmitter;
based on a microwave radiation receiver, receiving the microwave radiation reflected by the waterproof paint, and acquiring the radiation absorption amount of the microwave radiation absorbed by the waterproof paint;
And inputting the radiation absorption amount as the detection result into the second dryness degree identification unit to obtain the second dryness degree identification result.
7. The method according to claim 6, wherein inputting the radiation absorption amount as the detection result to the second dryness level identifying unit, obtaining the second dryness level identifying result, comprises:
obtaining a detection result obtained by adopting the second detection mode after the waterproof paint is used according to the preset coating amount and the corresponding drying time is reached in the historical time, and obtaining a plurality of sample detection results;
obtaining a second dryness identification result of a plurality of samples after the historical time is obtained, using the waterproof paint according to the preset coating amount and reaching the corresponding drying time;
marking data of the detection results of the plurality of samples and the second dryness degree identification result of the plurality of samples, constructing and supervising learning based on a feedforward neural network to obtain a second dryness degree identification unit, wherein the input data of the second dryness degree identification unit is the detection result, and the output data is the second dryness degree identification result;
And inputting the radiation absorption amount as the detection result into the second dryness degree identification unit to obtain the second dryness degree identification result.
8. The method according to claim 1, wherein the method further comprises:
judging whether the drying degree identification result is completely dried or not;
if yes, displaying the drying degree identification result, if not, continuously identifying the drying degree of the waterproof coating, acquiring the actual drying time when the waterproof coating is completely dried, and updating the drying time prediction model.
9. A system for detecting and identifying a drying stage of a waterproof paint, the system comprising:
the environment parameter obtaining module is used for obtaining environment parameters of the environment in which the waterproof coating is used currently according to a plurality of environment indexes affecting the drying speed of the waterproof coating, and obtaining an environment parameter set;
the drying time acquisition module is used for inputting the environment parameter set and the drying mode of the waterproof coating into a drying time prediction model to acquire the drying time of the waterproof coating in the current environment;
the physical detection module is used for physically detecting the waterproof paint based on a first detection mode after the waterproof paint is used according to a preset coating amount and the drying time is reached, and acquiring a paint image after detection;
The first dryness identification module is used for inputting the paint image into a first dryness identification unit in the dryness detection model to obtain a first dryness identification result;
the second dryness degree identification module is used for detecting the microwave radiation absorption amount of the waterproof paint based on a second detection mode to obtain a detection result, and inputting the detection result into a second dryness degree identification unit in the dryness degree detection model to obtain a second dryness degree identification result;
and the weighting calculation module is used for carrying out weighting calculation on the first dryness identification result and the second dryness identification result based on the accuracy of the first dryness identification unit and the second dryness identification unit to obtain the dryness identification result of the waterproof coating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310050898.2A CN117761048B (en) | 2023-02-02 | 2023-02-02 | Waterproof coating drying stage detection and identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310050898.2A CN117761048B (en) | 2023-02-02 | 2023-02-02 | Waterproof coating drying stage detection and identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117761048A true CN117761048A (en) | 2024-03-26 |
| CN117761048B CN117761048B (en) | 2024-06-11 |
Family
ID=90316915
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310050898.2A Active CN117761048B (en) | 2023-02-02 | 2023-02-02 | Waterproof coating drying stage detection and identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117761048B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118570734A (en) * | 2024-06-18 | 2024-08-30 | 定西国骏建筑安装工程有限公司 | Method and system for determining paint information in decoration industry |
| CN118588213A (en) * | 2024-05-24 | 2024-09-03 | 珑彩环保材料(苏州)有限公司 | Thermosetting plastic powder coating performance detection system based on component analysis |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010173306A (en) * | 2009-02-02 | 2010-08-12 | Ricoh Co Ltd | Image processing apparatus, image processing method, program, and recording medium |
| CN102112831A (en) * | 2008-08-06 | 2011-06-29 | 空中客车运营有限公司 | Device for the contact-less detection of the degree of dryness of a coat of varnish, and method for the same |
| CN104833312A (en) * | 2014-01-28 | 2015-08-12 | Abb技术有限公司 | Sensor system and method for characterizing a wet paint layer |
| CN108732300A (en) * | 2017-04-14 | 2018-11-02 | 中国科学院福建物质结构研究所 | A kind of test device and method of liquid material drying property |
| CN109181517A (en) * | 2018-08-03 | 2019-01-11 | 苏州东沧涂料科技有限公司 | A kind of microwave absorption rapid draing water-borne wood coating and preparation method thereof, coating process |
| CN109724398A (en) * | 2019-02-02 | 2019-05-07 | 北京木业邦科技有限公司 | A kind of drying of wood control method and device based on artificial intelligence |
| CN111011471A (en) * | 2019-12-14 | 2020-04-17 | 江南大学 | Multispectral-radio frequency-hot air fruit and vegetable drying detection device and method |
| CN113341113A (en) * | 2021-04-30 | 2021-09-03 | 东南大学 | Method for matching corresponding drying shrinkage under humidity gradient in cement-based material |
| CN115527203A (en) * | 2022-10-21 | 2022-12-27 | 中粮工程装备无锡有限公司 | Grain drying remote control method and system based on Internet of things |
| CN115588094A (en) * | 2022-10-19 | 2023-01-10 | 浙江纺织服装职业技术学院 | Industrial robot visual image recognition method and system based on deep learning |
-
2023
- 2023-02-02 CN CN202310050898.2A patent/CN117761048B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102112831A (en) * | 2008-08-06 | 2011-06-29 | 空中客车运营有限公司 | Device for the contact-less detection of the degree of dryness of a coat of varnish, and method for the same |
| JP2010173306A (en) * | 2009-02-02 | 2010-08-12 | Ricoh Co Ltd | Image processing apparatus, image processing method, program, and recording medium |
| CN104833312A (en) * | 2014-01-28 | 2015-08-12 | Abb技术有限公司 | Sensor system and method for characterizing a wet paint layer |
| CN108732300A (en) * | 2017-04-14 | 2018-11-02 | 中国科学院福建物质结构研究所 | A kind of test device and method of liquid material drying property |
| CN109181517A (en) * | 2018-08-03 | 2019-01-11 | 苏州东沧涂料科技有限公司 | A kind of microwave absorption rapid draing water-borne wood coating and preparation method thereof, coating process |
| CN109724398A (en) * | 2019-02-02 | 2019-05-07 | 北京木业邦科技有限公司 | A kind of drying of wood control method and device based on artificial intelligence |
| CN111011471A (en) * | 2019-12-14 | 2020-04-17 | 江南大学 | Multispectral-radio frequency-hot air fruit and vegetable drying detection device and method |
| CN113341113A (en) * | 2021-04-30 | 2021-09-03 | 东南大学 | Method for matching corresponding drying shrinkage under humidity gradient in cement-based material |
| CN115588094A (en) * | 2022-10-19 | 2023-01-10 | 浙江纺织服装职业技术学院 | Industrial robot visual image recognition method and system based on deep learning |
| CN115527203A (en) * | 2022-10-21 | 2022-12-27 | 中粮工程装备无锡有限公司 | Grain drying remote control method and system based on Internet of things |
Non-Patent Citations (2)
| Title |
|---|
| 任建宾;: "不同干燥方式耦合作用下煤泥干燥特性的研究", 煤, no. 08, 14 August 2020 (2020-08-14), pages 38 - 40 * |
| 郭乐扬 等: "防/疏冰涂料的机理及其发展趋势", 《表面技术》, vol. 51, no. 11, 30 September 2022 (2022-09-30), pages 113 - 125 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118588213A (en) * | 2024-05-24 | 2024-09-03 | 珑彩环保材料(苏州)有限公司 | Thermosetting plastic powder coating performance detection system based on component analysis |
| CN118570734A (en) * | 2024-06-18 | 2024-08-30 | 定西国骏建筑安装工程有限公司 | Method and system for determining paint information in decoration industry |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117761048B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117761048B (en) | Waterproof coating drying stage detection and identification method and system | |
| CN106231609B (en) | A kind of underwater sensor network Optimization deployment method based on highest priority region | |
| CN111476278B (en) | Intelligent gas concentration detection system | |
| CN111461413B (en) | Highway road surface performance detecting system | |
| CN110580021B (en) | Granary environmental safety intelligent monitoring system based on field bus | |
| CN111982302A (en) | Temperature measurement method with noise filtering and environment temperature compensation | |
| CN110598902A (en) | Water quality prediction method based on combination of support vector machine and KNN | |
| CN115220133A (en) | Multi-meteorological-element rainfall prediction method, device, equipment and storage medium | |
| CN111444947A (en) | Bridge settlement intelligent detection system | |
| CN116930042B (en) | Building waterproof material performance detection equipment and method | |
| CN114117953A (en) | Hydrological model structure diagnosis method, runoff forecasting method and device | |
| CN116596326B (en) | Urban environment detection and comprehensive evaluation method based on remote sensing data | |
| Wang et al. | Research on air pollution gases recognition method based on lstm recurrent neural network and gas sensors array | |
| CN117370766A (en) | Satellite mission planning scheme evaluation method based on deep learning | |
| CN116451322A (en) | Bayesian optimization-based LSTM deep learning network mechanical prediction method | |
| CN112819087B (en) | Method for detecting abnormality of BOD sensor of outlet water based on modularized neural network | |
| CN115687995A (en) | Big data environmental pollution monitoring method and system | |
| CN114911185A (en) | Security big data Internet of things intelligent system based on cloud platform and mobile terminal App | |
| CN114386672B (en) | Environment big data Internet of things intelligent detection system | |
| CN117541125A (en) | Intelligent food quality detection method and device | |
| CN110287924A (en) | A kind of soil parameters classification method based on GRU-RNN model | |
| CN117436355A (en) | Method for establishing optical film thickness model and related equipment | |
| CN116894517A (en) | Photovoltaic power prediction method and device, terminal equipment and storage medium | |
| CN114358244B (en) | Big data intelligent detection system of pressure based on thing networking | |
| Hong et al. | Drainage network flow anomaly classification based on XGBoost |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |